diff options
author | Pablo Neira Ayuso <pablo@netfilter.org> | 2016-09-25 21:23:57 (GMT) |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2016-09-25 21:34:19 (GMT) |
commit | f20fbc0717f9f007c94b2641134b19228d0ce9ed (patch) | |
tree | 1404248ebbec552a3fb7928b75322b65d74de1bd /net | |
parent | 8cb2a7d5667ab9a9c2fdd356357b85b63b320901 (diff) | |
parent | fe0acb5fcb7fe8cb3d68bbdb8459865c972d8f83 (diff) | |
download | linux-f20fbc0717f9f007c94b2641134b19228d0ce9ed.tar.xz |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Conflicts:
net/netfilter/core.c
net/netfilter/nf_tables_netdev.c
Resolve two conflicts before pull request for David's net-next tree:
1) Between c73c24849011 ("netfilter: nf_tables_netdev: remove redundant
ip_hdr assignment") from the net tree and commit ddc8b6027ad0
("netfilter: introduce nft_set_pktinfo_{ipv4, ipv6}_validate()").
2) Between e8bffe0cf964 ("net: Add _nf_(un)register_hooks symbols") and
Aaron Conole's patches to replace list_head with single linked list.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net')
243 files changed, 10530 insertions, 5889 deletions
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c index 86450b7..941df2f 100644 --- a/net/6lowpan/ndisc.c +++ b/net/6lowpan/ndisc.c @@ -101,8 +101,6 @@ static void lowpan_ndisc_802154_update(struct neighbour *n, u32 flags, ieee802154_be16_to_le16(&neigh->short_addr, lladdr_short); if (!lowpan_802154_is_valid_src_short_addr(neigh->short_addr)) neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); - } else { - neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); } write_unlock_bh(&n->lock); } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index f066781..10d2bdc 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1278,7 +1278,7 @@ out: return err; } -#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE) +#if IS_ENABLED(CONFIG_IPDDP) static __inline__ int is_ip_over_ddp(struct sk_buff *skb) { return skb->data[12] == 22; diff --git a/net/atm/lec.c b/net/atm/lec.c index e574a7e..5d26938 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -31,7 +31,7 @@ #include <linux/atmlec.h> /* Proxy LEC knows about bridging */ -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +#if IS_ENABLED(CONFIG_BRIDGE) #include "../bridge/br_private.h" static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; @@ -121,7 +121,7 @@ static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; /* Device structures */ static struct net_device *dev_lec[MAX_LEC_ITF]; -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +#if IS_ENABLED(CONFIG_BRIDGE) static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) { char *buff; @@ -155,7 +155,7 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) sk->sk_data_ready(sk); } } -#endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ +#endif /* IS_ENABLED(CONFIG_BRIDGE) */ /* * Open/initialize the netdevice. This is called (in the current kernel) @@ -222,7 +222,7 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, pr_debug("skbuff head:%lx data:%lx tail:%lx end:%lx\n", (long)skb->head, (long)skb->data, (long)skb_tail_pointer(skb), (long)skb_end_pointer(skb)); -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +#if IS_ENABLED(CONFIG_BRIDGE) if (memcmp(skb->data, bridge_ula_lec, sizeof(bridge_ula_lec)) == 0) lec_handle_bridge(skb, dev); #endif @@ -426,7 +426,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) (unsigned short)(0xffff & mesg->content.normal.flag); break; case l_should_bridge: -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +#if IS_ENABLED(CONFIG_BRIDGE) { pr_debug("%s: bridge zeppelin asks about %pM\n", dev->name, mesg->content.proxy.mac_addr); @@ -452,7 +452,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) sk->sk_data_ready(sk); } } -#endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ +#endif /* IS_ENABLED(CONFIG_BRIDGE) */ break; default: pr_info("%s: Unknown message type %d\n", dev->name, mesg->type); diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 7d17001..ee08540 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -335,7 +335,7 @@ int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface) goto out; skb_reserve(hard_iface->bat_v.elp_skb, ETH_HLEN + NET_IP_ALIGN); - elp_buff = skb_push(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN); + elp_buff = skb_put(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN); elp_packet = (struct batadv_elp_packet *)elp_buff; memset(elp_packet, 0, BATADV_ELP_HLEN); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 610f2c4..7e8dc64 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -461,6 +461,29 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, } /** + * batadv_last_bonding_get - Get last_bonding_candidate of orig_node + * @orig_node: originator node whose last bonding candidate should be retrieved + * + * Return: last bonding candidate of router or NULL if not found + * + * The object is returned with refcounter increased by 1. + */ +static struct batadv_orig_ifinfo * +batadv_last_bonding_get(struct batadv_orig_node *orig_node) +{ + struct batadv_orig_ifinfo *last_bonding_candidate; + + spin_lock_bh(&orig_node->neigh_list_lock); + last_bonding_candidate = orig_node->last_bonding_candidate; + + if (last_bonding_candidate) + kref_get(&last_bonding_candidate->refcount); + spin_unlock_bh(&orig_node->neigh_list_lock); + + return last_bonding_candidate; +} + +/** * batadv_last_bonding_replace - Replace last_bonding_candidate of orig_node * @orig_node: originator node whose bonding candidates should be replaced * @new_candidate: new bonding candidate or NULL @@ -530,7 +553,7 @@ batadv_find_router(struct batadv_priv *bat_priv, * router - obviously there are no other candidates. */ rcu_read_lock(); - last_candidate = orig_node->last_bonding_candidate; + last_candidate = batadv_last_bonding_get(orig_node); if (last_candidate) last_cand_router = rcu_dereference(last_candidate->router); @@ -622,6 +645,9 @@ next: batadv_orig_ifinfo_put(next_candidate); } + if (last_candidate) + batadv_orig_ifinfo_put(last_candidate); + return router; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 0b5f729..1aff2da 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -26,11 +26,13 @@ #include <linux/module.h> #include <linux/debugfs.h> +#include <linux/stringify.h> #include <asm/ioctls.h> #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> +#include "leds.h" #include "selftest.h" /* Bluetooth sockets */ @@ -712,13 +714,16 @@ static struct net_proto_family bt_sock_family_ops = { struct dentry *bt_debugfs; EXPORT_SYMBOL_GPL(bt_debugfs); +#define VERSION __stringify(BT_SUBSYS_VERSION) "." \ + __stringify(BT_SUBSYS_REVISION) + static int __init bt_init(void) { int err; sock_skb_cb_check_size(sizeof(struct bt_skb_cb)); - BT_INFO("Core ver %s", BT_SUBSYS_VERSION); + BT_INFO("Core ver %s", VERSION); err = bt_selftest(); if (err < 0) @@ -726,6 +731,8 @@ static int __init bt_init(void) bt_debugfs = debugfs_create_dir("bluetooth", NULL); + bt_leds_init(); + err = bt_sysfs_init(); if (err < 0) return err; @@ -785,6 +792,8 @@ static void __exit bt_exit(void) bt_sysfs_cleanup(); + bt_leds_cleanup(); + debugfs_remove_recursive(bt_debugfs); } @@ -792,7 +801,7 @@ subsys_initcall(bt_init); module_exit(bt_exit); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); -MODULE_DESCRIPTION("Bluetooth Core ver " BT_SUBSYS_VERSION); -MODULE_VERSION(BT_SUBSYS_VERSION); +MODULE_DESCRIPTION("Bluetooth Core ver " VERSION); +MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_BLUETOOTH); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ddf8432..3ac89e9 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1562,6 +1562,7 @@ int hci_dev_do_close(struct hci_dev *hdev) auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF); if (!auto_off && hdev->dev_type == HCI_PRIMARY && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hci_dev_test_flag(hdev, HCI_MGMT)) __mgmt_power_off(hdev); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index b0e23df..c813568 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -971,14 +971,14 @@ void __hci_req_enable_advertising(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); } -static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) +static u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { - u8 ad_len = 0; size_t name_len; + int max_len; + max_len = HCI_MAX_AD_LENGTH - ad_len - 2; name_len = strlen(hdev->dev_name); - if (name_len > 0) { - size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2; + if (name_len > 0 && max_len > 0) { if (name_len > max_len) { name_len = max_len; @@ -997,22 +997,42 @@ static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) return ad_len; } +static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) +{ + return append_local_name(hdev, ptr, 0); +} + static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, u8 *ptr) { struct adv_info *adv_instance; + u32 instance_flags; + u8 scan_rsp_len = 0; adv_instance = hci_find_adv_instance(hdev, instance); if (!adv_instance) return 0; - /* TODO: Set the appropriate entries based on advertising instance flags - * here once flags other than 0 are supported. - */ + instance_flags = adv_instance->flags; + + if ((instance_flags & MGMT_ADV_FLAG_APPEARANCE) && hdev->appearance) { + ptr[0] = 3; + ptr[1] = EIR_APPEARANCE; + put_unaligned_le16(hdev->appearance, ptr + 2); + scan_rsp_len += 4; + ptr += 4; + } + memcpy(ptr, adv_instance->scan_rsp_data, adv_instance->scan_rsp_len); - return adv_instance->scan_rsp_len; + scan_rsp_len += adv_instance->scan_rsp_len; + ptr += adv_instance->scan_rsp_len; + + if (instance_flags & MGMT_ADV_FLAG_LOCAL_NAME) + scan_rsp_len = append_local_name(hdev, ptr, scan_rsp_len); + + return scan_rsp_len; } void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) @@ -1194,7 +1214,7 @@ static void adv_timeout_expire(struct work_struct *work) hci_req_init(&req, hdev); - hci_req_clear_adv_instance(hdev, &req, instance, false); + hci_req_clear_adv_instance(hdev, NULL, &req, instance, false); if (list_empty(&hdev->adv_instances)) __hci_req_disable_advertising(&req); @@ -1284,8 +1304,9 @@ static void cancel_adv_timeout(struct hci_dev *hdev) * setting. * - force == false: Only instances that have a timeout will be removed. */ -void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, - u8 instance, bool force) +void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, + struct hci_request *req, u8 instance, + bool force) { struct adv_info *adv_instance, *n, *next_instance = NULL; int err; @@ -1311,7 +1332,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, rem_inst = adv_instance->instance; err = hci_remove_adv_instance(hdev, rem_inst); if (!err) - mgmt_advertising_removed(NULL, hdev, rem_inst); + mgmt_advertising_removed(sk, hdev, rem_inst); } } else { adv_instance = hci_find_adv_instance(hdev, instance); @@ -1325,7 +1346,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, err = hci_remove_adv_instance(hdev, instance); if (!err) - mgmt_advertising_removed(NULL, hdev, instance); + mgmt_advertising_removed(sk, hdev, instance); } } @@ -1716,7 +1737,7 @@ void __hci_abort_conn(struct hci_request *req, struct hci_conn *conn, * function. To be safe hard-code one of the * values that's suitable for SCO. */ - rej.reason = HCI_ERROR_REMOTE_LOW_RESOURCES; + rej.reason = HCI_ERROR_REJ_LIMITED_RESOURCES; hci_req_add(req, HCI_OP_REJECT_SYNC_CONN_REQ, sizeof(rej), &rej); diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index b2d044b..ac1e110 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -73,8 +73,9 @@ void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance); int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, bool force); -void hci_req_clear_adv_instance(struct hci_dev *hdev, struct hci_request *req, - u8 instance, bool force); +void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, + struct hci_request *req, u8 instance, + bool force); void __hci_req_update_class(struct hci_request *req); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 96f04b7..48f9471 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -26,6 +26,7 @@ #include <linux/export.h> #include <linux/utsname.h> +#include <linux/sched.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -38,6 +39,8 @@ static LIST_HEAD(mgmt_chan_list); static DEFINE_MUTEX(mgmt_chan_list_lock); +static DEFINE_IDA(sock_cookie_ida); + static atomic_t monitor_promisc = ATOMIC_INIT(0); /* ----- HCI socket interface ----- */ @@ -52,6 +55,8 @@ struct hci_pinfo { __u32 cmsg_mask; unsigned short channel; unsigned long flags; + __u32 cookie; + char comm[TASK_COMM_LEN]; }; void hci_sock_set_flag(struct sock *sk, int nr) @@ -74,6 +79,38 @@ unsigned short hci_sock_get_channel(struct sock *sk) return hci_pi(sk)->channel; } +u32 hci_sock_get_cookie(struct sock *sk) +{ + return hci_pi(sk)->cookie; +} + +static bool hci_sock_gen_cookie(struct sock *sk) +{ + int id = hci_pi(sk)->cookie; + + if (!id) { + id = ida_simple_get(&sock_cookie_ida, 1, 0, GFP_KERNEL); + if (id < 0) + id = 0xffffffff; + + hci_pi(sk)->cookie = id; + get_task_comm(hci_pi(sk)->comm, current); + return true; + } + + return false; +} + +static void hci_sock_free_cookie(struct sock *sk) +{ + int id = hci_pi(sk)->cookie; + + if (id) { + hci_pi(sk)->cookie = 0xffffffff; + ida_simple_remove(&sock_cookie_ida, id); + } +} + static inline int hci_test_bit(int nr, const void *addr) { return *((const __u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31)); @@ -305,6 +342,60 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb_copy); } +void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, + void *data, u16 data_len, ktime_t tstamp, + int flag, struct sock *skip_sk) +{ + struct sock *sk; + __le16 index; + + if (hdev) + index = cpu_to_le16(hdev->id); + else + index = cpu_to_le16(MGMT_INDEX_NONE); + + read_lock(&hci_sk_list.lock); + + sk_for_each(sk, &hci_sk_list.head) { + struct hci_mon_hdr *hdr; + struct sk_buff *skb; + + if (hci_pi(sk)->channel != HCI_CHANNEL_CONTROL) + continue; + + /* Ignore socket without the flag set */ + if (!hci_sock_test_flag(sk, flag)) + continue; + + /* Skip the original socket */ + if (sk == skip_sk) + continue; + + skb = bt_skb_alloc(6 + data_len, GFP_ATOMIC); + if (!skb) + continue; + + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); + put_unaligned_le16(event, skb_put(skb, 2)); + + if (data) + memcpy(skb_put(skb, data_len), data, data_len); + + skb->tstamp = tstamp; + + hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr->opcode = cpu_to_le16(HCI_MON_CTRL_EVENT); + hdr->index = index; + hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); + + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + + read_unlock(&hci_sk_list.lock); +} + static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) { struct hci_mon_hdr *hdr; @@ -384,6 +475,129 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) return skb; } +static struct sk_buff *create_monitor_ctrl_open(struct sock *sk) +{ + struct hci_mon_hdr *hdr; + struct sk_buff *skb; + u16 format; + u8 ver[3]; + u32 flags; + + /* No message needed when cookie is not present */ + if (!hci_pi(sk)->cookie) + return NULL; + + switch (hci_pi(sk)->channel) { + case HCI_CHANNEL_RAW: + format = 0x0000; + ver[0] = BT_SUBSYS_VERSION; + put_unaligned_le16(BT_SUBSYS_REVISION, ver + 1); + break; + case HCI_CHANNEL_USER: + format = 0x0001; + ver[0] = BT_SUBSYS_VERSION; + put_unaligned_le16(BT_SUBSYS_REVISION, ver + 1); + break; + case HCI_CHANNEL_CONTROL: + format = 0x0002; + mgmt_fill_version_info(ver); + break; + default: + /* No message for unsupported format */ + return NULL; + } + + skb = bt_skb_alloc(14 + TASK_COMM_LEN , GFP_ATOMIC); + if (!skb) + return NULL; + + flags = hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) ? 0x1 : 0x0; + + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); + put_unaligned_le16(format, skb_put(skb, 2)); + memcpy(skb_put(skb, sizeof(ver)), ver, sizeof(ver)); + put_unaligned_le32(flags, skb_put(skb, 4)); + *skb_put(skb, 1) = TASK_COMM_LEN; + memcpy(skb_put(skb, TASK_COMM_LEN), hci_pi(sk)->comm, TASK_COMM_LEN); + + __net_timestamp(skb); + + hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr->opcode = cpu_to_le16(HCI_MON_CTRL_OPEN); + if (hci_pi(sk)->hdev) + hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); + else + hdr->index = cpu_to_le16(HCI_DEV_NONE); + hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); + + return skb; +} + +static struct sk_buff *create_monitor_ctrl_close(struct sock *sk) +{ + struct hci_mon_hdr *hdr; + struct sk_buff *skb; + + /* No message needed when cookie is not present */ + if (!hci_pi(sk)->cookie) + return NULL; + + switch (hci_pi(sk)->channel) { + case HCI_CHANNEL_RAW: + case HCI_CHANNEL_USER: + case HCI_CHANNEL_CONTROL: + break; + default: + /* No message for unsupported format */ + return NULL; + } + + skb = bt_skb_alloc(4, GFP_ATOMIC); + if (!skb) + return NULL; + + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); + + __net_timestamp(skb); + + hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr->opcode = cpu_to_le16(HCI_MON_CTRL_CLOSE); + if (hci_pi(sk)->hdev) + hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); + else + hdr->index = cpu_to_le16(HCI_DEV_NONE); + hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); + + return skb; +} + +static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index, + u16 opcode, u16 len, + const void *buf) +{ + struct hci_mon_hdr *hdr; + struct sk_buff *skb; + + skb = bt_skb_alloc(6 + len, GFP_ATOMIC); + if (!skb) + return NULL; + + put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); + put_unaligned_le16(opcode, skb_put(skb, 2)); + + if (buf) + memcpy(skb_put(skb, len), buf, len); + + __net_timestamp(skb); + + hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr->opcode = cpu_to_le16(HCI_MON_CTRL_COMMAND); + hdr->index = cpu_to_le16(index); + hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); + + return skb; +} + static void __printf(2, 3) send_monitor_note(struct sock *sk, const char *fmt, ...) { @@ -458,6 +672,26 @@ static void send_monitor_replay(struct sock *sk) read_unlock(&hci_dev_list_lock); } +static void send_monitor_control_replay(struct sock *mon_sk) +{ + struct sock *sk; + + read_lock(&hci_sk_list.lock); + + sk_for_each(sk, &hci_sk_list.head) { + struct sk_buff *skb; + + skb = create_monitor_ctrl_open(sk); + if (!skb) + continue; + + if (sock_queue_rcv_skb(mon_sk, skb)) + kfree_skb(skb); + } + + read_unlock(&hci_sk_list.lock); +} + /* Generate internal stack event */ static void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data) { @@ -585,6 +819,7 @@ static int hci_sock_release(struct socket *sock) { struct sock *sk = sock->sk; struct hci_dev *hdev; + struct sk_buff *skb; BT_DBG("sock %p sk %p", sock, sk); @@ -593,8 +828,24 @@ static int hci_sock_release(struct socket *sock) hdev = hci_pi(sk)->hdev; - if (hci_pi(sk)->channel == HCI_CHANNEL_MONITOR) + switch (hci_pi(sk)->channel) { + case HCI_CHANNEL_MONITOR: atomic_dec(&monitor_promisc); + break; + case HCI_CHANNEL_RAW: + case HCI_CHANNEL_USER: + case HCI_CHANNEL_CONTROL: + /* Send event to monitor */ + skb = create_monitor_ctrl_close(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + + hci_sock_free_cookie(sk); + break; + } bt_sock_unlink(&hci_sk_list, sk); @@ -721,6 +972,27 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, goto done; } + /* When calling an ioctl on an unbound raw socket, then ensure + * that the monitor gets informed. Ensure that the resulting event + * is only send once by checking if the cookie exists or not. The + * socket cookie will be only ever generated once for the lifetime + * of a given socket. + */ + if (hci_sock_gen_cookie(sk)) { + struct sk_buff *skb; + + if (capable(CAP_NET_ADMIN)) + hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); + + /* Send event to monitor */ + skb = create_monitor_ctrl_open(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + } + release_sock(sk); switch (cmd) { @@ -784,6 +1056,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_hci haddr; struct sock *sk = sock->sk; struct hci_dev *hdev = NULL; + struct sk_buff *skb; int len, err = 0; BT_DBG("sock %p sk %p", sock, sk); @@ -822,7 +1095,35 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, atomic_inc(&hdev->promisc); } + hci_pi(sk)->channel = haddr.hci_channel; + + if (!hci_sock_gen_cookie(sk)) { + /* In the case when a cookie has already been assigned, + * then there has been already an ioctl issued against + * an unbound socket and with that triggerd an open + * notification. Send a close notification first to + * allow the state transition to bounded. + */ + skb = create_monitor_ctrl_close(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + } + + if (capable(CAP_NET_ADMIN)) + hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); + hci_pi(sk)->hdev = hdev; + + /* Send event to monitor */ + skb = create_monitor_ctrl_open(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } break; case HCI_CHANNEL_USER: @@ -884,9 +1185,38 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, } } - atomic_inc(&hdev->promisc); + hci_pi(sk)->channel = haddr.hci_channel; + + if (!hci_sock_gen_cookie(sk)) { + /* In the case when a cookie has already been assigned, + * this socket will transition from a raw socket into + * an user channel socket. For a clean transition, send + * the close notification first. + */ + skb = create_monitor_ctrl_close(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + } + + /* The user channel is restricted to CAP_NET_ADMIN + * capabilities and with that implicitly trusted. + */ + hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); hci_pi(sk)->hdev = hdev; + + /* Send event to monitor */ + skb = create_monitor_ctrl_open(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + + atomic_inc(&hdev->promisc); break; case HCI_CHANNEL_MONITOR: @@ -900,6 +1230,8 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, goto done; } + hci_pi(sk)->channel = haddr.hci_channel; + /* The monitor interface is restricted to CAP_NET_RAW * capabilities and with that implicitly trusted. */ @@ -908,9 +1240,10 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, send_monitor_note(sk, "Linux version %s (%s)", init_utsname()->release, init_utsname()->machine); - send_monitor_note(sk, "Bluetooth subsystem version %s", - BT_SUBSYS_VERSION); + send_monitor_note(sk, "Bluetooth subsystem version %u.%u", + BT_SUBSYS_VERSION, BT_SUBSYS_REVISION); send_monitor_replay(sk); + send_monitor_control_replay(sk); atomic_inc(&monitor_promisc); break; @@ -925,6 +1258,8 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, err = -EPERM; goto done; } + + hci_pi(sk)->channel = haddr.hci_channel; break; default: @@ -946,6 +1281,8 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (capable(CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); + hci_pi(sk)->channel = haddr.hci_channel; + /* At the moment the index and unconfigured index events * are enabled unconditionally. Setting them on each * socket when binding keeps this functionality. They @@ -956,16 +1293,40 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, * received by untrusted users. Example for such events * are changes to settings, class of device, name etc. */ - if (haddr.hci_channel == HCI_CHANNEL_CONTROL) { + if (hci_pi(sk)->channel == HCI_CHANNEL_CONTROL) { + if (!hci_sock_gen_cookie(sk)) { + /* In the case when a cookie has already been + * assigned, this socket will transtion from + * a raw socket into a control socket. To + * allow for a clean transtion, send the + * close notification first. + */ + skb = create_monitor_ctrl_close(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + } + + /* Send event to monitor */ + skb = create_monitor_ctrl_open(sk); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + hci_sock_set_flag(sk, HCI_MGMT_INDEX_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS); - hci_sock_set_flag(sk, HCI_MGMT_GENERIC_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_OPTION_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_SETTING_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_DEV_CLASS_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_LOCAL_NAME_EVENTS); } break; } - - hci_pi(sk)->channel = haddr.hci_channel; sk->sk_state = BT_BOUND; done: @@ -1133,6 +1494,19 @@ static int hci_mgmt_cmd(struct hci_mgmt_chan *chan, struct sock *sk, goto done; } + if (chan->channel == HCI_CHANNEL_CONTROL) { + struct sk_buff *skb; + + /* Send event to monitor */ + skb = create_monitor_ctrl_command(sk, index, opcode, len, + buf + sizeof(*hdr)); + if (skb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(skb); + } + } + if (opcode >= chan->handler_count || chan->handlers[opcode].func == NULL) { BT_DBG("Unknown op %u", opcode); @@ -1440,6 +1814,9 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, BT_DBG("sk %p, opt %d", sk, optname); + if (level != SOL_HCI) + return -ENOPROTOOPT; + lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { @@ -1523,6 +1900,9 @@ static int hci_sock_getsockopt(struct socket *sock, int level, int optname, BT_DBG("sk %p, opt %d", sk, optname); + if (level != SOL_HCI) + return -ENOPROTOOPT; + if (get_user(len, optlen)) return -EFAULT; diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c index 8319c84..cb670b5 100644 --- a/net/bluetooth/leds.c +++ b/net/bluetooth/leds.c @@ -11,6 +11,8 @@ #include "leds.h" +DEFINE_LED_TRIGGER(bt_power_led_trigger); + struct hci_basic_led_trigger { struct led_trigger led_trigger; struct hci_dev *hdev; @@ -24,6 +26,21 @@ void hci_leds_update_powered(struct hci_dev *hdev, bool enabled) if (hdev->power_led) led_trigger_event(hdev->power_led, enabled ? LED_FULL : LED_OFF); + + if (!enabled) { + struct hci_dev *d; + + read_lock(&hci_dev_list_lock); + + list_for_each_entry(d, &hci_dev_list, list) { + if (test_bit(HCI_UP, &d->flags)) + enabled = true; + } + + read_unlock(&hci_dev_list_lock); + } + + led_trigger_event(bt_power_led_trigger, enabled ? LED_FULL : LED_OFF); } static void power_activate(struct led_classdev *led_cdev) @@ -72,3 +89,13 @@ void hci_leds_init(struct hci_dev *hdev) /* initialize power_led */ hdev->power_led = led_allocate_basic(hdev, power_activate, "power"); } + +void bt_leds_init(void) +{ + led_trigger_register_simple("bluetooth-power", &bt_power_led_trigger); +} + +void bt_leds_cleanup(void) +{ + led_trigger_unregister_simple(bt_power_led_trigger); +} diff --git a/net/bluetooth/leds.h b/net/bluetooth/leds.h index a9c4d6e..08725a2 100644 --- a/net/bluetooth/leds.h +++ b/net/bluetooth/leds.h @@ -7,10 +7,20 @@ */ #if IS_ENABLED(CONFIG_BT_LEDS) + void hci_leds_update_powered(struct hci_dev *hdev, bool enabled); void hci_leds_init(struct hci_dev *hdev); + +void bt_leds_init(void); +void bt_leds_cleanup(void); + #else + static inline void hci_leds_update_powered(struct hci_dev *hdev, bool enabled) {} static inline void hci_leds_init(struct hci_dev *hdev) {} + +static inline void bt_leds_init(void) {} +static inline void bt_leds_cleanup(void) {} + #endif diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7639290..7b2bac4 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -38,7 +38,7 @@ #include "mgmt_util.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 13 +#define MGMT_REVISION 14 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -104,6 +104,8 @@ static const u16 mgmt_commands[] = { MGMT_OP_REMOVE_ADVERTISING, MGMT_OP_GET_ADV_SIZE_INFO, MGMT_OP_START_LIMITED_DISCOVERY, + MGMT_OP_READ_EXT_INFO, + MGMT_OP_SET_APPEARANCE, }; static const u16 mgmt_events[] = { @@ -141,6 +143,7 @@ static const u16 mgmt_events[] = { MGMT_EV_LOCAL_OOB_DATA_UPDATED, MGMT_EV_ADVERTISING_ADDED, MGMT_EV_ADVERTISING_REMOVED, + MGMT_EV_EXT_INFO_CHANGED, }; static const u16 mgmt_untrusted_commands[] = { @@ -149,6 +152,7 @@ static const u16 mgmt_untrusted_commands[] = { MGMT_OP_READ_UNCONF_INDEX_LIST, MGMT_OP_READ_CONFIG_INFO, MGMT_OP_READ_EXT_INDEX_LIST, + MGMT_OP_READ_EXT_INFO, }; static const u16 mgmt_untrusted_events[] = { @@ -162,6 +166,7 @@ static const u16 mgmt_untrusted_events[] = { MGMT_EV_NEW_CONFIG_OPTIONS, MGMT_EV_EXT_INDEX_ADDED, MGMT_EV_EXT_INDEX_REMOVED, + MGMT_EV_EXT_INFO_CHANGED, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -256,13 +261,6 @@ static int mgmt_limited_event(u16 event, struct hci_dev *hdev, void *data, flag, skip_sk); } -static int mgmt_generic_event(u16 event, struct hci_dev *hdev, void *data, - u16 len, struct sock *skip_sk) -{ - return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len, - HCI_MGMT_GENERIC_EVENTS, skip_sk); -} - static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 len, struct sock *skip_sk) { @@ -278,6 +276,14 @@ static u8 le_addr_type(u8 mgmt_addr_type) return ADDR_LE_DEV_RANDOM; } +void mgmt_fill_version_info(void *ver) +{ + struct mgmt_rp_read_version *rp = ver; + + rp->version = MGMT_VERSION; + rp->revision = cpu_to_le16(MGMT_REVISION); +} + static int read_version(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { @@ -285,8 +291,7 @@ static int read_version(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("sock %p", sk); - rp.version = MGMT_VERSION; - rp.revision = cpu_to_le16(MGMT_REVISION); + mgmt_fill_version_info(&rp); return mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, &rp, sizeof(rp)); @@ -572,8 +577,8 @@ static int new_options(struct hci_dev *hdev, struct sock *skip) { __le32 options = get_missing_options(hdev); - return mgmt_generic_event(MGMT_EV_NEW_CONFIG_OPTIONS, hdev, &options, - sizeof(options), skip); + return mgmt_limited_event(MGMT_EV_NEW_CONFIG_OPTIONS, hdev, &options, + sizeof(options), HCI_MGMT_OPTION_EVENTS, skip); } static int send_options_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) @@ -862,6 +867,107 @@ static int read_controller_info(struct sock *sk, struct hci_dev *hdev, sizeof(rp)); } +static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, + u8 data_len) +{ + eir[eir_len++] = sizeof(type) + data_len; + eir[eir_len++] = type; + memcpy(&eir[eir_len], data, data_len); + eir_len += data_len; + + return eir_len; +} + +static inline u16 eir_append_le16(u8 *eir, u16 eir_len, u8 type, u16 data) +{ + eir[eir_len++] = sizeof(type) + sizeof(data); + eir[eir_len++] = type; + put_unaligned_le16(data, &eir[eir_len]); + eir_len += sizeof(data); + + return eir_len; +} + +static u16 append_eir_data_to_buf(struct hci_dev *hdev, u8 *eir) +{ + u16 eir_len = 0; + size_t name_len; + + if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + eir_len = eir_append_data(eir, eir_len, EIR_CLASS_OF_DEV, + hdev->dev_class, 3); + + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + eir_len = eir_append_le16(eir, eir_len, EIR_APPEARANCE, + hdev->appearance); + + name_len = strlen(hdev->dev_name); + eir_len = eir_append_data(eir, eir_len, EIR_NAME_COMPLETE, + hdev->dev_name, name_len); + + name_len = strlen(hdev->short_name); + eir_len = eir_append_data(eir, eir_len, EIR_NAME_SHORT, + hdev->short_name, name_len); + + return eir_len; +} + +static int read_ext_controller_info(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + char buf[512]; + struct mgmt_rp_read_ext_info *rp = (void *)buf; + u16 eir_len; + + BT_DBG("sock %p %s", sk, hdev->name); + + memset(&buf, 0, sizeof(buf)); + + hci_dev_lock(hdev); + + bacpy(&rp->bdaddr, &hdev->bdaddr); + + rp->version = hdev->hci_ver; + rp->manufacturer = cpu_to_le16(hdev->manufacturer); + + rp->supported_settings = cpu_to_le32(get_supported_settings(hdev)); + rp->current_settings = cpu_to_le32(get_current_settings(hdev)); + + + eir_len = append_eir_data_to_buf(hdev, rp->eir); + rp->eir_len = cpu_to_le16(eir_len); + + hci_dev_unlock(hdev); + + /* If this command is called at least once, then the events + * for class of device and local name changes are disabled + * and only the new extended controller information event + * is used. + */ + hci_sock_set_flag(sk, HCI_MGMT_EXT_INFO_EVENTS); + hci_sock_clear_flag(sk, HCI_MGMT_DEV_CLASS_EVENTS); + hci_sock_clear_flag(sk, HCI_MGMT_LOCAL_NAME_EVENTS); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_EXT_INFO, 0, rp, + sizeof(*rp) + eir_len); +} + +static int ext_info_changed(struct hci_dev *hdev, struct sock *skip) +{ + char buf[512]; + struct mgmt_ev_ext_info_changed *ev = (void *)buf; + u16 eir_len; + + memset(buf, 0, sizeof(buf)); + + eir_len = append_eir_data_to_buf(hdev, ev->eir); + ev->eir_len = cpu_to_le16(eir_len); + + return mgmt_limited_event(MGMT_EV_EXT_INFO_CHANGED, hdev, ev, + sizeof(*ev) + eir_len, + HCI_MGMT_EXT_INFO_EVENTS, skip); +} + static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) { __le32 settings = cpu_to_le32(get_current_settings(hdev)); @@ -922,7 +1028,7 @@ static int clean_up_hci_state(struct hci_dev *hdev) hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } - hci_req_clear_adv_instance(hdev, NULL, 0x00, false); + hci_req_clear_adv_instance(hdev, NULL, NULL, 0x00, false); if (hci_dev_test_flag(hdev, HCI_LE_ADV)) __hci_req_disable_advertising(&req); @@ -1000,8 +1106,8 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip) { __le32 ev = cpu_to_le32(get_current_settings(hdev)); - return mgmt_generic_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, - sizeof(ev), skip); + return mgmt_limited_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, + sizeof(ev), HCI_MGMT_SETTING_EVENTS, skip); } int mgmt_new_settings(struct hci_dev *hdev) @@ -1690,7 +1796,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) enabled = lmp_host_le_capable(hdev); if (!val) - hci_req_clear_adv_instance(hdev, NULL, 0x00, true); + hci_req_clear_adv_instance(hdev, NULL, NULL, 0x00, true); if (!hdev_is_powered(hdev) || val == enabled) { bool changed = false; @@ -2513,8 +2619,8 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG(""); if (cp->io_capability > SMP_IO_KEYBOARD_DISPLAY) - return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, - MGMT_STATUS_INVALID_PARAMS, NULL, 0); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); @@ -2932,6 +3038,35 @@ static int user_passkey_neg_reply(struct sock *sk, struct hci_dev *hdev, HCI_OP_USER_PASSKEY_NEG_REPLY, 0); } +static void adv_expire(struct hci_dev *hdev, u32 flags) +{ + struct adv_info *adv_instance; + struct hci_request req; + int err; + + adv_instance = hci_find_adv_instance(hdev, hdev->cur_adv_instance); + if (!adv_instance) + return; + + /* stop if current instance doesn't need to be changed */ + if (!(adv_instance->flags & flags)) + return; + + cancel_adv_timeout(hdev); + + adv_instance = hci_get_next_instance(hdev, adv_instance->instance); + if (!adv_instance) + return; + + hci_req_init(&req, hdev); + err = __hci_req_schedule_adv_instance(&req, adv_instance->instance, + true); + if (err) + return; + + hci_req_run(&req, NULL); +} + static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct mgmt_cp_set_local_name *cp; @@ -2947,13 +3082,17 @@ static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode) cp = cmd->param; - if (status) + if (status) { mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, mgmt_status(status)); - else + } else { mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, cp, sizeof(*cp)); + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + adv_expire(hdev, MGMT_ADV_FLAG_LOCAL_NAME); + } + mgmt_pending_remove(cmd); unlock: @@ -2993,8 +3132,9 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, if (err < 0) goto failed; - err = mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, - data, len, sk); + err = mgmt_limited_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, data, + len, HCI_MGMT_LOCAL_NAME_EVENTS, sk); + ext_info_changed(hdev, sk); goto failed; } @@ -3029,6 +3169,40 @@ failed: return err; } +static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + struct mgmt_cp_set_appearance *cp = data; + u16 apperance; + int err; + + BT_DBG(""); + + if (!lmp_le_capable(hdev)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_APPEARANCE, + MGMT_STATUS_NOT_SUPPORTED); + + apperance = le16_to_cpu(cp->appearance); + + hci_dev_lock(hdev); + + if (hdev->appearance != apperance) { + hdev->appearance = apperance; + + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + adv_expire(hdev, MGMT_ADV_FLAG_APPEARANCE); + + ext_info_changed(hdev, sk); + } + + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_APPEARANCE, 0, NULL, + 0); + + hci_dev_unlock(hdev); + + return err; +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -4869,7 +5043,7 @@ static int clock_info_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) int err; memset(&rp, 0, sizeof(rp)); - memcpy(&rp.addr, &cmd->param, sizeof(rp.addr)); + memcpy(&rp.addr, cmd->param, sizeof(rp.addr)); if (status) goto complete; @@ -5501,17 +5675,6 @@ unlock: return err; } -static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, - u8 data_len) -{ - eir[eir_len++] = sizeof(type) + data_len; - eir[eir_len++] = type; - memcpy(&eir[eir_len], data, data_len); - eir_len += data_len; - - return eir_len; -} - static void read_local_oob_ext_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -5815,6 +5978,8 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev) flags |= MGMT_ADV_FLAG_DISCOV; flags |= MGMT_ADV_FLAG_LIMITED_DISCOV; flags |= MGMT_ADV_FLAG_MANAGED_FLAGS; + flags |= MGMT_ADV_FLAG_APPEARANCE; + flags |= MGMT_ADV_FLAG_LOCAL_NAME; if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) flags |= MGMT_ADV_FLAG_TX_POWER; @@ -5871,28 +6036,59 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, return err; } -static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, - u8 len, bool is_adv_data) +static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data) { u8 max_len = HCI_MAX_AD_LENGTH; - int i, cur_len; - bool flags_managed = false; - bool tx_power_managed = false; if (is_adv_data) { if (adv_flags & (MGMT_ADV_FLAG_DISCOV | MGMT_ADV_FLAG_LIMITED_DISCOV | - MGMT_ADV_FLAG_MANAGED_FLAGS)) { - flags_managed = true; + MGMT_ADV_FLAG_MANAGED_FLAGS)) max_len -= 3; - } - if (adv_flags & MGMT_ADV_FLAG_TX_POWER) { - tx_power_managed = true; + if (adv_flags & MGMT_ADV_FLAG_TX_POWER) max_len -= 3; - } + } else { + /* at least 1 byte of name should fit in */ + if (adv_flags & MGMT_ADV_FLAG_LOCAL_NAME) + max_len -= 3; + + if (adv_flags & (MGMT_ADV_FLAG_APPEARANCE)) + max_len -= 4; } + return max_len; +} + +static bool flags_managed(u32 adv_flags) +{ + return adv_flags & (MGMT_ADV_FLAG_DISCOV | + MGMT_ADV_FLAG_LIMITED_DISCOV | + MGMT_ADV_FLAG_MANAGED_FLAGS); +} + +static bool tx_power_managed(u32 adv_flags) +{ + return adv_flags & MGMT_ADV_FLAG_TX_POWER; +} + +static bool name_managed(u32 adv_flags) +{ + return adv_flags & MGMT_ADV_FLAG_LOCAL_NAME; +} + +static bool appearance_managed(u32 adv_flags) +{ + return adv_flags & MGMT_ADV_FLAG_APPEARANCE; +} + +static bool tlv_data_is_valid(u32 adv_flags, u8 *data, u8 len, bool is_adv_data) +{ + int i, cur_len; + u8 max_len; + + max_len = tlv_data_max_len(adv_flags, is_adv_data); + if (len > max_len) return false; @@ -5900,10 +6096,21 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) { cur_len = data[i]; - if (flags_managed && data[i + 1] == EIR_FLAGS) + if (data[i + 1] == EIR_FLAGS && + (!is_adv_data || flags_managed(adv_flags))) + return false; + + if (data[i + 1] == EIR_TX_POWER && tx_power_managed(adv_flags)) + return false; + + if (data[i + 1] == EIR_NAME_COMPLETE && name_managed(adv_flags)) return false; - if (tx_power_managed && data[i + 1] == EIR_TX_POWER) + if (data[i + 1] == EIR_NAME_SHORT && name_managed(adv_flags)) + return false; + + if (data[i + 1] == EIR_APPEARANCE && + appearance_managed(adv_flags)) return false; /* If the current field length would exceed the total data @@ -6027,8 +6234,8 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (!tlv_data_is_valid(hdev, flags, cp->data, cp->adv_data_len, true) || - !tlv_data_is_valid(hdev, flags, cp->data + cp->adv_data_len, + if (!tlv_data_is_valid(flags, cp->data, cp->adv_data_len, true) || + !tlv_data_is_valid(flags, cp->data + cp->adv_data_len, cp->scan_rsp_len, false)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); @@ -6175,7 +6382,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); - hci_req_clear_adv_instance(hdev, &req, cp->instance, true); + hci_req_clear_adv_instance(hdev, sk, &req, cp->instance, true); if (list_empty(&hdev->adv_instances)) __hci_req_disable_advertising(&req); @@ -6211,23 +6418,6 @@ unlock: return err; } -static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data) -{ - u8 max_len = HCI_MAX_AD_LENGTH; - - if (is_adv_data) { - if (adv_flags & (MGMT_ADV_FLAG_DISCOV | - MGMT_ADV_FLAG_LIMITED_DISCOV | - MGMT_ADV_FLAG_MANAGED_FLAGS)) - max_len -= 3; - - if (adv_flags & MGMT_ADV_FLAG_TX_POWER) - max_len -= 3; - } - - return max_len; -} - static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { @@ -6356,6 +6546,9 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { remove_advertising, MGMT_REMOVE_ADVERTISING_SIZE }, { get_adv_size_info, MGMT_GET_ADV_SIZE_INFO_SIZE }, { start_limited_discovery, MGMT_START_DISCOVERY_SIZE }, + { read_ext_controller_info,MGMT_READ_EXT_INFO_SIZE, + HCI_MGMT_UNTRUSTED }, + { set_appearance, MGMT_SET_APPEARANCE_SIZE }, }; void mgmt_index_added(struct hci_dev *hdev) @@ -6494,9 +6687,12 @@ void __mgmt_power_off(struct hci_dev *hdev) mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); - if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) - mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, - zero_cod, sizeof(zero_cod), NULL); + if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) { + mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, + zero_cod, sizeof(zero_cod), + HCI_MGMT_DEV_CLASS_EVENTS, NULL); + ext_info_changed(hdev, NULL); + } new_settings(hdev, match.sk); @@ -7092,9 +7288,11 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, sk_lookup, &match); mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match); - if (!status) - mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, - dev_class, 3, NULL); + if (!status) { + mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class, + 3, HCI_MGMT_DEV_CLASS_EVENTS, NULL); + ext_info_changed(hdev, NULL); + } if (match.sk) sock_put(match.sk); @@ -7123,8 +7321,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) return; } - mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev), - cmd ? cmd->sk : NULL); + mgmt_limited_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev), + HCI_MGMT_LOCAL_NAME_EVENTS, cmd ? cmd->sk : NULL); + ext_info_changed(hdev, cmd ? cmd->sk : NULL); } static inline bool has_uuid(u8 *uuid, u16 uuid_count, u8 (*uuids)[16]) diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index 8c30c7e..c933bd0 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -21,12 +21,41 @@ SOFTWARE IS DISCLAIMED. */ +#include <asm/unaligned.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/hci_mon.h> #include <net/bluetooth/mgmt.h> #include "mgmt_util.h" +static struct sk_buff *create_monitor_ctrl_event(__le16 index, u32 cookie, + u16 opcode, u16 len, void *buf) +{ + struct hci_mon_hdr *hdr; + struct sk_buff *skb; + + skb = bt_skb_alloc(6 + len, GFP_ATOMIC); + if (!skb) + return NULL; + + put_unaligned_le32(cookie, skb_put(skb, 4)); + put_unaligned_le16(opcode, skb_put(skb, 2)); + + if (buf) + memcpy(skb_put(skb, len), buf, len); + + __net_timestamp(skb); + + hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); + hdr->opcode = cpu_to_le16(HCI_MON_CTRL_EVENT); + hdr->index = index; + hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); + + return skb; +} + int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, void *data, u16 data_len, int flag, struct sock *skip_sk) { @@ -52,14 +81,18 @@ int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, __net_timestamp(skb); hci_send_to_channel(channel, skb, flag, skip_sk); - kfree_skb(skb); + if (channel == HCI_CHANNEL_CONTROL) + hci_send_monitor_ctrl_event(hdev, event, data, data_len, + skb_get_ktime(skb), flag, skip_sk); + + kfree_skb(skb); return 0; } int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) { - struct sk_buff *skb; + struct sk_buff *skb, *mskb; struct mgmt_hdr *hdr; struct mgmt_ev_cmd_status *ev; int err; @@ -80,17 +113,30 @@ int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) ev->status = status; ev->opcode = cpu_to_le16(cmd); + mskb = create_monitor_ctrl_event(hdr->index, hci_sock_get_cookie(sk), + MGMT_EV_CMD_STATUS, sizeof(*ev), ev); + if (mskb) + skb->tstamp = mskb->tstamp; + else + __net_timestamp(skb); + err = sock_queue_rcv_skb(sk, skb); if (err < 0) kfree_skb(skb); + if (mskb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, mskb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(mskb); + } + return err; } int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, void *rp, size_t rp_len) { - struct sk_buff *skb; + struct sk_buff *skb, *mskb; struct mgmt_hdr *hdr; struct mgmt_ev_cmd_complete *ev; int err; @@ -114,10 +160,24 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, if (rp) memcpy(ev->data, rp, rp_len); + mskb = create_monitor_ctrl_event(hdr->index, hci_sock_get_cookie(sk), + MGMT_EV_CMD_COMPLETE, + sizeof(*ev) + rp_len, ev); + if (mskb) + skb->tstamp = mskb->tstamp; + else + __net_timestamp(skb); + err = sock_queue_rcv_skb(sk, skb); if (err < 0) kfree_skb(skb); + if (mskb) { + hci_send_to_channel(HCI_CHANNEL_MONITOR, mskb, + HCI_SOCK_TRUSTED, NULL); + kfree_skb(mskb); + } + return err; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 4c1a16a..43faf2a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3387,7 +3387,10 @@ int smp_register(struct hci_dev *hdev) if (!lmp_sc_capable(hdev)) { debugfs_create_file("force_bredr_smp", 0644, hdev->debugfs, hdev, &force_bredr_smp_fops); - return 0; + + /* Flag can be already set here (due to power toggle) */ + if (!hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP)) + return 0; } if (WARN_ON(hdev->smp_bredr_data)) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8a43684..855b72f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,13 +80,10 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; - if (dev->flags & IFF_NOARP) + if ((dev->flags & IFF_NOARP) || + !pskb_may_pull(skb, arp_hdr_len(dev))) return; - if (!pskb_may_pull(skb, arp_hdr_len(dev))) { - dev->stats.tx_dropped++; - return; - } parp = arp_hdr(skb); if (parp->ar_pro != htons(ETH_P_IP) || diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a5423a1..c5fea93 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1138,7 +1138,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, } else { err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 341caa0..d8ad73b 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -134,17 +134,36 @@ void br_stp_disable_port(struct net_bridge_port *p) br_become_root_bridge(br); } -static void br_stp_start(struct net_bridge *br) +static int br_stp_call_user(struct net_bridge *br, char *arg) { - int r; - char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; + char *argv[] = { BR_STP_PROG, br->dev->name, arg, NULL }; char *envp[] = { NULL }; + int rc; + + /* call userspace STP and report program errors */ + rc = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + if (rc > 0) { + if (rc & 0xff) + br_debug(br, BR_STP_PROG " received signal %d\n", + rc & 0x7f); + else + br_debug(br, BR_STP_PROG " exited with code %d\n", + (rc >> 8) & 0xff); + } + + return rc; +} + +static void br_stp_start(struct net_bridge *br) +{ struct net_bridge_port *p; + int err = -ENOENT; if (net_eq(dev_net(br->dev), &init_net)) - r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); - else - r = -ENOENT; + err = br_stp_call_user(br, "start"); + + if (err && err != -ENOENT) + br_err(br, "failed to start userspace STP (%d)\n", err); spin_lock_bh(&br->lock); @@ -153,9 +172,10 @@ static void br_stp_start(struct net_bridge *br) else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); - if (r == 0) { + if (!err) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); + /* Stop hello and hold timers */ del_timer(&br->hello_timer); list_for_each_entry(p, &br->port_list, list) @@ -173,14 +193,13 @@ static void br_stp_start(struct net_bridge *br) static void br_stp_stop(struct net_bridge *br) { - int r; - char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL }; - char *envp[] = { NULL }; struct net_bridge_port *p; + int err; if (br->stp_enabled == BR_USER_STP) { - r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); - br_info(br, "userspace STP stopped, return code %d\n", r); + err = br_stp_call_user(br, "stop"); + if (err) + br_err(br, "failed to stop userspace STP (%d)\n", err); /* To start timers on any ports left in blocking */ mod_timer(&br->hello_timer, jiffies + br->hello_time); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index dd71332..f5c11bb 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -368,6 +368,8 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0); if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) { + if (!IS_ERR(match)) + module_put(match->me); request_module("ebt_%s", m->u.name); match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0); } diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 4b901d9..ad47a92 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -86,6 +86,7 @@ static const struct nft_expr_ops nft_meta_bridge_set_ops = { .init = nft_meta_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, + .validate = nft_meta_set_validate, }; static const struct nft_expr_ops * diff --git a/net/core/dev.c b/net/core/dev.c index 0649194..c0c291f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3904,8 +3904,7 @@ static void net_tx_action(struct softirq_action *h) } } -#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ - (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) +#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; @@ -3965,6 +3964,22 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } /** + * netdev_is_rx_handler_busy - check if receive handler is registered + * @dev: device to check + * + * Check if a receive handler is already registered for a given device. + * Return true if there one. + * + * The caller must hold the rtnl_mutex. + */ +bool netdev_is_rx_handler_busy(struct net_device *dev) +{ + ASSERT_RTNL(); + return dev && rtnl_dereference(dev->rx_handler); +} +EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); + +/** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register diff --git a/net/core/filter.c b/net/core/filter.c index a83766b..00351cd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -94,14 +94,13 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) } EXPORT_SYMBOL(sk_filter_trim_cap); -static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb) { - return skb_get_poff((struct sk_buff *)(unsigned long) ctx); + return skb_get_poff(skb); } -static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -120,9 +119,8 @@ static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return 0; } -static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -145,7 +143,7 @@ static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return 0; } -static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_0(__get_raw_cpu_id) { return raw_smp_processor_id(); } @@ -233,9 +231,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ @@ -1365,6 +1362,11 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, return err; } +static int bpf_try_make_head_writable(struct sk_buff *skb) +{ + return bpf_try_make_writable(skb, skb_headlen(skb)); +} + static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) @@ -1377,12 +1379,9 @@ static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } -static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) +BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, + const void *, from, u32, len, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - unsigned int offset = (unsigned int) r2; - void *from = (void *) (long) r3; - unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) @@ -1417,12 +1416,9 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, + void *, to, u32, len) { - const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - unsigned int offset = (unsigned int) r2; - void *to = (void *)(unsigned long) r3; - unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(offset > 0xffff)) @@ -1450,10 +1446,31 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_STACK_SIZE, }; -static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto bpf_skb_pull_data_proto = { + .func = bpf_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, + u64, from, u64, to, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - unsigned int offset = (unsigned int) r2; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) @@ -1495,12 +1512,11 @@ static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, + u64, from, u64, to, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - unsigned int offset = (unsigned int) r2; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | @@ -1548,12 +1564,11 @@ static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) +BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, + __be32 *, to, u32, to_size, __wsum, seed) { struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); - u64 diff_size = from_size + to_size; - __be32 *from = (__be32 *) (long) r1; - __be32 *to = (__be32 *) (long) r3; + u32 diff_size = from_size + to_size; int i, j = 0; /* This is quite flexible, some examples: @@ -1579,6 +1594,7 @@ static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_STACK, .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, @@ -1587,6 +1603,26 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { .arg5_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) +{ + /* The interface is to be used in combination with bpf_csum_diff() + * for direct packet writes. csum rotation for alignment as well + * as emulating csum_sub() can be done from the eBPF program. + */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + return (skb->csum = csum_add(skb->csum, csum)); + + return -ENOTSUPP; +} + +static const struct bpf_func_proto bpf_csum_update_proto = { + .func = bpf_csum_update, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb(dev, skb); @@ -1611,10 +1647,11 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) return ret; } -static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; struct net_device *dev; + struct sk_buff *clone; + int ret; if (unlikely(flags & ~(BPF_F_INGRESS))) return -EINVAL; @@ -1623,14 +1660,25 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) if (unlikely(!dev)) return -EINVAL; - skb = skb_clone(skb, GFP_ATOMIC); - if (unlikely(!skb)) + clone = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!clone)) return -ENOMEM; - bpf_push_mac_rcsum(skb); + /* For direct write, we need to keep the invariant that the skbs + * we're dealing with need to be uncloned. Should uncloning fail + * here, we need to free the just generated clone to unclone once + * again. + */ + ret = bpf_try_make_head_writable(skb); + if (unlikely(ret)) { + kfree_skb(clone); + return -ENOMEM; + } + + bpf_push_mac_rcsum(clone); return flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); + __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone); } static const struct bpf_func_proto bpf_clone_redirect_proto = { @@ -1649,7 +1697,7 @@ struct redirect_info { static DEFINE_PER_CPU(struct redirect_info, redirect_info); -static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); @@ -1688,9 +1736,9 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { - return task_get_classid((struct sk_buff *) (unsigned long) r1); + return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { @@ -1700,9 +1748,9 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { - return dst_tclassid((struct sk_buff *) (unsigned long) r1); + return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { @@ -1712,14 +1760,14 @@ static const struct bpf_func_proto bpf_get_route_realm_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_get_hash_recalc(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ - return skb_get_hash((struct sk_buff *) (unsigned long) r1); + return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { @@ -1729,10 +1777,25 @@ static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) +BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) +{ + /* After all direct packet write, this can be used once for + * triggering a lazy recalc on next skb_get_hash() invocation. + */ + skb_clear_hash(skb); + return 0; +} + +static const struct bpf_func_proto bpf_set_hash_invalid_proto = { + .func = bpf_set_hash_invalid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, + u16, vlan_tci) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - __be16 vlan_proto = (__force __be16) r2; int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && @@ -1757,9 +1820,8 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = { }; EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); -static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; int ret; bpf_push_mac_rcsum(skb); @@ -1934,10 +1996,9 @@ static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) return -ENOTSUPP; } -static u64 bpf_skb_change_proto(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, + u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - __be16 proto = (__force __be16) r2; int ret; if (unlikely(flags)) @@ -1974,11 +2035,8 @@ static const struct bpf_func_proto bpf_skb_change_proto_proto = { .arg3_type = ARG_ANYTHING, }; -static u64 bpf_skb_change_type(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u32 pkt_type = r2; - /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) @@ -2010,8 +2068,7 @@ static u32 __bpf_skb_min_len(const struct sk_buff *skb) static u32 __bpf_skb_max_len(const struct sk_buff *skb) { - return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : - 65536; + return skb->dev->mtu + skb->dev->hard_header_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) @@ -2030,12 +2087,11 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -static u64 bpf_skb_change_tail(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) { - struct sk_buff *skb = (struct sk_buff *)(long) r1; u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); - u32 new_len = (u32) r2; int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) @@ -2084,19 +2140,14 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { bool bpf_helper_changes_skb_data(void *func) { - if (func == bpf_skb_vlan_push) - return true; - if (func == bpf_skb_vlan_pop) - return true; - if (func == bpf_skb_store_bytes) - return true; - if (func == bpf_skb_change_proto) - return true; - if (func == bpf_skb_change_tail) - return true; - if (func == bpf_l3_csum_replace) - return true; - if (func == bpf_l4_csum_replace) + if (func == bpf_skb_vlan_push || + func == bpf_skb_vlan_pop || + func == bpf_skb_store_bytes || + func == bpf_skb_change_proto || + func == bpf_skb_change_tail || + func == bpf_skb_pull_data || + func == bpf_l3_csum_replace || + func == bpf_l4_csum_replace) return true; return false; @@ -2115,13 +2166,10 @@ static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, return 0; } -static u64 bpf_skb_event_output(u64 r1, u64 r2, u64 flags, u64 r4, - u64 meta_size) +BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, + u64, flags, void *, meta, u64, meta_size) { - struct sk_buff *skb = (struct sk_buff *)(long) r1; - struct bpf_map *map = (struct bpf_map *)(long) r2; u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; - void *meta = (void *)(long) r4; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; @@ -2148,10 +2196,9 @@ static unsigned short bpf_tunnel_key_af(u64 flags) return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } -static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, + u32, size, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2; const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; @@ -2216,10 +2263,8 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static u64 bpf_skb_get_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u8 *to = (u8 *) (long) r2; const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; @@ -2254,10 +2299,9 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { static struct metadata_dst __percpu *md_dst; -static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, + const struct bpf_tunnel_key *, from, u32, size, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - struct bpf_tunnel_key *from = (struct bpf_tunnel_key *) (long) r2; struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; @@ -2275,7 +2319,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); - from = (struct bpf_tunnel_key *)compat; + from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; @@ -2325,10 +2369,9 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, + const u8 *, from, u32, size) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u8 *from = (u8 *) (long) r2; struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); @@ -2374,23 +2417,20 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } } -static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, + u32, idx) { - struct sk_buff *skb = (struct sk_buff *)(long)r1; - struct bpf_map *map = (struct bpf_map *)(long)r2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; - u32 i = (u32)r3; - sk = skb->sk; + sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; - - if (unlikely(i >= array->map.max_entries)) + if (unlikely(idx >= array->map.max_entries)) return -E2BIG; - cgrp = READ_ONCE(array->ptrs[i]); + cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; @@ -2413,13 +2453,10 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, return 0; } -static u64 bpf_xdp_event_output(u64 r1, u64 r2, u64 flags, u64 r4, - u64 meta_size) +BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, + u64, flags, void *, meta, u64, meta_size) { - struct xdp_buff *xdp = (struct xdp_buff *)(long) r1; - struct bpf_map *map = (struct bpf_map *)(long) r2; u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; - void *meta = (void *)(long) r4; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; @@ -2475,8 +2512,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; + case BPF_FUNC_csum_update: + return &bpf_csum_update_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: @@ -2509,6 +2550,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; + case BPF_FUNC_set_hash_invalid: + return &bpf_set_hash_invalid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: @@ -2526,6 +2569,8 @@ xdp_func_proto(enum bpf_func_id func_id) switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_smp_processor_id_proto; default: return sk_filter_func_proto(func_id); } @@ -2568,6 +2613,45 @@ static bool sk_filter_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + if (!direct_write) + return 0; + + /* if (!skb->cloned) + * goto start; + * + * (Fast-path, otherwise approximation that we might be + * a clone, do the rest in helper.) + */ + *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); + + /* ret = bpf_skb_pull_data(skb, 0); */ + *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); + *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_pull_data); + /* if (!ret) + * goto restore; + * return TC_ACT_SHOT; + */ + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, TC_ACT_SHOT); + *insn++ = BPF_EXIT_INSN(); + + /* restore: */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + /* start: */ + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) @@ -2605,7 +2689,7 @@ static bool __is_valid_xdp_access(int off, int size, return false; if (off % size != 0) return false; - if (size != 4) + if (size != sizeof(__u32)) return false; return true; @@ -2636,10 +2720,10 @@ void bpf_warn_invalid_xdp_action(u32 act) } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); -static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, - int src_reg, int ctx_off, - struct bpf_insn *insn_buf, - struct bpf_prog *prog) +static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; @@ -2686,7 +2770,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, case offsetof(struct __sk_buff, ifindex): BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), dst_reg, src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); @@ -2727,7 +2811,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, dst_reg, src_reg, insn); case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); prog->cb_access = 1; @@ -2751,7 +2835,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, break; case offsetof(struct __sk_buff, data): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, data)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), dst_reg, src_reg, offsetof(struct sk_buff, data)); break; @@ -2760,8 +2844,8 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, ctx_off -= offsetof(struct __sk_buff, data_end); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct bpf_skb_data_end, data_end); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(void *)), - dst_reg, src_reg, ctx_off); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), dst_reg, src_reg, + ctx_off); break; case offsetof(struct __sk_buff, tc_index): @@ -2787,6 +2871,31 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, return insn - insn_buf; } +static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct __sk_buff, ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), + dst_reg, src_reg, + offsetof(struct sk_buff, dev)); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + offsetof(struct net_device, ifindex)); + break; + default: + return sk_filter_convert_ctx_access(type, dst_reg, src_reg, + ctx_off, insn_buf, prog); + } + + return insn - insn_buf; +} + static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn_buf, @@ -2796,12 +2905,12 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, switch (ctx_off) { case offsetof(struct xdp_md, data): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), dst_reg, src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_end): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data_end)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), dst_reg, src_reg, offsetof(struct xdp_buff, data_end)); break; @@ -2813,13 +2922,14 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = bpf_net_convert_ctx_access, + .convert_ctx_access = sk_filter_convert_ctx_access, }; static const struct bpf_verifier_ops tc_cls_act_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, - .convert_ctx_access = bpf_net_convert_ctx_access, + .convert_ctx_access = tc_cls_act_convert_ctx_access, + .gen_prologue = tc_cls_act_prologue, }; static const struct bpf_verifier_ops xdp_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a2879c0..1a7b80f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -750,11 +750,13 @@ EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; + u32 hash; __flow_hash_secret_init(); - __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd), - flow_keys_have_l4(&keys)); + hash = ___skb_get_hash(skb, &keys, hashrnd); + + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1dfca1c..3ac8946 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -843,7 +843,10 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, size += nla_total_size(num_vfs * sizeof(struct nlattr)); size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct nlattr)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + @@ -1111,14 +1114,15 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct nlattr *vfinfo) { struct ifla_vf_rss_query_en vf_rss_query_en; + struct nlattr *vf, *vfstats, *vfvlanlist; struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_vlan_info vf_vlan_info; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_stats vf_stats; struct ifla_vf_trust vf_trust; struct ifla_vf_vlan vf_vlan; struct ifla_vf_rate vf_rate; - struct nlattr *vf, *vfstats; struct ifla_vf_mac vf_mac; struct ifla_vf_info ivi; @@ -1135,11 +1139,14 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, * IFLA_VF_LINK_STATE_AUTO which equals zero */ ivi.linkstate = 0; + /* VLAN Protocol by default is 802.1Q */ + ivi.vlan_proto = htons(ETH_P_8021Q); if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi)) return 0; vf_mac.vf = vf_vlan.vf = + vf_vlan_info.vf = vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = @@ -1150,6 +1157,9 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; + vf_vlan_info.vlan = ivi.vlan; + vf_vlan_info.qos = ivi.qos; + vf_vlan_info.vlan_proto = ivi.vlan_proto; vf_tx_rate.rate = ivi.max_tx_rate; vf_rate.min_tx_rate = ivi.min_tx_rate; vf_rate.max_tx_rate = ivi.max_tx_rate; @@ -1158,10 +1168,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, vf_rss_query_en.setting = ivi.rss_query_en; vf_trust.setting = ivi.trusted; vf = nla_nest_start(skb, IFLA_VF_INFO); - if (!vf) { - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vf) + goto nla_put_vfinfo_failure; if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), @@ -1177,17 +1185,23 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, &vf_rss_query_en) || nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) - return -EMSGSIZE; + goto nla_put_vf_failure; + vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST); + if (!vfvlanlist) + goto nla_put_vf_failure; + if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info), + &vf_vlan_info)) { + nla_nest_cancel(skb, vfvlanlist); + goto nla_put_vf_failure; + } + nla_nest_end(skb, vfvlanlist); memset(&vf_stats, 0, sizeof(vf_stats)); if (dev->netdev_ops->ndo_get_vf_stats) dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, &vf_stats); vfstats = nla_nest_start(skb, IFLA_VF_STATS); - if (!vfstats) { - nla_nest_cancel(skb, vf); - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vfstats) + goto nla_put_vf_failure; if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, vf_stats.rx_packets, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS, @@ -1199,11 +1213,19 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST, vf_stats.broadcast, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast, IFLA_VF_STATS_PAD)) - return -EMSGSIZE; + vf_stats.multicast, IFLA_VF_STATS_PAD)) { + nla_nest_cancel(skb, vfstats); + goto nla_put_vf_failure; + } nla_nest_end(skb, vfstats); nla_nest_end(skb, vf); return 0; + +nla_put_vf_failure: + nla_nest_cancel(skb, vf); +nla_put_vfinfo_failure: + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; } static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) @@ -1448,6 +1470,7 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_VLAN_LIST] = { .type = NLA_NESTED }, [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, [IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) }, @@ -1704,7 +1727,34 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, - ivv->qos); + ivv->qos, + htons(ETH_P_8021Q)); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_VLAN_LIST]) { + struct ifla_vf_vlan_info *ivvl[MAX_VLAN_LIST_LEN]; + struct nlattr *attr; + int rem, len = 0; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_vlan) + return err; + + nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) { + if (nla_type(attr) != IFLA_VF_VLAN_INFO || + nla_len(attr) < NLA_HDRLEN) { + return -EINVAL; + } + if (len >= MAX_VLAN_LIST_LEN) + return -EOPNOTSUPP; + ivvl[len] = nla_data(attr); + + len++; + } + err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, + ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) return err; } @@ -3577,6 +3627,91 @@ static bool stats_attr_valid(unsigned int mask, int attrid, int idxattr) (!idxattr || idxattr == attrid); } +#define IFLA_OFFLOAD_XSTATS_FIRST (IFLA_OFFLOAD_XSTATS_UNSPEC + 1) +static int rtnl_get_offload_stats_attr_size(int attr_id) +{ + switch (attr_id) { + case IFLA_OFFLOAD_XSTATS_CPU_HIT: + return sizeof(struct rtnl_link_stats64); + } + + return 0; +} + +static int rtnl_get_offload_stats(struct sk_buff *skb, struct net_device *dev, + int *prividx) +{ + struct nlattr *attr = NULL; + int attr_id, size; + void *attr_data; + int err; + + if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats && + dev->netdev_ops->ndo_get_offload_stats)) + return -ENODATA; + + for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST; + attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) { + if (attr_id < *prividx) + continue; + + size = rtnl_get_offload_stats_attr_size(attr_id); + if (!size) + continue; + + if (!dev->netdev_ops->ndo_has_offload_stats(attr_id)) + continue; + + attr = nla_reserve_64bit(skb, attr_id, size, + IFLA_OFFLOAD_XSTATS_UNSPEC); + if (!attr) + goto nla_put_failure; + + attr_data = nla_data(attr); + memset(attr_data, 0, size); + err = dev->netdev_ops->ndo_get_offload_stats(attr_id, dev, + attr_data); + if (err) + goto get_offload_stats_failure; + } + + if (!attr) + return -ENODATA; + + *prividx = 0; + return 0; + +nla_put_failure: + err = -EMSGSIZE; +get_offload_stats_failure: + *prividx = attr_id; + return err; +} + +static int rtnl_get_offload_stats_size(const struct net_device *dev) +{ + int nla_size = 0; + int attr_id; + int size; + + if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats && + dev->netdev_ops->ndo_get_offload_stats)) + return 0; + + for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST; + attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) { + if (!dev->netdev_ops->ndo_has_offload_stats(attr_id)) + continue; + size = rtnl_get_offload_stats_attr_size(attr_id); + nla_size += nla_total_size_64bit(size); + } + + if (nla_size != 0) + nla_size += nla_total_size(0); + + return nla_size; +} + static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, unsigned int filter_mask, @@ -3586,6 +3721,7 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, struct nlmsghdr *nlh; struct nlattr *attr; int s_prividx = *prividx; + int err; ASSERT_RTNL(); @@ -3614,8 +3750,6 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_ops *ops = dev->rtnl_link_ops; if (ops && ops->fill_linkxstats) { - int err; - *idxattr = IFLA_STATS_LINK_XSTATS; attr = nla_nest_start(skb, IFLA_STATS_LINK_XSTATS); @@ -3639,8 +3773,6 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (master) ops = master->rtnl_link_ops; if (ops && ops->fill_linkxstats) { - int err; - *idxattr = IFLA_STATS_LINK_XSTATS_SLAVE; attr = nla_nest_start(skb, IFLA_STATS_LINK_XSTATS_SLAVE); @@ -3655,6 +3787,24 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, } } + if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, + *idxattr)) { + *idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS; + attr = nla_nest_start(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS); + if (!attr) + goto nla_put_failure; + + err = rtnl_get_offload_stats(skb, dev, prividx); + if (err == -ENODATA) + nla_nest_cancel(skb, attr); + else + nla_nest_end(skb, attr); + + if (err && err != -ENODATA) + goto nla_put_failure; + *idxattr = 0; + } + nlmsg_end(skb, nlh); return 0; @@ -3669,10 +3819,6 @@ nla_put_failure: return -EMSGSIZE; } -static const struct nla_policy ifla_stats_policy[IFLA_STATS_MAX + 1] = { - [IFLA_STATS_LINK_64] = { .len = sizeof(struct rtnl_link_stats64) }, -}; - static size_t if_nlmsg_stats_size(const struct net_device *dev, u32 filter_mask) { @@ -3712,6 +3858,9 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, } } + if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) + size += rtnl_get_offload_stats_size(dev); + return size; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3864b4b6..d36c754 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2445,6 +2445,25 @@ void skb_queue_purge(struct sk_buff_head *list) EXPORT_SYMBOL(skb_queue_purge); /** + * skb_rbtree_purge - empty a skb rbtree + * @root: root of the rbtree to empty + * + * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from + * the list and one reference dropped. This function does not take + * any lock. Synchronization should be handled by the caller (e.g., TCP + * out-of-order queue is protected by the socket lock). + */ +void skb_rbtree_purge(struct rb_root *root) +{ + struct sk_buff *skb, *next; + + rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode) + kfree_skb(skb); + + *root = RB_ROOT; +} + +/** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue @@ -3078,11 +3097,31 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); - /* GSO partial only requires that we trim off any excess that - * doesn't fit into an MSS sized block, so take care of that - * now. - */ - if (sg && csum && (features & NETIF_F_GSO_PARTIAL)) { + if (sg && csum && (mss != GSO_BY_FRAGS)) { + if (!(features & NETIF_F_GSO_PARTIAL)) { + struct sk_buff *iter; + + if (!list_skb || + !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) + goto normal; + + /* Split the buffer at the frag_list pointer. + * This is based on the assumption that all + * buffers in the chain excluding the last + * containing the same amount of data. + */ + skb_walk_frags(head_skb, iter) { + if (skb_headlen(iter)) + goto normal; + + len -= iter->len; + } + } + + /* GSO partial only requires that we trim off any excess that + * doesn't fit into an MSS sized block, so take care of that + * now. + */ partial_segs = len / mss; if (partial_segs > 1) mss *= partial_segs; @@ -3090,6 +3129,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, partial_segs = 0; } +normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); @@ -3281,21 +3321,29 @@ perform_csum_check: */ segs->prev = tail; - /* Update GSO info on first skb in partial sequence. */ if (partial_segs) { + struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; + unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ - type |= SKB_GSO_PARTIAL; + type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ - skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size; - skb_shinfo(segs)->gso_segs = partial_segs; - skb_shinfo(segs)->gso_type = type; - SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset; + for (iter = segs; iter; iter = iter->next) { + skb_shinfo(iter)->gso_size = gso_size; + skb_shinfo(iter)->gso_segs = partial_segs; + skb_shinfo(iter)->gso_type = type; + SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; + } + + if (tail->len - doffset <= gso_size) + skb_shinfo(tail)->gso_size = 0; + else if (tail != segs) + skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols @@ -4474,8 +4522,10 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len) } EXPORT_SYMBOL(skb_ensure_writable); -/* remove VLAN header from packet and update csum accordingly. */ -static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) +/* remove VLAN header from packet and update csum accordingly. + * expects a non skb_vlan_tag_present skb with a vlan tag payload + */ +int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr; unsigned int offset = skb->data - skb_mac_header(skb); @@ -4506,6 +4556,7 @@ pull: return err; } +EXPORT_SYMBOL(__skb_vlan_pop); int skb_vlan_pop(struct sk_buff *skb) { @@ -4516,9 +4567,7 @@ int skb_vlan_pop(struct sk_buff *skb) if (likely(skb_vlan_tag_present(skb))) { skb->vlan_tci = 0; } else { - if (unlikely((skb->protocol != htons(ETH_P_8021Q) && - skb->protocol != htons(ETH_P_8021AD)) || - skb->len < VLAN_ETH_HLEN)) + if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); @@ -4526,9 +4575,7 @@ int skb_vlan_pop(struct sk_buff *skb) return err; } /* move next vlan tag to hw accel tag */ - if (likely((skb->protocol != htons(ETH_P_8021Q) && - skb->protocol != htons(ETH_P_8021AD)) || - skb->len < VLAN_ETH_HLEN)) + if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; diff --git a/net/core/sock.c b/net/core/sock.c index 51a7304..038e660 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1340,7 +1340,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; sk_tx_queue_clear(sk); - cgroup_sk_alloc(&sk->sk_cgrp_data); } return sk; @@ -1400,6 +1399,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_net_set(sk, net); atomic_set(&sk->sk_wmem_alloc, 1); + cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); } @@ -1544,6 +1544,9 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); + + cgroup_sk_alloc(&newsk->sk_cgrp_data); + /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index ff7736f..96e47c5 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -38,4 +38,7 @@ config NET_DSA_TAG_EDSA config NET_DSA_TAG_TRAILER bool +config NET_DSA_TAG_QCA + bool + endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 8af4ded..a3380ed 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -7,3 +7,4 @@ dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index d8d267e..a6902c1 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -54,6 +54,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_BRCM [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_QCA + [DSA_TAG_PROTO_QCA] = &qca_netdev_ops, +#endif [DSA_TAG_PROTO_NONE] = &none_ops, }; @@ -375,9 +378,11 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (ret < 0) goto out; - ret = ops->set_addr(ds, dst->master_netdev->dev_addr); - if (ret < 0) - goto out; + if (ops->set_addr) { + ret = ops->set_addr(ds, dst->master_netdev->dev_addr); + if (ret < 0) + goto out; + } if (!ds->slave_mii_bus && ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(parent); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 8278385..f8a7d9a 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -304,13 +304,11 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) if (err < 0) return err; - err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); - if (err < 0) - return err; - - err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); - if (err < 0) - return err; + if (ds->ops->set_addr) { + err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); + if (err < 0) + return err; + } if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 00077a9..6cfd738 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -81,5 +81,7 @@ extern const struct dsa_device_ops trailer_netdev_ops; /* tag_brcm.c */ extern const struct dsa_device_ops brcm_netdev_ops; +/* tag_qca.c */ +extern const struct dsa_device_ops qca_netdev_ops; #endif diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 9ecbe78..6b1282c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -69,6 +69,30 @@ static inline bool dsa_port_is_bridged(struct dsa_slave_priv *p) return !!p->bridge_dev; } +static void dsa_port_set_stp_state(struct dsa_switch *ds, int port, u8 state) +{ + struct dsa_port *dp = &ds->ports[port]; + + if (ds->ops->port_stp_state_set) + ds->ops->port_stp_state_set(ds, port, state); + + if (ds->ops->port_fast_age) { + /* Fast age FDB entries or flush appropriate forwarding database + * for the given port, if we are moving it from Learning or + * Forwarding state, to Disabled or Blocking or Listening state. + */ + + if ((dp->stp_state == BR_STATE_LEARNING || + dp->stp_state == BR_STATE_FORWARDING) && + (state == BR_STATE_DISABLED || + state == BR_STATE_BLOCKING || + state == BR_STATE_LISTENING)) + ds->ops->port_fast_age(ds, port); + } + + dp->stp_state = state; +} + static int dsa_slave_open(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -104,8 +128,7 @@ static int dsa_slave_open(struct net_device *dev) goto clear_promisc; } - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, p->port, stp_state); + dsa_port_set_stp_state(ds, p->port, stp_state); if (p->phy) phy_start(p->phy); @@ -147,8 +170,7 @@ static int dsa_slave_close(struct net_device *dev) if (ds->ops->port_disable) ds->ops->port_disable(ds, p->port, p->phy); - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, p->port, BR_STATE_DISABLED); + dsa_port_set_stp_state(ds, p->port, BR_STATE_DISABLED); return 0; } @@ -354,7 +376,7 @@ static int dsa_slave_stp_state_set(struct net_device *dev, if (switchdev_trans_ph_prepare(trans)) return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; - ds->ops->port_stp_state_set(ds, p->port, attr->u.stp_state); + dsa_port_set_stp_state(ds, p->port, attr->u.stp_state); return 0; } @@ -556,8 +578,7 @@ static void dsa_slave_bridge_port_leave(struct net_device *dev) /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional */ - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, p->port, BR_STATE_FORWARDING); + dsa_port_set_stp_state(ds, p->port, BR_STATE_FORWARDING); } static int dsa_slave_port_attr_get(struct net_device *dev, diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c new file mode 100644 index 0000000..0c90cac --- /dev/null +++ b/net/dsa/tag_qca.c @@ -0,0 +1,138 @@ +/* + * Copyright (c) 2015, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/etherdevice.h> +#include "dsa_priv.h" + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION_MASK GENMASK(15, 14) +#define QCA_HDR_RECV_VERSION_S 14 +#define QCA_HDR_RECV_PRIORITY_MASK GENMASK(13, 11) +#define QCA_HDR_RECV_PRIORITY_S 11 +#define QCA_HDR_RECV_TYPE_MASK GENMASK(10, 6) +#define QCA_HDR_RECV_TYPE_S 6 +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) + +#define QCA_HDR_XMIT_VERSION_MASK GENMASK(15, 14) +#define QCA_HDR_XMIT_VERSION_S 14 +#define QCA_HDR_XMIT_PRIORITY_MASK GENMASK(13, 11) +#define QCA_HDR_XMIT_PRIORITY_S 11 +#define QCA_HDR_XMIT_CONTROL_MASK GENMASK(10, 8) +#define QCA_HDR_XMIT_CONTROL_S 8 +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT_MASK GENMASK(6, 0) + +static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + u16 *phdr, hdr; + + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + if (skb_cow_head(skb, 0) < 0) + goto out_free; + + skb_push(skb, QCA_HDR_LEN); + + memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN); + phdr = (u16 *)(skb->data + 2 * ETH_ALEN); + + /* Set the version field, and set destination port information */ + hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | + QCA_HDR_XMIT_FROM_CPU | + BIT(p->port); + + *phdr = htons(hdr); + + return skb; + +out_free: + kfree_skb(skb); + return NULL; +} + +static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_switch *ds; + u8 ver; + int port; + __be16 *phdr, hdr; + + if (unlikely(!dst)) + goto out_drop; + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + goto out; + + if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) + goto out_drop; + + /* The QCA header is added by the switch between src addr and Ethertype + * At this point, skb->data points to ethertype so header should be + * right before + */ + phdr = (__be16 *)(skb->data - 2); + hdr = ntohs(*phdr); + + /* Make sure the version is correct */ + ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S; + if (unlikely(ver != QCA_HDR_VERSION)) + goto out_drop; + + /* Remove QCA tag and recalculate checksum */ + skb_pull_rcsum(skb, QCA_HDR_LEN); + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN, + ETH_HLEN - QCA_HDR_LEN); + + /* This protocol doesn't support cascading multiple switches so it's + * safe to assume the switch is first in the tree + */ + ds = dst->ds[0]; + if (!ds) + goto out_drop; + + /* Get source port information */ + port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); + if (!ds->ports[port].netdev) + goto out_drop; + + /* Update skb & forward the frame accordingly */ + skb_push(skb, ETH_HLEN); + skb->pkt_type = PACKET_HOST; + skb->dev = ds->ports[port].netdev; + skb->protocol = eth_type_trans(skb, skb->dev); + + skb->dev->stats.rx_packets++; + skb->dev->stats.rx_bytes += skb->len; + + netif_receive_skb(skb); + + return 0; + +out_drop: + kfree_skb(skb); +out: + return 0; +} + +const struct dsa_device_ops qca_netdev_ops = { + .xmit = qca_tag_xmit, + .rcv = qca_tag_rcv, +}; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 50d6a9b..300b068 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -640,6 +640,21 @@ config TCP_CONG_CDG D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg +config TCP_CONG_BBR + tristate "BBR TCP" + default n + ---help--- + + BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to + maximize network utilization and minimize queues. It builds an explicit + model of the the bottleneck delivery rate and path round-trip + propagation delay. It tolerates packet loss and delay unrelated to + congestion. It can operate over LAN, WAN, cellular, wifi, or cable + modem links. It can coexist with flows that use loss-based congestion + control, and can operate with shallow buffers, deep buffers, + bufferbloat, policers, or AQM schemes that do not provide a delay + signal. It requires the fq ("Fair Queue") pacing packet scheduler. + choice prompt "Default TCP congestion control" default DEFAULT_CUBIC @@ -674,6 +689,9 @@ choice config DEFAULT_CDG bool "CDG" if TCP_CONG_CDG=y + config DEFAULT_BBR + bool "BBR" if TCP_CONG_BBR=y + config DEFAULT_RENO bool "Reno" endchoice diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 24629b6..bc6a6c8 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_recovery.o \ + tcp_rate.o tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ @@ -41,6 +41,7 @@ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o +obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e94b47b..1effc98 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1192,7 +1192,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { - bool udpfrag = false, fixedid = false, encap; + bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; @@ -1245,6 +1245,8 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (IS_ERR_OR_NULL(segs)) goto out; + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); @@ -1259,9 +1261,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } - tot_len = skb_shinfo(skb)->gso_size + - SKB_GSO_CB(skb)->data_offset + - skb->head - (unsigned char *)iph; + + if (gso_partial) + tot_len = skb_shinfo(skb)->gso_size + + SKB_GSO_CB(skb)->data_offset + + skb->head - (unsigned char *)iph; + else + tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 415e117..062a67c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2232,7 +2232,7 @@ static struct devinet_sysctl_table { }; static int __devinet_sysctl_register(struct net *net, char *dev_name, - struct ipv4_devconf *p) + int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; @@ -2255,6 +2255,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, goto free; p->sysctl = t; + + inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); return 0; free: @@ -2286,7 +2288,7 @@ static int devinet_sysctl_register(struct in_device *idev) if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, - &idev->cnf); + idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; @@ -2347,11 +2349,12 @@ static __net_init int devinet_init_net(struct net *net) } #ifdef CONFIG_SYSCTL - err = __devinet_sysctl_register(net, "all", all); + err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; - err = __devinet_sysctl_register(net, "default", dflt); + err = __devinet_sysctl_register(net, "default", + NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 317c319..4e56a4c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -503,6 +503,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; + cfg->fc_table = l3mdev_fib_table(dev); if (colon) { struct in_ifaddr *ifa; struct in_device *in_dev = __in_dev_get_rtnl(dev); @@ -1021,7 +1022,7 @@ no_promotions: * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ - if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) + if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 6e9ea69..770bebe 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -56,6 +56,9 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, }; int err; + /* update flow if oif or iif point to device enslaved to l3mdev */ + l3mdev_update_flow(net, flowi4_to_flowi(flp)); + err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg); #ifdef CONFIG_IP_ROUTE_CLASSID if (arg.rule) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 8066ccc..388d3e2 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1057,6 +1057,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_priority = cfg->fc_priority; fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_type = cfg->fc_type; + fi->fib_tb_id = cfg->fc_table; fi->fib_nhs = nhs; change_nexthops(fi) { @@ -1337,18 +1338,21 @@ nla_put_failure: * referring to it. * - device went down -> we must shutdown all nexthops going via it. */ -int fib_sync_down_addr(struct net *net, __be32 local) +int fib_sync_down_addr(struct net_device *dev, __be32 local) { int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + struct net *net = dev_net(dev); + int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) return 0; hlist_for_each_entry(fi, head, fib_lhash) { - if (!net_eq(fi->fib_net, net)) + if (!net_eq(fi->fib_net, net) || + fi->fib_tb_id != tb_id) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e2ffc2a..241f27b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1081,7 +1081,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; - unsigned int nlflags = 0; + u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; @@ -1126,6 +1126,8 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (cfg->fc_nlflags & NLM_F_EXCL) goto out; + nlflags &= ~NLM_F_EXCL; + /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes @@ -1151,6 +1153,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) struct fib_info *fi_drop; u8 state; + nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) @@ -1191,7 +1194,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, - tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); + tb->tb_id, &cfg->fc_nlinfo, nlflags); goto succeeded; } @@ -1203,7 +1206,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) - nlflags = NLM_F_APPEND; + nlflags |= NLM_F_APPEND; else fa = fa_first; } @@ -1211,6 +1214,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; + nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index ecd1e09..96e0efe 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -24,7 +24,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, ufo; + bool need_csum, ufo, gso_partial; if (!skb->encapsulation) goto out; @@ -69,6 +69,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, goto out; } + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + outer_hlen = skb_tnl_header_len(skb); gre_offset = outer_hlen - tnl_hlen; skb = segs; @@ -96,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (skb_is_gso(skb)) { + if (gso_partial) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index abfbe49..e4d16fc 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -99,6 +99,7 @@ static size_t inet_sk_attr_size(void) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -109,7 +110,8 @@ static size_t inet_sk_attr_size(void) int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns) + struct user_namespace *user_ns, + bool net_admin) { const struct inet_sock *inet = inet_sk(sk); @@ -136,6 +138,9 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + goto errout; + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -149,7 +154,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; @@ -175,7 +181,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 0; r->idiag_retrans = 0; - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -274,10 +280,11 @@ static int inet_csk_diag_fill(struct sock *sk, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { - return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, - user_ns, portid, seq, nlmsg_flags, unlh); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, + portid, seq, nlmsg_flags, unlh, net_admin); } static int inet_twsk_diag_fill(struct sock *sk, @@ -319,8 +326,9 @@ static int inet_twsk_diag_fill(struct sock *sk, static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { + struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; @@ -334,7 +342,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = inet_reqsk(sk)->num_retrans; + r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); @@ -346,6 +354,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + inet_rsk(reqsk)->ir_mark)) + return -EMSGSIZE; + nlmsg_end(skb, nlh); return 0; } @@ -354,7 +366,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, @@ -362,10 +374,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, @@ -435,7 +447,8 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); @@ -796,7 +809,8 @@ static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - const struct nlattr *bc) + const struct nlattr *bc, + bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -804,7 +818,8 @@ static int inet_csk_diag_dump(struct sock *sk, return inet_csk_diag_fill(sk, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, + net_admin); } static void twsk_build_assert(void) @@ -840,6 +855,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct net *net = sock_net(skb->sk); int i, num, s_i, s_num; u32 idiag_states = r->idiag_states; + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; @@ -880,7 +896,8 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, cb->args[3] > 0) goto next_listen; - if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, + bc, net_admin) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -948,7 +965,7 @@ skip_listen_ht: sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh); + cb->nlh, net_admin); if (res < 0) { spin_unlock_bh(lock); goto done; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 113cc43..576f705 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -246,25 +246,6 @@ static void gre_err(struct sk_buff *skb, u32 info) ipgre_err(skb, info, &tpi); } -static __be64 key_to_tunnel_id(__be32 key) -{ -#ifdef __BIG_ENDIAN - return (__force __be64)((__force u32)key); -#else - return (__force __be64)((__force u64)key << 32); -#endif -} - -/* Returns the least-significant 32 bits of a __be64. */ -static __be32 tunnel_id_to_key(__be64 x) -{ -#ifdef __BIG_ENDIAN - return (__force __be32)x; -#else - return (__force __be32)((__force u64)x >> 32); -#endif -} - static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { @@ -290,7 +271,7 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, __be64 tun_id; flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); - tun_id = key_to_tunnel_id(tpi->key); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; @@ -446,7 +427,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); gre_build_header(skb, tunnel_hlen, flags, proto, - tunnel_id_to_key(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 4b351af..d6feabb 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -312,6 +312,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; + struct net_device *dev = skb->dev; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -341,7 +342,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) */ if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev); + iph->tos, dev); if (unlikely(err)) { if (err == -EXDEV) __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); @@ -370,7 +371,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) __IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len); } else if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); /* RFC 1122 3.3.6: * diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6556927..05d1058 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -99,6 +99,14 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); + + /* if egress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip_out(sk, skb); + if (unlikely(!skb)) + return 0; + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); @@ -490,7 +498,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) +#if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); @@ -1574,8 +1582,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) - oif = skb->skb_iif; + oif = oif ? : skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 71a52f4d..af49197 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -284,9 +284,12 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->ttl = val; break; case IP_TOS: - if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + if (cmsg->cmsg_len == CMSG_LEN(sizeof(int))) + val = *(int *)CMSG_DATA(cmsg); + else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8))) + val = *(u8 *)CMSG_DATA(cmsg); + else return -EINVAL; - val = *(int *)CMSG_DATA(cmsg); if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 95649eb..5719d6b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -55,6 +55,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/udp.h> +#include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -546,6 +547,81 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + u32 headroom = sizeof(struct iphdr); + struct ip_tunnel_info *tun_info; + const struct ip_tunnel_key *key; + const struct iphdr *inner_iph; + struct rtable *rt; + struct flowi4 fl4; + __be16 df = 0; + u8 tos, ttl; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET)) + goto tx_error; + key = &tun_info->key; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + tos = key->tos; + if (tos == 1) { + if (skb->protocol == htons(ETH_P_IP)) + tos = inner_iph->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); + } + init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link); + if (tunnel->encap.type != TUNNEL_ENCAP_NONE) + goto tx_error; + rt = ip_route_output_key(tunnel->net, &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (rt->dst.dev == dev) { + ip_rt_put(rt); + dev->stats.collisions++; + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); + ttl = key->ttl; + if (ttl == 0) { + if (skb->protocol == htons(ETH_P_IP)) + ttl = inner_iph->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; + else + ttl = ip4_dst_hoplimit(&rt->dst); + } + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + else if (skb->protocol == htons(ETH_P_IP)) + df = inner_iph->frag_off & htons(IP_DF); + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; + if (headroom > dev->needed_headroom) + dev->needed_headroom = headroom; + + if (skb_cow_head(skb, dev->needed_headroom)) { + ip_rt_put(rt); + goto tx_dropped; + } + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos, + key->ttl, df, !net_eq(tunnel->net, dev_net(dev))); + return; +tx_error: + dev->stats.tx_errors++; + goto kfree; +tx_dropped: + dev->stats.tx_dropped++; +kfree: + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); + void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 0f227db..777bc18 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -69,7 +69,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_scrub_packet(skb, xnet); - skb_clear_hash(skb); + skb_clear_hash_if_not_l4(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cc701fa..5d7944f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -88,6 +88,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) struct net_device *dev; struct pcpu_sw_netstats *tstats; struct xfrm_state *x; + struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; u32 orig_mark = skb->mark; int ret; @@ -105,7 +106,19 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) } x = xfrm_input_state(skb); - family = x->inner_mode->afinfo->family; + + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + family = inner_mode->afinfo->family; skb->mark = be32_to_cpu(tunnel->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 4ae3f8e..c939258 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -115,6 +115,7 @@ #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/dst_metadata.h> static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); @@ -193,6 +194,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -216,7 +218,12 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; - return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); + if (tunnel->collect_md) { + tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + if (!tun_dst) + return 0; + } + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } return -1; @@ -270,7 +277,10 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, ipproto); - ip_tunnel_xmit(skb, dev, tiph, ipproto); + if (tunnel->collect_md) + ip_md_tunnel_xmit(skb, dev, ipproto); + else + ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: @@ -380,13 +390,14 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm *parms, bool *collect_md) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPIP; parms->iph.ihl = 5; + *collect_md = false; if (!data) return; @@ -414,6 +425,9 @@ static void ipip_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_COLLECT_METADATA]) + *collect_md = true; } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -453,18 +467,18 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { + struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; if (ipip_netlink_encap_parms(data, &ipencap)) { - struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &t->collect_md); return ip_tunnel_newlink(dev, tb, &p); } @@ -473,6 +487,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + bool collect_md; if (ipip_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); @@ -482,7 +497,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &collect_md); + if (collect_md) + return -EINVAL; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) @@ -516,6 +533,8 @@ static size_t ipip_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_IPTUN_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -544,6 +563,9 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) tunnel->encap.flags)) goto nla_put_failure; + if (tunnel->collect_md) + if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) + goto nla_put_failure; return 0; nla_put_failure: @@ -562,6 +584,7 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2625332..a87bcd2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2076,6 +2076,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct rta_mfc_stats mfcs; struct nlattr *mp_attr; struct rtnexthop *nhp; + unsigned long lastuse; int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ @@ -2105,12 +2106,14 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_nest_end(skb, mp_attr); + lastuse = READ_ONCE(c->mfc_un.res.lastuse); + lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; + mfcs.mfcs_packets = c->mfc_un.res.pkt; mfcs.mfcs_bytes = c->mfc_un.res.bytes; mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, - jiffies_to_clock_t(c->mfc_un.res.lastuse), + nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) return -EMSGSIZE; diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 2375b0a..30493be 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv, __be32 saddr, daddr; u_int8_t tos; const struct iphdr *iph; + int err; /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || @@ -46,15 +47,17 @@ static unsigned int nf_route_table_hook(void *priv, tos = iph->tos; ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_QUEUE) { + if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || iph->daddr != daddr || skb->mark != mark || - iph->tos != tos) - if (ip_route_me_harder(state->net, skb, RTN_UNSPEC)) - ret = NF_DROP; + iph->tos != tos) { + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + if (err < 0) + ret = NF_DROP_ERR(err); + } } return ret; } diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index c24f41c..2c2553b 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -46,6 +46,7 @@ static const struct nft_expr_ops nft_reject_ipv4_ops = { .eval = nft_reject_ipv4_eval, .init = nft_reject_init, .dump = nft_reject_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 438f50c..90a85c9 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -606,12 +606,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!saddr && ipc.oif) { - err = l3mdev_get_saddr(net, ipc.oif, &fl4); - if (err < 0) - goto done; - } - if (!inet->hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3e99278..654a9af 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -476,12 +476,18 @@ u32 ip_idents_reserve(u32 hash, int segs) atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; u32 old = ACCESS_ONCE(*p_tstamp); u32 now = (u32)jiffies; - u32 delta = 0; + u32 new, delta = 0; if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - return atomic_add_return(segs + delta, p_id) - segs; + /* Do not use atomic_add_return() as it makes UBSAN unhappy */ + do { + old = (u32)atomic_read(p_id); + new = old + delta + segs; + } while (atomic_cmpxchg(p_id, old, new) != old); + + return new - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -1831,7 +1837,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev); + fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; @@ -2018,7 +2024,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res, return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) - if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + if (ipv4_is_loopback(fl4->saddr) && + !(dev_out->flags & IFF_LOOPBACK) && + !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) @@ -2148,7 +2156,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int master_idx; int orig_oif; int err = -ENETUNREACH; @@ -2158,9 +2165,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, orig_oif = fl4->flowi4_oif; - master_idx = l3mdev_master_ifindex_by_index(net, fl4->flowi4_oif); - if (master_idx) - fl4->flowi4_oif = master_idx; fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? @@ -2244,10 +2248,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } - - rth = l3mdev_get_rtable(dev_out, fl4); - if (rth) - goto out; } if (!fl4->daddr) { @@ -2265,8 +2265,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (err) { res.fi = NULL; res.table = NULL; - if (fl4->flowi4_oif && - !netif_index_is_l3_master(net, fl4->flowi4_oif)) { + if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2302,7 +2301,9 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, else fl4->saddr = fl4->daddr; } - dev_out = net->loopback_dev; + + /* L3 master device is the loopback for that domain */ + dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; @@ -2577,9 +2578,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; - if (netif_index_is_l3_master(net, fl4.flowi4_oif)) - fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; - if (iif) { struct net_device *dev; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77311a9..f253e50 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -380,14 +380,14 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __skb_queue_head_init(&tp->out_of_order_queue); + tp->out_of_order_queue = RB_ROOT; tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - tp->rtt_min[0].rtt = ~0U; + minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -396,6 +396,9 @@ void tcp_init_sock(struct sock *sk) */ tp->snd_cwnd = TCP_INIT_CWND; + /* There's a bubble in the pipe until at least the first ACK. */ + tp->app_limited = ~0U; + /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ @@ -1014,23 +1017,40 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, flags); lock_sock(sk); + + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + res = do_tcp_sendpages(sk, page, offset, size, flags); release_sock(sk); return res; } EXPORT_SYMBOL(tcp_sendpage); -static inline int select_size(const struct sock *sk, bool sg) +/* Do not bother using a page frag for very small frames. + * But use this heuristic only for the first skb in write queue. + * + * Having no payload in skb->head allows better SACK shifting + * in tcp_shift_skb_data(), reducing sack/rack overhead, because + * write queue has less skbs. + * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB. + * This also speeds up tso_fragment(), since it wont fallback + * to tcp_fragment(). + */ +static int linear_payload_sz(bool first_skb) +{ + if (first_skb) + return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + return 0; +} + +static int select_size(const struct sock *sk, bool sg, bool first_skb) { const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; if (sg) { if (sk_can_gso(sk)) { - /* Small frames wont use a full page: - * Payload will immediately follow tcp header. - */ - tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + tmp = linear_payload_sz(first_skb); } else { int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); @@ -1101,6 +1121,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. @@ -1161,6 +1183,8 @@ restart: } if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { + bool first_skb; + new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -1172,10 +1196,11 @@ new_segment: process_backlog = false; goto restart; } + first_skb = skb_queue_empty(&sk->sk_write_queue); skb = sk_stream_alloc_skb(sk, - select_size(sk, sg), + select_size(sk, sg, first_skb), sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + first_skb); if (!skb) goto wait_for_memory; @@ -2243,7 +2268,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); tcp_write_queue_purge(sk); - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; @@ -2687,7 +2712,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp, intv; unsigned int start; int notsent_bytes; u64 rate64; @@ -2777,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_in = tp->data_segs_in; info->tcpi_data_segs_out = tp->data_segs_out; + + info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; + rate = READ_ONCE(tp->rate_delivered); + intv = READ_ONCE(tp->rate_interval_us); + if (rate && intv) { + rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; + do_div(rate64, intv); + put_unaligned(rate64, &info->tcpi_delivery_rate); + } } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3244,11 +3278,12 @@ static void __init tcp_init_mem(void) void __init tcp_init(void) { - unsigned long limit; int max_rshare, max_wshare, cnt; + unsigned long limit; unsigned int i; - sock_skb_cb_check_size(sizeof(struct tcp_skb_cb)); + BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > + FIELD_SIZEOF(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c new file mode 100644 index 0000000..0ea66c2 --- /dev/null +++ b/net/ipv4/tcp_bbr.c @@ -0,0 +1,896 @@ +/* Bottleneck Bandwidth and RTT (BBR) congestion control + * + * BBR congestion control computes the sending rate based on the delivery + * rate (throughput) estimated from ACKs. In a nutshell: + * + * On each ACK, update our model of the network path: + * bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips) + * min_rtt = windowed_min(rtt, 10 seconds) + * pacing_rate = pacing_gain * bottleneck_bandwidth + * cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4) + * + * The core algorithm does not react directly to packet losses or delays, + * although BBR may adjust the size of next send per ACK when loss is + * observed, or adjust the sending rate if it estimates there is a + * traffic policer, in order to keep the drop rate reasonable. + * + * BBR is described in detail in: + * "BBR: Congestion-Based Congestion Control", + * Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh, + * Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016. + * + * There is a public e-mail list for discussing BBR development and testing: + * https://groups.google.com/forum/#!forum/bbr-dev + * + * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, + * since pacing is integral to the BBR design and implementation. + * BBR without pacing would not function properly, and may incur unnecessary + * high packet loss rates. + */ +#include <linux/module.h> +#include <net/tcp.h> +#include <linux/inet_diag.h> +#include <linux/inet.h> +#include <linux/random.h> +#include <linux/win_minmax.h> + +/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth + * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps. + * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32. + * Since the minimum window is >=4 packets, the lower bound isn't + * an issue. The upper bound isn't an issue with existing technologies. + */ +#define BW_SCALE 24 +#define BW_UNIT (1 << BW_SCALE) + +#define BBR_SCALE 8 /* scaling factor for fractions in BBR (e.g. gains) */ +#define BBR_UNIT (1 << BBR_SCALE) + +/* BBR has the following modes for deciding how fast to send: */ +enum bbr_mode { + BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */ + BBR_DRAIN, /* drain any queue created during startup */ + BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */ + BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */ +}; + +/* BBR congestion control block */ +struct bbr { + u32 min_rtt_us; /* min RTT in min_rtt_win_sec window */ + u32 min_rtt_stamp; /* timestamp of min_rtt_us */ + u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode */ + struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ + u32 rtt_cnt; /* count of packet-timed rounds elapsed */ + u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ + struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u32 mode:3, /* current bbr_mode in state machine */ + prev_ca_state:3, /* CA state on previous ACK */ + packet_conservation:1, /* use packet conservation? */ + restore_cwnd:1, /* decided to revert cwnd to old value */ + round_start:1, /* start of packet-timed tx->ack round? */ + tso_segs_goal:7, /* segments we want in each skb we send */ + idle_restart:1, /* restarting after idle? */ + probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ + unused:5, + lt_is_sampling:1, /* taking long-term ("LT") samples now? */ + lt_rtt_cnt:7, /* round trips in long-term interval */ + lt_use_bw:1; /* use lt_bw as our bw estimate? */ + u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 */ + u32 lt_last_delivered; /* LT intvl start: tp->delivered */ + u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp */ + u32 lt_last_lost; /* LT intvl start: tp->lost */ + u32 pacing_gain:10, /* current gain for setting pacing rate */ + cwnd_gain:10, /* current gain for setting cwnd */ + full_bw_cnt:3, /* number of rounds without large bw gains */ + cycle_idx:3, /* current index in pacing_gain cycle array */ + unused_b:6; + u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ + u32 full_bw; /* recent bw, to estimate if pipe is full */ +}; + +#define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ + +/* Window length of bw filter (in rounds): */ +static const int bbr_bw_rtts = CYCLE_LEN + 2; +/* Window length of min_rtt filter (in sec): */ +static const u32 bbr_min_rtt_win_sec = 10; +/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ +static const u32 bbr_probe_rtt_mode_ms = 200; +/* Skip TSO below the following bandwidth (bits/sec): */ +static const int bbr_min_tso_rate = 1200000; + +/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain + * that will allow a smoothly increasing pacing rate that will double each RTT + * and send the same number of packets per RTT that an un-paced, slow-starting + * Reno or CUBIC flow would: + */ +static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1; +/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain + * the queue created in BBR_STARTUP in a single round: + */ +static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885; +/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ +static const int bbr_cwnd_gain = BBR_UNIT * 2; +/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ +static const int bbr_pacing_gain[] = { + BBR_UNIT * 5 / 4, /* probe for more available bw */ + BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */ + BBR_UNIT, BBR_UNIT, BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */ + BBR_UNIT, BBR_UNIT, BBR_UNIT /* without creating excess queue... */ +}; +/* Randomize the starting gain cycling phase over N phases: */ +static const u32 bbr_cycle_rand = 7; + +/* Try to keep at least this many packets in flight, if things go smoothly. For + * smooth functioning, a sliding window protocol ACKing every other packet + * needs at least 4 packets in flight: + */ +static const u32 bbr_cwnd_min_target = 4; + +/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */ +/* If bw has increased significantly (1.25x), there may be more bw available: */ +static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4; +/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ +static const u32 bbr_full_bw_cnt = 3; + +/* "long-term" ("LT") bandwidth estimator parameters... */ +/* The minimum number of rounds in an LT bw sampling interval: */ +static const u32 bbr_lt_intvl_min_rtts = 4; +/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ +static const u32 bbr_lt_loss_thresh = 50; +/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ +static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8; +/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ +static const u32 bbr_lt_bw_diff = 4000 / 8; +/* If we estimate we're policed, use lt_bw for this many round trips: */ +static const u32 bbr_lt_bw_max_rtts = 48; + +/* Do we estimate that STARTUP filled the pipe? */ +static bool bbr_full_bw_reached(const struct sock *sk) +{ + const struct bbr *bbr = inet_csk_ca(sk); + + return bbr->full_bw_cnt >= bbr_full_bw_cnt; +} + +/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ +static u32 bbr_max_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return minmax_get(&bbr->bw); +} + +/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ +static u32 bbr_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); +} + +/* Return rate in bytes per second, optionally with a gain. + * The order here is chosen carefully to avoid overflow of u64. This should + * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. + */ +static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) +{ + rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + rate *= gain; + rate >>= BBR_SCALE; + rate *= USEC_PER_SEC; + return rate >> BW_SCALE; +} + +/* Pace using current bw estimate and a gain factor. In order to help drive the + * network toward lower queues while maintaining high utilization and low + * latency, the average pacing rate aims to be slightly (~1%) lower than the + * estimated bandwidth. This is an important aspect of the design. In this + * implementation this slightly lower pacing rate is achieved implicitly by not + * including link-layer headers in the packet size used for the pacing rate. + */ +static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + sk->sk_pacing_rate = rate; +} + +/* Return count of segments we want in the skbs we send, or 0 for default. */ +static u32 bbr_tso_segs_goal(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->tso_segs_goal; +} + +static void bbr_set_tso_segs_goal(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 min_segs; + + min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; + bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs), + 0x7FU); +} + +/* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ +static void bbr_save_cwnd(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT) + bbr->prior_cwnd = tp->snd_cwnd; /* this cwnd is good enough */ + else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */ + bbr->prior_cwnd = max(bbr->prior_cwnd, tp->snd_cwnd); +} + +static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (event == CA_EVENT_TX_START && tp->app_limited) { + bbr->idle_restart = 1; + /* Avoid pointless buffer overflows: pace at est. bw if we don't + * need more speed (we're restarting from idle and app-limited). + */ + if (bbr->mode == BBR_PROBE_BW) + bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + } +} + +/* Find target cwnd. Right-size the cwnd based on min RTT and the + * estimated bottleneck bandwidth: + * + * cwnd = bw * min_rtt * gain = BDP * gain + * + * The key factor, gain, controls the amount of queue. While a small gain + * builds a smaller queue, it becomes more vulnerable to noise in RTT + * measurements (e.g., delayed ACKs or other ACK compression effects). This + * noise may cause BBR to under-estimate the rate. + * + * To achieve full performance in high-speed paths, we budget enough cwnd to + * fit full-sized skbs in-flight on both end hosts to fully utilize the path: + * - one skb in sending host Qdisc, + * - one skb in sending host TSO/GSO engine + * - one skb being received by receiver host LRO/GRO/delayed-ACK engine + * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because + * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, + * which allows 2 outstanding 2-packet sequences, to try to keep pipe + * full even with ACK-every-other-packet delayed ACKs. + */ +static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd; + u64 w; + + /* If we've never had a valid RTT sample, cap cwnd at the initial + * default. This should only happen when the connection is not using TCP + * timestamps and has retransmitted all of the SYN/SYNACK/data packets + * ACKed so far. In this case, an RTO can cut cwnd to 1, in which + * case we need to slow-start up toward something safe: TCP_INIT_CWND. + */ + if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */ + return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/ + + w = (u64)bw * bbr->min_rtt_us; + + /* Apply a gain to the given value, then remove the BW_SCALE shift. */ + cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; + + /* Allow enough full-sized skbs in flight to utilize end systems. */ + cwnd += 3 * bbr->tso_segs_goal; + + /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ + cwnd = (cwnd + 1) & ~1U; + + return cwnd; +} + +/* An optimization in BBR to reduce losses: On the first round of recovery, we + * follow the packet conservation principle: send P packets per P packets acked. + * After that, we slow-start and send at most 2*P packets per P packets acked. + * After recovery finishes, or upon undo, we restore the cwnd we had when + * recovery started (capped by the target cwnd based on estimated BDP). + * + * TODO(ycheng/ncardwell): implement a rate-based approach. + */ +static bool bbr_set_cwnd_to_recover_or_restore( + struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state; + u32 cwnd = tp->snd_cwnd; + + /* An ACK for P pkts should release at most 2*P packets. We do this + * in two steps. First, here we deduct the number of lost packets. + * Then, in bbr_set_cwnd() we slow start up toward the target cwnd. + */ + if (rs->losses > 0) + cwnd = max_t(s32, cwnd - rs->losses, 1); + + if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) { + /* Starting 1st round of Recovery, so do packet conservation. */ + bbr->packet_conservation = 1; + bbr->next_rtt_delivered = tp->delivered; /* start round now */ + /* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */ + cwnd = tcp_packets_in_flight(tp) + acked; + } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { + /* Exiting loss recovery; restore cwnd saved before recovery. */ + bbr->restore_cwnd = 1; + bbr->packet_conservation = 0; + } + bbr->prev_ca_state = state; + + if (bbr->restore_cwnd) { + /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ + cwnd = max(cwnd, bbr->prior_cwnd); + bbr->restore_cwnd = 0; + } + + if (bbr->packet_conservation) { + *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); + return true; /* yes, using packet conservation */ + } + *new_cwnd = cwnd; + return false; +} + +/* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss + * has drawn us down below target), or snap down to target if we're above it. + */ +static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, + u32 acked, u32 bw, int gain) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd = 0, target_cwnd = 0; + + if (!acked) + return; + + if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) + goto done; + + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ + target_cwnd = bbr_target_cwnd(sk, bw, gain); + if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ + cwnd = min(cwnd + acked, target_cwnd); + else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) + cwnd = cwnd + acked; + cwnd = max(cwnd, bbr_cwnd_min_target); + +done: + tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); /* apply global cap */ + if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */ + tp->snd_cwnd = min(tp->snd_cwnd, bbr_cwnd_min_target); +} + +/* End cycle phase if it's time and/or we hit the phase's in-flight target. */ +static bool bbr_is_next_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool is_full_length = + skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + bbr->min_rtt_us; + u32 inflight, bw; + + /* The pacing_gain of 1.0 paces at the estimated bw to try to fully + * use the pipe without increasing the queue. + */ + if (bbr->pacing_gain == BBR_UNIT) + return is_full_length; /* just use wall clock time */ + + inflight = rs->prior_in_flight; /* what was in-flight before ACK? */ + bw = bbr_max_bw(sk); + + /* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at + * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is + * small (e.g. on a LAN). We do not persist if packets are lost, since + * a path with small buffers may not hold that much. + */ + if (bbr->pacing_gain > BBR_UNIT) + return is_full_length && + (rs->losses || /* perhaps pacing_gain*BDP won't fit */ + inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain)); + + /* A pacing_gain < 1.0 tries to drain extra queue we added if bw + * probing didn't find more bw. If inflight falls to match BDP then we + * estimate queue is drained; persisting would underutilize the pipe. + */ + return is_full_length || + inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT); +} + +static void bbr_advance_cycle_phase(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); + bbr->cycle_mstamp = tp->delivered_mstamp; + bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; +} + +/* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ +static void bbr_update_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && + bbr_is_next_cycle_phase(sk, rs)) + bbr_advance_cycle_phase(sk); +} + +static void bbr_reset_startup_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_STARTUP; + bbr->pacing_gain = bbr_high_gain; + bbr->cwnd_gain = bbr_high_gain; +} + +static void bbr_reset_probe_bw_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_PROBE_BW; + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = bbr_cwnd_gain; + bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); + bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ +} + +static void bbr_reset_mode(struct sock *sk) +{ + if (!bbr_full_bw_reached(sk)) + bbr_reset_startup_mode(sk); + else + bbr_reset_probe_bw_mode(sk); +} + +/* Start a new long-term sampling interval. */ +static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_delivered = tp->delivered; + bbr->lt_last_lost = tp->lost; + bbr->lt_rtt_cnt = 0; +} + +/* Completely reset long-term bandwidth sampling. */ +static void bbr_reset_lt_bw_sampling(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_bw = 0; + bbr->lt_use_bw = 0; + bbr->lt_is_sampling = false; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Long-term bw sampling interval is done. Estimate whether we're policed. */ +static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 diff; + + if (bbr->lt_bw) { /* do we have bw from a previous interval? */ + /* Is new bw close to the lt_bw from the previous interval? */ + diff = abs(bw - bbr->lt_bw); + if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) || + (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <= + bbr_lt_bw_diff)) { + /* All criteria are met; estimate we're policed. */ + bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */ + bbr->lt_use_bw = 1; + bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */ + bbr->lt_rtt_cnt = 0; + return; + } + } + bbr->lt_bw = bw; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of + * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and + * explicitly models their policed rate, to reduce unnecessary losses. We + * estimate that we're policed if we see 2 consecutive sampling intervals with + * consistent throughput and high packet loss. If we think we're being policed, + * set lt_bw to the "long-term" average delivery rate from those 2 intervals. + */ +static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 lost, delivered; + u64 bw; + s32 t; + + if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ + if (bbr->mode == BBR_PROBE_BW && bbr->round_start && + ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) { + bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */ + bbr_reset_probe_bw_mode(sk); /* restart gain cycling */ + } + return; + } + + /* Wait for the first loss before sampling, to let the policer exhaust + * its tokens and estimate the steady-state rate allowed by the policer. + * Starting samples earlier includes bursts that over-estimate the bw. + */ + if (!bbr->lt_is_sampling) { + if (!rs->losses) + return; + bbr_reset_lt_bw_sampling_interval(sk); + bbr->lt_is_sampling = true; + } + + /* To avoid underestimates, reset sampling if we run out of data. */ + if (rs->is_app_limited) { + bbr_reset_lt_bw_sampling(sk); + return; + } + + if (bbr->round_start) + bbr->lt_rtt_cnt++; /* count round trips in this interval */ + if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts) + return; /* sampling interval needs to be longer */ + if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) { + bbr_reset_lt_bw_sampling(sk); /* interval is too long */ + return; + } + + /* End sampling interval when a packet is lost, so we estimate the + * policer tokens were exhausted. Stopping the sampling before the + * tokens are exhausted under-estimates the policed rate. + */ + if (!rs->losses) + return; + + /* Calculate packets lost and delivered in sampling interval. */ + lost = tp->lost - bbr->lt_last_lost; + delivered = tp->delivered - bbr->lt_last_delivered; + /* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */ + if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered) + return; + + /* Find average delivery rate in this sampling interval. */ + t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); + if (t < 1) + return; /* interval is less than one jiffy, so wait */ + t = jiffies_to_usecs(t); + /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ + if (t < 1) { + bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ + return; + } + bw = (u64)delivered * BW_UNIT; + do_div(bw, t); + bbr_lt_bw_interval_done(sk, bw); +} + +/* Estimate the bandwidth based on how fast packets are delivered */ +static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->round_start = 0; + if (rs->delivered < 0 || rs->interval_us <= 0) + return; /* Not a valid observation */ + + /* See if we've reached the next RTT */ + if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) { + bbr->next_rtt_delivered = tp->delivered; + bbr->rtt_cnt++; + bbr->round_start = 1; + bbr->packet_conservation = 0; + } + + bbr_lt_bw_sampling(sk, rs); + + /* Divide delivered by the interval to find a (lower bound) bottleneck + * bandwidth sample. Delivered is in packets and interval_us in uS and + * ratio will be <<1 for most connections. So delivered is first scaled. + */ + bw = (u64)rs->delivered * BW_UNIT; + do_div(bw, rs->interval_us); + + /* If this sample is application-limited, it is likely to have a very + * low delivered count that represents application behavior rather than + * the available network rate. Such a sample could drag down estimated + * bw, causing needless slow-down. Thus, to continue to send at the + * last measured network rate, we filter out app-limited samples unless + * they describe the path bw at least as well as our bw model. + * + * So the goal during app-limited phase is to proceed with the best + * network rate no matter how long. We automatically leave this + * phase when app writes faster than the network can deliver :) + */ + if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) { + /* Incorporate new sample into our max bw filter. */ + minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw); + } +} + +/* Estimate when the pipe is full, using the change in delivery rate: BBR + * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by + * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited + * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the + * higher rwin, 3: we get higher delivery rate samples. Or transient + * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar + * design goal, but uses delay and inter-ACK spacing instead of bandwidth. + */ +static void bbr_check_full_bw_reached(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw_thresh; + + if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited) + return; + + bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE; + if (bbr_max_bw(sk) >= bw_thresh) { + bbr->full_bw = bbr_max_bw(sk); + bbr->full_bw_cnt = 0; + return; + } + ++bbr->full_bw_cnt; +} + +/* If pipe is probably full, drain the queue and then enter steady-state. */ +static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { + bbr->mode = BBR_DRAIN; /* drain queue we created */ + bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ + bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ + } /* fall through to check if in-flight is already small: */ + if (bbr->mode == BBR_DRAIN && + tcp_packets_in_flight(tcp_sk(sk)) <= + bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) + bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ +} + +/* The goal of PROBE_RTT mode is to have BBR flows cooperatively and + * periodically drain the bottleneck queue, to converge to measure the true + * min_rtt (unloaded propagation delay). This allows the flows to keep queues + * small (reducing queuing delay and packet loss) and achieve fairness among + * BBR flows. + * + * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires, + * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets. + * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed + * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and + * re-enter the previous mode. BBR uses 200ms to approximately bound the + * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s). + * + * Note that flows need only pay 2% if they are busy sending over the last 10 + * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have + * natural silences or low-rate periods within 10 seconds where the rate is low + * enough for long enough to drain its queue in the bottleneck. We pick up + * these min RTT measurements opportunistically with our min_rtt filter. :-) + */ +static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool filter_expired; + + /* Track min RTT seen in the min_rtt_win_sec filter window: */ + filter_expired = after(tcp_time_stamp, + bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); + if (rs->rtt_us >= 0 && + (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) { + bbr->min_rtt_us = rs->rtt_us; + bbr->min_rtt_stamp = tcp_time_stamp; + } + + if (bbr_probe_rtt_mode_ms > 0 && filter_expired && + !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { + bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = BBR_UNIT; + bbr_save_cwnd(sk); /* note cwnd so we can restore it */ + bbr->probe_rtt_done_stamp = 0; + } + + if (bbr->mode == BBR_PROBE_RTT) { + /* Ignore low rate samples during this mode. */ + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; + /* Maintain min packets in flight for max(200 ms, 1 round). */ + if (!bbr->probe_rtt_done_stamp && + tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { + bbr->probe_rtt_done_stamp = tcp_time_stamp + + msecs_to_jiffies(bbr_probe_rtt_mode_ms); + bbr->probe_rtt_round_done = 0; + bbr->next_rtt_delivered = tp->delivered; + } else if (bbr->probe_rtt_done_stamp) { + if (bbr->round_start) + bbr->probe_rtt_round_done = 1; + if (bbr->probe_rtt_round_done && + after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) { + bbr->min_rtt_stamp = tcp_time_stamp; + bbr->restore_cwnd = 1; /* snap to prior_cwnd */ + bbr_reset_mode(sk); + } + } + } + bbr->idle_restart = 0; +} + +static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) +{ + bbr_update_bw(sk, rs); + bbr_update_cycle_phase(sk, rs); + bbr_check_full_bw_reached(sk, rs); + bbr_check_drain(sk, rs); + bbr_update_min_rtt(sk, rs); +} + +static void bbr_main(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw; + + bbr_update_model(sk, rs); + + bw = bbr_bw(sk); + bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); + bbr_set_tso_segs_goal(sk); + bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); +} + +static void bbr_init(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->prior_cwnd = 0; + bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ + bbr->rtt_cnt = 0; + bbr->next_rtt_delivered = 0; + bbr->prev_ca_state = TCP_CA_Open; + bbr->packet_conservation = 0; + + bbr->probe_rtt_done_stamp = 0; + bbr->probe_rtt_round_done = 0; + bbr->min_rtt_us = tcp_min_rtt(tp); + bbr->min_rtt_stamp = tcp_time_stamp; + + minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ + + /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); + sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ + bbr_set_pacing_rate(sk, bw, bbr_high_gain); + + bbr->restore_cwnd = 0; + bbr->round_start = 0; + bbr->idle_restart = 0; + bbr->full_bw = 0; + bbr->full_bw_cnt = 0; + bbr->cycle_mstamp.v64 = 0; + bbr->cycle_idx = 0; + bbr_reset_lt_bw_sampling(sk); + bbr_reset_startup_mode(sk); +} + +static u32 bbr_sndbuf_expand(struct sock *sk) +{ + /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ + return 3; +} + +/* In theory BBR does not need to undo the cwnd since it does not + * always reduce cwnd on losses (see bbr_main()). Keep it for now. + */ +static u32 bbr_undo_cwnd(struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +/* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ +static u32 bbr_ssthresh(struct sock *sk) +{ + bbr_save_cwnd(sk); + return TCP_INFINITE_SSTHRESH; /* BBR does not use ssthresh */ +} + +static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) +{ + if (ext & (1 << (INET_DIAG_BBRINFO - 1)) || + ext & (1 << (INET_DIAG_VEGASINFO - 1))) { + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw = bbr_bw(sk); + + bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE; + memset(&info->bbr, 0, sizeof(info->bbr)); + info->bbr.bbr_bw_lo = (u32)bw; + info->bbr.bbr_bw_hi = (u32)(bw >> 32); + info->bbr.bbr_min_rtt = bbr->min_rtt_us; + info->bbr.bbr_pacing_gain = bbr->pacing_gain; + info->bbr.bbr_cwnd_gain = bbr->cwnd_gain; + *attr = INET_DIAG_BBRINFO; + return sizeof(info->bbr); + } + return 0; +} + +static void bbr_set_state(struct sock *sk, u8 new_state) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (new_state == TCP_CA_Loss) { + struct rate_sample rs = { .losses = 1 }; + + bbr->prev_ca_state = TCP_CA_Loss; + bbr->full_bw = 0; + bbr->round_start = 1; /* treat RTO like end of a round */ + bbr_lt_bw_sampling(sk, &rs); + } +} + +static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { + .flags = TCP_CONG_NON_RESTRICTED, + .name = "bbr", + .owner = THIS_MODULE, + .init = bbr_init, + .cong_control = bbr_main, + .sndbuf_expand = bbr_sndbuf_expand, + .undo_cwnd = bbr_undo_cwnd, + .cwnd_event = bbr_cwnd_event, + .ssthresh = bbr_ssthresh, + .tso_segs_goal = bbr_tso_segs_goal, + .get_info = bbr_get_info, + .set_state = bbr_set_state, +}; + +static int __init bbr_register(void) +{ + BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); + return tcp_register_congestion_control(&tcp_bbr_cong_ops); +} + +static void __exit bbr_unregister(void) +{ + tcp_unregister_congestion_control(&tcp_bbr_cong_ops); +} + +module_init(bbr_register); +module_exit(bbr_unregister); + +MODULE_AUTHOR("Van Jacobson <vanj@google.com>"); +MODULE_AUTHOR("Neal Cardwell <ncardwell@google.com>"); +MODULE_AUTHOR("Yuchung Cheng <ycheng@google.com>"); +MODULE_AUTHOR("Soheil Hassas Yeganeh <soheil@google.com>"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)"); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 03725b2..35b2803 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -56,7 +56,7 @@ MODULE_PARM_DESC(use_shadow, "use shadow window heuristic"); module_param(use_tolerance, bool, 0644); MODULE_PARM_DESC(use_tolerance, "use loss tolerance heuristic"); -struct minmax { +struct cdg_minmax { union { struct { s32 min; @@ -74,10 +74,10 @@ enum cdg_state { }; struct cdg { - struct minmax rtt; - struct minmax rtt_prev; - struct minmax *gradients; - struct minmax gsum; + struct cdg_minmax rtt; + struct cdg_minmax rtt_prev; + struct cdg_minmax *gradients; + struct cdg_minmax gsum; bool gfilled; u8 tail; u8 state; @@ -353,7 +353,7 @@ static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev) { struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - struct minmax *gradients; + struct cdg_minmax *gradients; switch (ev) { case CA_EVENT_CWND_RESTART: diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 882caa4..1294af4 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -69,7 +69,7 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) int ret = 0; /* all algorithms must implement ssthresh and cong_avoid ops */ - if (!ca->ssthresh || !ca->cong_avoid) { + if (!ca->ssthresh || !(ca->cong_avoid || ca->cong_control)) { pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 54d9f9b..4e777a3 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -150,6 +150,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); + sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; @@ -226,6 +227,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; + tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f3a9f3c..8c6ad2d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -289,6 +289,7 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr static void tcp_sndbuf_expand(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; int sndmem, per_mss; u32 nr_segs; @@ -309,7 +310,8 @@ static void tcp_sndbuf_expand(struct sock *sk) * Cubic needs 1.7 factor, rounded to 2 to include * extra cushion (application might react slowly to POLLOUT) */ - sndmem = 2 * nr_segs * per_mss; + sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2; + sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]); @@ -899,12 +901,29 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; } +/* Sum the number of packets on the wire we have marked as lost. + * There are two cases we care about here: + * a) Packet hasn't been marked lost (nor retransmitted), + * and this is the first loss. + * b) Packet has been marked both lost and retransmitted, + * and this means we think it was lost again. + */ +static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb) +{ + __u8 sacked = TCP_SKB_CB(skb)->sacked; + + if (!(sacked & TCPCB_LOST) || + ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS))) + tp->lost += tcp_skb_pcount(skb); +} + static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) { if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tcp_verify_retransmit_hint(tp, skb); tp->lost_out += tcp_skb_pcount(skb); + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; } } @@ -913,6 +932,7 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); + tcp_sum_lost(tp, skb); if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tp->lost_out += tcp_skb_pcount(skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; @@ -1094,6 +1114,7 @@ struct tcp_sacktag_state { */ struct skb_mstamp first_sackt; struct skb_mstamp last_sackt; + struct rate_sample *rate; int flag; }; @@ -1261,6 +1282,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1311,6 +1333,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) + TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1540,6 +1565,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, dup_sack, tcp_skb_pcount(skb), &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1622,8 +1648,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); - if (found_dup_sack) + if (found_dup_sack) { state->flag |= FLAG_DSACKING_ACK; + tp->delivered++; /* A spurious retransmission is delivered */ + } /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can @@ -1890,6 +1918,7 @@ void tcp_enter_loss(struct sock *sk) struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ + bool mark_lost; /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || @@ -1923,8 +1952,12 @@ void tcp_enter_loss(struct sock *sk) if (skb == tcp_send_head(sk)) break; + mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || + is_reneg); + if (mark_lost) + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; - if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) { + if (mark_lost) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); @@ -2503,6 +2536,9 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + if (inet_csk(sk)->icsk_ca_ops->cong_control) + return; + /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { @@ -2879,67 +2915,13 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, *rexmit = REXMIT_LOST; } -/* Kathleen Nichols' algorithm for tracking the minimum value of - * a data stream over some fixed time interval. (E.g., the minimum - * RTT over the past five minutes.) It uses constant space and constant - * time per update yet almost always delivers the same minimum as an - * implementation that has to keep all the data in the window. - * - * The algorithm keeps track of the best, 2nd best & 3rd best min - * values, maintaining an invariant that the measurement time of the - * n'th best >= n-1'th best. It also makes sure that the three values - * are widely separated in the time window since that bounds the worse - * case error when that data is monotonically increasing over the window. - * - * Upon getting a new min, we can forget everything earlier because it - * has no value - the new min is <= everything else in the window by - * definition and it's the most recent. So we restart fresh on every new min - * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd - * best. - */ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { - const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; - struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { - .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), - .ts = now, - }; - u32 elapsed; - - /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ - if (unlikely(rttm.rtt <= m[0].rtt)) - m[0] = m[1] = m[2] = rttm; - else if (rttm.rtt <= m[1].rtt) - m[1] = m[2] = rttm; - else if (rttm.rtt <= m[2].rtt) - m[2] = rttm; - - elapsed = now - m[0].ts; - if (unlikely(elapsed > wlen)) { - /* Passed entire window without a new min so make 2nd choice - * the new min & 3rd choice the new 2nd. So forth and so on. - */ - m[0] = m[1]; - m[1] = m[2]; - m[2] = rttm; - if (now - m[0].ts > wlen) { - m[0] = m[1]; - m[1] = rttm; - if (now - m[0].ts > wlen) - m[0] = rttm; - } - } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) { - /* Passed a quarter of the window without a new min so - * take 2nd choice from the 2nd quarter of the window. - */ - m[2] = m[1] = rttm; - } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) { - /* Passed half the window without a new min so take the 3rd - * choice from the last half of the window. - */ - m[2] = rttm; - } + struct tcp_sock *tp = tcp_sk(sk); + u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; + + minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, + rtt_us ? : jiffies_to_usecs(1)); } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, @@ -3102,10 +3084,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, u32 prior_snd_una, int *acked, - struct tcp_sacktag_state *sack) + struct tcp_sacktag_state *sack, + struct skb_mstamp *now) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt, now; + struct skb_mstamp first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; @@ -3137,7 +3120,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, acked_pcount = tcp_tso_acked(sk, skb); if (!acked_pcount) break; - fully_acked = false; } else { /* Speedup tcp_unlink_write_queue() and next loop */ @@ -3173,6 +3155,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->packets_out -= acked_pcount; pkts_acked += acked_pcount; + tcp_rate_skb_delivered(sk, skb, sack->rate); /* Initial outgoing SYN's get put onto the write_queue * just like anything else we transmit. It is not @@ -3205,16 +3188,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - skb_mstamp_get(&now); if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); + ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); } if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); + sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); + ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); } - + sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, ca_rtt_us); @@ -3242,7 +3224,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { + sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3333,8 +3315,15 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * information. All transmission or retransmission are delayed afterwards. */ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, - int flag) + int flag, const struct rate_sample *rs) { + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ca_ops->cong_control) { + icsk->icsk_ca_ops->cong_control(sk, rs); + return; + } + if (tcp_in_cwnd_reduction(sk)) { /* Reduce cwnd if state mandates */ tcp_cwnd_reduction(sk, acked_sacked, flag); @@ -3579,17 +3568,21 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; + struct rate_sample rs = { .prior_delivered = 0 }; u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; u32 prior_fackets; int prior_packets = tp->packets_out; - u32 prior_delivered = tp->delivered; + u32 delivered = tp->delivered; + u32 lost = tp->lost; int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ + struct skb_mstamp now; sack_state.first_sackt.v64 = 0; + sack_state.rate = &rs; /* We very likely will need to access write queue head. */ prefetchw(sk->sk_write_queue.next); @@ -3612,6 +3605,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; + skb_mstamp_get(&now); + if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -3622,6 +3617,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) } prior_fackets = tp->fackets_out; + rs.prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet * is in window. @@ -3677,7 +3673,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, - &sack_state); + &sack_state, &now); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@ -3694,7 +3690,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - tcp_cong_control(sk, ack, tp->delivered - prior_delivered, flag); + delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ + lost = tp->lost - lost; /* freshly marked lost */ + tcp_rate_gen(sk, delivered, lost, &now, &rs); + tcp_cong_control(sk, ack, delivered, flag, &rs); tcp_xmit_recovery(sk, rexmit); return 1; @@ -4108,7 +4107,7 @@ void tcp_fin(struct sock *sk) /* It _is_ possible, that we have something out-of-order _after_ FIN. * Probably, we should reset in this case. For now drop them. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); @@ -4268,7 +4267,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ - if (skb_queue_empty(&tp->out_of_order_queue)) { + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; return; } @@ -4344,10 +4343,13 @@ static void tcp_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); __u32 dsack_high = tp->rcv_nxt; + bool fin, fragstolen, eaten; struct sk_buff *skb, *tail; - bool fragstolen, eaten; + struct rb_node *p; - while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) { + p = rb_first(&tp->out_of_order_queue); + while (p) { + skb = rb_entry(p, struct sk_buff, rbnode); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4357,9 +4359,10 @@ static void tcp_ofo_queue(struct sock *sk) dsack_high = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } + p = rb_next(p); + rb_erase(&skb->rbnode, &tp->out_of_order_queue); - __skb_unlink(skb, &tp->out_of_order_queue); - if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); tcp_drop(sk, skb); continue; @@ -4371,12 +4374,19 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - tcp_fin(sk); - if (eaten) + else kfree_skb_partial(skb, fragstolen); + + if (unlikely(fin)) { + tcp_fin(sk); + /* tcp_fin() purges tp->out_of_order_queue, + * so we must end this loop right now. + */ + break; + } } } @@ -4403,8 +4413,10 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct rb_node **p, *q, *parent; struct sk_buff *skb1; u32 seq, end_seq; + bool fragstolen; tcp_ecn_check_ce(tp, skb); @@ -4419,88 +4431,92 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) inet_csk_schedule_ack(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + tp->rcv_nxt, seq, end_seq); - skb1 = skb_peek_tail(&tp->out_of_order_queue); - if (!skb1) { + p = &tp->out_of_order_queue.rb_node; + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { /* Initial out of order segment, build 1 SACK. */ if (tcp_is_sack(tp)) { tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; + tp->selective_acks[0].start_seq = seq; + tp->selective_acks[0].end_seq = end_seq; } - __skb_queue_head(&tp->out_of_order_queue, skb); + rb_link_node(&skb->rbnode, NULL, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); + tp->ooo_last_skb = skb; goto end; } - seq = TCP_SKB_CB(skb)->seq; - end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - bool fragstolen; - - if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - } else { - tcp_grow_window(sk, skb); - kfree_skb_partial(skb, fragstolen); - skb = NULL; - } - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; - goto end; - } - - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; - } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); - } - - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb); - skb = NULL; - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; + /* In the typical case, we are adding an skb to the end of the list. + * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. + */ + if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { +coalesce_done: + tcp_grow_window(sk, skb); + kfree_skb_partial(skb, fragstolen); + skb = NULL; + goto add_sack; + } + /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ + if (!before(seq, TCP_SKB_CB(tp->ooo_last_skb)->end_seq)) { + parent = &tp->ooo_last_skb->rbnode; + p = &parent->rb_right; + goto insert; + } + + /* Find place to insert this segment. Handle overlaps on the way. */ + parent = NULL; + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(seq, TCP_SKB_CB(skb1)->seq)) { + p = &parent->rb_left; + continue; } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); + if (before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); + } else { + /* skb's seq == skb1's seq and skb covers skb1. + * Replace skb1 with skb. + */ + rb_replace_node(&skb1->rbnode, &skb->rbnode, + &tp->out_of_order_queue); + tcp_dsack_extend(sk, + TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb1); + goto merge_right; + } + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { + goto coalesce_done; } + p = &parent->rb_right; } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); +insert: + /* Insert segment into RB tree. */ + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); +merge_right: + /* Remove other segments covered by skb. */ + while ((q = rb_next(&skb->rbnode)) != NULL) { + skb1 = rb_entry(q, struct sk_buff, rbnode); if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; @@ -4509,12 +4525,15 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) end_seq); break; } - __skb_unlink(skb1, &tp->out_of_order_queue); + rb_erase(&skb1->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); } + /* If there is no skb after us, we are the last_skb ! */ + if (!q) + tp->ooo_last_skb = skb; add_sack: if (tcp_is_sack(tp)) @@ -4651,13 +4670,13 @@ queue_and_out: if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); - if (!skb_queue_empty(&tp->out_of_order_queue)) { + if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) inet_csk(sk)->icsk_ack.pingpong = 0; } @@ -4711,48 +4730,76 @@ drop: tcp_data_queue_ofo(sk, skb); } +static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list) +{ + if (list) + return !skb_queue_is_last(list, skb) ? skb->next : NULL; + + return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); +} + static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct rb_root *root) { - struct sk_buff *next = NULL; + struct sk_buff *next = tcp_skb_next(skb, list); - if (!skb_queue_is_last(list, skb)) - next = skb_queue_next(list, skb); + if (list) + __skb_unlink(skb, list); + else + rb_erase(&skb->rbnode, root); - __skb_unlink(skb, list); __kfree_skb(skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } +/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ +static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct sk_buff *skb1; + + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, root); +} + /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. * - * If tail is NULL, this means until the end of the list. + * If tail is NULL, this means until the end of the queue. * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ static void -tcp_collapse(struct sock *sk, struct sk_buff_head *list, - struct sk_buff *head, struct sk_buff *tail, - u32 start, u32 end) +tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, + struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { - struct sk_buff *skb, *n; + struct sk_buff *skb = head, *n; + struct sk_buff_head tmp; bool end_of_skbs; /* First, check that queue is collapsible and find - * the point where collapsing can be useful. */ - skb = head; + * the point where collapsing can be useful. + */ restart: - end_of_skbs = true; - skb_queue_walk_from_safe(list, skb, n) { - if (skb == tail) - break; + for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { + n = tcp_skb_next(skb, list); + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb) break; goto restart; @@ -4770,13 +4817,10 @@ restart: break; } - if (!skb_queue_is_last(list, skb)) { - struct sk_buff *next = skb_queue_next(list, skb); - if (next != tail && - TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) { - end_of_skbs = false; - break; - } + if (n && n != tail && + TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { + end_of_skbs = false; + break; } /* Decided to skip this, advance start seq. */ @@ -4786,17 +4830,22 @@ restart: (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) return; + __skb_queue_head_init(&tmp); + while (before(start, end)) { int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start); struct sk_buff *nskb; nskb = alloc_skb(copy, GFP_ATOMIC); if (!nskb) - return; + break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; - __skb_queue_before(list, skb, nskb); + if (list) + __skb_queue_before(list, skb, nskb); + else + __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); /* Copy data, releasing collapsed skbs. */ @@ -4814,14 +4863,17 @@ restart: start += size; } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) - return; + goto end; } } } +end: + skb_queue_walk_safe(&tmp, skb, n) + tcp_rbtree_insert(root, skb); } /* Collapse ofo queue. Algorithm: select contiguous sequence of skbs @@ -4830,43 +4882,43 @@ restart: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = skb_peek(&tp->out_of_order_queue); - struct sk_buff *head; + struct sk_buff *skb, *head; + struct rb_node *p; u32 start, end; - if (!skb) + p = rb_first(&tp->out_of_order_queue); + skb = rb_entry_safe(p, struct sk_buff, rbnode); +new_range: + if (!skb) { + p = rb_last(&tp->out_of_order_queue); + /* Note: This is possible p is NULL here. We do not + * use rb_entry_safe(), as ooo_last_skb is valid only + * if rbtree is not empty. + */ + tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); return; - + } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; - head = skb; - - for (;;) { - struct sk_buff *next = NULL; - if (!skb_queue_is_last(&tp->out_of_order_queue, skb)) - next = skb_queue_next(&tp->out_of_order_queue, skb); - skb = next; + for (head = skb;;) { + skb = tcp_skb_next(skb, NULL); - /* Segment is terminated when we see gap or when - * we are at the end of all the queue. */ + /* Range is terminated when we see a gap or when + * we are at the queue end. + */ if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, &tp->out_of_order_queue, + tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); - head = skb; - if (!skb) - break; - /* Start new segment */ + goto new_range; + } + + if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; + if (after(TCP_SKB_CB(skb)->end_seq, end)) end = TCP_SKB_CB(skb)->end_seq; - } else { - if (before(TCP_SKB_CB(skb)->seq, start)) - start = TCP_SKB_CB(skb)->seq; - if (after(TCP_SKB_CB(skb)->end_seq, end)) - end = TCP_SKB_CB(skb)->end_seq; - } } } @@ -4883,20 +4935,24 @@ static void tcp_collapse_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + struct rb_node *node, *prev; - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); - - while ((skb = __skb_dequeue_tail(&tp->out_of_order_queue)) != NULL) { - tcp_drop(sk, skb); + node = &tp->ooo_last_skb->rbnode; + do { + prev = rb_prev(node); + rb_erase(node, &tp->out_of_order_queue); + tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; - } + node = prev; + } while (node); + tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -4930,7 +4986,7 @@ static int tcp_prune_queue(struct sock *sk) tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) - tcp_collapse(sk, &sk->sk_receive_queue, + tcp_collapse(sk, &sk->sk_receive_queue, NULL, skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); @@ -5035,7 +5091,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ - (ofo_possible && skb_peek(&tp->out_of_order_queue))) { + (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { /* Then ack it now */ tcp_send_ack(sk); } else { @@ -5894,7 +5950,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * so release it. */ if (req) { - tp->total_retrans = req->num_retrans; + inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for correct metrics. */ @@ -5936,7 +5992,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else tcp_init_metrics(sk); - tcp_update_pacing_rate(sk); + if (!inet_csk(sk)->icsk_ca_ops->cong_control) + tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 13b05ad..7ac37c3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1844,7 +1844,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_write_queue_purge(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4b95ec4..6234eba 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -464,7 +464,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - newtp->rtt_min[0].rtt = ~0U; + minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; @@ -487,8 +487,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; + /* There's a bubble in the pipe until at least the first ACK. */ + newtp->app_limited = ~0U; + tcp_init_xmit_timers(newsk); - __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 5c59649..bc68da3 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -90,12 +90,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, goto out; } - /* GSO partial only requires splitting the frame into an MSS - * multiple and possibly a remainder. So update the mss now. - */ - if (features & NETIF_F_GSO_PARTIAL) - mss = skb->len - (skb->len % mss); - copy_destructor = gso_skb->destructor == tcp_wfree; ooo_okay = gso_skb->ooo_okay; /* All segments but the first should have ooo_okay cleared */ @@ -108,6 +102,13 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, /* Only first segment might have ooo_okay set */ segs->ooo_okay = ooo_okay; + /* GSO partial and frag_list segmentation only requires splitting + * the frame into an MSS multiple and possibly a remainder, both + * cases return a GSO skb. So update the mss now. + */ + if (skb_is_gso(segs)) + mss *= skb_shinfo(segs)->gso_segs; + delta = htonl(oldlen + (thlen + mss)); skb = segs; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8b45794..7c777089 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -734,9 +734,16 @@ static void tcp_tsq_handler(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | - TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->lost_out > tp->retrans_out && + tp->snd_cwnd > tcp_packets_in_flight(tp)) + tcp_xmit_retransmit_queue(sk); + + tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); + } } /* * One tasklet per cpu tries to send more skbs. @@ -918,6 +925,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_mstamp_get(&skb->skb_mstamp); TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; + tcp_rate_skb_sent(sk, skb); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -1213,6 +1221,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); + /* Update delivered info for the new segment */ + TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; + /* If this packet has been sent out already, we must * adjust the various packet counters. */ @@ -1358,6 +1369,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) } return mtu; } +EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) @@ -1545,7 +1557,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ -static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now) +u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, + int min_tso_segs) { u32 bytes, segs; @@ -1557,10 +1570,23 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now) * This preserves ACK clocking and is consistent * with tcp_tso_should_defer() heuristic. */ - segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs); + segs = max_t(u32, bytes / mss_now, min_tso_segs); return min_t(u32, segs, sk->sk_gso_max_segs); } +EXPORT_SYMBOL(tcp_tso_autosize); + +/* Return the number of segments we want in the skb we are transmitting. + * See if congestion control module wants to decide; otherwise, autosize. + */ +static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) +{ + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; + u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; + + return tso_segs ? : + tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs); +} /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, @@ -2020,6 +2046,39 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } +/* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * (These limits are doubled for retransmits) + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) + */ +static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, + unsigned int factor) +{ + unsigned int limit; + + limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); + limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); + limit <<= factor; + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { + set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags); + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + */ + smp_mb__after_atomic(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + return true; + } + return false; +} + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -2057,7 +2116,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } } - max_segs = tcp_tso_autosize(sk, mss_now); + max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -2106,29 +2165,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; - /* TCP Small Queues : - * Control number of packets in qdisc/devices to two packets / or ~1 ms. - * This allows for : - * - better RTT estimation and ACK scheduling - * - faster recovery - * - high rates - * Alas, some drivers / subsystems require a fair amount - * of queued bytes to ensure line rate. - * One example is wifi aggregation (802.11 AMPDU) - */ - limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); - limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); - - if (atomic_read(&sk->sk_wmem_alloc) > limit) { - set_bit(TSQ_THROTTLED, &tp->tsq_flags); - /* It is possible TX completion already happened - * before we set TSQ_THROTTLED, so we must - * test again the condition. - */ - smp_mb__after_atomic(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) - break; - } + if (tcp_small_queue_check(sk, skb, 0)) + break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -2605,7 +2643,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) * copying overhead: fragmentation, tunneling, mangling etc. */ if (atomic_read(&sk->sk_wmem_alloc) > - min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) + min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), + sk->sk_sndbuf)) return -EAGAIN; if (skb_still_in_host_queue(sk, skb)) @@ -2774,7 +2813,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) last_lost = tp->snd_una; } - max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk)); + max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); tcp_for_write_queue_from(skb, sk) { __u8 sacked; int segs; @@ -2828,10 +2867,13 @@ begin_fwd: if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; + if (tcp_small_queue_check(sk, skb, 1)) + return; + if (tcp_retransmit_skb(sk, skb, segs)) return; - NET_INC_STATS(sock_net(sk), mib_idx); + NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); @@ -3568,6 +3610,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + if (unlikely(tcp_passive_fastopen(sk))) + tcp_sk(sk)->total_retrans++; } return res; } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c new file mode 100644 index 0000000..9be1581 --- /dev/null +++ b/net/ipv4/tcp_rate.c @@ -0,0 +1,186 @@ +#include <net/tcp.h> + +/* The bandwidth estimator estimates the rate at which the network + * can currently deliver outbound data packets for this flow. At a high + * level, it operates by taking a delivery rate sample for each ACK. + * + * A rate sample records the rate at which the network delivered packets + * for this flow, calculated over the time interval between the transmission + * of a data packet and the acknowledgment of that packet. + * + * Specifically, over the interval between each transmit and corresponding ACK, + * the estimator generates a delivery rate sample. Typically it uses the rate + * at which packets were acknowledged. However, the approach of using only the + * acknowledgment rate faces a challenge under the prevalent ACK decimation or + * compression: packets can temporarily appear to be delivered much quicker + * than the bottleneck rate. Since it is physically impossible to do that in a + * sustained fashion, when the estimator notices that the ACK rate is faster + * than the transmit rate, it uses the latter: + * + * send_rate = #pkts_delivered/(last_snd_time - first_snd_time) + * ack_rate = #pkts_delivered/(last_ack_time - first_ack_time) + * bw = min(send_rate, ack_rate) + * + * Notice the estimator essentially estimates the goodput, not always the + * network bottleneck link rate when the sending or receiving is limited by + * other factors like applications or receiver window limits. The estimator + * deliberately avoids using the inter-packet spacing approach because that + * approach requires a large number of samples and sophisticated filtering. + * + * TCP flows can often be application-limited in request/response workloads. + * The estimator marks a bandwidth sample as application-limited if there + * was some moment during the sampled window of packets when there was no data + * ready to send in the write queue. + */ + +/* Snapshot the current delivery information in the skb, to generate + * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered(). + */ +void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + + /* In general we need to start delivery rate samples from the + * time we received the most recent ACK, to ensure we include + * the full time the network needs to deliver all in-flight + * packets. If there are no packets in flight yet, then we + * know that any ACKs after now indicate that the network was + * able to deliver those packets completely in the sampling + * interval between now and the next ACK. + * + * Note that we use packets_out instead of tcp_packets_in_flight(tp) + * because the latter is a guess based on RTO and loss-marking + * heuristics. We don't want spurious RTOs or loss markings to cause + * a spuriously small time interval, causing a spuriously high + * bandwidth estimate. + */ + if (!tp->packets_out) { + tp->first_tx_mstamp = skb->skb_mstamp; + tp->delivered_mstamp = skb->skb_mstamp; + } + + TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; + TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; + TCP_SKB_CB(skb)->tx.delivered = tp->delivered; + TCP_SKB_CB(skb)->tx.is_app_limited = tp->app_limited ? 1 : 0; +} + +/* When an skb is sacked or acked, we fill in the rate sample with the (prior) + * delivery information when the skb was last transmitted. + * + * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is + * called multiple times. We favor the information from the most recently + * sent skb, i.e., the skb with the highest prior_delivered count. + */ +void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, + struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + + if (!scb->tx.delivered_mstamp.v64) + return; + + if (!rs->prior_delivered || + after(scb->tx.delivered, rs->prior_delivered)) { + rs->prior_delivered = scb->tx.delivered; + rs->prior_mstamp = scb->tx.delivered_mstamp; + rs->is_app_limited = scb->tx.is_app_limited; + rs->is_retrans = scb->sacked & TCPCB_RETRANS; + + /* Find the duration of the "send phase" of this window: */ + rs->interval_us = skb_mstamp_us_delta( + &skb->skb_mstamp, + &scb->tx.first_tx_mstamp); + + /* Record send time of most recently ACKed packet: */ + tp->first_tx_mstamp = skb->skb_mstamp; + } + /* Mark off the skb delivered once it's sacked to avoid being + * used again when it's cumulatively acked. For acked packets + * we don't need to reset since it'll be freed soon. + */ + if (scb->sacked & TCPCB_SACKED_ACKED) + scb->tx.delivered_mstamp.v64 = 0; +} + +/* Update the connection delivery information and generate a rate sample. */ +void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, + struct skb_mstamp *now, struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + u32 snd_us, ack_us; + + /* Clear app limited if bubble is acked and gone. */ + if (tp->app_limited && after(tp->delivered, tp->app_limited)) + tp->app_limited = 0; + + /* TODO: there are multiple places throughout tcp_ack() to get + * current time. Refactor the code using a new "tcp_acktag_state" + * to carry current time, flags, stats like "tcp_sacktag_state". + */ + if (delivered) + tp->delivered_mstamp = *now; + + rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ + rs->losses = lost; /* freshly marked lost */ + /* Return an invalid sample if no timing information is available. */ + if (!rs->prior_mstamp.v64) { + rs->delivered = -1; + rs->interval_us = -1; + return; + } + rs->delivered = tp->delivered - rs->prior_delivered; + + /* Model sending data and receiving ACKs as separate pipeline phases + * for a window. Usually the ACK phase is longer, but with ACK + * compression the send phase can be longer. To be safe we use the + * longer phase. + */ + snd_us = rs->interval_us; /* send phase */ + ack_us = skb_mstamp_us_delta(now, &rs->prior_mstamp); /* ack phase */ + rs->interval_us = max(snd_us, ack_us); + + /* Normally we expect interval_us >= min-rtt. + * Note that rate may still be over-estimated when a spuriously + * retransmistted skb was first (s)acked because "interval_us" + * is under-estimated (up to an RTT). However continuously + * measuring the delivery rate during loss recovery is crucial + * for connections suffer heavy or prolonged losses. + */ + if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { + if (!rs->is_retrans) + pr_debug("tcp rate: %ld %d %u %u %u\n", + rs->interval_us, rs->delivered, + inet_csk(sk)->icsk_ca_state, + tp->rx_opt.sack_ok, tcp_min_rtt(tp)); + rs->interval_us = -1; + return; + } + + /* Record the last non-app-limited or the highest app-limited bw */ + if (!rs->is_app_limited || + ((u64)rs->delivered * tp->rate_interval_us >= + (u64)tp->rate_delivered * rs->interval_us)) { + tp->rate_delivered = rs->delivered; + tp->rate_interval_us = rs->interval_us; + tp->rate_app_limited = rs->is_app_limited; + } +} + +/* If a gap is detected between sends, mark the socket application-limited. */ +void tcp_rate_check_app_limited(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (/* We have less than one packet to send. */ + tp->write_seq - tp->snd_nxt < tp->mss_cache && + /* Nothing in sending host's qdisc queues or NIC tx queue. */ + sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) && + /* We are not limited by CWND. */ + tcp_packets_in_flight(tp) < tp->snd_cwnd && + /* All lost packets have been retransmitted. */ + tp->lost_out <= tp->retrans_out) + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; +} diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d84930b..f712b41 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -384,6 +384,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) */ inet_rtx_syn_ack(sk, req); req->num_timeout++; + icsk->icsk_retransmits++; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 028eb04..9c5fc97 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -76,7 +76,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else if (!yeah->doing_reno_now) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 058c312..7d96dc2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1021,12 +1021,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flow_flags, faddr, saddr, dport, inet->inet_sport); - if (!saddr && ipc.oif) { - err = l3mdev_get_saddr(net, ipc.oif, fl4); - if (err < 0) - goto out; - } - security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 8a9f6e5..9a89c10 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -20,7 +20,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, - struct nlattr *bc) + struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -28,7 +28,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, return inet_sk_diag_fill(sk, NULL, skb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, @@ -76,7 +76,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, err = inet_sk_diag_fill(sk, NULL, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); @@ -97,6 +98,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); int num, s_num, slot, s_slot; @@ -132,7 +134,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } @@ -186,8 +188,8 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = __udp4_lib_lookup(net, - req->id.idiag_dst[0], req->id.idiag_dport, - req->id.idiag_src[0], req->id.idiag_sport, + req->id.idiag_dst[3], req->id.idiag_dport, + req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if, tbl, NULL); else diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 81f253b..f9333c9 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -21,7 +21,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); - bool remcsum, need_csum, offload_csum, ufo; + bool remcsum, need_csum, offload_csum, ufo, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; @@ -88,6 +88,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, goto out; } + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; @@ -117,7 +119,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (skb_is_gso(skb)) { + if (gso_partial) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index b644a23..6a7ff69 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -29,7 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; - fl4->flowi4_oif = oif; + fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); if (saddr) fl4->saddr = saddr->a4; @@ -112,7 +112,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) int oif = 0; if (skb_dst(skb)) - oif = l3mdev_fib_oif(skb_dst(skb)->dev); + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f418d2e..2f1f5d4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -778,7 +778,14 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->forwarding) { + int old_dflt = net->ipv6.devconf_dflt->forwarding; + net->ipv6.devconf_dflt->forwarding = newf; + if ((!newf) ^ (!old_dflt)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + addrconf_forward_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, @@ -1941,6 +1948,7 @@ errdad: spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); + in6_ifa_put(ifp); } /* Join to solicited addr multicast group. @@ -3850,6 +3858,7 @@ static void addrconf_dad_work(struct work_struct *w) addrconf_dad_begin(ifp); goto out; } else if (action == DAD_ABORT) { + in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); if (disable_ipv6) addrconf_ifdown(idev->dev, 0); @@ -6025,7 +6034,7 @@ static const struct ctl_table addrconf_sysctl[] = { static int __addrconf_sysctl_register(struct net *net, char *dev_name, struct inet6_dev *idev, struct ipv6_devconf *p) { - int i; + int i, ifindex; struct ctl_table *table; char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; @@ -6045,6 +6054,13 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, if (!p->sysctl_header) goto free; + if (!strcmp(dev_name, "all")) + ifindex = NETCONFA_IFINDEX_ALL; + else if (!strcmp(dev_name, "default")) + ifindex = NETCONFA_IFINDEX_DEFAULT; + else + ifindex = idev->dev->ifindex; + inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); return 0; free: diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 5857c1f..eea23b5 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -38,6 +38,9 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, .flags = FIB_LOOKUP_NOREF, }; + /* update flow if oif or iif point to device enslaved to l3mdev */ + l3mdev_update_flow(net, flowi6_to_flowi(fl6)); + fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 771be1f..ef54852 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -743,6 +743,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + u16 nlflags = NLM_F_EXCL; int err; ins = &fn->leaf; @@ -759,6 +760,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; + + nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; @@ -856,6 +859,7 @@ next_iter: pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: + nlflags |= NLM_F_CREATE; err = fib6_commit_metrics(&rt->dst, mxc); if (err) return err; @@ -864,7 +868,7 @@ add: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); + inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 397e1ed..4ce74f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1239,7 +1239,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[], parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]); if (data[IFLA_GRE_FLOWINFO]) - parms->flowinfo = nla_get_u32(data[IFLA_GRE_FLOWINFO]); + parms->flowinfo = nla_get_be32(data[IFLA_GRE_FLOWINFO]); if (data[IFLA_GRE_FLAGS]) parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 22e90e5..e7bfd55 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -69,6 +69,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int offset = 0; bool encap, udpfrag; int nhoff; + bool gso_partial; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); @@ -101,9 +102,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (IS_ERR(segs)) goto out; + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); - if (skb_is_gso(skb)) + if (gso_partial) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 993fd96..6001e78 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -236,6 +236,14 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); + + /* if egress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip6_out((struct sock *)sk, skb); + if (unlikely(!skb)) + return 0; + /* hooks should never assume socket lock is held. * we promote our socket to non const */ @@ -918,13 +926,6 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, int err; int flags = 0; - if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif && - (!*dst || !(*dst)->error)) { - err = l3mdev_get_saddr6(net, sk, fl6); - if (err) - goto out_err; - } - /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, * the route-specific preferred source forces the @@ -1016,7 +1017,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, out_err_release: dst_release(*dst); *dst = NULL; -out_err: + if (err == -ENETUNREACH) IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); return err; @@ -1062,8 +1063,6 @@ struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - if (!fl6->flowi6_oif) - fl6->flowi6_oif = l3mdev_fib_oif(dst->dev); return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2050217..6a66adb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -57,6 +57,7 @@ #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/dst_metadata.h> MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); @@ -90,6 +91,7 @@ struct ip6_tnl_net { struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; + struct ip6_tnl __rcu *collect_md_tun; }; static struct net_device_stats *ip6_get_stats(struct net_device *dev) @@ -166,6 +168,10 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_ return t; } + t = rcu_dereference(ip6n->collect_md_tun); + if (t) + return t; + t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; @@ -209,6 +215,8 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); + if (t->parms.collect_md) + rcu_assign_pointer(ip6n->collect_md_tun, t); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } @@ -224,6 +232,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; + if (t->parms.collect_md) + rcu_assign_pointer(ip6n->collect_md_tun, NULL); + for (tp = ip6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { @@ -829,6 +840,9 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); + if (tun_dst) + skb_dst_set(skb, (struct dst_entry *)tun_dst); + gro_cells_receive(&tunnel->gro_cells, skb); return 0; @@ -865,6 +879,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct metadata_dst *tun_dst = NULL; int ret = -1; rcu_read_lock(); @@ -881,7 +896,12 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; - ret = __ip6_tnl_rcv(t, skb, tpi, NULL, dscp_ecn_decapsulate, + if (t->parms.collect_md) { + tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0); + if (!tun_dst) + return 0; + } + ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_error); } @@ -1012,8 +1032,16 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, int mtu; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; + u8 hop_limit; int err = -1; + if (t->parms.collect_md) { + hop_limit = skb_tunnel_info(skb)->key.ttl; + goto route_lookup; + } else { + hop_limit = t->parms.hop_limit; + } + /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { struct in6_addr *addr6; @@ -1043,6 +1071,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, goto tx_err_link_failure; if (!dst) { +route_lookup: dst = ip6_route_output(net, NULL, fl6); if (dst->error) @@ -1053,6 +1082,10 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, dst = NULL; goto tx_err_link_failure; } + if (t->parms.collect_md && + ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, + &fl6->daddr, 0, &fl6->saddr)) + goto tx_err_link_failure; ndst = dst; } @@ -1071,7 +1104,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb_dst(skb)) + if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { *pmtu = mtu; @@ -1111,8 +1144,13 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, skb = new_skb; } - if (!fl6->flowi6_mark && ndst) - dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); + if (t->parms.collect_md) { + if (t->encap.type != TUNNEL_ENCAP_NONE) + goto tx_err_dst_release; + } else { + if (!fl6->flowi6_mark && ndst) + dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); + } skb_dst_set(skb, dst); if (encap_limit >= 0) { @@ -1137,7 +1175,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); - ipv6h->hop_limit = t->parms.hop_limit; + ipv6h->hop_limit = hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; @@ -1170,18 +1208,34 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) if (tproto != IPPROTO_IPIP && tproto != 0) return -1; - if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - encap_limit = t->parms.encap_limit; + dsfield = ipv4_get_dsfield(iph); - memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + if (t->parms.collect_md) { + struct ip_tunnel_info *tun_info; + const struct ip_tunnel_key *key; - dsfield = ipv4_get_dsfield(iph); + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET6)) + return -1; + key = &tun_info->key; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; + fl6.daddr = key->u.ipv6.dst; + fl6.flowlabel = key->label; + } else { + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; - if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) - fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) - & IPV6_TCLASS_MASK; - if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) - fl6.flowi6_mark = skb->mark; + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; + + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) + fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) + & IPV6_TCLASS_MASK; + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; @@ -1219,28 +1273,47 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) ip6_tnl_addr_conflict(t, ipv6h)) return -1; - offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); - if (offset > 0) { - struct ipv6_tlv_tnl_enc_lim *tel; - tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; - if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + dsfield = ipv6_get_dsfield(ipv6h); + + if (t->parms.collect_md) { + struct ip_tunnel_info *tun_info; + const struct ip_tunnel_key *key; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET6)) return -1; + key = &tun_info->key; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; + fl6.daddr = key->u.ipv6.dst; + fl6.flowlabel = key->label; + } else { + offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + if (offset > 0) { + struct ipv6_tlv_tnl_enc_lim *tel; + + tel = (void *)&skb_network_header(skb)[offset]; + if (tel->encap_limit == 0) { + icmpv6_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); + return -1; + } + encap_limit = tel->encap_limit - 1; + } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) { + encap_limit = t->parms.encap_limit; } - encap_limit = tel->encap_limit - 1; - } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - encap_limit = t->parms.encap_limit; - memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; - dsfield = ipv6_get_dsfield(ipv6h); - if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) - fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); - if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) - fl6.flowlabel |= ip6_flowlabel(ipv6h); - if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) - fl6.flowi6_mark = skb->mark; + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) + fl6.flowlabel |= (*(__be32 *)ipv6h & IPV6_TCLASS_MASK); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) + fl6.flowlabel |= ip6_flowlabel(ipv6h); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; @@ -1739,6 +1812,10 @@ static int ip6_tnl_dev_init(struct net_device *dev) if (err) return err; ip6_tnl_link_config(t); + if (t->parms.collect_md) { + dev->features |= NETIF_F_NETNS_LOCAL; + netif_keep_dst(dev); + } return 0; } @@ -1809,6 +1886,9 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[], if (data[IFLA_IPTUN_PROTO]) parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + + if (data[IFLA_IPTUN_COLLECT_METADATA]) + parms->collect_md = true; } static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[], @@ -1848,6 +1928,7 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; @@ -1862,9 +1943,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, ip6_tnl_netlink_parms(data, &nt->parms); - t = ip6_tnl_locate(net, &nt->parms, 0); - if (!IS_ERR(t)) - return -EEXIST; + if (nt->parms.collect_md) { + if (rtnl_dereference(ip6n->collect_md_tun)) + return -EEXIST; + } else { + t = ip6_tnl_locate(net, &nt->parms, 0); + if (!IS_ERR(t)) + return -EEXIST; + } return ip6_tnl_create2(dev); } @@ -1888,6 +1974,8 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], return err; } ip6_tnl_netlink_parms(data, &p); + if (p.collect_md) + return -EINVAL; t = ip6_tnl_locate(net, &p, 0); if (!IS_ERR(t)) { @@ -1935,6 +2023,8 @@ static size_t ip6_tnl_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_IPTUN_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -1953,16 +2043,15 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) goto nla_put_failure; - if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, - tunnel->encap.type) || - nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, - tunnel->encap.sport) || - nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, - tunnel->encap.dport) || - nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, - tunnel->encap.flags)) + if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || + nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || + nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || + nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; + if (parm->collect_md) + if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) + goto nla_put_failure; return 0; nla_put_failure: @@ -1990,6 +2079,7 @@ static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ip6_link_ops __read_mostly = { diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index cc7e058..8a02ca8 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -321,11 +321,9 @@ static int vti6_rcv(struct sk_buff *skb) goto discard; } - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; - rcu_read_unlock(); - return xfrm6_rcv(skb); + return xfrm6_rcv_tnl(skb, t); } rcu_read_unlock(); return -EINVAL; @@ -340,6 +338,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) struct net_device *dev; struct pcpu_sw_netstats *tstats; struct xfrm_state *x; + struct xfrm_mode *inner_mode; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; u32 orig_mark = skb->mark; int ret; @@ -357,7 +356,19 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) } x = xfrm_input_state(skb); - family = x->inner_mode->afinfo->family; + + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + family = inner_mode->afinfo->family; skb->mark = be32_to_cpu(t->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 6122f9c..fccb5dd 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2239,6 +2239,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct rta_mfc_stats mfcs; struct nlattr *mp_attr; struct rtnexthop *nhp; + unsigned long lastuse; int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ @@ -2269,12 +2270,14 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, nla_nest_end(skb, mp_attr); + lastuse = READ_ONCE(c->mfc_un.res.lastuse); + lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; + mfcs.mfcs_packets = c->mfc_un.res.pkt; mfcs.mfcs_bytes = c->mfc_un.res.bytes; mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, - jiffies_to_clock_t(c->mfc_un.res.lastuse), + nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) return -EMSGSIZE; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index fe65cdc..d8e6714 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -67,7 +67,6 @@ #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> -#include <net/l3mdev.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> @@ -457,11 +456,9 @@ static void ndisc_send_skb(struct sk_buff *skb, if (!dst) { struct flowi6 fl6; - int oif = l3mdev_fib_oif(skb->dev); + int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); - if (oif != skb->dev->ifindex) - fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); @@ -1538,7 +1535,6 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; - int oif = l3mdev_fib_oif(dev); bool ret; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { @@ -1555,10 +1551,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, - &saddr_buf, &ipv6_hdr(skb)->saddr, oif); - - if (oif != skb->dev->ifindex) - fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; + &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 01eb0f6..f272747 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv, struct in6_addr saddr, daddr; u_int8_t hop_limit; u32 mark, flowlabel; + int err; nft_set_pktinfo_ipv6(&pkt, skb, state); @@ -44,13 +45,16 @@ static unsigned int nf_route_table_hook(void *priv, flowlabel = *((u32 *)ipv6_hdr(skb)); ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_QUEUE && + if (ret != NF_DROP && ret != NF_STOLEN && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || - flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) - return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP; + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { + err = ip6_route_me_harder(state->net, skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } return ret; } diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 533cd57..92bda99 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -47,6 +47,7 @@ static const struct nft_expr_ops nft_reject_ipv6_ops = { .eval = nft_reject_ipv6_eval, .init = nft_reject_init, .dump = nft_reject_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 462f2a76b..7cca8ac 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -148,6 +148,13 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + /* if egress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip6_out(sk, skb); + if (unlikely(!skb)) + return 0; + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 0900352..0e983b6 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -126,8 +126,10 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rt = (struct rt6_info *) dst; np = inet6_sk(sk); - if (!np) - return -EBADF; + if (!np) { + err = -EBADF; + goto dst_err_out; + } if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; @@ -163,6 +165,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } release_sock(sk); +dst_err_out: + dst_release(dst); + if (err) return err; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 590dd1f..54404f0 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -653,6 +653,13 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, if (err) goto error_fault; + /* if egress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip6_out(sk, skb); + if (unlikely(!skb)) + return 0; + IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 09d43ff..5a5aeb9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1147,15 +1147,16 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table * return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); } -static struct dst_entry *ip6_route_input_lookup(struct net *net, - struct net_device *dev, - struct flowi6 *fl6, int flags) +struct dst_entry *ip6_route_input_lookup(struct net *net, + struct net_device *dev, + struct flowi6 *fl6, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input); } +EXPORT_SYMBOL_GPL(ip6_route_input_lookup); void ip6_route_input(struct sk_buff *skb) { @@ -1164,7 +1165,7 @@ void ip6_route_input(struct sk_buff *skb) int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { - .flowi6_iif = l3mdev_fib_oif(skb->dev), + .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), @@ -1188,12 +1189,15 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { - struct dst_entry *dst; bool any_src; - dst = l3mdev_get_rt6_dst(net, fl6); - if (dst) - return dst; + if (rt6_need_strict(&fl6->daddr)) { + struct dst_entry *dst; + + dst = l3mdev_link_scope_lookup(net, fl6); + if (dst) + return dst; + } fl6->flowi6_iif = LOOPBACK_IFINDEX; @@ -1988,9 +1992,18 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) if (!(gwa_type & IPV6_ADDR_UNICAST)) goto out; - if (cfg->fc_table) + if (cfg->fc_table) { grt = ip6_nh_lookup_table(net, cfg, gw_addr); + if (grt) { + if (grt->rt6i_flags & RTF_GATEWAY || + (dev && dev != grt->dst.dev)) { + ip6_rt_put(grt); + grt = NULL; + } + } + } + if (!grt) grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1); @@ -2558,8 +2571,16 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, { u32 tb_id; struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, - DST_NOCOUNT); + struct net_device *dev = net->loopback_dev; + struct rt6_info *rt; + + /* use L3 Master device as loopback for host routes if device + * is enslaved and address is not link local or multicast + */ + if (!rt6_need_strict(addr)) + dev = l3mdev_master_dev_rcu(idev->dev) ? : dev; + + rt = ip6_dst_alloc(net, dev, DST_NOCOUNT); if (!rt) return ERR_PTR(-ENOMEM); @@ -3338,11 +3359,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) } else { fl6.flowi6_oif = oif; - if (netif_index_is_l3_master(net, oif)) { - fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | - FLOWI_FLAG_SKIP_NH_OIF; - } - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 04529a3..54cf719 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -818,12 +818,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); - else { - if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) - oif = skb->skb_iif; - - fl6.flowi6_oif = oif; - } + else + fl6.flowi6_oif = oif ? : skb->skb_iif; fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 0eaab1f..b578956 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -21,8 +21,10 @@ int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm6_extract_header(skb); } -int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) +int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, + struct ip6_tnl *t) { + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); @@ -48,13 +50,18 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) return -1; } -int xfrm6_rcv(struct sk_buff *skb) +int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t) { return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0); + 0, t); } -EXPORT_SYMBOL(xfrm6_rcv); +EXPORT_SYMBOL(xfrm6_rcv_tnl); +int xfrm6_rcv(struct sk_buff *skb) +{ + return xfrm6_rcv_tnl(skb, NULL); +} +EXPORT_SYMBOL(xfrm6_rcv); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto) { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6cc9700..e0f71c0 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -36,7 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, int err; memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = oif; + fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif); fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) @@ -134,7 +134,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) nexthdr = nh[nhoff]; if (skb_dst(skb)) - oif = l3mdev_fib_oif(skb_dst(skb)->dev); + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 5743044..e1c0bbe 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -236,7 +236,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb) __be32 spi; spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr); - return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi); + return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL); } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index db63969..391c3cb 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -832,7 +832,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) struct sock *sk = sock->sk; struct irda_sock *new, *self = irda_sk(sk); struct sock *newsk; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int err; err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); @@ -897,7 +897,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) err = -EPERM; /* value does not seem to make sense. -arnd */ if (!new->tsap) { pr_debug("%s(), dup failed!\n", __func__); - kfree_skb(skb); goto out; } @@ -916,7 +915,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) /* Clean up the original one to keep it in listen state */ irttp_listen(self->tsap); - kfree_skb(skb); sk->sk_ack_backlog--; newsock->state = SS_CONNECTED; @@ -924,6 +922,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) irda_connect_response(new); err = 0; out: + kfree_skb(skb); release_sock(sk); return err; } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2632ac7..b7f869a8 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -23,6 +23,7 @@ #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> +#include <linux/syscalls.h> #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> @@ -1721,7 +1722,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (copy_to_user((void __user *)arg, &info, sizeof(info))) { err = -EFAULT; - sock_release(newsock); + sys_close(info.fd); } } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1e40dac..a2ed3bd 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1855,6 +1855,9 @@ static __net_exit void l2tp_exit_net(struct net *net) (void)l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); + + flush_workqueue(l2tp_wq); + rcu_barrier(); } static struct pernet_operations l2tp_net_ops = { diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 5871537..2599af6 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -139,7 +139,7 @@ struct l2tp_session { void (*session_close)(struct l2tp_session *session); void (*ref)(struct l2tp_session *session); void (*deref)(struct l2tp_session *session); -#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE) +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) void (*show)(struct seq_file *m, void *priv); #endif uint8_t priv[0]; /* private data */ diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 57fc5a4..965f7e3 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -121,7 +121,7 @@ static struct rtnl_link_stats64 *l2tp_eth_get_stats64(struct net_device *dev, } -static struct net_device_ops l2tp_eth_netdev_ops = { +static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, @@ -195,7 +195,7 @@ static void l2tp_eth_delete(struct l2tp_session *session) } } -#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE) +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) static void l2tp_eth_show(struct seq_file *m, void *arg) { struct l2tp_session *session = arg; @@ -268,7 +268,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p priv->tunnel_sock = tunnel->sock; session->recv_skb = l2tp_eth_dev_recv; session->session_close = l2tp_eth_delete; -#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE) +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) session->show = l2tp_eth_show; #endif diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 34eff77..41d47bf 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -552,7 +552,7 @@ out: return error; } -#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE) +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) static void pppol2tp_show(struct seq_file *m, void *arg) { struct l2tp_session *session = arg; @@ -723,7 +723,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, session->recv_skb = pppol2tp_recv; session->session_close = pppol2tp_session_close; -#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE) +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) session->show = pppol2tp_show; #endif diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index c4a1c3e..8da86ce 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -100,15 +100,14 @@ u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index); /** - * l3mdev_get_rt6_dst - IPv6 route lookup based on flow. Returns - * cached route for L3 master device if relevant - * to flow + * l3mdev_link_scope_lookup - IPv6 route lookup based on flow for link + * local and multicast addresses * @net: network namespace for device index lookup * @fl6: IPv6 flow struct for lookup */ -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, - struct flowi6 *fl6) +struct dst_entry *l3mdev_link_scope_lookup(struct net *net, + struct flowi6 *fl6) { struct dst_entry *dst = NULL; struct net_device *dev; @@ -121,70 +120,15 @@ struct dst_entry *l3mdev_get_rt6_dst(struct net *net, dev = netdev_master_upper_dev_get_rcu(dev); if (dev && netif_is_l3_master(dev) && - dev->l3mdev_ops->l3mdev_get_rt6_dst) - dst = dev->l3mdev_ops->l3mdev_get_rt6_dst(dev, fl6); + dev->l3mdev_ops->l3mdev_link_scope_lookup) + dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6); rcu_read_unlock(); } return dst; } -EXPORT_SYMBOL_GPL(l3mdev_get_rt6_dst); - -/** - * l3mdev_get_saddr - get source address for a flow based on an interface - * enslaved to an L3 master device - * @net: network namespace for device index lookup - * @ifindex: Interface index - * @fl4: IPv4 flow struct - */ - -int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4) -{ - struct net_device *dev; - int rc = 0; - - if (ifindex) { - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev && netif_is_l3_slave(dev)) - dev = netdev_master_upper_dev_get_rcu(dev); - - if (dev && netif_is_l3_master(dev) && - dev->l3mdev_ops->l3mdev_get_saddr) - rc = dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); - - rcu_read_unlock(); - } - - return rc; -} -EXPORT_SYMBOL_GPL(l3mdev_get_saddr); - -int l3mdev_get_saddr6(struct net *net, const struct sock *sk, - struct flowi6 *fl6) -{ - struct net_device *dev; - int rc = 0; - - if (fl6->flowi6_oif) { - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); - if (dev && netif_is_l3_slave(dev)) - dev = netdev_master_upper_dev_get_rcu(dev); - - if (dev && netif_is_l3_master(dev) && - dev->l3mdev_ops->l3mdev_get_saddr6) - rc = dev->l3mdev_ops->l3mdev_get_saddr6(dev, sk, fl6); - - rcu_read_unlock(); - } - - return rc; -} -EXPORT_SYMBOL_GPL(l3mdev_get_saddr6); +EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup); /** * l3mdev_fib_rule_match - Determine if flowi references an @@ -222,3 +166,38 @@ out: return rc; } + +void l3mdev_update_flow(struct net *net, struct flowi *fl) +{ + struct net_device *dev; + int ifindex; + + rcu_read_lock(); + + if (fl->flowi_oif) { + dev = dev_get_by_index_rcu(net, fl->flowi_oif); + if (dev) { + ifindex = l3mdev_master_ifindex_rcu(dev); + if (ifindex) { + fl->flowi_oif = ifindex; + fl->flowi_flags |= FLOWI_FLAG_SKIP_NH_OIF; + goto out; + } + } + } + + if (fl->flowi_iif) { + dev = dev_get_by_index_rcu(net, fl->flowi_iif); + if (dev) { + ifindex = l3mdev_master_ifindex_rcu(dev); + if (ifindex) { + fl->flowi_iif = ifindex; + fl->flowi_flags |= FLOWI_FLAG_SKIP_NH_OIF; + } + } + } + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(l3mdev_update_flow); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8ae3ed9..db916cf 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -38,7 +38,7 @@ static u16 llc_ui_sap_link_no_max[256]; static struct sockaddr_llc llc_ui_addrnull; static const struct proto_ops llc_ui_ops; -static long llc_ui_wait_for_conn(struct sock *sk, long timeout); +static bool llc_ui_wait_for_conn(struct sock *sk, long timeout); static int llc_ui_wait_for_disc(struct sock *sk, long timeout); static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); @@ -551,7 +551,7 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) return rc; } -static long llc_ui_wait_for_conn(struct sock *sk, long timeout) +static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) { DEFINE_WAIT(wait); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index a9aff60..f6749dc 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -261,10 +261,16 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, .timeout = timeout, .ssn = start_seq_num, }; - int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; + if (tid >= IEEE80211_FIRST_TSPEC_TSID) { + ht_dbg(sta->sdata, + "STA %pM requests BA session on unsupported tid %d\n", + sta->sta.addr, tid); + goto end_no_lock; + } + if (!sta->sta.ht_cap.ht_supported) { ht_dbg(sta->sdata, "STA %pM erroneously requests BA session on tid %d w/o QoS\n", @@ -298,10 +304,13 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, buf_size = IEEE80211_MAX_AMPDU_BUF; /* make sure the size doesn't exceed the maximum supported by the hw */ - if (buf_size > local->hw.max_rx_aggregation_subframes) - buf_size = local->hw.max_rx_aggregation_subframes; + if (buf_size > sta->sta.max_rx_aggregation_subframes) + buf_size = sta->sta.max_rx_aggregation_subframes; params.buf_size = buf_size; + ht_dbg(sta->sdata, "AddBA Req buf_size=%d for %pM\n", + buf_size, sta->sta.addr); + /* examine state machine */ mutex_lock(&sta->ampdu_mlme.mtx); @@ -406,8 +415,10 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } end: - if (status == WLAN_STATUS_SUCCESS) + if (status == WLAN_STATUS_SUCCESS) { __set_bit(tid, sta->ampdu_mlme.agg_session_valid); + __clear_bit(tid, sta->ampdu_mlme.unexpected_agg); + } mutex_unlock(&sta->ampdu_mlme.mtx); end_no_lock: diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 5650c46..45319cc 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -584,6 +584,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) return -EINVAL; + if (WARN_ON(tid >= IEEE80211_FIRST_TSPEC_TSID)) + return -EINVAL; + ht_dbg(sdata, "Open BA session requested for %pM tid %u\n", pubsta->addr, tid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 543b1d4..e29ff57 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -39,7 +39,7 @@ static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, if (type == NL80211_IFTYPE_MONITOR && flags) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); - sdata->u.mntr_flags = *flags; + sdata->u.mntr.flags = *flags; } return wdev; @@ -73,8 +73,29 @@ static int ieee80211_change_iface(struct wiphy *wiphy, sdata->u.mgd.use_4addr = params->use_4addr; } - if (sdata->vif.type == NL80211_IFTYPE_MONITOR && flags) { + if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *monitor_sdata; + u32 mu_mntr_cap_flag = NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER; + + monitor_sdata = rtnl_dereference(local->monitor_sdata); + if (monitor_sdata && + wiphy_ext_feature_isset(wiphy, mu_mntr_cap_flag)) { + memcpy(monitor_sdata->vif.bss_conf.mu_group.membership, + params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); + memcpy(monitor_sdata->vif.bss_conf.mu_group.position, + params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, + WLAN_USER_POSITION_LEN); + monitor_sdata->vif.mu_mimo_owner = true; + ieee80211_bss_info_change_notify(monitor_sdata, + BSS_CHANGED_MU_GROUPS); + + ether_addr_copy(monitor_sdata->u.mntr.mu_follow_addr, + params->macaddr); + } + + if (!flags) + return 0; if (ieee80211_sdata_running(sdata)) { u32 mask = MONITOR_FLAG_COOK_FRAMES | @@ -89,11 +110,11 @@ static int ieee80211_change_iface(struct wiphy *wiphy, * cooked_mntrs, monitor and all fif_* counters * reconfigure hardware */ - if ((*flags & mask) != (sdata->u.mntr_flags & mask)) + if ((*flags & mask) != (sdata->u.mntr.flags & mask)) return -EBUSY; ieee80211_adjust_monitor_flags(sdata, -1); - sdata->u.mntr_flags = *flags; + sdata->u.mntr.flags = *flags; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); @@ -103,7 +124,7 @@ static int ieee80211_change_iface(struct wiphy *wiphy, * and ieee80211_do_open take care of "everything" * mentioned in the comment above. */ - sdata->u.mntr_flags = *flags; + sdata->u.mntr.flags = *flags; } } @@ -2940,10 +2961,6 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, } chanctx = container_of(conf, struct ieee80211_chanctx, conf); - if (!chanctx) { - err = -EBUSY; - goto out; - } ch_switch.timestamp = 0; ch_switch.device_timestamp = 0; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 2906c10..8ca62b6 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -71,138 +71,39 @@ DEBUGFS_READONLY_FILE(wep_iv, "%#08x", DEBUGFS_READONLY_FILE(rate_ctrl_alg, "%s", local->rate_ctrl ? local->rate_ctrl->ops->name : "hw/driver"); -struct aqm_info { - struct ieee80211_local *local; - size_t size; - size_t len; - unsigned char buf[0]; -}; - -#define AQM_HDR_LEN 200 -#define AQM_HW_ENTRY_LEN 40 -#define AQM_TXQ_ENTRY_LEN 110 - -static int aqm_open(struct inode *inode, struct file *file) +static ssize_t aqm_read(struct file *file, + char __user *user_buf, + size_t count, + loff_t *ppos) { - struct ieee80211_local *local = inode->i_private; - struct ieee80211_sub_if_data *sdata; - struct sta_info *sta; - struct txq_info *txqi; + struct ieee80211_local *local = file->private_data; struct fq *fq = &local->fq; - struct aqm_info *info = NULL; + char buf[200]; int len = 0; - int i; - - if (!local->ops->wake_tx_queue) - return -EOPNOTSUPP; - - len += AQM_HDR_LEN; - len += 6 * AQM_HW_ENTRY_LEN; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - len += AQM_TXQ_ENTRY_LEN; - list_for_each_entry_rcu(sta, &local->sta_list, list) - len += AQM_TXQ_ENTRY_LEN * ARRAY_SIZE(sta->sta.txq); - rcu_read_unlock(); - - info = vmalloc(len); - if (!info) - return -ENOMEM; spin_lock_bh(&local->fq.lock); rcu_read_lock(); - file->private_data = info; - info->local = local; - info->size = len; - len = 0; - - len += scnprintf(info->buf + len, info->size - len, - "* hw\n" - "access name value\n" - "R fq_flows_cnt %u\n" - "R fq_backlog %u\n" - "R fq_overlimit %u\n" - "R fq_collisions %u\n" - "RW fq_limit %u\n" - "RW fq_quantum %u\n", - fq->flows_cnt, - fq->backlog, - fq->overlimit, - fq->collisions, - fq->limit, - fq->quantum); - - len += scnprintf(info->buf + len, - info->size - len, - "* vif\n" - "ifname addr ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n"); - - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - txqi = to_txq_info(sdata->vif.txq); - len += scnprintf(info->buf + len, info->size - len, - "%s %pM %u %u %u %u %u %u %u %u\n", - sdata->name, - sdata->vif.addr, - txqi->txq.ac, - txqi->tin.backlog_bytes, - txqi->tin.backlog_packets, - txqi->tin.flows, - txqi->tin.overlimit, - txqi->tin.collisions, - txqi->tin.tx_bytes, - txqi->tin.tx_packets); - } - - len += scnprintf(info->buf + len, - info->size - len, - "* sta\n" - "ifname addr tid ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n"); - - list_for_each_entry_rcu(sta, &local->sta_list, list) { - sdata = sta->sdata; - for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - txqi = to_txq_info(sta->sta.txq[i]); - len += scnprintf(info->buf + len, info->size - len, - "%s %pM %d %d %u %u %u %u %u %u %u\n", - sdata->name, - sta->sta.addr, - txqi->txq.tid, - txqi->txq.ac, - txqi->tin.backlog_bytes, - txqi->tin.backlog_packets, - txqi->tin.flows, - txqi->tin.overlimit, - txqi->tin.collisions, - txqi->tin.tx_bytes, - txqi->tin.tx_packets); - } - } - - info->len = len; + len = scnprintf(buf, sizeof(buf), + "access name value\n" + "R fq_flows_cnt %u\n" + "R fq_backlog %u\n" + "R fq_overlimit %u\n" + "R fq_collisions %u\n" + "RW fq_limit %u\n" + "RW fq_quantum %u\n", + fq->flows_cnt, + fq->backlog, + fq->overlimit, + fq->collisions, + fq->limit, + fq->quantum); rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); - return 0; -} - -static int aqm_release(struct inode *inode, struct file *file) -{ - vfree(file->private_data); - return 0; -} - -static ssize_t aqm_read(struct file *file, - char __user *user_buf, - size_t count, - loff_t *ppos) -{ - struct aqm_info *info = file->private_data; - return simple_read_from_buffer(user_buf, count, ppos, - info->buf, info->len); + buf, len); } static ssize_t aqm_write(struct file *file, @@ -210,8 +111,7 @@ static ssize_t aqm_write(struct file *file, size_t count, loff_t *ppos) { - struct aqm_info *info = file->private_data; - struct ieee80211_local *local = info->local; + struct ieee80211_local *local = file->private_data; char buf[100]; size_t len; @@ -237,8 +137,7 @@ static ssize_t aqm_write(struct file *file, static const struct file_operations aqm_ops = { .write = aqm_write, .read = aqm_read, - .open = aqm_open, - .release = aqm_release, + .open = simple_open, .llseek = default_llseek, }; @@ -302,6 +201,7 @@ static const char *hw_flag_names[] = { FLAG(USES_RSS), FLAG(TX_AMSDU), FLAG(TX_FRAG_LIST), + FLAG(REPORTS_LOW_ACK), #undef FLAG }; @@ -428,7 +328,9 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_ADD(hwflags); DEBUGFS_ADD(user_power); DEBUGFS_ADD(power); - DEBUGFS_ADD_MODE(aqm, 0600); + + if (local->ops->wake_tx_queue) + DEBUGFS_ADD_MODE(aqm, 0600); statsd = debugfs_create_dir("statistics", phyd); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index a5ba739..5d35c0f 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -30,7 +30,7 @@ static ssize_t ieee80211_if_read( size_t count, loff_t *ppos, ssize_t (*format)(const struct ieee80211_sub_if_data *, char *, int)) { - char buf[70]; + char buf[200]; ssize_t ret = -EINVAL; read_lock(&dev_base_lock); @@ -486,6 +486,38 @@ static ssize_t ieee80211_if_fmt_num_buffered_multicast( } IEEE80211_IF_FILE_R(num_buffered_multicast); +static ssize_t ieee80211_if_fmt_aqm( + const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + struct txq_info *txqi = to_txq_info(sdata->vif.txq); + int len; + + spin_lock_bh(&local->fq.lock); + rcu_read_lock(); + + len = scnprintf(buf, + buflen, + "ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n" + "%u %u %u %u %u %u %u %u %u %u\n", + txqi->txq.ac, + txqi->tin.backlog_bytes, + txqi->tin.backlog_packets, + txqi->tin.flows, + txqi->cstats.drop_count, + txqi->cstats.ecn_mark, + txqi->tin.overlimit, + txqi->tin.collisions, + txqi->tin.tx_bytes, + txqi->tin.tx_packets); + + rcu_read_unlock(); + spin_unlock_bh(&local->fq.lock); + + return len; +} +IEEE80211_IF_FILE_R(aqm); + /* IBSS attributes */ static ssize_t ieee80211_if_fmt_tsf( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) @@ -618,6 +650,9 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); + + if (sdata->local->ops->wake_tx_queue) + DEBUGFS_ADD(aqm); } static void add_sta_files(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index fd33413..a2fcdb4 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -133,6 +133,55 @@ static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf, } STA_OPS(last_seq_ctrl); +#define AQM_TXQ_ENTRY_LEN 130 + +static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->local; + size_t bufsz = AQM_TXQ_ENTRY_LEN*(IEEE80211_NUM_TIDS+1); + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + struct txq_info *txqi; + ssize_t rv; + int i; + + if (!buf) + return -ENOMEM; + + spin_lock_bh(&local->fq.lock); + rcu_read_lock(); + + p += scnprintf(p, + bufsz+buf-p, + "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n"); + + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + txqi = to_txq_info(sta->sta.txq[i]); + p += scnprintf(p, bufsz+buf-p, + "%d %d %u %u %u %u %u %u %u %u %u\n", + txqi->txq.tid, + txqi->txq.ac, + txqi->tin.backlog_bytes, + txqi->tin.backlog_packets, + txqi->tin.flows, + txqi->cstats.drop_count, + txqi->cstats.ecn_mark, + txqi->tin.overlimit, + txqi->tin.collisions, + txqi->tin.tx_bytes, + txqi->tin.tx_packets); + } + + rcu_read_unlock(); + spin_unlock_bh(&local->fq.lock); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} +STA_OPS(aqm); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -478,6 +527,9 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); DEBUGFS_ADD_COUNTER(tx_filtered, status_stats.filtered); + if (local->ops->wake_tx_queue) + DEBUGFS_ADD(aqm); + if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, sta->debugfs_dir, @@ -492,10 +544,6 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) void ieee80211_sta_debugfs_remove(struct sta_info *sta) { - struct ieee80211_local *local = sta->local; - struct ieee80211_sub_if_data *sdata = sta->sdata; - - drv_sta_remove_debugfs(local, sdata, &sta->sta, sta->debugfs_dir); debugfs_remove_recursive(sta->debugfs_dir); sta->debugfs_dir = NULL; } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index c258f10..c701b64 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -62,7 +62,7 @@ int drv_add_interface(struct ieee80211_local *local, if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN || (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && - !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE)))) + !(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)))) return -EINVAL; trace_drv_add_interface(local, sdata); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 42a41ae..fe35a1c 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -162,7 +162,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, return; if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE || - sdata->vif.type == NL80211_IFTYPE_MONITOR)) + (sdata->vif.type == NL80211_IFTYPE_MONITOR && + !sdata->vif.mu_mimo_owner))) return; if (!check_sdata_in_driver(sdata)) @@ -498,21 +499,6 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local, local->ops->sta_add_debugfs(&local->hw, &sdata->vif, sta, dir); } - -static inline void drv_sta_remove_debugfs(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - struct ieee80211_sta *sta, - struct dentry *dir) -{ - might_sleep(); - - sdata = get_bss_sdata(sdata); - check_sdata_in_driver(sdata); - - if (local->ops->sta_remove_debugfs) - local->ops->sta_remove_debugfs(&local->hw, &sdata->vif, - sta, dir); -} #endif static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index f56d342..e496dee 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -3,7 +3,7 @@ * Copyright 2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> - * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2013-2015 Intel Mobile Communications GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -818,12 +818,18 @@ struct txq_info { struct fq_tin tin; struct fq_flow def_flow; struct codel_vars def_cvars; + struct codel_stats cstats; unsigned long flags; /* keep last! */ struct ieee80211_txq txq; }; +struct ieee80211_if_mntr { + u32 flags; + u8 mu_follow_addr[ETH_ALEN] __aligned(2); +}; + struct ieee80211_sub_if_data { struct list_head list; @@ -922,7 +928,7 @@ struct ieee80211_sub_if_data { struct ieee80211_if_ibss ibss; struct ieee80211_if_mesh mesh; struct ieee80211_if_ocb ocb; - u32 mntr_flags; + struct ieee80211_if_mntr mntr; } u; #ifdef CONFIG_MAC80211_DEBUGFS @@ -1112,7 +1118,6 @@ struct ieee80211_local { struct fq fq; struct codel_vars *cvars; struct codel_params cparams; - struct codel_stats cstats; const struct ieee80211_ops *ops; @@ -1208,7 +1213,7 @@ struct ieee80211_local { spinlock_t tim_lock; unsigned long num_sta; struct list_head sta_list; - struct rhashtable sta_hash; + struct rhltable sta_hash; struct timer_list sta_cleanup; int sta_generation; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b123a9e..b0abddc7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -43,6 +43,8 @@ * by either the RTNL, the iflist_mtx or RCU. */ +static void ieee80211_iface_work(struct work_struct *work); + bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) { struct ieee80211_chanctx_conf *chanctx_conf; @@ -188,7 +190,7 @@ static int ieee80211_verify_mac(struct ieee80211_sub_if_data *sdata, u8 *addr, continue; if (iter->vif.type == NL80211_IFTYPE_MONITOR && - !(iter->u.mntr_flags & MONITOR_FLAG_ACTIVE)) + !(iter->u.mntr.flags & MONITOR_FLAG_ACTIVE)) continue; m = iter->vif.addr; @@ -217,7 +219,7 @@ static int ieee80211_change_mac(struct net_device *dev, void *addr) return -EBUSY; if (sdata->vif.type == NL80211_IFTYPE_MONITOR && - !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE)) + !(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) check_dup = false; ret = ieee80211_verify_mac(sdata, sa->sa_data, check_dup); @@ -357,7 +359,7 @@ void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset) { struct ieee80211_local *local = sdata->local; - u32 flags = sdata->u.mntr_flags; + u32 flags = sdata->u.mntr.flags; #define ADJUST(_f, _s) do { \ if (flags & MONITOR_FLAG_##_f) \ @@ -448,6 +450,9 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return ret; } + skb_queue_head_init(&sdata->skb_queue); + INIT_WORK(&sdata->work, ieee80211_iface_work); + return 0; } @@ -589,12 +594,12 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) } break; case NL80211_IFTYPE_MONITOR: - if (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) { + if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) { local->cooked_mntrs++; break; } - if (sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE) { + if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) { res = drv_add_interface(local, sdata); if (res) goto err_stop; @@ -926,7 +931,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, /* no need to tell driver */ break; case NL80211_IFTYPE_MONITOR: - if (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) { + if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) { local->cooked_mntrs--; break; } @@ -1012,7 +1017,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_idle(local); mutex_unlock(&local->mtx); - if (!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE)) + if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) break; /* fall through */ @@ -1444,7 +1449,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_MONITOR: sdata->dev->type = ARPHRD_IEEE80211_RADIOTAP; sdata->dev->netdev_ops = &ieee80211_monitorif_ops; - sdata->u.mntr_flags = MONITOR_FLAG_CONTROL | + sdata->u.mntr.flags = MONITOR_FLAG_CONTROL | MONITOR_FLAG_OTHER_BSS; break; case NL80211_IFTYPE_WDS: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d00ea9b..ac053a9 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -660,6 +660,9 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, ieee80211_roc_setup(local); + local->hw.radiotap_timestamp.units_pos = -1; + local->hw.radiotap_timestamp.accuracy = -1; + return &local->hw; err_free: wiphy_free(wiphy); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index fa7d37c..b747c96 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -757,6 +757,7 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata, sta = next_hop_deref_protected(mpath); if (mpath->flags & MESH_PATH_ACTIVE && ether_addr_equal(ta, sta->sta.addr) && + !(mpath->flags & MESH_PATH_FIXED) && (!(mpath->flags & MESH_PATH_SN_VALID) || SN_GT(target_sn, mpath->sn) || target_sn == 0)) { mpath->flags &= ~MESH_PATH_ACTIVE; @@ -1023,7 +1024,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) goto enddiscovery; spin_lock_bh(&mpath->state_lock); - if (mpath->flags & MESH_PATH_DELETED) { + if (mpath->flags & (MESH_PATH_DELETED | MESH_PATH_FIXED)) { spin_unlock_bh(&mpath->state_lock); goto enddiscovery; } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 6db2ddf..f0e6175 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -826,7 +826,7 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mpath->metric = 0; mpath->hop_count = 0; mpath->exp_time = 0; - mpath->flags |= MESH_PATH_FIXED; + mpath->flags = MESH_PATH_FIXED | MESH_PATH_SN_VALID; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); mesh_path_tx_pending(mpath); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 8d426f6..7486f2d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1672,11 +1672,15 @@ __ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata) non_acm_ac++) if (!(sdata->wmm_acm & BIT(7 - 2 * non_acm_ac))) break; - /* The loop will result in using BK even if it requires - * admission control, such configuration makes no sense - * and we have to transmit somehow - the AC selection - * does the same thing. + /* Usually the loop will result in using BK even if it + * requires admission control, but such a configuration + * makes no sense and we have to transmit somehow - the + * AC selection does the same thing. + * If we started out trying to downgrade from BK, then + * the extra condition here might be needed. */ + if (non_acm_ac >= IEEE80211_NUM_ACS) + non_acm_ac = IEEE80211_AC_BK; if (drv_conf_tx(local, sdata, ac, &sdata->tx_conf[non_acm_ac])) sdata_err(sdata, diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 00a43a7..28a3a09 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -178,8 +178,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) WARN_ON(!list_empty(&local->chanctx_list)); /* stop hardware - this must stop RX */ - if (local->open_count) - ieee80211_stop_device(local); + ieee80211_stop_device(local); suspend: local->suspended = true; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9dce3b1..f7cf342 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -180,6 +180,11 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, len += 12; } + if (local->hw.radiotap_timestamp.units_pos >= 0) { + len = ALIGN(len, 8); + len += 12; + } + if (status->chains) { /* antenna and antenna signal fields */ len += 2 * hweight8(status->chains); @@ -447,6 +452,31 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos += 2; } + if (local->hw.radiotap_timestamp.units_pos >= 0) { + u16 accuracy = 0; + u8 flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT; + + rthdr->it_present |= + cpu_to_le32(1 << IEEE80211_RADIOTAP_TIMESTAMP); + + /* ensure 8 byte alignment */ + while ((pos - (u8 *)rthdr) & 7) + pos++; + + put_unaligned_le64(status->device_timestamp, pos); + pos += sizeof(u64); + + if (local->hw.radiotap_timestamp.accuracy >= 0) { + accuracy = local->hw.radiotap_timestamp.accuracy; + flags |= IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY; + } + put_unaligned_le16(accuracy, pos); + pos += sizeof(u16); + + *pos++ = local->hw.radiotap_timestamp.units_pos; + *pos++ = flags; + } + for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) { *pos++ = status->chain_signal[chain]; *pos++ = chain; @@ -485,6 +515,9 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, struct net_device *prev_dev = NULL; int present_fcs_len = 0; unsigned int rtap_vendor_space = 0; + struct ieee80211_mgmt *mgmt; + struct ieee80211_sub_if_data *monitor_sdata = + rcu_dereference(local->monitor_sdata); if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) { struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data; @@ -567,7 +600,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (sdata->vif.type != NL80211_IFTYPE_MONITOR) continue; - if (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) + if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) continue; if (!ieee80211_sdata_running(sdata)) @@ -585,6 +618,23 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, ieee80211_rx_stats(sdata->dev, skb->len); } + mgmt = (void *)skb->data; + if (monitor_sdata && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + VHT_MUMIMO_GROUPS_DATA_LEN && + ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_VHT && + mgmt->u.action.u.vht_group_notif.action_code == WLAN_VHT_ACTION_GROUPID_MGMT && + is_valid_ether_addr(monitor_sdata->u.mntr.mu_follow_addr) && + ether_addr_equal(mgmt->da, monitor_sdata->u.mntr.mu_follow_addr)) { + struct sk_buff *mu_skb = skb_copy(skb, GFP_ATOMIC); + + if (mu_skb) { + mu_skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; + skb_queue_tail(&monitor_sdata->skb_queue, mu_skb); + ieee80211_queue_work(&local->hw, &monitor_sdata->work); + } + } + if (prev_dev) { skb->dev = prev_dev; netif_receive_skb(skb); @@ -1072,8 +1122,15 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); - if (!tid_agg_rx) + if (!tid_agg_rx) { + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && + !test_bit(tid, rx->sta->ampdu_mlme.agg_session_valid) && + !test_and_set_bit(tid, rx->sta->ampdu_mlme.unexpected_agg)) + ieee80211_send_delba(rx->sdata, rx->sta->sta.addr, tid, + WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_REQUIRE_SETUP); goto dont_reorder; + } /* qos null data frames are excluded */ if (unlikely(hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_NULLFUNC))) @@ -2535,6 +2592,12 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) tid = le16_to_cpu(bar_data.control) >> 12; + if (!test_bit(tid, rx->sta->ampdu_mlme.agg_session_valid) && + !test_and_set_bit(tid, rx->sta->ampdu_mlme.unexpected_agg)) + ieee80211_send_delba(rx->sdata, rx->sta->sta.addr, tid, + WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_REQUIRE_SETUP); + tid_agg_rx = rcu_dereference(rx->sta->ampdu_mlme.tid_rx[tid]); if (!tid_agg_rx) return RX_DROP_MONITOR; @@ -3147,7 +3210,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, continue; if (sdata->vif.type != NL80211_IFTYPE_MONITOR || - !(sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES)) + !(sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)) continue; if (prev_dev) { @@ -3940,7 +4003,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, __le16 fc; struct ieee80211_rx_data rx; struct ieee80211_sub_if_data *prev; - struct rhash_head *tmp; + struct rhlist_head *tmp; int err = 0; fc = ((struct ieee80211_hdr *)skb->data)->frame_control; @@ -3983,13 +4046,10 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, goto out; } else if (ieee80211_is_data(fc)) { struct sta_info *sta, *prev_sta; - const struct bucket_table *tbl; prev_sta = NULL; - tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); - - for_each_sta_info(local, tbl, hdr->addr2, sta, tmp) { + for_each_sta_info(local, hdr->addr2, sta, tmp) { if (!prev_sta) { prev_sta = sta; continue; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 070b40f..23d8ac8 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -420,7 +420,7 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, { struct ieee80211_local *local = hw_to_local(hw); - trace_api_scan_completed(local, info); + trace_api_scan_completed(local, info->aborted); set_bit(SCAN_COMPLETED, &local->scanning); if (info->aborted) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 19f14c9..011880d 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -67,12 +67,10 @@ static const struct rhashtable_params sta_rht_params = { .nelem_hint = 3, /* start small */ - .insecure_elasticity = true, /* Disable chain-length checks. */ .automatic_shrinking = true, .head_offset = offsetof(struct sta_info, hash_node), .key_offset = offsetof(struct sta_info, addr), .key_len = ETH_ALEN, - .hashfn = sta_addr_hash, .max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE, }; @@ -80,8 +78,8 @@ static const struct rhashtable_params sta_rht_params = { static int sta_info_hash_del(struct ieee80211_local *local, struct sta_info *sta) { - return rhashtable_remove_fast(&local->sta_hash, &sta->hash_node, - sta_rht_params); + return rhltable_remove(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void __cleanup_single_sta(struct sta_info *sta) @@ -157,19 +155,22 @@ static void cleanup_single_sta(struct sta_info *sta) sta_info_free(local, sta); } +struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local, + const u8 *addr) +{ + return rhltable_lookup(&local->sta_hash, addr, sta_rht_params); +} + /* protected by RCU */ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; + struct rhlist_head *tmp; struct sta_info *sta; - struct rhash_head *tmp; - const struct bucket_table *tbl; rcu_read_lock(); - tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); - - for_each_sta_info(local, tbl, addr, sta, tmp) { + for_each_sta_info(local, addr, sta, tmp) { if (sta->sdata == sdata) { rcu_read_unlock(); /* this is safe as the caller must already hold @@ -190,14 +191,11 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; + struct rhlist_head *tmp; struct sta_info *sta; - struct rhash_head *tmp; - const struct bucket_table *tbl; rcu_read_lock(); - tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); - - for_each_sta_info(local, tbl, addr, sta, tmp) { + for_each_sta_info(local, addr, sta, tmp) { if (sta->sdata == sdata || (sta->sdata->bss && sta->sdata->bss == sdata->bss)) { rcu_read_unlock(); @@ -263,8 +261,8 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) static int sta_info_hash_add(struct ieee80211_local *local, struct sta_info *sta) { - return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, - sta_rht_params); + return rhltable_insert(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) @@ -340,6 +338,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, memcpy(sta->addr, addr, ETH_ALEN); memcpy(sta->sta.addr, addr, ETH_ALEN); + sta->sta.max_rx_aggregation_subframes = + local->hw.max_rx_aggregation_subframes; + sta->local = local; sta->sdata = sdata; sta->rx_stats.last_rx = jiffies; @@ -450,9 +451,9 @@ static int sta_info_insert_check(struct sta_info *sta) is_multicast_ether_addr(sta->sta.addr))) return -EINVAL; - /* Strictly speaking this isn't necessary as we hold the mutex, but - * the rhashtable code can't really deal with that distinction. We - * do require the mutex for correctness though. + /* The RCU read lock is required by rhashtable due to + * asynchronous resize/rehash. We also require the mutex + * for correctness. */ rcu_read_lock(); lockdep_assert_held(&sdata->local->sta_mtx); @@ -687,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) } /* No need to do anything if the driver does all */ - if (ieee80211_hw_check(&local->hw, AP_LINK_PS)) + if (!local->ops->set_tim) return; if (sta->dead) @@ -1040,16 +1041,11 @@ static void sta_info_cleanup(unsigned long data) round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL)); } -u32 sta_addr_hash(const void *key, u32 length, u32 seed) -{ - return jhash(key, ETH_ALEN, seed); -} - int sta_info_init(struct ieee80211_local *local) { int err; - err = rhashtable_init(&local->sta_hash, &sta_rht_params); + err = rhltable_init(&local->sta_hash, &sta_rht_params); if (err) return err; @@ -1065,7 +1061,7 @@ int sta_info_init(struct ieee80211_local *local) void sta_info_stop(struct ieee80211_local *local) { del_timer_sync(&local->sta_cleanup); - rhashtable_destroy(&local->sta_hash); + rhltable_destroy(&local->sta_hash); } @@ -1135,17 +1131,14 @@ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, const u8 *localaddr) { struct ieee80211_local *local = hw_to_local(hw); + struct rhlist_head *tmp; struct sta_info *sta; - struct rhash_head *tmp; - const struct bucket_table *tbl; - - tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); /* * Just return a random station if localaddr is NULL * ... first in list. */ - for_each_sta_info(local, tbl, addr, sta, tmp) { + for_each_sta_info(local, addr, sta, tmp) { if (localaddr && !ether_addr_equal(sta->sdata->vif.addr, localaddr)) continue; @@ -1616,7 +1609,6 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, sta_info_recalc_tim(sta); } else { - unsigned long tids = sta->txq_buffered_tids & driver_release_tids; int tid; /* @@ -1648,7 +1640,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); - if (!(tids & BIT(tid)) || txqi->tin.backlog_packets) + if (!(driver_release_tids & BIT(tid)) || + txqi->tin.backlog_packets) continue; sta_info_recalc_tim(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 0556be3..ed5fcb9 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -230,6 +230,8 @@ struct tid_ampdu_rx { * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the * driver requested to close until the work for it runs * @agg_session_valid: bitmap indicating which TID has a rx BA session open on + * @unexpected_agg: bitmap indicating which TID already sent a delBA due to + * unexpected aggregation related frames outside a session * @work: work struct for starting/stopping aggregation * @tid_tx: aggregation info for Tx per TID * @tid_start_tx: sessions where start was requested @@ -244,6 +246,7 @@ struct sta_ampdu_mlme { unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; + unsigned long unexpected_agg[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ struct work_struct work; struct tid_ampdu_tx __rcu *tid_tx[IEEE80211_NUM_TIDS]; @@ -452,7 +455,7 @@ struct sta_info { /* General information, mostly static */ struct list_head list, free_list; struct rcu_head rcu_head; - struct rhash_head hash_node; + struct rhlist_head hash_node; u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; @@ -635,6 +638,9 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid) */ #define STA_INFO_CLEANUP_INTERVAL (10 * HZ) +struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local, + const u8 *addr); + /* * Get a STA info, must be under RCU read lock. */ @@ -644,17 +650,9 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); -u32 sta_addr_hash(const void *key, u32 length, u32 seed); - -#define _sta_bucket_idx(_tbl, _a) \ - rht_bucket_index(_tbl, sta_addr_hash(_a, ETH_ALEN, (_tbl)->hash_rnd)) - -#define for_each_sta_info(local, tbl, _addr, _sta, _tmp) \ - rht_for_each_entry_rcu(_sta, _tmp, tbl, \ - _sta_bucket_idx(tbl, _addr), \ - hash_node) \ - /* compare address and run code only if it matches */ \ - if (ether_addr_equal(_sta->addr, (_addr))) +#define for_each_sta_info(local, _addr, _sta, _tmp) \ + rhl_for_each_entry_rcu(_sta, _tmp, \ + sta_info_hash_lookup(local, _addr), hash_node) /* * Get STA info by index, BROKEN! diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a2a6826..ddf71c6 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -557,6 +557,12 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { + /* If driver relies on its own algorithm for station kickout, skip + * mac80211 packet loss mechanism. + */ + if (ieee80211_hw_check(&sta->local->hw, REPORTS_LOW_ACK)) + return; + /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) @@ -709,7 +715,7 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, if (!ieee80211_sdata_running(sdata)) continue; - if ((sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) && + if ((sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) && !send_to_cooked) continue; @@ -740,8 +746,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); __le16 fc; struct ieee80211_supported_band *sband; + struct rhlist_head *tmp; struct sta_info *sta; - struct rhash_head *tmp; int retry_count; int rates_idx; bool send_to_cooked; @@ -749,7 +755,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_bar *bar; int shift = 0; int tid = IEEE80211_NUM_TIDS; - const struct bucket_table *tbl; rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); @@ -758,9 +763,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) sband = local->hw.wiphy->bands[info->band]; fc = hdr->frame_control; - tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); - - for_each_sta_info(local, tbl, hdr->addr1, sta, tmp) { + for_each_sta_info(local, hdr->addr1, sta, tmp) { /* skip wrong virtual interface */ if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr)) continue; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index b5d28f1..afca7d1 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -333,10 +333,11 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, if (!uc.center_freq1) return; - /* proceed to downgrade the chandef until usable or the same */ + /* proceed to downgrade the chandef until usable or the same as AP BW */ while (uc.width > max_width || - !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, - sdata->wdev.iftype)) + (uc.width > sta->tdls_chandef.width && + !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, + sdata->wdev.iftype))) ieee80211_chandef_downgrade(&uc); if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1d0746d..1ff08be 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -796,6 +796,36 @@ static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid) return ret; } +static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct ieee80211_sta *pubsta, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_txq *txq = NULL; + + if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) || + (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) + return NULL; + + if (!ieee80211_is_data(hdr->frame_control)) + return NULL; + + if (pubsta) { + u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + + txq = pubsta->txq[tid]; + } else if (vif) { + txq = vif->txq; + } + + if (!txq) + return NULL; + + return to_txq_info(txq); +} + static ieee80211_tx_result debug_noinline ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) { @@ -853,7 +883,8 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) tid = *qc & IEEE80211_QOS_CTL_TID_MASK; tx->sta->tx_stats.msdu[tid]++; - if (!tx->sta->sta.txq[0]) + if (!ieee80211_get_txq(tx->local, info->control.vif, &tx->sta->sta, + tx->skb)) hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid); return TX_CONTINUE; @@ -1243,36 +1274,6 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, return TX_CONTINUE; } -static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, - struct ieee80211_vif *vif, - struct ieee80211_sta *pubsta, - struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_txq *txq = NULL; - - if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) || - (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) - return NULL; - - if (!ieee80211_is_data(hdr->frame_control)) - return NULL; - - if (pubsta) { - u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - - txq = pubsta->txq[tid]; - } else if (vif) { - txq = vif->txq; - } - - if (!txq) - return NULL; - - return to_txq_info(txq); -} - static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb) { IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time(); @@ -1343,7 +1344,7 @@ static struct sk_buff *fq_tin_dequeue_func(struct fq *fq, local = container_of(fq, struct ieee80211_local, fq); txqi = container_of(tin, struct txq_info, tin); cparams = &local->cparams; - cstats = &local->cstats; + cstats = &txqi->cstats; if (flow == &txqi->def_flow) cvars = &txqi->def_cvars; @@ -1403,6 +1404,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, fq_tin_init(&txqi->tin); fq_flow_init(&txqi->def_flow); codel_vars_init(&txqi->def_cvars); + codel_stats_init(&txqi->cstats); txqi->txq.vif = &sdata->vif; @@ -1441,7 +1443,6 @@ int ieee80211_txq_setup_flows(struct ieee80211_local *local) return ret; codel_params_init(&local->cparams); - codel_stats_init(&local->cstats); local->cparams.interval = MS2TIME(100); local->cparams.target = MS2TIME(20); local->cparams.ecn = true; @@ -1514,8 +1515,12 @@ out: spin_unlock_bh(&fq->lock); if (skb && skb_has_frag_list(skb) && - !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) - skb_linearize(skb); + !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) { + if (skb_linearize(skb)) { + ieee80211_free_txskb(&local->hw, skb); + return NULL; + } + } return skb; } @@ -1643,7 +1648,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, switch (sdata->vif.type) { case NL80211_IFTYPE_MONITOR: - if (sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE) { + if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) { vif = &sdata->vif; break; } @@ -2263,15 +2268,9 @@ static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_STATION: if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { sta = sta_info_get(sdata, skb->data); - if (sta) { - bool tdls_peer, tdls_auth; - - tdls_peer = test_sta_flag(sta, - WLAN_STA_TDLS_PEER); - tdls_auth = test_sta_flag(sta, - WLAN_STA_TDLS_PEER_AUTH); - - if (tdls_peer && tdls_auth) { + if (sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { + if (test_sta_flag(sta, + WLAN_STA_TDLS_PEER_AUTH)) { *sta_out = sta; return 0; } @@ -2283,8 +2282,7 @@ static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, * after a TDLS sta is removed due to being * unreachable. */ - if (tdls_peer && !tdls_auth && - !ieee80211_is_tdls_setup(skb)) + if (!ieee80211_is_tdls_setup(skb)) return -EINVAL; } @@ -3243,7 +3241,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { *ieee80211_get_qos_ctl(hdr) = tid; - if (!sta->sta.txq[0]) + if (!ieee80211_get_txq(local, &sdata->vif, &sta->sta, skb)) hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); } else { info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 42bf0b6..b6865d8 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -598,7 +598,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, list_for_each_entry_rcu(sdata, &local->interfaces, list) { switch (sdata->vif.type) { case NL80211_IFTYPE_MONITOR: - if (!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE)) + if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) continue; break; case NL80211_IFTYPE_AP_VLAN: @@ -2555,7 +2555,6 @@ int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, if (need_basic && basic_rates & BIT(i)) basic = 0x80; - rate = sband->bitrates[i].bitrate; rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5 * (1 << shift)); *pos++ = basic | (u8) rate; diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 7079cd3..06019db 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -663,6 +663,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, /* TODO check this */ SET_NETDEV_DEV(ndev, &local->phy->dev); + dev_net_set(ndev, wpan_phy_net(local->hw.phy)); sdata = netdev_priv(ndev); ndev->ieee802154_ptr = &sdata->wpan_dev; memcpy(sdata->name, ndev->name, IFNAMSIZ); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 446e130..4dcf6e1 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -101,11 +101,16 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, sdata->dev->stats.rx_bytes += skb->len; switch (mac_cb(skb)->type) { + case IEEE802154_FC_TYPE_BEACON: + case IEEE802154_FC_TYPE_ACK: + case IEEE802154_FC_TYPE_MAC_CMD: + goto fail; + case IEEE802154_FC_TYPE_DATA: return ieee802154_deliver_skb(skb); default: - pr_warn("ieee802154: bad frame received (type = %d)\n", - mac_cb(skb)->type); + pr_warn_ratelimited("ieee802154: bad frame received " + "(type = %d)\n", mac_cb(skb)->type); goto fail; } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 72fc514..fa6715d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -231,19 +231,17 @@ EXPORT_SYMBOL(nf_unregister_net_hooks); static LIST_HEAD(nf_hook_list); -int nf_register_hook(struct nf_hook_ops *reg) +static int _nf_register_hook(struct nf_hook_ops *reg) { struct net *net, *last; int ret; - rtnl_lock(); for_each_net(net) { ret = nf_register_net_hook(net, reg); if (ret && ret != -ENOENT) goto rollback; } list_add_tail(®->list, &nf_hook_list); - rtnl_unlock(); return 0; rollback: @@ -253,19 +251,34 @@ rollback: break; nf_unregister_net_hook(net, reg); } + return ret; +} + +int nf_register_hook(struct nf_hook_ops *reg) +{ + int ret; + + rtnl_lock(); + ret = _nf_register_hook(reg); rtnl_unlock(); + return ret; } EXPORT_SYMBOL(nf_register_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +static void _nf_unregister_hook(struct nf_hook_ops *reg) { struct net *net; - rtnl_lock(); list_del(®->list); for_each_net(net) nf_unregister_net_hook(net, reg); +} + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + rtnl_lock(); + _nf_unregister_hook(reg); rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -289,6 +302,26 @@ err: } EXPORT_SYMBOL(nf_register_hooks); +/* Caller MUST take rtnl_lock() */ +int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = _nf_register_hook(®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + _nf_unregister_hooks(reg, i); + return err; +} +EXPORT_SYMBOL(_nf_register_hooks); + void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) { while (n-- > 0) @@ -296,6 +329,14 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) } EXPORT_SYMBOL(nf_unregister_hooks); +/* Caller MUST take rtnl_lock */ +void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + while (n-- > 0) + _nf_unregister_hook(®[n]); +} +EXPORT_SYMBOL(_nf_unregister_hooks); + unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, struct nf_hook_entry **entryp) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c94ec19..ba6a1d4 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1108,9 +1108,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - if (tmpl && nfct_synproxy(tmpl)) { - nfct_seqadj_ext_add(ct); - nfct_synproxy_ext_add(ct); + if (!nf_ct_add_synproxy(ct, tmpl)) { + nf_conntrack_free(ct); + return ERR_PTR(-ENOMEM); } timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 81ae41f..bbb8f3d 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -441,7 +441,8 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_DST_NAT; if (nfct_help(ct)) - nfct_seqadj_ext_add(ct); + if (!nfct_seqadj_ext_add(ct)) + return NF_DROP; } if (maniptype == NF_NAT_MANIP_SRC) { @@ -801,7 +802,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, if (err < 0) return err; - return nf_nat_setup_info(ct, &range, manip); + return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0; } #else static int diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 696fe8f..ab695f8 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -239,7 +239,7 @@ void nft_trace_notify(struct nft_traceinfo *info) break; case NFT_TRACETYPE_POLICY: if (nla_put_be32(skb, NFTA_TRACE_POLICY, - info->basechain->policy)) + htonl(info->basechain->policy))) goto nla_put_failure; break; } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 70eb2f6a..d44d89b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -343,12 +343,12 @@ static int nfnl_acct_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { - char *acct_name; - struct nf_acct *cur; + struct nf_acct *cur, *tmp; int ret = -ENOENT; + char *acct_name; if (!tb[NFACCT_NAME]) { - list_for_each_entry(cur, &net->nfnl_acct_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) nfnl_acct_try_del(cur); return 0; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 68216cd..139e086 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -98,31 +98,28 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, break; } - l4proto = nf_ct_l4proto_find_get(l3num, l4num); - - /* This protocol is not supportted, skip. */ - if (l4proto->l4proto != l4num) { - ret = -EOPNOTSUPP; - goto err_proto_put; - } - if (matching) { if (nlh->nlmsg_flags & NLM_F_REPLACE) { /* You cannot replace one timeout policy by another of * different kind, sorry. */ if (matching->l3num != l3num || - matching->l4proto->l4proto != l4num) { - ret = -EINVAL; - goto err_proto_put; - } - - ret = ctnl_timeout_parse_policy(&matching->data, - l4proto, net, - cda[CTA_TIMEOUT_DATA]); - return ret; + matching->l4proto->l4proto != l4num) + return -EINVAL; + + return ctnl_timeout_parse_policy(&matching->data, + matching->l4proto, net, + cda[CTA_TIMEOUT_DATA]); } - ret = -EBUSY; + + return -EBUSY; + } + + l4proto = nf_ct_l4proto_find_get(l3num, l4num); + + /* This protocol is not supportted, skip. */ + if (l4proto->l4proto != l4num) { + ret = -EOPNOTSUPP; goto err_proto_put; } @@ -305,7 +302,16 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) const struct hlist_nulls_node *nn; unsigned int last_hsize; spinlock_t *lock; - int i; + int i, cpu; + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) + untimeout(h, timeout); + spin_unlock_bh(&pcpu->lock); + } local_bh_disable(); restart: @@ -350,12 +356,13 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { - struct ctnl_timeout *cur; + struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; char *name; if (!cda[CTA_TIMEOUT_NAME]) { - list_for_each_entry(cur, &net->nfct_timeout_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, + head) ctnl_timeout_try_del(net, cur); return 0; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 14264ed..6c1e024 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -293,10 +293,16 @@ int nft_meta_get_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_meta_get_init); -static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) +int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { + struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; + if (priv->key != NFT_META_PKTTYPE) + return 0; + switch (ctx->afi->family) { case NFPROTO_BRIDGE: hooks = 1 << NF_BR_PRE_ROUTING; @@ -310,6 +316,7 @@ static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) return nft_chain_validate_hooks(ctx->chain, hooks); } +EXPORT_SYMBOL_GPL(nft_meta_set_validate); int nft_meta_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, @@ -329,15 +336,16 @@ int nft_meta_set_init(const struct nft_ctx *ctx, len = sizeof(u8); break; case NFT_META_PKTTYPE: - err = nft_meta_set_init_pkttype(ctx); - if (err) - return err; len = sizeof(u8); break; default: return -EOPNOTSUPP; } + err = nft_meta_set_validate(ctx, expr, NULL); + if (err < 0) + return err; + priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) @@ -409,6 +417,7 @@ static const struct nft_expr_ops nft_meta_set_ops = { .init = nft_meta_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, + .validate = nft_meta_set_validate, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 0522fc9..c64de3f7 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -26,11 +26,27 @@ const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { }; EXPORT_SYMBOL_GPL(nft_reject_policy); +int nft_reject_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT)); +} +EXPORT_SYMBOL_GPL(nft_reject_validate); + int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); + int err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 759ca52..e79d9ca 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -66,7 +66,11 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code; + int icmp_code, err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; @@ -124,6 +128,7 @@ static const struct nft_expr_ops nft_reject_inet_ops = { .eval = nft_reject_inet_eval, .init = nft_reject_inet_init, .dump = nft_reject_inet_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_inet_type __read_mostly = { diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index ef36a56..4dedb96 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -68,7 +68,7 @@ match_packet(const struct sk_buff *skb, ++i, offset, sch->type, htons(sch->length), sch->flags); #endif - offset += WORD_ROUND(ntohs(sch->length)); + offset += SCTP_PAD4(ntohs(sch->length)); pr_debug("skb->len: %d\toffset: %d\n", skb->len, offset); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 3e3e253..b2f0e98 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -127,7 +127,6 @@ stop: goto done; rhashtable_walk_exit(hti); - cb->args[2] = 0; num++; mc_list: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca91fc3..863e992 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -71,6 +71,8 @@ struct ovs_frag_data { static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage); #define DEFERRED_ACTION_FIFO_SIZE 10 +#define OVS_RECURSION_LIMIT 5 +#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2) struct action_fifo { int head; int tail; @@ -78,7 +80,12 @@ struct action_fifo { struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE]; }; +struct recirc_keys { + struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD]; +}; + static struct action_fifo __percpu *action_fifos; +static struct recirc_keys __percpu *recirc_keys; static DEFINE_PER_CPU(int, exec_actions_level); static void action_fifo_init(struct action_fifo *fifo) @@ -246,20 +253,24 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) int err; err = skb_vlan_pop(skb); - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { invalidate_flow_key(key); - else - key->eth.tci = 0; + } else { + key->eth.vlan.tci = 0; + key->eth.vlan.tpid = 0; + } return err; } static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { invalidate_flow_key(key); - else - key->eth.tci = vlan->vlan_tci; + } else { + key->eth.vlan.tci = vlan->vlan_tci; + key->eth.vlan.tpid = vlan->vlan_tpid; + } return skb_vlan_push(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT); } @@ -1016,6 +1027,7 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, const struct nlattr *a, int rem) { struct deferred_action *da; + int level; if (!is_flow_key_valid(key)) { int err; @@ -1039,6 +1051,18 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, return 0; } + level = this_cpu_read(exec_actions_level); + if (level <= OVS_DEFERRED_ACTION_THRESHOLD) { + struct recirc_keys *rks = this_cpu_ptr(recirc_keys); + struct sw_flow_key *recirc_key = &rks->key[level - 1]; + + *recirc_key = *key; + recirc_key->recirc_id = nla_get_u32(a); + ovs_dp_process_packet(skb, recirc_key); + + return 0; + } + da = add_deferred_actions(skb, key, NULL); if (da) { da->pkt_key.recirc_id = nla_get_u32(a); @@ -1205,11 +1229,10 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_actions *acts, struct sw_flow_key *key) { - static const int ovs_recursion_limit = 5; int err, level; level = __this_cpu_inc_return(exec_actions_level); - if (unlikely(level > ovs_recursion_limit)) { + if (unlikely(level > OVS_RECURSION_LIMIT)) { net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n", ovs_dp_name(dp)); kfree_skb(skb); @@ -1234,10 +1257,17 @@ int action_fifos_init(void) if (!action_fifos) return -ENOMEM; + recirc_keys = alloc_percpu(struct recirc_keys); + if (!recirc_keys) { + free_percpu(action_fifos); + return -ENOMEM; + } + return 0; } void action_fifos_exit(void) { free_percpu(action_fifos); + free_percpu(recirc_keys); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 524c0fd..4d67ea8 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -928,7 +928,6 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; - struct sw_flow_key key; struct sw_flow_actions *acts; struct sw_flow_match match; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); @@ -956,20 +955,24 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } /* Extract key. */ - ovs_match_init(&match, &key, &mask); + ovs_match_init(&match, &new_flow->key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto err_kfree_flow; - ovs_flow_mask_key(&new_flow->key, &key, true, &mask); - /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], - &key, log); + &new_flow->key, log); if (error) goto err_kfree_flow; + /* unmasked key is needed to match when ufid is not used. */ + if (ovs_identifier_is_key(&new_flow->id)) + match.key = new_flow->id.unmasked_key; + + ovs_flow_mask_key(&new_flow->key, &new_flow->key, true, &mask); + /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); @@ -996,7 +999,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (ovs_identifier_is_ufid(&new_flow->id)) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id); if (!flow) - flow = ovs_flow_tbl_lookup(&dp->table, &key); + flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->key); if (likely(!flow)) { rcu_assign_pointer(new_flow->sf_acts, acts); @@ -1121,7 +1124,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { - ovs_match_init(&match, &key, &mask); + ovs_match_init(&match, &key, true, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); } else if (!ufid_present) { @@ -1238,7 +1241,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { - ovs_match_init(&match, &key, NULL); + ovs_match_init(&match, &key, true, NULL); err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], NULL, log); } else if (!ufid_present) { @@ -1297,7 +1300,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { - ovs_match_init(&match, &key, NULL); + ovs_match_init(&match, &key, true, NULL); err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], NULL, log); if (unlikely(err)) @@ -2437,3 +2440,7 @@ module_exit(dp_cleanup); MODULE_DESCRIPTION("Open vSwitch switching datapath"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_GENL_FAMILY(OVS_DATAPATH_FAMILY); +MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY); +MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY); +MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 0ea128e..634cc10 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/in.h> #include <linux/rcupdate.h> +#include <linux/cpumask.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -72,32 +73,33 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, { struct flow_stats *stats; int node = numa_node_id(); + int cpu = smp_processor_id(); int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - stats = rcu_dereference(flow->stats[node]); + stats = rcu_dereference(flow->stats[cpu]); - /* Check if already have node-specific stats. */ + /* Check if already have CPU-specific stats. */ if (likely(stats)) { spin_lock(&stats->lock); /* Mark if we write on the pre-allocated stats. */ - if (node == 0 && unlikely(flow->stats_last_writer != node)) - flow->stats_last_writer = node; + if (cpu == 0 && unlikely(flow->stats_last_writer != cpu)) + flow->stats_last_writer = cpu; } else { stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */ spin_lock(&stats->lock); - /* If the current NUMA-node is the only writer on the + /* If the current CPU is the only writer on the * pre-allocated stats keep using them. */ - if (unlikely(flow->stats_last_writer != node)) { + if (unlikely(flow->stats_last_writer != cpu)) { /* A previous locker may have already allocated the - * stats, so we need to check again. If node-specific + * stats, so we need to check again. If CPU-specific * stats were already allocated, we update the pre- * allocated stats as we have already locked them. */ - if (likely(flow->stats_last_writer != NUMA_NO_NODE) - && likely(!rcu_access_pointer(flow->stats[node]))) { - /* Try to allocate node-specific stats. */ + if (likely(flow->stats_last_writer != -1) && + likely(!rcu_access_pointer(flow->stats[cpu]))) { + /* Try to allocate CPU-specific stats. */ struct flow_stats *new_stats; new_stats = @@ -114,12 +116,12 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, new_stats->tcp_flags = tcp_flags; spin_lock_init(&new_stats->lock); - rcu_assign_pointer(flow->stats[node], + rcu_assign_pointer(flow->stats[cpu], new_stats); goto unlock; } } - flow->stats_last_writer = node; + flow->stats_last_writer = cpu; } } @@ -136,14 +138,15 @@ void ovs_flow_stats_get(const struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, unsigned long *used, __be16 *tcp_flags) { - int node; + int cpu; *used = 0; *tcp_flags = 0; memset(ovs_stats, 0, sizeof(*ovs_stats)); - for_each_node(node) { - struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]); + /* We open code this to make sure cpu 0 is always considered */ + for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask)) { + struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { /* Local CPU may write on non-local stats, so we must @@ -163,10 +166,11 @@ void ovs_flow_stats_get(const struct sw_flow *flow, /* Called with ovs_mutex. */ void ovs_flow_stats_clear(struct sw_flow *flow) { - int node; + int cpu; - for_each_node(node) { - struct flow_stats *stats = ovsl_dereference(flow->stats[node]); + /* We open code this to make sure cpu 0 is always considered */ + for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask)) { + struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { spin_lock_bh(&stats->lock); @@ -302,24 +306,57 @@ static bool icmp6hdr_ok(struct sk_buff *skb) sizeof(struct icmp6hdr)); } -static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) +/** + * Parse vlan tag from vlan header. + * Returns ERROR on memory error. + * Returns 0 if it encounters a non-vlan or incomplete packet. + * Returns 1 after successfully parsing vlan tag. + */ +static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh) { - struct qtag_prefix { - __be16 eth_type; /* ETH_P_8021Q */ - __be16 tci; - }; - struct qtag_prefix *qp; + struct vlan_head *vh = (struct vlan_head *)skb->data; + + if (likely(!eth_type_vlan(vh->tpid))) + return 0; - if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16))) + if (unlikely(skb->len < sizeof(struct vlan_head) + sizeof(__be16))) return 0; - if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) + - sizeof(__be16)))) + if (unlikely(!pskb_may_pull(skb, sizeof(struct vlan_head) + + sizeof(__be16)))) return -ENOMEM; - qp = (struct qtag_prefix *) skb->data; - key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT); - __skb_pull(skb, sizeof(struct qtag_prefix)); + vh = (struct vlan_head *)skb->data; + key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT); + key_vh->tpid = vh->tpid; + + __skb_pull(skb, sizeof(struct vlan_head)); + return 1; +} + +static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) +{ + int res; + + key->eth.vlan.tci = 0; + key->eth.vlan.tpid = 0; + key->eth.cvlan.tci = 0; + key->eth.cvlan.tpid = 0; + + if (likely(skb_vlan_tag_present(skb))) { + key->eth.vlan.tci = htons(skb->vlan_tci); + key->eth.vlan.tpid = skb->vlan_proto; + } else { + /* Parse outer vlan tag in the non-accelerated case. */ + res = parse_vlan_tag(skb, &key->eth.vlan); + if (res <= 0) + return res; + } + + /* Parse inner vlan tag. */ + res = parse_vlan_tag(skb, &key->eth.cvlan); + if (res <= 0) + return res; return 0; } @@ -480,12 +517,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) * update skb->csum here. */ - key->eth.tci = 0; - if (skb_vlan_tag_present(skb)) - key->eth.tci = htons(skb->vlan_tci); - else if (eth->h_proto == htons(ETH_P_8021Q)) - if (unlikely(parse_vlan(skb, key))) - return -ENOMEM; + if (unlikely(parse_vlan(skb, key))) + return -ENOMEM; key->eth.type = parse_ethertype(skb); if (unlikely(key->eth.type == htons(0))) @@ -734,8 +767,6 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, { int err; - memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE); - /* Extract metadata from netlink attributes. */ err = ovs_nla_get_flow_metadata(net, attr, key, log); if (err) diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 03378e7..ae783f5 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -50,6 +50,11 @@ struct ovs_tunnel_info { struct metadata_dst *tun_dst; }; +struct vlan_head { + __be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/ + __be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */ +}; + #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ FIELD_SIZEOF(struct sw_flow_key, recirc_id)) @@ -69,7 +74,8 @@ struct sw_flow_key { struct { u8 src[ETH_ALEN]; /* Ethernet source address. */ u8 dst[ETH_ALEN]; /* Ethernet destination address. */ - __be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */ + struct vlan_head vlan; + struct vlan_head cvlan; __be16 type; /* Ethernet frame type. */ } eth; union { @@ -172,14 +178,14 @@ struct sw_flow { struct hlist_node node[2]; u32 hash; } flow_table, ufid_table; - int stats_last_writer; /* NUMA-node id of the last writer on + int stats_last_writer; /* CPU id of the last writer on * 'stats[0]'. */ struct sw_flow_key key; struct sw_flow_id id; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - struct flow_stats __rcu *stats[]; /* One for each NUMA node. First one + struct flow_stats __rcu *stats[]; /* One for each CPU. First one * is allocated at flow creation time, * the rest are allocated on demand * while holding the 'stats[0].lock'. diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c78a6a1..ae25ded 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -808,6 +808,167 @@ int ovs_nla_put_tunnel_info(struct sk_buff *skb, ip_tunnel_info_af(tun_info)); } +static int encode_vlan_from_nlattrs(struct sw_flow_match *match, + const struct nlattr *a[], + bool is_mask, bool inner) +{ + __be16 tci = 0; + __be16 tpid = 0; + + if (a[OVS_KEY_ATTR_VLAN]) + tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); + + if (a[OVS_KEY_ATTR_ETHERTYPE]) + tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); + + if (likely(!inner)) { + SW_FLOW_KEY_PUT(match, eth.vlan.tpid, tpid, is_mask); + SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask); + } else { + SW_FLOW_KEY_PUT(match, eth.cvlan.tpid, tpid, is_mask); + SW_FLOW_KEY_PUT(match, eth.cvlan.tci, tci, is_mask); + } + return 0; +} + +static int validate_vlan_from_nlattrs(const struct sw_flow_match *match, + u64 key_attrs, bool inner, + const struct nlattr **a, bool log) +{ + __be16 tci = 0; + + if (!((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && + (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && + eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE])))) { + /* Not a VLAN. */ + return 0; + } + + if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && + (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { + OVS_NLERR(log, "Invalid %s frame", (inner) ? "C-VLAN" : "VLAN"); + return -EINVAL; + } + + if (a[OVS_KEY_ATTR_VLAN]) + tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); + + if (!(tci & htons(VLAN_TAG_PRESENT))) { + if (tci) { + OVS_NLERR(log, "%s TCI does not have VLAN_TAG_PRESENT bit set.", + (inner) ? "C-VLAN" : "VLAN"); + return -EINVAL; + } else if (nla_len(a[OVS_KEY_ATTR_ENCAP])) { + /* Corner case for truncated VLAN header. */ + OVS_NLERR(log, "Truncated %s header has non-zero encap attribute.", + (inner) ? "C-VLAN" : "VLAN"); + return -EINVAL; + } + } + + return 1; +} + +static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match, + u64 key_attrs, bool inner, + const struct nlattr **a, bool log) +{ + __be16 tci = 0; + __be16 tpid = 0; + bool encap_valid = !!(match->key->eth.vlan.tci & + htons(VLAN_TAG_PRESENT)); + bool i_encap_valid = !!(match->key->eth.cvlan.tci & + htons(VLAN_TAG_PRESENT)); + + if (!(key_attrs & (1 << OVS_KEY_ATTR_ENCAP))) { + /* Not a VLAN. */ + return 0; + } + + if ((!inner && !encap_valid) || (inner && !i_encap_valid)) { + OVS_NLERR(log, "Encap mask attribute is set for non-%s frame.", + (inner) ? "C-VLAN" : "VLAN"); + return -EINVAL; + } + + if (a[OVS_KEY_ATTR_VLAN]) + tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); + + if (a[OVS_KEY_ATTR_ETHERTYPE]) + tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); + + if (tpid != htons(0xffff)) { + OVS_NLERR(log, "Must have an exact match on %s TPID (mask=%x).", + (inner) ? "C-VLAN" : "VLAN", ntohs(tpid)); + return -EINVAL; + } + if (!(tci & htons(VLAN_TAG_PRESENT))) { + OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_TAG_PRESENT bit.", + (inner) ? "C-VLAN" : "VLAN"); + return -EINVAL; + } + + return 1; +} + +static int __parse_vlan_from_nlattrs(struct sw_flow_match *match, + u64 *key_attrs, bool inner, + const struct nlattr **a, bool is_mask, + bool log) +{ + int err; + const struct nlattr *encap; + + if (!is_mask) + err = validate_vlan_from_nlattrs(match, *key_attrs, inner, + a, log); + else + err = validate_vlan_mask_from_nlattrs(match, *key_attrs, inner, + a, log); + if (err <= 0) + return err; + + err = encode_vlan_from_nlattrs(match, a, is_mask, inner); + if (err) + return err; + + *key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); + *key_attrs &= ~(1 << OVS_KEY_ATTR_VLAN); + *key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); + + encap = a[OVS_KEY_ATTR_ENCAP]; + + if (!is_mask) + err = parse_flow_nlattrs(encap, a, key_attrs, log); + else + err = parse_flow_mask_nlattrs(encap, a, key_attrs, log); + + return err; +} + +static int parse_vlan_from_nlattrs(struct sw_flow_match *match, + u64 *key_attrs, const struct nlattr **a, + bool is_mask, bool log) +{ + int err; + bool encap_valid = false; + + err = __parse_vlan_from_nlattrs(match, key_attrs, false, a, + is_mask, log); + if (err) + return err; + + encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_TAG_PRESENT)); + if (encap_valid) { + err = __parse_vlan_from_nlattrs(match, key_attrs, true, a, + is_mask, log); + if (err) + return err; + } + + return 0; +} + static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 *attrs, const struct nlattr **a, bool is_mask, bool log) @@ -923,20 +1084,11 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, } if (attrs & (1 << OVS_KEY_ATTR_VLAN)) { - __be16 tci; - - tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); - if (!(tci & htons(VLAN_TAG_PRESENT))) { - if (is_mask) - OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit."); - else - OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set."); - - return -EINVAL; - } - - SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask); - attrs &= ~(1 << OVS_KEY_ATTR_VLAN); + /* VLAN attribute is always parsed before getting here since it + * may occur multiple times. + */ + OVS_NLERR(log, "VLAN attribute unexpected."); + return -EINVAL; } if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) { @@ -1182,49 +1334,18 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, bool log) { const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; - const struct nlattr *encap; struct nlattr *newmask = NULL; u64 key_attrs = 0; u64 mask_attrs = 0; - bool encap_valid = false; int err; err = parse_flow_nlattrs(nla_key, a, &key_attrs, log); if (err) return err; - if ((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && - (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && - (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) { - __be16 tci; - - if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && - (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { - OVS_NLERR(log, "Invalid Vlan frame."); - return -EINVAL; - } - - key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); - tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); - encap = a[OVS_KEY_ATTR_ENCAP]; - key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); - encap_valid = true; - - if (tci & htons(VLAN_TAG_PRESENT)) { - err = parse_flow_nlattrs(encap, a, &key_attrs, log); - if (err) - return err; - } else if (!tci) { - /* Corner case for truncated 802.1Q header. */ - if (nla_len(encap)) { - OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute."); - return -EINVAL; - } - } else { - OVS_NLERR(log, "Encap attr is set for non-VLAN frame"); - return -EINVAL; - } - } + err = parse_vlan_from_nlattrs(match, &key_attrs, a, false, log); + if (err) + return err; err = ovs_key_from_nlattrs(net, match, key_attrs, a, false, log); if (err) @@ -1265,46 +1386,12 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, goto free_newmask; /* Always match on tci. */ - SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true); - - if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) { - __be16 eth_type = 0; - __be16 tci = 0; - - if (!encap_valid) { - OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame."); - err = -EINVAL; - goto free_newmask; - } - - mask_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); - if (a[OVS_KEY_ATTR_ETHERTYPE]) - eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); - - if (eth_type == htons(0xffff)) { - mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); - encap = a[OVS_KEY_ATTR_ENCAP]; - err = parse_flow_mask_nlattrs(encap, a, - &mask_attrs, log); - if (err) - goto free_newmask; - } else { - OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).", - ntohs(eth_type)); - err = -EINVAL; - goto free_newmask; - } - - if (a[OVS_KEY_ATTR_VLAN]) - tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); + SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true); + SW_FLOW_KEY_PUT(match, eth.cvlan.tci, htons(0xffff), true); - if (!(tci & htons(VLAN_TAG_PRESENT))) { - OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).", - ntohs(tci)); - err = -EINVAL; - goto free_newmask; - } - } + err = parse_vlan_from_nlattrs(match, &mask_attrs, a, true, log); + if (err) + goto free_newmask; err = ovs_key_from_nlattrs(net, match, mask_attrs, a, true, log); @@ -1410,12 +1497,25 @@ int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr, return metadata_from_nlattrs(net, &match, &attrs, a, false, log); } +static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh, + bool is_mask) +{ + __be16 eth_type = !is_mask ? vh->tpid : htons(0xffff); + + if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || + nla_put_be16(skb, OVS_KEY_ATTR_VLAN, vh->tci)) + return -EMSGSIZE; + return 0; +} + static int __ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, bool is_mask, struct sk_buff *skb) { struct ovs_key_ethernet *eth_key; - struct nlattr *nla, *encap; + struct nlattr *nla; + struct nlattr *encap = NULL; + struct nlattr *in_encap = NULL; if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id)) goto nla_put_failure; @@ -1464,17 +1564,21 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ether_addr_copy(eth_key->eth_src, output->eth.src); ether_addr_copy(eth_key->eth_dst, output->eth.dst); - if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) { - __be16 eth_type; - eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff); - if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || - nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci)) + if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { + if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask)) goto nla_put_failure; encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); - if (!swkey->eth.tci) + if (!swkey->eth.vlan.tci) goto unencap; - } else - encap = NULL; + + if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) { + if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask)) + goto nla_put_failure; + in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP); + if (!swkey->eth.cvlan.tci) + goto unencap; + } + } if (swkey->eth.type == htons(ETH_P_802_2)) { /* @@ -1493,6 +1597,14 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type)) goto nla_put_failure; + if (eth_type_vlan(swkey->eth.type)) { + /* There are 3 VLAN tags, we don't know anything about the rest + * of the packet, so truncate here. + */ + WARN_ON_ONCE(!(encap && in_encap)); + goto unencap; + } + if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ipv4 *ipv4_key; @@ -1619,6 +1731,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, } unencap: + if (in_encap) + nla_nest_end(skb, in_encap); if (encap) nla_nest_end(skb, encap); @@ -1882,13 +1996,15 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, void ovs_match_init(struct sw_flow_match *match, struct sw_flow_key *key, + bool reset_key, struct sw_flow_mask *mask) { memset(match, 0, sizeof(*match)); match->key = key; match->mask = mask; - memset(key, 0, sizeof(*key)); + if (reset_key) + memset(key, 0, sizeof(*key)); if (mask) { memset(&mask->key, 0, sizeof(mask->key)); @@ -1935,7 +2051,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct nlattr *a; int err = 0, start, opts_type; - ovs_match_init(&match, &key, NULL); + ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) return opts_type; @@ -2283,7 +2399,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_PUSH_VLAN: vlan = nla_data(a); - if (vlan->vlan_tpid != htons(ETH_P_8021Q)) + if (!eth_type_vlan(vlan->vlan_tpid)) return -EINVAL; if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT))) return -EINVAL; @@ -2388,7 +2504,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type, - key->eth.tci, log); + key->eth.vlan.tci, log); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 47dd142..45f9769 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -41,7 +41,8 @@ size_t ovs_tun_key_attr_size(void); size_t ovs_key_attr_size(void); void ovs_match_init(struct sw_flow_match *match, - struct sw_flow_key *key, struct sw_flow_mask *mask); + struct sw_flow_key *key, bool reset_key, + struct sw_flow_mask *mask); int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, int attr, bool is_mask, struct sk_buff *); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index d073fff..ea7a807 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/in.h> #include <linux/rcupdate.h> +#include <linux/cpumask.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -79,17 +80,12 @@ struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; struct flow_stats *stats; - int node; - flow = kmem_cache_alloc(flow_cache, GFP_KERNEL); + flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL); if (!flow) return ERR_PTR(-ENOMEM); - flow->sf_acts = NULL; - flow->mask = NULL; - flow->id.unmasked_key = NULL; - flow->id.ufid_len = 0; - flow->stats_last_writer = NUMA_NO_NODE; + flow->stats_last_writer = -1; /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, @@ -102,10 +98,6 @@ struct sw_flow *ovs_flow_alloc(void) RCU_INIT_POINTER(flow->stats[0], stats); - for_each_node(node) - if (node != 0) - RCU_INIT_POINTER(flow->stats[node], NULL); - return flow; err: kmem_cache_free(flow_cache, flow); @@ -142,16 +134,17 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets) static void flow_free(struct sw_flow *flow) { - int node; + int cpu; if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); if (flow->sf_acts) ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); - for_each_node(node) - if (flow->stats[node]) + /* We open code this to make sure cpu 0 is always considered */ + for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask)) + if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, - (struct flow_stats __force *)flow->stats[node]); + (struct flow_stats __force *)flow->stats[cpu]); kmem_cache_free(flow_cache, flow); } @@ -756,7 +749,7 @@ int ovs_flow_init(void) BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long)); flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) - + (nr_node_ids + + (nr_cpu_ids * sizeof(struct flow_stats *)), 0, 0, NULL); if (flow_cache == NULL) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 6b21fd0..8f19843 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -485,9 +485,14 @@ static unsigned int packet_length(const struct sk_buff *skb) { unsigned int length = skb->len - ETH_HLEN; - if (skb->protocol == htons(ETH_P_8021Q)) + if (skb_vlan_tagged(skb)) length -= VLAN_HLEN; + /* Don't subtract for multiple VLAN tags. Most (all?) drivers allow + * (ETH_LEN + VLAN_HLEN) in addition to the mtu value, but almost none + * account for 802.1ad. e.g. is_skb_forwardable(). + */ + return length; } diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index 784c531..86f8853 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -19,6 +19,20 @@ config AF_RXRPC See Documentation/networking/rxrpc.txt. +config AF_RXRPC_IPV6 + bool "IPv6 support for RxRPC" + depends on (IPV6 = m && AF_RXRPC = m) || (IPV6 = y && AF_RXRPC) + help + Say Y here to allow AF_RXRPC to use IPV6 UDP as well as IPV4 UDP as + its network transport. + +config AF_RXRPC_INJECT_LOSS + bool "Inject packet loss into RxRPC packet stream" + depends on AF_RXRPC + help + Say Y here to inject packet loss by discarding some received and some + transmitted packets. + config AF_RXRPC_DEBUG bool "RxRPC dynamic debugging" diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index b66a9e6..8dbf7be 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -45,7 +45,7 @@ u32 rxrpc_epoch; atomic_t rxrpc_debug_id; /* count of skbs currently in use */ -atomic_t rxrpc_n_skbs; +atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; @@ -106,19 +106,25 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, case AF_INET: if (srx->transport_len < sizeof(struct sockaddr_in)) return -EINVAL; - _debug("INET: %x @ %pI4", - ntohs(srx->transport.sin.sin_port), - &srx->transport.sin.sin_addr); tail = offsetof(struct sockaddr_rxrpc, transport.sin.__pad); break; +#ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: + if (srx->transport_len < sizeof(struct sockaddr_in6)) + return -EINVAL; + tail = offsetof(struct sockaddr_rxrpc, transport) + + sizeof(struct sockaddr_in6); + break; +#endif + default: return -EAFNOSUPPORT; } if (tail < len) memset((void *)srx + tail, 0, len - tail); + _debug("INET: %pISp", &srx->transport); return 0; } @@ -155,15 +161,15 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) } if (rx->srx.srx_service) { - write_lock_bh(&local->services_lock); - list_for_each_entry(prx, &local->services, listen_link) { + write_lock(&local->services_lock); + hlist_for_each_entry(prx, &local->services, listen_link) { if (prx->srx.srx_service == rx->srx.srx_service) goto service_in_use; } rx->local = local; - list_add_tail(&rx->listen_link, &local->services); - write_unlock_bh(&local->services_lock); + hlist_add_head_rcu(&rx->listen_link, &local->services); + write_unlock(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; } else { @@ -176,7 +182,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) return 0; service_in_use: - write_unlock_bh(&local->services_lock); + write_unlock(&local->services_lock); rxrpc_put_local(local); ret = -EADDRINUSE; error_unlock: @@ -193,7 +199,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct rxrpc_sock *rx = rxrpc_sk(sk); - unsigned int max; + unsigned int max, old; int ret; _enter("%p,%d", rx, backlog); @@ -212,9 +218,13 @@ static int rxrpc_listen(struct socket *sock, int backlog) backlog = max; else if (backlog < 0 || backlog > max) break; + old = sk->sk_max_ack_backlog; sk->sk_max_ack_backlog = backlog; - rx->sk.sk_state = RXRPC_SERVER_LISTENING; - ret = 0; + ret = rxrpc_service_prealloc(rx, GFP_KERNEL); + if (ret == 0) + rx->sk.sk_state = RXRPC_SERVER_LISTENING; + else + sk->sk_max_ack_backlog = old; break; default: ret = -EBUSY; @@ -294,9 +304,8 @@ EXPORT_SYMBOL(rxrpc_kernel_begin_call); void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) { _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); - rxrpc_remove_user_ID(rxrpc_sk(sock->sk), call); - rxrpc_purge_queue(&call->knlrecv_queue); - rxrpc_put_call(call); + rxrpc_release_call(rxrpc_sk(sock->sk), call); + rxrpc_put_call(call, rxrpc_call_put_kernel); } EXPORT_SYMBOL(rxrpc_kernel_end_call); @@ -304,16 +313,19 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * rxrpc_kernel_new_call_notification - Get notifications of new calls * @sock: The socket to intercept received messages on * @notify_new_call: Function to be called when new calls appear + * @discard_new_call: Function to discard preallocated calls * * Allow a kernel service to be given notifications about new calls. */ void rxrpc_kernel_new_call_notification( struct socket *sock, - rxrpc_notify_new_call_t notify_new_call) + rxrpc_notify_new_call_t notify_new_call, + rxrpc_discard_new_call_t discard_new_call) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); rx->notify_new_call = notify_new_call; + rx->discard_new_call = discard_new_call; } EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); @@ -395,6 +407,23 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) switch (rx->sk.sk_state) { case RXRPC_UNBOUND: + rx->srx.srx_family = AF_RXRPC; + rx->srx.srx_service = 0; + rx->srx.transport_type = SOCK_DGRAM; + rx->srx.transport.family = rx->family; + switch (rx->family) { + case AF_INET: + rx->srx.transport_len = sizeof(struct sockaddr_in); + break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + rx->srx.transport_len = sizeof(struct sockaddr_in6); + break; +#endif + default: + ret = -EAFNOSUPPORT; + goto error_unlock; + } local = rxrpc_lookup_local(&rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); @@ -509,15 +538,16 @@ error: static unsigned int rxrpc_poll(struct file *file, struct socket *sock, poll_table *wait) { - unsigned int mask; struct sock *sk = sock->sk; + struct rxrpc_sock *rx = rxrpc_sk(sk); + unsigned int mask; sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx * queue */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!list_empty(&rx->recvmsg_q)) mask |= POLLIN | POLLRDNORM; /* the socket is writable if there is space to add new data to the @@ -544,7 +574,8 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, return -EAFNOSUPPORT; /* we support transport protocol UDP/UDP6 only */ - if (protocol != PF_INET) + if (protocol != PF_INET && + IS_ENABLED(CONFIG_AF_RXRPC_IPV6) && protocol != PF_INET6) return -EPROTONOSUPPORT; if (sock->type != SOCK_DGRAM) @@ -558,6 +589,7 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, return -ENOMEM; sock_init_data(sock, sk); + sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_state = RXRPC_UNBOUND; sk->sk_write_space = rxrpc_write_space; sk->sk_max_ack_backlog = 0; @@ -567,9 +599,12 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, rx->family = protocol; rx->calls = RB_ROOT; - INIT_LIST_HEAD(&rx->listen_link); - INIT_LIST_HEAD(&rx->secureq); - INIT_LIST_HEAD(&rx->acceptq); + INIT_HLIST_NODE(&rx->listen_link); + spin_lock_init(&rx->incoming_lock); + INIT_LIST_HEAD(&rx->sock_calls); + INIT_LIST_HEAD(&rx->to_be_accepted); + INIT_LIST_HEAD(&rx->recvmsg_q); + rwlock_init(&rx->recvmsg_lock); rwlock_init(&rx->call_lock); memset(&rx->srx, 0, sizeof(rx->srx)); @@ -578,6 +613,39 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, } /* + * Kill all the calls on a socket and shut it down. + */ +static int rxrpc_shutdown(struct socket *sock, int flags) +{ + struct sock *sk = sock->sk; + struct rxrpc_sock *rx = rxrpc_sk(sk); + int ret = 0; + + _enter("%p,%d", sk, flags); + + if (flags != SHUT_RDWR) + return -EOPNOTSUPP; + if (sk->sk_state == RXRPC_CLOSE) + return -ESHUTDOWN; + + lock_sock(sk); + + spin_lock_bh(&sk->sk_receive_queue.lock); + if (sk->sk_state < RXRPC_CLOSE) { + sk->sk_state = RXRPC_CLOSE; + sk->sk_shutdown = SHUTDOWN_MASK; + } else { + ret = -ESHUTDOWN; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); + + rxrpc_discard_prealloc(rx); + + release_sock(sk); + return ret; +} + +/* * RxRPC socket destructor */ static void rxrpc_sock_destructor(struct sock *sk) @@ -615,13 +683,14 @@ static int rxrpc_release_sock(struct sock *sk) ASSERTCMP(rx->listen_link.next, !=, LIST_POISON1); - if (!list_empty(&rx->listen_link)) { - write_lock_bh(&rx->local->services_lock); - list_del(&rx->listen_link); - write_unlock_bh(&rx->local->services_lock); + if (!hlist_unhashed(&rx->listen_link)) { + write_lock(&rx->local->services_lock); + hlist_del_rcu(&rx->listen_link); + write_unlock(&rx->local->services_lock); } /* try to flush out this socket */ + rxrpc_discard_prealloc(rx); rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); @@ -670,7 +739,7 @@ static const struct proto_ops rxrpc_rpc_ops = { .poll = rxrpc_poll, .ioctl = sock_no_ioctl, .listen = rxrpc_listen, - .shutdown = sock_no_shutdown, + .shutdown = rxrpc_shutdown, .setsockopt = rxrpc_setsockopt, .getsockopt = sock_no_getsockopt, .sendmsg = rxrpc_sendmsg, @@ -798,7 +867,8 @@ static void __exit af_rxrpc_exit(void) proto_unregister(&rxrpc_proto); rxrpc_destroy_all_calls(); rxrpc_destroy_all_connections(); - ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0); + ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); + ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); rxrpc_destroy_all_locals(); remove_proc_entry("rxrpc_conns", init_net.proc_net); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bb342f5..ca96e54 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -35,8 +35,6 @@ struct rxrpc_crypt { #define rxrpc_queue_delayed_work(WS,D) \ queue_delayed_work(rxrpc_workqueue, (WS), (D)) -#define rxrpc_queue_call(CALL) rxrpc_queue_work(&(CALL)->processor) - struct rxrpc_connection; /* @@ -66,19 +64,45 @@ enum { }; /* + * Service backlog preallocation. + * + * This contains circular buffers of preallocated peers, connections and calls + * for incoming service calls and their head and tail pointers. This allows + * calls to be set up in the data_ready handler, thereby avoiding the need to + * shuffle packets around so much. + */ +struct rxrpc_backlog { + unsigned short peer_backlog_head; + unsigned short peer_backlog_tail; + unsigned short conn_backlog_head; + unsigned short conn_backlog_tail; + unsigned short call_backlog_head; + unsigned short call_backlog_tail; +#define RXRPC_BACKLOG_MAX 32 + struct rxrpc_peer *peer_backlog[RXRPC_BACKLOG_MAX]; + struct rxrpc_connection *conn_backlog[RXRPC_BACKLOG_MAX]; + struct rxrpc_call *call_backlog[RXRPC_BACKLOG_MAX]; +}; + +/* * RxRPC socket definition */ struct rxrpc_sock { /* WARNING: sk has to be the first member */ struct sock sk; rxrpc_notify_new_call_t notify_new_call; /* Func to notify of new call */ + rxrpc_discard_new_call_t discard_new_call; /* Func to discard a new call */ struct rxrpc_local *local; /* local endpoint */ - struct list_head listen_link; /* link in the local endpoint's listen list */ - struct list_head secureq; /* calls awaiting connection security clearance */ - struct list_head acceptq; /* calls awaiting acceptance */ + struct hlist_node listen_link; /* link in the local endpoint's listen list */ + struct rxrpc_backlog *backlog; /* Preallocation for services */ + spinlock_t incoming_lock; /* Incoming call vs service shutdown lock */ + struct list_head sock_calls; /* List of calls owned by this socket */ + struct list_head to_be_accepted; /* calls awaiting acceptance */ + struct list_head recvmsg_q; /* Calls awaiting recvmsg's attention */ + rwlock_t recvmsg_lock; /* Lock for recvmsg_q */ struct key *key; /* security for this socket */ struct key *securities; /* list of server security descriptors */ - struct rb_root calls; /* outstanding calls on this socket */ + struct rb_root calls; /* User ID -> call mapping */ unsigned long flags; #define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ rwlock_t call_lock; /* lock for calls */ @@ -117,13 +141,13 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - struct rxrpc_call *call; /* call with which associated */ - unsigned long resend_at; /* time in jiffies at which to resend */ + union { + u8 nr_jumbo; /* Number of jumbo subpackets */ + }; union { unsigned int offset; /* offset into buffer of next read */ int remain; /* amount of space remaining for next write */ u32 error; /* network error code */ - bool need_resend; /* T if needs resending */ }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ @@ -157,7 +181,12 @@ struct rxrpc_security { void *); /* verify the security on a received packet */ - int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, u32 *); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, + unsigned int, unsigned int, rxrpc_seq_t, u16); + + /* Locate the data in a received packet that has been verified. */ + void (*locate_data)(struct rxrpc_call *, struct sk_buff *, + unsigned int *, unsigned int *); /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -187,9 +216,8 @@ struct rxrpc_local { struct list_head link; struct socket *socket; /* my UDP socket */ struct work_struct processor; - struct list_head services; /* services listening on this endpoint */ + struct hlist_head services; /* services listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ - struct sk_buff_head accept_queue; /* incoming calls awaiting acceptance */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct rb_root client_conns; /* Client connections by socket params */ @@ -227,10 +255,12 @@ struct rxrpc_peer { /* calculated RTT cache */ #define RXRPC_RTT_CACHE_SIZE 32 - suseconds_t rtt; /* current RTT estimate (in uS) */ - unsigned int rtt_point; /* next entry at which to insert */ - unsigned int rtt_usage; /* amount of cache actually used */ - suseconds_t rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* calculated RTT cache */ + ktime_t rtt_last_req; /* Time of last RTT request */ + u64 rtt; /* Current RTT estimate (in nS) */ + u64 rtt_sum; /* Sum of cache contents */ + u64 rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */ + u8 rtt_cursor; /* next entry at which to insert */ + u8 rtt_usage; /* amount of cache actually used */ }; /* @@ -283,6 +313,7 @@ enum rxrpc_conn_cache_state { RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */ RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */ RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */ + RXRPC_CONN__NR_CACHE_STATES }; /* @@ -291,6 +322,7 @@ enum rxrpc_conn_cache_state { enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ RXRPC_CONN_CLIENT, /* Client connection */ + RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ @@ -345,17 +377,16 @@ struct rxrpc_connection { unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ - enum rxrpc_conn_cache_state cache_state : 8; - enum rxrpc_conn_proto_state state : 8; /* current state of connection */ + enum rxrpc_conn_cache_state cache_state; + enum rxrpc_conn_proto_state state; /* current state of connection */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ + u32 security_nonce; /* response re-use preventer */ u8 size_align; /* data size alignment (for security) */ - u8 header_size; /* rxrpc + security header size */ u8 security_size; /* security header size */ - u32 security_nonce; /* response re-use preventer */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ }; @@ -365,39 +396,23 @@ struct rxrpc_connection { */ enum rxrpc_call_flag { RXRPC_CALL_RELEASED, /* call has been released - no more message to userspace */ - RXRPC_CALL_TERMINAL_MSG, /* call has given the socket its final message */ - RXRPC_CALL_RCVD_LAST, /* all packets received */ - RXRPC_CALL_RUN_RTIMER, /* Tx resend timer started */ - RXRPC_CALL_TX_SOFT_ACK, /* sent some soft ACKs */ - RXRPC_CALL_INIT_ACCEPT, /* acceptance was initiated */ RXRPC_CALL_HAS_USERID, /* has a user ID attached */ - RXRPC_CALL_EXPECT_OOS, /* expect out of sequence packets */ RXRPC_CALL_IS_SERVICE, /* Call is service call */ RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ - RXRPC_CALL_RX_NO_MORE, /* Don't indicate MSG_MORE from recvmsg() */ + RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ + RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_PINGING, /* Ping in process */ + RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_RCVD_ACKALL, /* ACKALL or reply received */ - RXRPC_CALL_EV_RCVD_BUSY, /* busy packet received */ - RXRPC_CALL_EV_RCVD_ABORT, /* abort packet received */ - RXRPC_CALL_EV_RCVD_ERROR, /* network error received */ - RXRPC_CALL_EV_ACK_FINAL, /* need to generate final ACK (and release call) */ RXRPC_CALL_EV_ACK, /* need to generate ACK */ - RXRPC_CALL_EV_REJECT_BUSY, /* need to generate busy message */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ - RXRPC_CALL_EV_CONN_ABORT, /* local connection abort generated */ - RXRPC_CALL_EV_RESEND_TIMER, /* Tx resend timer expired */ + RXRPC_CALL_EV_TIMER, /* Timer expired */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_DRAIN_RX_OOS, /* drain the Rx out of sequence queue */ - RXRPC_CALL_EV_LIFE_TIMER, /* call's lifetimer ran out */ - RXRPC_CALL_EV_ACCEPTED, /* incoming call accepted by userspace app */ - RXRPC_CALL_EV_SECURED, /* incoming call's connection is now secure */ - RXRPC_CALL_EV_POST_ACCEPT, /* need to post an "accept?" message to the app */ - RXRPC_CALL_EV_RELEASE, /* need to release the call's resources */ }; /* @@ -409,7 +424,7 @@ enum rxrpc_call_state { RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */ RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ - RXRPC_CALL_CLIENT_FINAL_ACK, /* - client sending final ACK phase */ + RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ RXRPC_CALL_SERVER_ACCEPTING, /* - server accepting request */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ @@ -417,7 +432,6 @@ enum rxrpc_call_state { RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ RXRPC_CALL_COMPLETE, /* - call complete */ - RXRPC_CALL_DEAD, /* - call is dead */ NR__RXRPC_CALL_STATES }; @@ -426,7 +440,6 @@ enum rxrpc_call_state { */ enum rxrpc_call_completion { RXRPC_CALL_SUCCEEDED, /* - Normal termination */ - RXRPC_CALL_SERVER_BUSY, /* - call rejected by busy server */ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ @@ -435,6 +448,17 @@ enum rxrpc_call_completion { }; /* + * Call Tx congestion management modes. + */ +enum rxrpc_congest_mode { + RXRPC_CALL_SLOW_START, + RXRPC_CALL_CONGEST_AVOIDANCE, + RXRPC_CALL_PACKET_LOSS, + RXRPC_CALL_FAST_RETRANSMIT, + NR__RXRPC_CONGEST_MODES +}; + +/* * RxRPC call definition * - matched by { connection, call_id } */ @@ -442,78 +466,329 @@ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ - struct rxrpc_sock *socket; /* socket responsible */ - struct timer_list lifetimer; /* lifetime remaining on call */ - struct timer_list deadspan; /* reap timer for re-ACK'ing, etc */ - struct timer_list ack_timer; /* ACK generation timer */ - struct timer_list resend_timer; /* Tx resend timer */ - struct work_struct destroyer; /* call destroyer */ - struct work_struct processor; /* packet processor and ACK generator */ + struct rxrpc_sock __rcu *socket; /* socket responsible */ + unsigned long ack_at; /* When deferred ACK needs to happen */ + unsigned long resend_at; /* When next resend needs to happen */ + unsigned long expire_at; /* When the call times out */ + struct timer_list timer; /* Combined event timer */ + struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head chan_wait_link; /* Link in conn->waiting_calls */ struct hlist_node error_link; /* link in error distribution list */ - struct list_head accept_link; /* calls awaiting acceptance */ - struct rb_node sock_node; /* node in socket call tree */ - struct sk_buff_head rx_queue; /* received packets */ - struct sk_buff_head rx_oos_queue; /* packets received out of sequence */ - struct sk_buff_head knlrecv_queue; /* Queue for kernel_recv [TODO: replace this] */ + struct list_head accept_link; /* Link in rx->acceptq */ + struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ + struct list_head sock_link; /* Link in rx->sock_calls */ + struct rb_node sock_node; /* Node in rx->calls */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ - unsigned long creation_jif; /* time of call creation */ unsigned long flags; unsigned long events; spinlock_t lock; rwlock_t state_lock; /* lock for state transition */ u32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ - enum rxrpc_call_state state : 8; /* current state of call */ - enum rxrpc_call_completion completion : 8; /* Call completion condition */ + enum rxrpc_call_state state; /* current state of call */ + enum rxrpc_call_completion completion; /* Call completion condition */ atomic_t usage; - atomic_t skb_count; /* Outstanding packets on this call */ - atomic_t sequence; /* Tx data packet sequence counter */ u16 service_id; /* service ID */ + u8 security_ix; /* Security type */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ int debug_id; /* debug ID for printks */ - - /* transmission-phase ACK management */ - u8 acks_head; /* offset into window of first entry */ - u8 acks_tail; /* offset into window of last entry */ - u8 acks_winsz; /* size of un-ACK'd window */ - u8 acks_unacked; /* lowest unacked packet in last ACK received */ - int acks_latest; /* serial number of latest ACK received */ - rxrpc_seq_t acks_hard; /* highest definitively ACK'd msg seq */ - unsigned long *acks_window; /* sent packet window - * - elements are pointers with LSB set if ACK'd + unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ + unsigned short rx_pkt_len; /* Current recvmsg packet len */ + + /* Rx/Tx circular buffer, depending on phase. + * + * In the Rx phase, packets are annotated with 0 or the number of the + * segment of a jumbo packet each buffer refers to. There can be up to + * 47 segments in a maximum-size UDP packet. + * + * In the Tx phase, packets are annotated with which buffers have been + * acked. + */ +#define RXRPC_RXTX_BUFF_SIZE 64 +#define RXRPC_RXTX_BUFF_MASK (RXRPC_RXTX_BUFF_SIZE - 1) +#define RXRPC_INIT_RX_WINDOW_SIZE 32 + struct sk_buff **rxtx_buffer; + u8 *rxtx_annotations; +#define RXRPC_TX_ANNO_ACK 0 +#define RXRPC_TX_ANNO_UNACK 1 +#define RXRPC_TX_ANNO_NAK 2 +#define RXRPC_TX_ANNO_RETRANS 3 +#define RXRPC_TX_ANNO_MASK 0x03 +#define RXRPC_TX_ANNO_LAST 0x04 +#define RXRPC_TX_ANNO_RESENT 0x08 + +#define RXRPC_RX_ANNO_JUMBO 0x3f /* Jumbo subpacket number + 1 if not zero */ +#define RXRPC_RX_ANNO_JLAST 0x40 /* Set if last element of a jumbo packet */ +#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ + rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but + * not hard-ACK'd packet follows this. + */ + rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + + /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS + * is fixed, we keep these numbers in terms of segments (ie. DATA + * packets) rather than bytes. + */ +#define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN + u8 cong_cwnd; /* Congestion window size */ + u8 cong_extra; /* Extra to send for congestion management */ + u8 cong_ssthresh; /* Slow-start threshold */ + enum rxrpc_congest_mode cong_mode:8; /* Congestion management mode */ + u8 cong_dup_acks; /* Count of ACKs showing missing packets */ + u8 cong_cumul_acks; /* Cumulative ACK count */ + ktime_t cong_tstamp; /* Last time cwnd was changed */ + + rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not + * consumed packet follows this. */ + rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ + rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ + u8 rx_winsize; /* Size of Rx window */ + u8 tx_winsize; /* Maximum size of Tx window */ + bool tx_phase; /* T if transmission phase, F if receive phase */ + u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ /* receive-phase ACK management */ - rxrpc_seq_t rx_data_expect; /* next data seq ID expected to be received */ - rxrpc_seq_t rx_data_post; /* next data seq ID expected to be posted */ - rxrpc_seq_t rx_data_recv; /* last data seq ID encountered by recvmsg */ - rxrpc_seq_t rx_data_eaten; /* last data seq ID consumed by recvmsg */ - rxrpc_seq_t rx_first_oos; /* first packet in rx_oos_queue (or 0) */ - rxrpc_seq_t ackr_win_top; /* top of ACK window (rx_data_eaten is bottom) */ - rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ u8 ackr_reason; /* reason to ACK */ u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - atomic_t ackr_not_idle; /* number of packets in Rx queue */ + rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ + rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ + rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ + rxrpc_serial_t ackr_ping; /* Last ping sent */ + ktime_t ackr_ping_time; /* Time last ping sent */ - /* received packet records, 1 bit per record */ -#define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) - unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; + /* transmission-phase ACK management */ + ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ + rxrpc_serial_t acks_latest; /* serial number of latest ACK received */ + rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ }; +/* + * Summary of a new ACK and the changes it made to the Tx buffer packet states. + */ +struct rxrpc_ack_summary { + u8 ack_reason; + u8 nr_acks; /* Number of ACKs in packet */ + u8 nr_nacks; /* Number of NACKs in packet */ + u8 nr_new_acks; /* Number of new ACKs in packet */ + u8 nr_new_nacks; /* Number of new NACKs in packet */ + u8 nr_rot_new_acks; /* Number of rotated new ACKs */ + bool new_low_nack; /* T if new low NACK found */ + bool retrans_timeo; /* T if reTx due to timeout happened */ + u8 flight_size; /* Number of unreceived transmissions */ + /* Place to stash values for tracing */ + enum rxrpc_congest_mode mode:8; + u8 cwnd; + u8 ssthresh; + u8 dup_acks; + u8 cumulative_acks; +}; + +enum rxrpc_skb_trace { + rxrpc_skb_rx_cleaned, + rxrpc_skb_rx_freed, + rxrpc_skb_rx_got, + rxrpc_skb_rx_lost, + rxrpc_skb_rx_received, + rxrpc_skb_rx_rotated, + rxrpc_skb_rx_purged, + rxrpc_skb_rx_seen, + rxrpc_skb_tx_cleaned, + rxrpc_skb_tx_freed, + rxrpc_skb_tx_got, + rxrpc_skb_tx_lost, + rxrpc_skb_tx_new, + rxrpc_skb_tx_rotated, + rxrpc_skb_tx_seen, + rxrpc_skb__nr_trace +}; + +extern const char rxrpc_skb_traces[rxrpc_skb__nr_trace][7]; + +enum rxrpc_conn_trace { + rxrpc_conn_new_client, + rxrpc_conn_new_service, + rxrpc_conn_queued, + rxrpc_conn_seen, + rxrpc_conn_got, + rxrpc_conn_put_client, + rxrpc_conn_put_service, + rxrpc_conn__nr_trace +}; + +extern const char rxrpc_conn_traces[rxrpc_conn__nr_trace][4]; + +enum rxrpc_client_trace { + rxrpc_client_activate_chans, + rxrpc_client_alloc, + rxrpc_client_chan_activate, + rxrpc_client_chan_disconnect, + rxrpc_client_chan_pass, + rxrpc_client_chan_unstarted, + rxrpc_client_cleanup, + rxrpc_client_count, + rxrpc_client_discard, + rxrpc_client_duplicate, + rxrpc_client_exposed, + rxrpc_client_replace, + rxrpc_client_to_active, + rxrpc_client_to_culled, + rxrpc_client_to_idle, + rxrpc_client_to_inactive, + rxrpc_client_to_waiting, + rxrpc_client_uncount, + rxrpc_client__nr_trace +}; + +extern const char rxrpc_client_traces[rxrpc_client__nr_trace][7]; +extern const char rxrpc_conn_cache_states[RXRPC_CONN__NR_CACHE_STATES][5]; + +enum rxrpc_call_trace { + rxrpc_call_new_client, + rxrpc_call_new_service, + rxrpc_call_queued, + rxrpc_call_queued_ref, + rxrpc_call_seen, + rxrpc_call_connected, + rxrpc_call_release, + rxrpc_call_got, + rxrpc_call_got_userid, + rxrpc_call_got_kernel, + rxrpc_call_put, + rxrpc_call_put_userid, + rxrpc_call_put_kernel, + rxrpc_call_put_noqueue, + rxrpc_call_error, + rxrpc_call__nr_trace +}; + +extern const char rxrpc_call_traces[rxrpc_call__nr_trace][4]; + +enum rxrpc_transmit_trace { + rxrpc_transmit_wait, + rxrpc_transmit_queue, + rxrpc_transmit_queue_last, + rxrpc_transmit_rotate, + rxrpc_transmit_rotate_last, + rxrpc_transmit_await_reply, + rxrpc_transmit_end, + rxrpc_transmit__nr_trace +}; + +extern const char rxrpc_transmit_traces[rxrpc_transmit__nr_trace][4]; + +enum rxrpc_receive_trace { + rxrpc_receive_incoming, + rxrpc_receive_queue, + rxrpc_receive_queue_last, + rxrpc_receive_front, + rxrpc_receive_rotate, + rxrpc_receive_end, + rxrpc_receive__nr_trace +}; + +extern const char rxrpc_receive_traces[rxrpc_receive__nr_trace][4]; + +enum rxrpc_recvmsg_trace { + rxrpc_recvmsg_enter, + rxrpc_recvmsg_wait, + rxrpc_recvmsg_dequeue, + rxrpc_recvmsg_hole, + rxrpc_recvmsg_next, + rxrpc_recvmsg_cont, + rxrpc_recvmsg_full, + rxrpc_recvmsg_data_return, + rxrpc_recvmsg_terminal, + rxrpc_recvmsg_to_be_accepted, + rxrpc_recvmsg_return, + rxrpc_recvmsg__nr_trace +}; + +extern const char rxrpc_recvmsg_traces[rxrpc_recvmsg__nr_trace][5]; + +enum rxrpc_rtt_tx_trace { + rxrpc_rtt_tx_ping, + rxrpc_rtt_tx_data, + rxrpc_rtt_tx__nr_trace +}; + +extern const char rxrpc_rtt_tx_traces[rxrpc_rtt_tx__nr_trace][5]; + +enum rxrpc_rtt_rx_trace { + rxrpc_rtt_rx_ping_response, + rxrpc_rtt_rx_requested_ack, + rxrpc_rtt_rx__nr_trace +}; + +extern const char rxrpc_rtt_rx_traces[rxrpc_rtt_rx__nr_trace][5]; + +enum rxrpc_timer_trace { + rxrpc_timer_begin, + rxrpc_timer_init_for_reply, + rxrpc_timer_expired, + rxrpc_timer_set_for_ack, + rxrpc_timer_set_for_resend, + rxrpc_timer_set_for_send, + rxrpc_timer__nr_trace +}; + +extern const char rxrpc_timer_traces[rxrpc_timer__nr_trace][8]; + +enum rxrpc_propose_ack_trace { + rxrpc_propose_ack_client_tx_end, + rxrpc_propose_ack_input_data, + rxrpc_propose_ack_ping_for_lost_ack, + rxrpc_propose_ack_ping_for_lost_reply, + rxrpc_propose_ack_ping_for_params, + rxrpc_propose_ack_respond_to_ack, + rxrpc_propose_ack_respond_to_ping, + rxrpc_propose_ack_retry_tx, + rxrpc_propose_ack_rotate_rx, + rxrpc_propose_ack_terminal_ack, + rxrpc_propose_ack__nr_trace +}; + +enum rxrpc_propose_ack_outcome { + rxrpc_propose_ack_use, + rxrpc_propose_ack_update, + rxrpc_propose_ack_subsume, + rxrpc_propose_ack__nr_outcomes +}; + +extern const char rxrpc_propose_ack_traces[rxrpc_propose_ack__nr_trace][8]; +extern const char *const rxrpc_propose_ack_outcomes[rxrpc_propose_ack__nr_outcomes]; + +enum rxrpc_congest_change { + rxrpc_cong_begin_retransmission, + rxrpc_cong_cleared_nacks, + rxrpc_cong_new_low_nack, + rxrpc_cong_no_change, + rxrpc_cong_progress, + rxrpc_cong_retransmit_again, + rxrpc_cong_rtt_window_end, + rxrpc_cong_saw_nack, + rxrpc_congest__nr_change +}; + +extern const char rxrpc_congest_modes[NR__RXRPC_CONGEST_MODES][10]; +extern const char rxrpc_congest_changes[rxrpc_congest__nr_change][9]; + +extern const char *const rxrpc_pkts[]; +extern const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4]; + #include <trace/events/rxrpc.h> /* * af_rxrpc.c */ -extern atomic_t rxrpc_n_skbs; +extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; extern u32 rxrpc_epoch; extern atomic_t rxrpc_debug_id; extern struct workqueue_struct *rxrpc_workqueue; @@ -521,6 +796,11 @@ extern struct workqueue_struct *rxrpc_workqueue; /* * call_accept.c */ +int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); +void rxrpc_discard_prealloc(struct rxrpc_sock *); +struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, + struct rxrpc_connection *, + struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, rxrpc_notify_rx_t); @@ -529,8 +809,9 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ -void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool); -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool); +void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace); +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, + enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); /* @@ -539,26 +820,26 @@ void rxrpc_process_call(struct work_struct *); extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern unsigned int rxrpc_max_call_lifetime; -extern unsigned int rxrpc_dead_call_expiry; extern struct kmem_cache *rxrpc_call_jar; extern struct list_head rxrpc_calls; extern rwlock_t rxrpc_call_lock; struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); +struct rxrpc_call *rxrpc_alloc_call(gfp_t); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, unsigned long, gfp_t); -struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, - struct rxrpc_connection *, - struct sk_buff *); -void rxrpc_release_call(struct rxrpc_call *); +void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, + struct sk_buff *); +void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); +bool __rxrpc_queue_call(struct rxrpc_call *); +bool rxrpc_queue_call(struct rxrpc_call *); void rxrpc_see_call(struct rxrpc_call *); -void rxrpc_get_call(struct rxrpc_call *); -void rxrpc_put_call(struct rxrpc_call *); -void rxrpc_get_call_for_skb(struct rxrpc_call *, struct sk_buff *); -void rxrpc_put_call_for_skb(struct rxrpc_call *, struct sk_buff *); +void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_cleanup_call(struct rxrpc_call *); void __exit rxrpc_destroy_all_calls(void); static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) @@ -584,6 +865,7 @@ static inline bool __rxrpc_set_call_completion(struct rxrpc_call *call, call->error = error; call->completion = compl, call->state = RXRPC_CALL_COMPLETE; + wake_up(&call->waitq); return true; } return false; @@ -594,7 +876,7 @@ static inline bool rxrpc_set_call_completion(struct rxrpc_call *call, u32 abort_code, int error) { - int ret; + bool ret; write_lock_bh(&call->state_lock); ret = __rxrpc_set_call_completion(call, compl, abort_code, error); @@ -605,40 +887,41 @@ static inline bool rxrpc_set_call_completion(struct rxrpc_call *call, /* * Record that a call successfully completed. */ -static inline void __rxrpc_call_completed(struct rxrpc_call *call) +static inline bool __rxrpc_call_completed(struct rxrpc_call *call) { - __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); + return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); } -static inline void rxrpc_call_completed(struct rxrpc_call *call) +static inline bool rxrpc_call_completed(struct rxrpc_call *call) { + bool ret; + write_lock_bh(&call->state_lock); - __rxrpc_call_completed(call); + ret = __rxrpc_call_completed(call); write_unlock_bh(&call->state_lock); + return ret; } /* * Record that a call is locally aborted. */ -static inline bool __rxrpc_abort_call(struct rxrpc_call *call, +static inline bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, + rxrpc_seq_t seq, u32 abort_code, int error) { - if (__rxrpc_set_call_completion(call, - RXRPC_CALL_LOCALLY_ABORTED, - abort_code, error)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - return true; - } - return false; + trace_rxrpc_abort(why, call->cid, call->call_id, seq, + abort_code, error); + return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error); } -static inline bool rxrpc_abort_call(struct rxrpc_call *call, - u32 abort_code, int error) +static inline bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, + rxrpc_seq_t seq, u32 abort_code, int error) { bool ret; write_lock_bh(&call->state_lock); - ret = __rxrpc_abort_call(call, abort_code, error); + ret = __rxrpc_abort_call(why, call, seq, abort_code, error); write_unlock_bh(&call->state_lock); return ret; } @@ -664,8 +947,6 @@ void __exit rxrpc_destroy_all_client_connections(void); * conn_event.c */ void rxrpc_process_connection(struct work_struct *); -void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *); -void rxrpc_reject_packets(struct rxrpc_local *); /* * conn_object.c @@ -682,7 +963,11 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); -void __rxrpc_put_connection(struct rxrpc_connection *); +bool rxrpc_queue_conn(struct rxrpc_connection *); +void rxrpc_see_connection(struct rxrpc_connection *); +void rxrpc_get_connection(struct rxrpc_connection *); +struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); +void rxrpc_put_service_conn(struct rxrpc_connection *); void __exit rxrpc_destroy_all_connections(void); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) @@ -695,39 +980,15 @@ static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) return !rxrpc_conn_is_client(conn); } -static inline void rxrpc_get_connection(struct rxrpc_connection *conn) -{ - atomic_inc(&conn->usage); -} - -static inline -struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *conn) -{ - return atomic_inc_not_zero(&conn->usage) ? conn : NULL; -} - static inline void rxrpc_put_connection(struct rxrpc_connection *conn) { if (!conn) return; - if (rxrpc_conn_is_client(conn)) { - if (atomic_dec_and_test(&conn->usage)) - rxrpc_put_client_conn(conn); - } else { - if (atomic_dec_return(&conn->usage) == 1) - __rxrpc_put_connection(conn); - } -} - - -static inline bool rxrpc_queue_conn(struct rxrpc_connection *conn) -{ - if (!rxrpc_get_connection_maybe(conn)) - return false; - if (!rxrpc_queue_work(&conn->processor)) - rxrpc_put_connection(conn); - return true; + if (rxrpc_conn_is_client(conn)) + rxrpc_put_client_conn(conn); + else + rxrpc_put_service_conn(conn); } /* @@ -735,17 +996,14 @@ static inline bool rxrpc_queue_conn(struct rxrpc_connection *conn) */ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); -struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *, - struct sockaddr_rxrpc *, - struct sk_buff *); +struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t); +void rxrpc_new_incoming_connection(struct rxrpc_connection *, struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ void rxrpc_data_ready(struct sock *); -int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool); -void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); /* * insecure.c @@ -809,21 +1067,22 @@ extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; extern unsigned int rxrpc_resend_timeout; -extern const char *const rxrpc_pkts[]; extern const s8 rxrpc_ack_priority[]; -extern const char *rxrpc_acks(u8 reason); - /* * output.c */ -int rxrpc_send_data_packet(struct rxrpc_connection *, struct sk_buff *); +int rxrpc_send_call_packet(struct rxrpc_call *, u8); +int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *); +void rxrpc_reject_packets(struct rxrpc_local *); /* * peer_event.c */ void rxrpc_error_report(struct sock *); void rxrpc_peer_error_distributor(struct work_struct *); +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, + rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); /* * peer_object.c @@ -833,6 +1092,8 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); +struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *, + struct rxrpc_peer *); static inline struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) { @@ -862,7 +1123,7 @@ extern const struct file_operations rxrpc_connection_seq_fops; /* * recvmsg.c */ -void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *); +void rxrpc_notify_socket(struct rxrpc_call *); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* @@ -879,7 +1140,7 @@ int __init rxrpc_init_security(void); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); int rxrpc_init_server_conn_security(struct rxrpc_connection *); - + /* * sendmsg.c */ @@ -890,10 +1151,11 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_packet_destructor(struct sk_buff *); -void rxrpc_new_skb(struct sk_buff *); -void rxrpc_see_skb(struct sk_buff *); -void rxrpc_get_skb(struct sk_buff *); -void rxrpc_free_skb(struct sk_buff *); +void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_lose_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* @@ -912,6 +1174,23 @@ static inline void rxrpc_sysctl_exit(void) {} */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); +static inline bool before(u32 seq1, u32 seq2) +{ + return (s32)(seq1 - seq2) < 0; +} +static inline bool before_eq(u32 seq1, u32 seq2) +{ + return (s32)(seq1 - seq2) <= 0; +} +static inline bool after(u32 seq1, u32 seq2) +{ + return (s32)(seq1 - seq2) > 0; +} +static inline bool after_eq(u32 seq1, u32 seq2) +{ + return (s32)(seq1 - seq2) >= 0; +} + /* * debug tracing */ @@ -994,11 +1273,12 @@ do { \ #define ASSERTCMP(X, OP, Y) \ do { \ - unsigned long _x = (unsigned long)(X); \ - unsigned long _y = (unsigned long)(Y); \ + __typeof__(X) _x = (X); \ + __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely(!(_x OP _y))) { \ - pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ - _x, _x, #OP, _y, _y); \ + pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ + (unsigned long)_x, (unsigned long)_x, #OP, \ + (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) @@ -1013,11 +1293,12 @@ do { \ #define ASSERTIFCMP(C, X, OP, Y) \ do { \ - unsigned long _x = (unsigned long)(X); \ - unsigned long _y = (unsigned long)(Y); \ + __typeof__(X) _x = (X); \ + __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely((C) && !(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ - _x, _x, #OP, _y, _y); \ + (unsigned long)_x, (unsigned long)_x, #OP, \ + (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 68a439e..a8d39d7 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -20,265 +20,409 @@ #include <linux/in6.h> #include <linux/icmp.h> #include <linux/gfp.h> +#include <linux/circ_buf.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> #include "ar-internal.h" /* - * generate a connection-level abort + * Preallocate a single service call, connection and peer and, if possible, + * give them a user ID and attach the user's side of the ID to them. */ -static int rxrpc_busy(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, - struct rxrpc_wire_header *whdr) +static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, + struct rxrpc_backlog *b, + rxrpc_notify_rx_t notify_rx, + rxrpc_user_attach_call_t user_attach_call, + unsigned long user_call_ID, gfp_t gfp) { - struct msghdr msg; - struct kvec iov[1]; - size_t len; - int ret; + const void *here = __builtin_return_address(0); + struct rxrpc_call *call; + int max, tmp; + unsigned int size = RXRPC_BACKLOG_MAX; + unsigned int head, tail, call_head, call_tail; + + max = rx->sk.sk_max_ack_backlog; + tmp = rx->sk.sk_ack_backlog; + if (tmp >= max) { + _leave(" = -ENOBUFS [full %u]", max); + return -ENOBUFS; + } + max -= tmp; + + /* We don't need more conns and peers than we have calls, but on the + * other hand, we shouldn't ever use more peers than conns or conns + * than calls. + */ + call_head = b->call_backlog_head; + call_tail = READ_ONCE(b->call_backlog_tail); + tmp = CIRC_CNT(call_head, call_tail, size); + if (tmp >= max) { + _leave(" = -ENOBUFS [enough %u]", tmp); + return -ENOBUFS; + } + max = tmp + 1; + + head = b->peer_backlog_head; + tail = READ_ONCE(b->peer_backlog_tail); + if (CIRC_CNT(head, tail, size) < max) { + struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp); + if (!peer) + return -ENOMEM; + b->peer_backlog[head] = peer; + smp_store_release(&b->peer_backlog_head, + (head + 1) & (size - 1)); + } - _enter("%d,,", local->debug_id); + head = b->conn_backlog_head; + tail = READ_ONCE(b->conn_backlog_tail); + if (CIRC_CNT(head, tail, size) < max) { + struct rxrpc_connection *conn; - whdr->type = RXRPC_PACKET_TYPE_BUSY; - whdr->serial = htonl(1); + conn = rxrpc_prealloc_service_connection(gfp); + if (!conn) + return -ENOMEM; + b->conn_backlog[head] = conn; + smp_store_release(&b->conn_backlog_head, + (head + 1) & (size - 1)); - msg.msg_name = &srx->transport.sin; - msg.msg_namelen = sizeof(srx->transport.sin); - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; + trace_rxrpc_conn(conn, rxrpc_conn_new_service, + atomic_read(&conn->usage), here); + } - iov[0].iov_base = whdr; - iov[0].iov_len = sizeof(*whdr); + /* Now it gets complicated, because calls get registered with the + * socket here, particularly if a user ID is preassigned by the user. + */ + call = rxrpc_alloc_call(gfp); + if (!call) + return -ENOMEM; + call->flags |= (1 << RXRPC_CALL_IS_SERVICE); + call->state = RXRPC_CALL_SERVER_PREALLOC; - len = iov[0].iov_len; + trace_rxrpc_call(call, rxrpc_call_new_service, + atomic_read(&call->usage), + here, (const void *)user_call_ID); - _proto("Tx BUSY %%1"); + write_lock(&rx->call_lock); + if (user_attach_call) { + struct rxrpc_call *xcall; + struct rb_node *parent, **pp; + + /* Check the user ID isn't already in use */ + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + xcall = rb_entry(parent, struct rxrpc_call, sock_node); + if (user_call_ID < call->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > call->user_call_ID) + pp = &(*pp)->rb_right; + else + goto id_in_use; + } - ret = kernel_sendmsg(local->socket, &msg, iov, 1, len); - if (ret < 0) { - _leave(" = -EAGAIN [sendmsg failed: %d]", ret); - return -EAGAIN; + call->user_call_ID = user_call_ID; + call->notify_rx = notify_rx; + rxrpc_get_call(call, rxrpc_call_got_kernel); + user_attach_call(call, user_call_ID); + rxrpc_get_call(call, rxrpc_call_got_userid); + rb_link_node(&call->sock_node, parent, pp); + rb_insert_color(&call->sock_node, &rx->calls); + set_bit(RXRPC_CALL_HAS_USERID, &call->flags); } - _leave(" = 0"); + list_add(&call->sock_link, &rx->sock_calls); + + write_unlock(&rx->call_lock); + + write_lock(&rxrpc_call_lock); + list_add_tail(&call->link, &rxrpc_calls); + write_unlock(&rxrpc_call_lock); + + b->call_backlog[call_head] = call; + smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1)); + _leave(" = 0 [%d -> %lx]", call->debug_id, user_call_ID); return 0; + +id_in_use: + write_unlock(&rx->call_lock); + rxrpc_cleanup_call(call); + _leave(" = -EBADSLT"); + return -EBADSLT; } /* - * accept an incoming call that needs peer, transport and/or connection setting - * up + * Preallocate sufficient service connections, calls and peers to cover the + * entire backlog of a socket. When a new call comes in, if we don't have + * sufficient of each available, the call gets rejected as busy or ignored. + * + * The backlog is replenished when a connection is accepted or rejected. */ -static int rxrpc_accept_incoming_call(struct rxrpc_local *local, - struct rxrpc_sock *rx, - struct sk_buff *skb, - struct sockaddr_rxrpc *srx) +int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) { - struct rxrpc_connection *conn; - struct rxrpc_skb_priv *sp, *nsp; - struct rxrpc_call *call; - struct sk_buff *notification; - int ret; + struct rxrpc_backlog *b = rx->backlog; - _enter(""); + if (!b) { + b = kzalloc(sizeof(struct rxrpc_backlog), gfp); + if (!b) + return -ENOMEM; + rx->backlog = b; + } + + if (rx->discard_new_call) + return 0; + + while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp) == 0) + ; - sp = rxrpc_skb(skb); + return 0; +} - /* get a notification message to send to the server app */ - notification = alloc_skb(0, GFP_NOFS); - if (!notification) { - _debug("no memory"); - ret = -ENOMEM; - goto error_nofree; +/* + * Discard the preallocation on a service. + */ +void rxrpc_discard_prealloc(struct rxrpc_sock *rx) +{ + struct rxrpc_backlog *b = rx->backlog; + unsigned int size = RXRPC_BACKLOG_MAX, head, tail; + + if (!b) + return; + rx->backlog = NULL; + + /* Make sure that there aren't any incoming calls in progress before we + * clear the preallocation buffers. + */ + spin_lock_bh(&rx->incoming_lock); + spin_unlock_bh(&rx->incoming_lock); + + head = b->peer_backlog_head; + tail = b->peer_backlog_tail; + while (CIRC_CNT(head, tail, size) > 0) { + struct rxrpc_peer *peer = b->peer_backlog[tail]; + kfree(peer); + tail = (tail + 1) & (size - 1); } - rxrpc_new_skb(notification); - notification->mark = RXRPC_SKB_MARK_NEW_CALL; - - conn = rxrpc_incoming_connection(local, srx, skb); - if (IS_ERR(conn)) { - _debug("no conn"); - ret = PTR_ERR(conn); - goto error; + + head = b->conn_backlog_head; + tail = b->conn_backlog_tail; + while (CIRC_CNT(head, tail, size) > 0) { + struct rxrpc_connection *conn = b->conn_backlog[tail]; + write_lock(&rxrpc_connection_lock); + list_del(&conn->link); + list_del(&conn->proc_link); + write_unlock(&rxrpc_connection_lock); + kfree(conn); + tail = (tail + 1) & (size - 1); } - call = rxrpc_incoming_call(rx, conn, skb); - rxrpc_put_connection(conn); - if (IS_ERR(call)) { - _debug("no call"); - ret = PTR_ERR(call); - goto error; + head = b->call_backlog_head; + tail = b->call_backlog_tail; + while (CIRC_CNT(head, tail, size) > 0) { + struct rxrpc_call *call = b->call_backlog[tail]; + if (rx->discard_new_call) { + _debug("discard %lx", call->user_call_ID); + rx->discard_new_call(call, call->user_call_ID); + rxrpc_put_call(call, rxrpc_call_put_kernel); + } + rxrpc_call_completed(call); + rxrpc_release_call(rx, call); + rxrpc_put_call(call, rxrpc_call_put); + tail = (tail + 1) & (size - 1); } - /* attach the call to the socket */ - read_lock_bh(&local->services_lock); - if (rx->sk.sk_state == RXRPC_CLOSE) - goto invalid_service; + kfree(b); +} - write_lock(&rx->call_lock); - if (!test_and_set_bit(RXRPC_CALL_INIT_ACCEPT, &call->flags)) { - rxrpc_get_call(call); - - spin_lock(&call->conn->state_lock); - if (sp->hdr.securityIndex > 0 && - call->conn->state == RXRPC_CONN_SERVICE_UNSECURED) { - _debug("await conn sec"); - list_add_tail(&call->accept_link, &rx->secureq); - call->conn->state = RXRPC_CONN_SERVICE_CHALLENGING; - set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); - rxrpc_queue_conn(call->conn); - } else { - _debug("conn ready"); - call->state = RXRPC_CALL_SERVER_ACCEPTING; - list_add_tail(&call->accept_link, &rx->acceptq); - rxrpc_get_call_for_skb(call, notification); - nsp = rxrpc_skb(notification); - nsp->call = call; - - ASSERTCMP(atomic_read(&call->usage), >=, 3); - - _debug("notify"); - spin_lock(&call->lock); - ret = rxrpc_queue_rcv_skb(call, notification, true, - false); - spin_unlock(&call->lock); - notification = NULL; - BUG_ON(ret < 0); +/* + * Allocate a new incoming call from the prealloc pool, along with a connection + * and a peer as necessary. + */ +static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, + struct rxrpc_local *local, + struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_backlog *b = rx->backlog; + struct rxrpc_peer *peer, *xpeer; + struct rxrpc_call *call; + unsigned short call_head, conn_head, peer_head; + unsigned short call_tail, conn_tail, peer_tail; + unsigned short call_count, conn_count; + + /* #calls >= #conns >= #peers must hold true. */ + call_head = smp_load_acquire(&b->call_backlog_head); + call_tail = b->call_backlog_tail; + call_count = CIRC_CNT(call_head, call_tail, RXRPC_BACKLOG_MAX); + conn_head = smp_load_acquire(&b->conn_backlog_head); + conn_tail = b->conn_backlog_tail; + conn_count = CIRC_CNT(conn_head, conn_tail, RXRPC_BACKLOG_MAX); + ASSERTCMP(conn_count, >=, call_count); + peer_head = smp_load_acquire(&b->peer_backlog_head); + peer_tail = b->peer_backlog_tail; + ASSERTCMP(CIRC_CNT(peer_head, peer_tail, RXRPC_BACKLOG_MAX), >=, + conn_count); + + if (call_count == 0) + return NULL; + + if (!conn) { + /* No connection. We're going to need a peer to start off + * with. If one doesn't yet exist, use a spare from the + * preallocation set. We dump the address into the spare in + * anticipation - and to save on stack space. + */ + xpeer = b->peer_backlog[peer_tail]; + if (rxrpc_extract_addr_from_skb(&xpeer->srx, skb) < 0) + return NULL; + + peer = rxrpc_lookup_incoming_peer(local, xpeer); + if (peer == xpeer) { + b->peer_backlog[peer_tail] = NULL; + smp_store_release(&b->peer_backlog_tail, + (peer_tail + 1) & + (RXRPC_BACKLOG_MAX - 1)); } - spin_unlock(&call->conn->state_lock); - _debug("queued"); + /* Now allocate and set up the connection */ + conn = b->conn_backlog[conn_tail]; + b->conn_backlog[conn_tail] = NULL; + smp_store_release(&b->conn_backlog_tail, + (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); + rxrpc_get_local(local); + conn->params.local = local; + conn->params.peer = peer; + rxrpc_see_connection(conn); + rxrpc_new_incoming_connection(conn, skb); + } else { + rxrpc_get_connection(conn); } - write_unlock(&rx->call_lock); - _debug("process"); - rxrpc_fast_process_packet(call, skb); + /* And now we can allocate and set up a new call */ + call = b->call_backlog[call_tail]; + b->call_backlog[call_tail] = NULL; + smp_store_release(&b->call_backlog_tail, + (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - _debug("done"); - read_unlock_bh(&local->services_lock); - rxrpc_free_skb(notification); - rxrpc_put_call(call); - _leave(" = 0"); - return 0; - -invalid_service: - _debug("invalid"); - read_unlock_bh(&local->services_lock); - - read_lock_bh(&call->state_lock); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { - rxrpc_get_call(call); - rxrpc_queue_call(call); - } - read_unlock_bh(&call->state_lock); - rxrpc_put_call(call); - ret = -ECONNREFUSED; -error: - rxrpc_free_skb(notification); -error_nofree: - _leave(" = %d", ret); - return ret; + rxrpc_see_call(call); + call->conn = conn; + call->peer = rxrpc_get_peer(conn->params.peer); + return call; } /* - * accept incoming calls that need peer, transport and/or connection setting up - * - the packets we get are all incoming client DATA packets that have seq == 1 + * Set up a new incoming call. Called in BH context with the RCU read lock + * held. + * + * If this is for a kernel service, when we allocate the call, it will have + * three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the + * retainer ref obtained from the backlog buffer. Prealloc calls for userspace + * services only have the ref from the backlog buffer. We want to pass this + * ref to non-BH context to dispose of. + * + * If we want to report an error, we mark the skb with the packet type and + * abort code and return NULL. */ -void rxrpc_accept_incoming_calls(struct rxrpc_local *local) +struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_connection *conn, + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp; - struct sockaddr_rxrpc srx; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_sock *rx; - struct rxrpc_wire_header whdr; - struct sk_buff *skb; - int ret; - - _enter("%d", local->debug_id); + struct rxrpc_call *call; - skb = skb_dequeue(&local->accept_queue); - if (!skb) { - _leave("\n"); - return; - } + _enter(""); - _net("incoming call skb %p", skb); - - rxrpc_see_skb(skb); - sp = rxrpc_skb(skb); - - /* Set up a response packet header in case we need it */ - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = 0; - whdr.flags = 0; - whdr.type = 0; - whdr.userStatus = 0; - whdr.securityIndex = sp->hdr.securityIndex; - whdr._rsvd = 0; - whdr.serviceId = htons(sp->hdr.serviceId); - - if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) - goto drop; - - /* get the socket providing the service */ - read_lock_bh(&local->services_lock); - list_for_each_entry(rx, &local->services, listen_link) { - if (rx->srx.srx_service == sp->hdr.serviceId && - rx->sk.sk_state != RXRPC_CLOSE) + /* Get the socket providing the service */ + hlist_for_each_entry_rcu_bh(rx, &local->services, listen_link) { + if (rx->srx.srx_service == sp->hdr.serviceId) goto found_service; } - read_unlock_bh(&local->services_lock); - goto invalid_service; + + trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EOPNOTSUPP); + skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->priority = RX_INVALID_OPERATION; + _leave(" = NULL [service]"); + return NULL; found_service: - _debug("found service %hd", rx->srx.srx_service); - if (sk_acceptq_is_full(&rx->sk)) - goto backlog_full; - sk_acceptq_added(&rx->sk); - sock_hold(&rx->sk); - read_unlock_bh(&local->services_lock); - - ret = rxrpc_accept_incoming_call(local, rx, skb, &srx); - if (ret < 0) - sk_acceptq_removed(&rx->sk); - sock_put(&rx->sk); - switch (ret) { - case -ECONNRESET: /* old calls are ignored */ - case -ECONNABORTED: /* aborted calls are reaborted or ignored */ - case 0: - return; - case -ECONNREFUSED: - goto invalid_service; - case -EBUSY: - goto busy; - case -EKEYREJECTED: - goto security_mismatch; + spin_lock(&rx->incoming_lock); + if (rx->sk.sk_state == RXRPC_CLOSE) { + trace_rxrpc_abort("CLS", sp->hdr.cid, sp->hdr.callNumber, + sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); + skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->priority = RX_INVALID_OPERATION; + _leave(" = NULL [close]"); + call = NULL; + goto out; + } + + call = rxrpc_alloc_incoming_call(rx, local, conn, skb); + if (!call) { + skb->mark = RXRPC_SKB_MARK_BUSY; + _leave(" = NULL [busy]"); + call = NULL; + goto out; + } + + trace_rxrpc_receive(call, rxrpc_receive_incoming, + sp->hdr.serial, sp->hdr.seq); + + /* Make the call live. */ + rxrpc_incoming_call(rx, call, skb); + conn = call->conn; + + if (rx->notify_new_call) + rx->notify_new_call(&rx->sk, call, call->user_call_ID); + else + sk_acceptq_added(&rx->sk); + + spin_lock(&conn->state_lock); + switch (conn->state) { + case RXRPC_CONN_SERVICE_UNSECURED: + conn->state = RXRPC_CONN_SERVICE_CHALLENGING; + set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); + rxrpc_queue_conn(call->conn); + break; + + case RXRPC_CONN_SERVICE: + write_lock(&call->state_lock); + if (rx->discard_new_call) + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + else + call->state = RXRPC_CALL_SERVER_ACCEPTING; + write_unlock(&call->state_lock); + break; + + case RXRPC_CONN_REMOTELY_ABORTED: + rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + conn->remote_abort, ECONNABORTED); + break; + case RXRPC_CONN_LOCALLY_ABORTED: + rxrpc_abort_call("CON", call, sp->hdr.seq, + conn->local_abort, ECONNABORTED); + break; default: BUG(); } + spin_unlock(&conn->state_lock); -backlog_full: - read_unlock_bh(&local->services_lock); -busy: - rxrpc_busy(local, &srx, &whdr); - rxrpc_free_skb(skb); - return; + if (call->state == RXRPC_CALL_SERVER_ACCEPTING) + rxrpc_notify_socket(call); -drop: - rxrpc_free_skb(skb); - return; + /* We have to discard the prealloc queue's ref here and rely on a + * combination of the RCU read lock and refs held either by the socket + * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel + * service to prevent the call from being deallocated too early. + */ + rxrpc_put_call(call, rxrpc_call_put); -invalid_service: - skb->priority = RX_INVALID_OPERATION; - rxrpc_reject_packet(local, skb); - return; - - /* can't change connection security type mid-flow */ -security_mismatch: - skb->priority = RX_PROTOCOL_ERROR; - rxrpc_reject_packet(local, skb); - return; + _leave(" = %p{%d}", call, call->debug_id); +out: + spin_unlock(&rx->incoming_lock); + return call; } /* @@ -299,12 +443,13 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, write_lock(&rx->call_lock); - ret = -ENODATA; - if (list_empty(&rx->acceptq)) - goto out; + if (list_empty(&rx->to_be_accepted)) { + write_unlock(&rx->call_lock); + kleave(" = -ENODATA [empty]"); + return ERR_PTR(-ENODATA); + } /* check the user ID isn't already in use */ - ret = -EBADSLT; pp = &rx->calls.rb_node; parent = NULL; while (*pp) { @@ -316,11 +461,14 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, else if (user_call_ID > call->user_call_ID) pp = &(*pp)->rb_right; else - goto out; + goto id_in_use; } - /* dequeue the first call and check it's still valid */ - call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); + /* Dequeue the first call and check it's still valid. We gain + * responsibility for the queue's reference. + */ + call = list_entry(rx->to_be_accepted.next, + struct rxrpc_call, accept_link); list_del_init(&call->accept_link); sk_acceptq_removed(&rx->sk); rxrpc_see_call(call); @@ -333,9 +481,6 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, case RXRPC_CALL_COMPLETE: ret = call->error; goto out_release; - case RXRPC_CALL_DEAD: - ret = -ETIME; - goto out_discard; default: BUG(); } @@ -343,33 +488,32 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, /* formalise the acceptance */ call->notify_rx = notify_rx; call->user_call_ID = user_call_ID; + rxrpc_get_call(call, rxrpc_call_got_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags)) BUG(); - if (test_and_set_bit(RXRPC_CALL_EV_ACCEPTED, &call->events)) - BUG(); - rxrpc_queue_call(call); - rxrpc_get_call(call); write_unlock_bh(&call->state_lock); write_unlock(&rx->call_lock); + rxrpc_notify_socket(call); + rxrpc_service_prealloc(rx, GFP_KERNEL); _leave(" = %p{%d}", call, call->debug_id); return call; - /* if the call is already dying or dead, then we leave the socket's ref - * on it to be released by rxrpc_dead_call_expired() as induced by - * rxrpc_release_call() */ out_release: _debug("release %p", call); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) - rxrpc_queue_call(call); -out_discard: write_unlock_bh(&call->state_lock); - _debug("discard %p", call); -out: write_unlock(&rx->call_lock); + rxrpc_release_call(rx, call); + rxrpc_put_call(call, rxrpc_call_put); + goto out; + +id_in_use: + ret = -EBADSLT; + write_unlock(&rx->call_lock); +out: + rxrpc_service_prealloc(rx, GFP_KERNEL); _leave(" = %d", ret); return ERR_PTR(ret); } @@ -381,6 +525,7 @@ out: int rxrpc_reject_call(struct rxrpc_sock *rx) { struct rxrpc_call *call; + bool abort = false; int ret; _enter(""); @@ -389,12 +534,16 @@ int rxrpc_reject_call(struct rxrpc_sock *rx) write_lock(&rx->call_lock); - ret = -ENODATA; - if (list_empty(&rx->acceptq)) - goto out; + if (list_empty(&rx->to_be_accepted)) { + write_unlock(&rx->call_lock); + return -ENODATA; + } - /* dequeue the first call and check it's still valid */ - call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); + /* Dequeue the first call and check it's still valid. We gain + * responsibility for the queue's reference. + */ + call = list_entry(rx->to_be_accepted.next, + struct rxrpc_call, accept_link); list_del_init(&call->accept_link); sk_acceptq_removed(&rx->sk); rxrpc_see_call(call); @@ -402,76 +551,56 @@ int rxrpc_reject_call(struct rxrpc_sock *rx) write_lock_bh(&call->state_lock); switch (call->state) { case RXRPC_CALL_SERVER_ACCEPTING: - __rxrpc_set_call_completion(call, RXRPC_CALL_SERVER_BUSY, - 0, ECONNABORTED); - if (test_and_set_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) - rxrpc_queue_call(call); - ret = 0; - goto out_release; + __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, ECONNABORTED); + abort = true; + /* fall through */ case RXRPC_CALL_COMPLETE: ret = call->error; - goto out_release; - case RXRPC_CALL_DEAD: - ret = -ETIME; goto out_discard; default: BUG(); } - /* if the call is already dying or dead, then we leave the socket's ref - * on it to be released by rxrpc_dead_call_expired() as induced by - * rxrpc_release_call() */ -out_release: - _debug("release %p", call); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) - rxrpc_queue_call(call); out_discard: write_unlock_bh(&call->state_lock); - _debug("discard %p", call); -out: write_unlock(&rx->call_lock); + if (abort) { + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_release_call(rx, call); + rxrpc_put_call(call, rxrpc_call_put); + } + rxrpc_service_prealloc(rx, GFP_KERNEL); _leave(" = %d", ret); return ret; } -/** - * rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call - * @sock: The socket on which the impending call is waiting - * @user_call_ID: The tag to attach to the call - * @notify_rx: Where to send notifications instead of socket queue +/* + * rxrpc_kernel_charge_accept - Charge up socket with preallocated calls + * @sock: The socket on which to preallocate + * @notify_rx: Event notification function for the call + * @user_attach_call: Func to attach call to user_call_ID + * @user_call_ID: The tag to attach to the preallocated call + * @gfp: The allocation conditions. * - * Allow a kernel service to accept an incoming call, assuming the incoming - * call is still valid. The caller should immediately trigger their own - * notification as there must be data waiting. - */ -struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock, - unsigned long user_call_ID, - rxrpc_notify_rx_t notify_rx) -{ - struct rxrpc_call *call; - - _enter(",%lx", user_call_ID); - call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID, notify_rx); - _leave(" = %p", call); - return call; -} -EXPORT_SYMBOL(rxrpc_kernel_accept_call); - -/** - * rxrpc_kernel_reject_call - Allow a kernel service to reject an incoming call - * @sock: The socket on which the impending call is waiting + * Charge up the socket with preallocated calls, each with a user ID. A + * function should be provided to effect the attachment from the user's side. + * The user is given a ref to hold on the call. * - * Allow a kernel service to reject an incoming call with a BUSY message, - * assuming the incoming call is still valid. + * Note that the call may be come connected before this function returns. */ -int rxrpc_kernel_reject_call(struct socket *sock) +int rxrpc_kernel_charge_accept(struct socket *sock, + rxrpc_notify_rx_t notify_rx, + rxrpc_user_attach_call_t user_attach_call, + unsigned long user_call_ID, gfp_t gfp) { - int ret; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + struct rxrpc_backlog *b = rx->backlog; - _enter(""); - ret = rxrpc_reject_call(rxrpc_sk(sock->sk)); - _leave(" = %d", ret); - return ret; + if (sock->sk->sk_state == RXRPC_CLOSE) + return -ESHUTDOWN; + + return rxrpc_service_prealloc_one(rx, b, notify_rx, + user_attach_call, user_call_ID, + gfp); } -EXPORT_SYMBOL(rxrpc_kernel_reject_call); +EXPORT_SYMBOL(rxrpc_kernel_charge_accept); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 4754c7f..0e84780 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -22,1270 +22,336 @@ #include "ar-internal.h" /* - * propose an ACK be sent + * Set the timer */ -void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate) +void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why) { - unsigned long expiry; - s8 prior = rxrpc_ack_priority[ack_reason]; + unsigned long t, now = jiffies; - ASSERTCMP(prior, >, 0); + read_lock_bh(&call->state_lock); - _enter("{%d},%s,%%%x,%u", - call->debug_id, rxrpc_acks(ack_reason), serial, immediate); + if (call->state < RXRPC_CALL_COMPLETE) { + t = call->expire_at; + if (time_before_eq(t, now)) + goto out; - if (prior < rxrpc_ack_priority[call->ackr_reason]) { - if (immediate) - goto cancel_timer; - return; - } + if (time_after(call->resend_at, now) && + time_before(call->resend_at, t)) + t = call->resend_at; - /* update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial - * numbers */ - if (prior == rxrpc_ack_priority[call->ackr_reason]) { - if (prior <= 4) { - call->ackr_skew = skew; - call->ackr_serial = serial; - } - if (immediate) - goto cancel_timer; - return; - } - - call->ackr_reason = ack_reason; - call->ackr_serial = serial; + if (time_after(call->ack_at, now) && + time_before(call->ack_at, t)) + t = call->ack_at; - switch (ack_reason) { - case RXRPC_ACK_DELAY: - _debug("run delay timer"); - expiry = rxrpc_soft_ack_delay; - goto run_timer; - - case RXRPC_ACK_IDLE: - if (!immediate) { - _debug("run defer timer"); - expiry = rxrpc_idle_ack_delay; - goto run_timer; - } - goto cancel_timer; - - case RXRPC_ACK_REQUESTED: - expiry = rxrpc_requested_ack_delay; - if (!expiry) - goto cancel_timer; - if (!immediate || serial == 1) { - _debug("run defer timer"); - goto run_timer; + if (call->timer.expires != t || !timer_pending(&call->timer)) { + mod_timer(&call->timer, t); + trace_rxrpc_timer(call, why, now); } - - default: - _debug("immediate ACK"); - goto cancel_timer; } -run_timer: - expiry += jiffies; - if (!timer_pending(&call->ack_timer) || - time_after(call->ack_timer.expires, expiry)) - mod_timer(&call->ack_timer, expiry); - return; - -cancel_timer: - _debug("cancel timer %%%u", serial); - try_to_del_timer_sync(&call->ack_timer); - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE && - !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) - rxrpc_queue_call(call); +out: read_unlock_bh(&call->state_lock); } /* - * propose an ACK be sent, locking the call structure + * propose an ACK be sent */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate) +static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, + u16 skew, u32 serial, bool immediate, + bool background, + enum rxrpc_propose_ack_trace why) { + enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; + unsigned long now, ack_at, expiry = rxrpc_soft_ack_delay; s8 prior = rxrpc_ack_priority[ack_reason]; - if (prior > rxrpc_ack_priority[call->ackr_reason]) { - spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, skew, serial, immediate); - spin_unlock_bh(&call->lock); - } -} - -/* - * set the resend timer - */ -static void rxrpc_set_resend(struct rxrpc_call *call, u8 resend, - unsigned long resend_at) -{ - read_lock_bh(&call->state_lock); - if (call->state == RXRPC_CALL_COMPLETE) - resend = 0; - - if (resend & 1) { - _debug("SET RESEND"); - set_bit(RXRPC_CALL_EV_RESEND, &call->events); - } - - if (resend & 2) { - _debug("MODIFY RESEND TIMER"); - set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - mod_timer(&call->resend_timer, resend_at); - } else { - _debug("KILL RESEND TIMER"); - del_timer_sync(&call->resend_timer); - clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - } - read_unlock_bh(&call->state_lock); -} - -/* - * resend packets - */ -static void rxrpc_resend(struct rxrpc_call *call) -{ - struct rxrpc_wire_header *whdr; - struct rxrpc_skb_priv *sp; - struct sk_buff *txb; - unsigned long *p_txb, resend_at; - bool stop; - int loop; - u8 resend; - - _enter("{%d,%d,%d,%d},", - call->acks_hard, call->acks_unacked, - atomic_read(&call->sequence), - CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz)); - - stop = false; - resend = 0; - resend_at = 0; - - for (loop = call->acks_tail; - loop != call->acks_head || stop; - loop = (loop + 1) & (call->acks_winsz - 1) - ) { - p_txb = call->acks_window + loop; - smp_read_barrier_depends(); - if (*p_txb & 1) - continue; - - txb = (struct sk_buff *) *p_txb; - sp = rxrpc_skb(txb); - - if (sp->need_resend) { - sp->need_resend = false; - - /* each Tx packet has a new serial number */ - sp->hdr.serial = atomic_inc_return(&call->conn->serial); - - whdr = (struct rxrpc_wire_header *)txb->head; - whdr->serial = htonl(sp->hdr.serial); - - _proto("Tx DATA %%%u { #%d }", - sp->hdr.serial, sp->hdr.seq); - if (rxrpc_send_data_packet(call->conn, txb) < 0) { - stop = true; - sp->resend_at = jiffies + 3; - } else { - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - sp->resend_at = - jiffies + rxrpc_resend_timeout; - } - } - - if (time_after_eq(jiffies + 1, sp->resend_at)) { - sp->need_resend = true; - resend |= 1; - } else if (resend & 2) { - if (time_before(sp->resend_at, resend_at)) - resend_at = sp->resend_at; - } else { - resend_at = sp->resend_at; - resend |= 2; - } - } - - rxrpc_set_resend(call, resend, resend_at); - _leave(""); -} - -/* - * handle resend timer expiry - */ -static void rxrpc_resend_timer(struct rxrpc_call *call) -{ - struct rxrpc_skb_priv *sp; - struct sk_buff *txb; - unsigned long *p_txb, resend_at; - int loop; - u8 resend; - - _enter("%d,%d,%d", - call->acks_tail, call->acks_unacked, call->acks_head); - - if (call->state == RXRPC_CALL_COMPLETE) - return; - - resend = 0; - resend_at = 0; - - for (loop = call->acks_unacked; - loop != call->acks_head; - loop = (loop + 1) & (call->acks_winsz - 1) - ) { - p_txb = call->acks_window + loop; - smp_read_barrier_depends(); - txb = (struct sk_buff *) (*p_txb & ~1); - sp = rxrpc_skb(txb); - - ASSERT(!(*p_txb & 1)); - - if (sp->need_resend) { - ; - } else if (time_after_eq(jiffies + 1, sp->resend_at)) { - sp->need_resend = true; - resend |= 1; - } else if (resend & 2) { - if (time_before(sp->resend_at, resend_at)) - resend_at = sp->resend_at; - } else { - resend_at = sp->resend_at; - resend |= 2; - } - } - - rxrpc_set_resend(call, resend, resend_at); - _leave(""); -} - -/* - * process soft ACKs of our transmitted packets - * - these indicate packets the peer has or has not received, but hasn't yet - * given to the consumer, and so can still be discarded and re-requested - */ -static int rxrpc_process_soft_ACKs(struct rxrpc_call *call, - struct rxrpc_ackpacket *ack, - struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp; - struct sk_buff *txb; - unsigned long *p_txb, resend_at; - int loop; - u8 sacks[RXRPC_MAXACKS], resend; - - _enter("{%d,%d},{%d},", - call->acks_hard, - CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz), - ack->nAcks); - - if (skb_copy_bits(skb, 0, sacks, ack->nAcks) < 0) - goto protocol_error; - - resend = 0; - resend_at = 0; - for (loop = 0; loop < ack->nAcks; loop++) { - p_txb = call->acks_window; - p_txb += (call->acks_tail + loop) & (call->acks_winsz - 1); - smp_read_barrier_depends(); - txb = (struct sk_buff *) (*p_txb & ~1); - sp = rxrpc_skb(txb); - - switch (sacks[loop]) { - case RXRPC_ACK_TYPE_ACK: - sp->need_resend = false; - *p_txb |= 1; - break; - case RXRPC_ACK_TYPE_NACK: - sp->need_resend = true; - *p_txb &= ~1; - resend = 1; - break; - default: - _debug("Unsupported ACK type %d", sacks[loop]); - goto protocol_error; - } - } - - smp_mb(); - call->acks_unacked = (call->acks_tail + loop) & (call->acks_winsz - 1); - - /* anything not explicitly ACK'd is implicitly NACK'd, but may just not - * have been received or processed yet by the far end */ - for (loop = call->acks_unacked; - loop != call->acks_head; - loop = (loop + 1) & (call->acks_winsz - 1) - ) { - p_txb = call->acks_window + loop; - smp_read_barrier_depends(); - txb = (struct sk_buff *) (*p_txb & ~1); - sp = rxrpc_skb(txb); - - if (*p_txb & 1) { - /* packet must have been discarded */ - sp->need_resend = true; - *p_txb &= ~1; - resend |= 1; - } else if (sp->need_resend) { - ; - } else if (time_after_eq(jiffies + 1, sp->resend_at)) { - sp->need_resend = true; - resend |= 1; - } else if (resend & 2) { - if (time_before(sp->resend_at, resend_at)) - resend_at = sp->resend_at; - } else { - resend_at = sp->resend_at; - resend |= 2; + /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial + * numbers, but we don't alter the timeout. + */ + _debug("prior %u %u vs %u %u", + ack_reason, prior, + call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]); + if (ack_reason == call->ackr_reason) { + if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { + outcome = rxrpc_propose_ack_update; + call->ackr_serial = serial; + call->ackr_skew = skew; } + if (!immediate) + goto trace; + } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { + call->ackr_reason = ack_reason; + call->ackr_serial = serial; + call->ackr_skew = skew; + } else { + outcome = rxrpc_propose_ack_subsume; } - rxrpc_set_resend(call, resend, resend_at); - _leave(" = 0"); - return 0; - -protocol_error: - _leave(" = -EPROTO"); - return -EPROTO; -} - -/* - * discard hard-ACK'd packets from the Tx window - */ -static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) -{ - unsigned long _skb; - int tail = call->acks_tail, old_tail; - int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz); + switch (ack_reason) { + case RXRPC_ACK_REQUESTED: + if (rxrpc_requested_ack_delay < expiry) + expiry = rxrpc_requested_ack_delay; + if (serial == 1) + immediate = false; + break; - _enter("{%u,%u},%u", call->acks_hard, win, hard); + case RXRPC_ACK_DELAY: + if (rxrpc_soft_ack_delay < expiry) + expiry = rxrpc_soft_ack_delay; + break; - ASSERTCMP(hard - call->acks_hard, <=, win); + case RXRPC_ACK_PING: + case RXRPC_ACK_IDLE: + if (rxrpc_idle_ack_delay < expiry) + expiry = rxrpc_idle_ack_delay; + break; - while (call->acks_hard < hard) { - smp_read_barrier_depends(); - _skb = call->acks_window[tail] & ~1; - rxrpc_free_skb((struct sk_buff *) _skb); - old_tail = tail; - tail = (tail + 1) & (call->acks_winsz - 1); - call->acks_tail = tail; - if (call->acks_unacked == old_tail) - call->acks_unacked = tail; - call->acks_hard++; + default: + immediate = true; + break; } - wake_up(&call->waitq); -} - -/* - * clear the Tx window in the event of a failure - */ -static void rxrpc_clear_tx_window(struct rxrpc_call *call) -{ - rxrpc_rotate_tx_window(call, atomic_read(&call->sequence)); -} - -/* - * drain the out of sequence received packet queue into the packet Rx queue - */ -static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call) -{ - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - bool terminal; - int ret; - - _enter("{%d,%d}", call->rx_data_post, call->rx_first_oos); - - spin_lock_bh(&call->lock); - - ret = -ECONNRESET; - if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) - goto socket_unavailable; - - skb = skb_dequeue(&call->rx_oos_queue); - if (skb) { - rxrpc_see_skb(skb); - sp = rxrpc_skb(skb); - - _debug("drain OOS packet %d [%d]", - sp->hdr.seq, call->rx_first_oos); - - if (sp->hdr.seq != call->rx_first_oos) { - skb_queue_head(&call->rx_oos_queue, skb); - call->rx_first_oos = rxrpc_skb(skb)->hdr.seq; - _debug("requeue %p {%u}", skb, call->rx_first_oos); - } else { - skb->mark = RXRPC_SKB_MARK_DATA; - terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && - !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); - ret = rxrpc_queue_rcv_skb(call, skb, true, terminal); - BUG_ON(ret < 0); - _debug("drain #%u", call->rx_data_post); - call->rx_data_post++; - - /* find out what the next packet is */ - skb = skb_peek(&call->rx_oos_queue); - rxrpc_see_skb(skb); - if (skb) - call->rx_first_oos = rxrpc_skb(skb)->hdr.seq; - else - call->rx_first_oos = 0; - _debug("peek %p {%u}", skb, call->rx_first_oos); + now = jiffies; + if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { + _debug("already scheduled"); + } else if (immediate || expiry == 0) { + _debug("immediate ACK %lx", call->events); + if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) && + background) + rxrpc_queue_call(call); + } else { + ack_at = now + expiry; + _debug("deferred ACK %ld < %ld", expiry, call->ack_at - now); + if (time_before(ack_at, call->ack_at)) { + call->ack_at = ack_at; + rxrpc_set_timer(call, rxrpc_timer_set_for_ack); } } - ret = 0; -socket_unavailable: - spin_unlock_bh(&call->lock); - _leave(" = %d", ret); - return ret; +trace: + trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate, + background, outcome); } /* - * insert an out of sequence packet into the buffer + * propose an ACK be sent, locking the call structure */ -static void rxrpc_insert_oos_packet(struct rxrpc_call *call, - struct sk_buff *skb) +void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, + u16 skew, u32 serial, bool immediate, bool background, + enum rxrpc_propose_ack_trace why) { - struct rxrpc_skb_priv *sp, *psp; - struct sk_buff *p; - u32 seq; - - sp = rxrpc_skb(skb); - seq = sp->hdr.seq; - _enter(",,{%u}", seq); - - skb->destructor = rxrpc_packet_destructor; - ASSERTCMP(sp->call, ==, NULL); - sp->call = call; - rxrpc_get_call_for_skb(call, skb); - - /* insert into the buffer in sequence order */ spin_lock_bh(&call->lock); - - skb_queue_walk(&call->rx_oos_queue, p) { - psp = rxrpc_skb(p); - if (psp->hdr.seq > seq) { - _debug("insert oos #%u before #%u", seq, psp->hdr.seq); - skb_insert(p, skb, &call->rx_oos_queue); - goto inserted; - } - } - - _debug("append oos #%u", seq); - skb_queue_tail(&call->rx_oos_queue, skb); -inserted: - - /* we might now have a new front to the queue */ - if (call->rx_first_oos == 0 || seq < call->rx_first_oos) - call->rx_first_oos = seq; - - read_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE && - call->rx_data_post == call->rx_first_oos) { - _debug("drain rx oos now"); - set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events); - } - read_unlock(&call->state_lock); - + __rxrpc_propose_ACK(call, ack_reason, skew, serial, + immediate, background, why); spin_unlock_bh(&call->lock); - _leave(" [stored #%u]", call->rx_first_oos); -} - -/* - * clear the Tx window on final ACK reception - */ -static void rxrpc_zap_tx_window(struct rxrpc_call *call) -{ - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - unsigned long _skb, *acks_window; - u8 winsz = call->acks_winsz; - int tail; - - acks_window = call->acks_window; - call->acks_window = NULL; - - while (CIRC_CNT(call->acks_head, call->acks_tail, winsz) > 0) { - tail = call->acks_tail; - smp_read_barrier_depends(); - _skb = acks_window[tail] & ~1; - smp_mb(); - call->acks_tail = (call->acks_tail + 1) & (winsz - 1); - - skb = (struct sk_buff *) _skb; - sp = rxrpc_skb(skb); - _debug("+++ clear Tx %u", sp->hdr.seq); - rxrpc_free_skb(skb); - } - - kfree(acks_window); } /* - * process the extra information that may be appended to an ACK packet + * Handle congestion being detected by the retransmit timeout. */ -static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int latest, int nAcks) +static void rxrpc_congestion_timeout(struct rxrpc_call *call) { - struct rxrpc_ackinfo ackinfo; - struct rxrpc_peer *peer; - unsigned int mtu; - - if (skb_copy_bits(skb, nAcks + 3, &ackinfo, sizeof(ackinfo)) < 0) { - _leave(" [no ackinfo]"); - return; - } - - _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", - latest, - ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU), - ntohl(ackinfo.rwind), ntohl(ackinfo.jumbo_max)); - - mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU)); - - peer = call->peer; - if (mtu < peer->maxdata) { - spin_lock_bh(&peer->lock); - peer->maxdata = mtu; - peer->mtu = mtu + peer->hdrsize; - spin_unlock_bh(&peer->lock); - _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata); - } + set_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags); } /* - * process packets in the reception queue + * Perform retransmission of NAK'd and unack'd packets. */ -static int rxrpc_process_rx_queue(struct rxrpc_call *call, - u32 *_abort_code) +static void rxrpc_resend(struct rxrpc_call *call) { - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp; struct sk_buff *skb; - bool post_ACK; - int latest; - u32 hard, tx; - - _enter(""); - -process_further: - skb = skb_dequeue(&call->rx_queue); - if (!skb) - return -EAGAIN; - - rxrpc_see_skb(skb); - _net("deferred skb %p", skb); - - sp = rxrpc_skb(skb); + rxrpc_seq_t cursor, seq, top; + ktime_t now = ktime_get_real(), max_age, oldest, resend_at, ack_ts; + int ix; + u8 annotation, anno_type, retrans = 0, unacked = 0; - _debug("process %s [st %d]", rxrpc_pkts[sp->hdr.type], call->state); + _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); - post_ACK = false; + max_age = ktime_sub_ms(now, rxrpc_resend_timeout); - switch (sp->hdr.type) { - /* data packets that wind up here have been received out of - * order, need security processing or are jumbo packets */ - case RXRPC_PACKET_TYPE_DATA: - _proto("OOSQ DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); + spin_lock_bh(&call->lock); - /* secured packets must be verified and possibly decrypted */ - if (call->conn->security->verify_packet(call, skb, - _abort_code) < 0) - goto protocol_error; + cursor = call->tx_hard_ack; + top = call->tx_top; + ASSERT(before_eq(cursor, top)); + if (cursor == top) + goto out_unlock; + + /* Scan the packet list without dropping the lock and decide which of + * the packets in the Tx buffer we're going to resend and what the new + * resend timeout will be. + */ + oldest = now; + for (seq = cursor + 1; before_eq(seq, top); seq++) { + ix = seq & RXRPC_RXTX_BUFF_MASK; + annotation = call->rxtx_annotations[ix]; + anno_type = annotation & RXRPC_TX_ANNO_MASK; + annotation &= ~RXRPC_TX_ANNO_MASK; + if (anno_type == RXRPC_TX_ANNO_ACK) + continue; - rxrpc_insert_oos_packet(call, skb); - goto process_further; + skb = call->rxtx_buffer[ix]; + rxrpc_see_skb(skb, rxrpc_skb_tx_seen); + sp = rxrpc_skb(skb); - /* partial ACK to process */ - case RXRPC_PACKET_TYPE_ACK: - if (skb_copy_bits(skb, 0, &ack, sizeof(ack)) < 0) { - _debug("extraction failure"); - goto protocol_error; + if (anno_type == RXRPC_TX_ANNO_UNACK) { + if (ktime_after(skb->tstamp, max_age)) { + if (ktime_before(skb->tstamp, oldest)) + oldest = skb->tstamp; + continue; + } + if (!(annotation & RXRPC_TX_ANNO_RESENT)) + unacked++; } - if (!skb_pull(skb, sizeof(ack))) - BUG(); - - latest = sp->hdr.serial; - hard = ntohl(ack.firstPacket); - tx = atomic_read(&call->sequence); - _proto("Rx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", - latest, - ntohs(ack.maxSkew), - hard, - ntohl(ack.previousPacket), - ntohl(ack.serial), - rxrpc_acks(ack.reason), - ack.nAcks); - - rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks); + /* Okay, we need to retransmit a packet. */ + call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation; + retrans++; + trace_rxrpc_retransmit(call, seq, annotation | anno_type, + ktime_to_ns(ktime_sub(skb->tstamp, max_age))); + } + + resend_at = ktime_add_ms(oldest, rxrpc_resend_timeout); + call->resend_at = jiffies + + nsecs_to_jiffies(ktime_to_ns(ktime_sub(resend_at, now))) + + 1; /* We have to make sure that the calculated jiffies value + * falls at or after the nsec value, or we shall loop + * ceaselessly because the timer times out, but we haven't + * reached the nsec timeout yet. + */ + + if (unacked) + rxrpc_congestion_timeout(call); + + /* If there was nothing that needed retransmission then it's likely + * that an ACK got lost somewhere. Send a ping to find out instead of + * retransmitting data. + */ + if (!retrans) { + rxrpc_set_timer(call, rxrpc_timer_set_for_resend); + spin_unlock_bh(&call->lock); + ack_ts = ktime_sub(now, call->acks_latest_ts); + if (ktime_to_ns(ack_ts) < call->peer->rtt) + goto out; + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ack_ping_for_lost_ack); + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + goto out; + } + + /* Now go through the Tx window and perform the retransmissions. We + * have to drop the lock for each send. If an ACK comes in whilst the + * lock is dropped, it may clear some of the retransmission markers for + * packets that it soft-ACKs. + */ + for (seq = cursor + 1; before_eq(seq, top); seq++) { + ix = seq & RXRPC_RXTX_BUFF_MASK; + annotation = call->rxtx_annotations[ix]; + anno_type = annotation & RXRPC_TX_ANNO_MASK; + if (anno_type != RXRPC_TX_ANNO_RETRANS) + continue; - if (ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", latest); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - skb->priority, sp->hdr.serial, true); - } + skb = call->rxtx_buffer[ix]; + rxrpc_get_skb(skb, rxrpc_skb_tx_got); + spin_unlock_bh(&call->lock); - /* discard any out-of-order or duplicate ACKs */ - if (latest - call->acks_latest <= 0) { - _debug("discard ACK %d <= %d", - latest, call->acks_latest); - goto discard; + if (rxrpc_send_data_packet(call, skb) < 0) { + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + return; } - call->acks_latest = latest; - if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && - call->state != RXRPC_CALL_CLIENT_AWAIT_REPLY && - call->state != RXRPC_CALL_SERVER_SEND_REPLY && - call->state != RXRPC_CALL_SERVER_AWAIT_ACK) - goto discard; + if (rxrpc_is_client_call(call)) + rxrpc_expose_client_call(call); - _debug("Tx=%d H=%u S=%d", tx, call->acks_hard, call->state); - - if (hard > 0) { - if (hard - 1 > tx) { - _debug("hard-ACK'd packet %d not transmitted" - " (%d top)", - hard - 1, tx); - goto protocol_error; - } - - if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY || - call->state == RXRPC_CALL_SERVER_AWAIT_ACK) && - hard > tx) { - call->acks_hard = tx; - goto all_acked; - } - - smp_rmb(); - rxrpc_rotate_tx_window(call, hard - 1); - } + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + spin_lock_bh(&call->lock); - if (ack.nAcks > 0) { - if (hard - 1 + ack.nAcks > tx) { - _debug("soft-ACK'd packet %d+%d not" - " transmitted (%d top)", - hard - 1, ack.nAcks, tx); - goto protocol_error; + /* We need to clear the retransmit state, but there are two + * things we need to be aware of: A new ACK/NAK might have been + * received and the packet might have been hard-ACK'd (in which + * case it will no longer be in the buffer). + */ + if (after(seq, call->tx_hard_ack)) { + annotation = call->rxtx_annotations[ix]; + anno_type = annotation & RXRPC_TX_ANNO_MASK; + if (anno_type == RXRPC_TX_ANNO_RETRANS || + anno_type == RXRPC_TX_ANNO_NAK) { + annotation &= ~RXRPC_TX_ANNO_MASK; + annotation |= RXRPC_TX_ANNO_UNACK; } - - if (rxrpc_process_soft_ACKs(call, &ack, skb) < 0) - goto protocol_error; + annotation |= RXRPC_TX_ANNO_RESENT; + call->rxtx_annotations[ix] = annotation; } - goto discard; - - /* complete ACK to process */ - case RXRPC_PACKET_TYPE_ACKALL: - goto all_acked; - - /* abort and busy are handled elsewhere */ - case RXRPC_PACKET_TYPE_BUSY: - case RXRPC_PACKET_TYPE_ABORT: - BUG(); - - /* connection level events - also handled elsewhere */ - case RXRPC_PACKET_TYPE_CHALLENGE: - case RXRPC_PACKET_TYPE_RESPONSE: - case RXRPC_PACKET_TYPE_DEBUG: - BUG(); - } - - /* if we've had a hard ACK that covers all the packets we've sent, then - * that ends that phase of the operation */ -all_acked: - write_lock_bh(&call->state_lock); - _debug("ack all %d", call->state); - - switch (call->state) { - case RXRPC_CALL_CLIENT_AWAIT_REPLY: - call->state = RXRPC_CALL_CLIENT_RECV_REPLY; - break; - case RXRPC_CALL_SERVER_AWAIT_ACK: - _debug("srv complete"); - __rxrpc_call_completed(call); - post_ACK = true; - break; - case RXRPC_CALL_CLIENT_SEND_REQUEST: - case RXRPC_CALL_SERVER_RECV_REQUEST: - goto protocol_error_unlock; /* can't occur yet */ - default: - write_unlock_bh(&call->state_lock); - goto discard; /* assume packet left over from earlier phase */ - } - - write_unlock_bh(&call->state_lock); - - /* if all the packets we sent are hard-ACK'd, then we can discard - * whatever we've got left */ - _debug("clear Tx %d", - CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz)); - del_timer_sync(&call->resend_timer); - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); - - if (call->acks_window) - rxrpc_zap_tx_window(call); - - if (post_ACK) { - /* post the final ACK message for userspace to pick up */ - _debug("post ACK"); - skb->mark = RXRPC_SKB_MARK_FINAL_ACK; - sp->call = call; - rxrpc_get_call_for_skb(call, skb); - spin_lock_bh(&call->lock); - if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0) - BUG(); - spin_unlock_bh(&call->lock); - goto process_further; + if (after(call->tx_hard_ack, seq)) + seq = call->tx_hard_ack; } -discard: - rxrpc_free_skb(skb); - goto process_further; - -protocol_error_unlock: - write_unlock_bh(&call->state_lock); -protocol_error: - rxrpc_free_skb(skb); - _leave(" = -EPROTO"); - return -EPROTO; -} - -/* - * post a message to the socket Rx queue for recvmsg() to pick up - */ -static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error, - bool fatal) -{ - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - int ret; - - _enter("{%d,%lx},%u,%u,%d", - call->debug_id, call->flags, mark, error, fatal); - - /* remove timers and things for fatal messages */ - if (fatal) { - del_timer_sync(&call->resend_timer); - del_timer_sync(&call->ack_timer); - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - } - - if (mark != RXRPC_SKB_MARK_NEW_CALL && - !test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { - _leave("[no userid]"); - return 0; - } - - if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { - skb = alloc_skb(0, GFP_NOFS); - if (!skb) - return -ENOMEM; - - rxrpc_new_skb(skb); - - skb->mark = mark; - - sp = rxrpc_skb(skb); - memset(sp, 0, sizeof(*sp)); - sp->error = error; - sp->call = call; - rxrpc_get_call_for_skb(call, skb); - - spin_lock_bh(&call->lock); - ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); - spin_unlock_bh(&call->lock); - BUG_ON(ret < 0); - } - - return 0; +out_unlock: + spin_unlock_bh(&call->lock); +out: + _leave(""); } /* - * handle background processing of incoming call packets and ACK / abort - * generation + * Handle retransmission and deferred ACK/abort generation. */ void rxrpc_process_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - struct rxrpc_wire_header whdr; - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo ackinfo; - struct msghdr msg; - struct kvec iov[5]; - enum rxrpc_call_event genbit; - unsigned long bits; - __be32 data, pad; - size_t len; - int loop, nbit, ioc, ret, mtu; - u32 serial, abort_code = RX_PROTOCOL_ERROR; - u8 *acks = NULL; + unsigned long now; rxrpc_see_call(call); //printk("\n--------------------\n"); - _enter("{%d,%s,%lx} [%lu]", - call->debug_id, rxrpc_call_states[call->state], call->events, - (jiffies - call->creation_jif) / (HZ / 10)); - - if (!call->conn) - goto skip_msg_init; - - /* there's a good chance we're going to have to send a message, so set - * one up in advance */ - msg.msg_name = &call->peer->srx.transport; - msg.msg_namelen = call->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; + _enter("{%d,%s,%lx}", + call->debug_id, rxrpc_call_states[call->state], call->events); - whdr.epoch = htonl(call->conn->proto.epoch); - whdr.cid = htonl(call->cid); - whdr.callNumber = htonl(call->call_id); - whdr.seq = 0; - whdr.type = RXRPC_PACKET_TYPE_ACK; - whdr.flags = call->conn->out_clientflag; - whdr.userStatus = 0; - whdr.securityIndex = call->conn->security_ix; - whdr._rsvd = 0; - whdr.serviceId = htons(call->service_id); - - memset(iov, 0, sizeof(iov)); - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); -skip_msg_init: - - /* deal with events of a final nature */ - if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { - enum rxrpc_skb_mark mark; - - clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); - clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); - clear_bit(RXRPC_CALL_EV_ABORT, &call->events); - - if (call->completion == RXRPC_CALL_NETWORK_ERROR) { - mark = RXRPC_SKB_MARK_NET_ERROR; - _debug("post net error %d", call->error); - } else { - mark = RXRPC_SKB_MARK_LOCAL_ERROR; - _debug("post net local error %d", call->error); - } - - if (rxrpc_post_message(call, mark, call->error, true) < 0) - goto no_mem; - clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); - goto kill_ACKs; +recheck_state: + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + goto recheck_state; } - if (test_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events)) { - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - - clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); - clear_bit(RXRPC_CALL_EV_ABORT, &call->events); - - _debug("post conn abort"); - - if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, - call->error, true) < 0) - goto no_mem; - clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); - goto kill_ACKs; + if (call->state == RXRPC_CALL_COMPLETE) { + del_timer_sync(&call->timer); + goto out_put; } - if (test_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) { - whdr.type = RXRPC_PACKET_TYPE_BUSY; - genbit = RXRPC_CALL_EV_REJECT_BUSY; - goto send_message; + now = jiffies; + if (time_after_eq(now, call->expire_at)) { + rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, ETIME); + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + goto recheck_state; } - if (test_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - - if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, - call->error, true) < 0) - goto no_mem; - whdr.type = RXRPC_PACKET_TYPE_ABORT; - data = htonl(call->abort_code); - iov[1].iov_base = &data; - iov[1].iov_len = sizeof(data); - genbit = RXRPC_CALL_EV_ABORT; - goto send_message; - } - - if (test_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events)) { - genbit = RXRPC_CALL_EV_ACK_FINAL; - - ack.bufferSpace = htons(8); - ack.maxSkew = 0; - ack.serial = 0; - ack.reason = RXRPC_ACK_IDLE; - ack.nAcks = 0; - call->ackr_reason = 0; - - spin_lock_bh(&call->lock); - ack.serial = htonl(call->ackr_serial); - ack.previousPacket = htonl(call->ackr_prev_seq); - ack.firstPacket = htonl(call->rx_data_eaten + 1); - spin_unlock_bh(&call->lock); - - pad = 0; - - iov[1].iov_base = &ack; - iov[1].iov_len = sizeof(ack); - iov[2].iov_base = &pad; - iov[2].iov_len = 3; - iov[3].iov_base = &ackinfo; - iov[3].iov_len = sizeof(ackinfo); - goto send_ACK; - } - - if (call->events & ((1 << RXRPC_CALL_EV_RCVD_BUSY) | - (1 << RXRPC_CALL_EV_RCVD_ABORT)) - ) { - u32 mark; - - if (test_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events)) - mark = RXRPC_SKB_MARK_REMOTE_ABORT; - else - mark = RXRPC_SKB_MARK_BUSY; - - _debug("post abort/busy"); - rxrpc_clear_tx_window(call); - if (rxrpc_post_message(call, mark, ECONNABORTED, true) < 0) - goto no_mem; - - clear_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events); - clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); - goto kill_ACKs; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_RCVD_ACKALL, &call->events)) { - _debug("do implicit ackall"); - rxrpc_clear_tx_window(call); - } - - if (test_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events)) { - rxrpc_abort_call(call, RX_CALL_TIMEOUT, ETIME); - - _debug("post timeout"); - if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, - ETIME, true) < 0) - goto no_mem; - - clear_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); - goto kill_ACKs; - } - - /* deal with assorted inbound messages */ - if (!skb_queue_empty(&call->rx_queue)) { - ret = rxrpc_process_rx_queue(call, &abort_code); - switch (ret) { - case 0: - case -EAGAIN: - break; - case -ENOMEM: - goto no_mem; - case -EKEYEXPIRED: - case -EKEYREJECTED: - case -EPROTO: - rxrpc_abort_call(call, abort_code, -ret); - goto kill_ACKs; + if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) || + time_after_eq(now, call->ack_at)) { + call->ack_at = call->expire_at; + if (call->ackr_reason) { + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + goto recheck_state; } } - /* handle resending */ - if (test_and_clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) - rxrpc_resend_timer(call); - if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) || + time_after_eq(now, call->resend_at)) { rxrpc_resend(call); - - /* consider sending an ordinary ACK */ - if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { - _debug("send ACK: window: %d - %d { %lx }", - call->rx_data_eaten, call->ackr_win_top, - call->ackr_window[0]); - - if (call->state > RXRPC_CALL_SERVER_ACK_REQUEST && - call->ackr_reason != RXRPC_ACK_PING_RESPONSE) { - /* ACK by sending reply DATA packet in this state */ - clear_bit(RXRPC_CALL_EV_ACK, &call->events); - goto maybe_reschedule; - } - - genbit = RXRPC_CALL_EV_ACK; - - acks = kzalloc(call->ackr_win_top - call->rx_data_eaten, - GFP_NOFS); - if (!acks) - goto no_mem; - - //hdr.flags = RXRPC_SLOW_START_OK; - ack.bufferSpace = htons(8); - ack.maxSkew = 0; - - spin_lock_bh(&call->lock); - ack.reason = call->ackr_reason; - ack.serial = htonl(call->ackr_serial); - ack.previousPacket = htonl(call->ackr_prev_seq); - ack.firstPacket = htonl(call->rx_data_eaten + 1); - - ack.nAcks = 0; - for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) { - nbit = loop * BITS_PER_LONG; - for (bits = call->ackr_window[loop]; bits; bits >>= 1 - ) { - _debug("- l=%d n=%d b=%lx", loop, nbit, bits); - if (bits & 1) { - acks[nbit] = RXRPC_ACK_TYPE_ACK; - ack.nAcks = nbit + 1; - } - nbit++; - } - } - call->ackr_reason = 0; - spin_unlock_bh(&call->lock); - - pad = 0; - - iov[1].iov_base = &ack; - iov[1].iov_len = sizeof(ack); - iov[2].iov_base = acks; - iov[2].iov_len = ack.nAcks; - iov[3].iov_base = &pad; - iov[3].iov_len = 3; - iov[4].iov_base = &ackinfo; - iov[4].iov_len = sizeof(ackinfo); - - switch (ack.reason) { - case RXRPC_ACK_REQUESTED: - case RXRPC_ACK_DUPLICATE: - case RXRPC_ACK_OUT_OF_SEQUENCE: - case RXRPC_ACK_EXCEEDS_WINDOW: - case RXRPC_ACK_NOSPACE: - case RXRPC_ACK_PING: - case RXRPC_ACK_PING_RESPONSE: - goto send_ACK_with_skew; - case RXRPC_ACK_DELAY: - case RXRPC_ACK_IDLE: - goto send_ACK; - } + goto recheck_state; } - /* handle completion of security negotiations on an incoming - * connection */ - if (test_and_clear_bit(RXRPC_CALL_EV_SECURED, &call->events)) { - _debug("secured"); - spin_lock_bh(&call->lock); - - if (call->state == RXRPC_CALL_SERVER_SECURING) { - _debug("securing"); - write_lock(&call->socket->call_lock); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { - _debug("not released"); - call->state = RXRPC_CALL_SERVER_ACCEPTING; - list_move_tail(&call->accept_link, - &call->socket->acceptq); - } - write_unlock(&call->socket->call_lock); - read_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) - set_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events); - read_unlock(&call->state_lock); - } - - spin_unlock_bh(&call->lock); - if (!test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events)) - goto maybe_reschedule; - } - - /* post a notification of an acceptable connection to the app */ - if (test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events)) { - _debug("post accept"); - if (rxrpc_post_message(call, RXRPC_SKB_MARK_NEW_CALL, - 0, false) < 0) - goto no_mem; - clear_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events); - goto maybe_reschedule; - } - - /* handle incoming call acceptance */ - if (test_and_clear_bit(RXRPC_CALL_EV_ACCEPTED, &call->events)) { - _debug("accepted"); - ASSERTCMP(call->rx_data_post, ==, 0); - call->rx_data_post = 1; - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) - set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events); - read_unlock_bh(&call->state_lock); - } - - /* drain the out of sequence received packet queue into the packet Rx - * queue */ - if (test_and_clear_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events)) { - while (call->rx_data_post == call->rx_first_oos) - if (rxrpc_drain_rx_oos_queue(call) < 0) - break; - goto maybe_reschedule; - } - - if (test_bit(RXRPC_CALL_EV_RELEASE, &call->events)) { - rxrpc_release_call(call); - clear_bit(RXRPC_CALL_EV_RELEASE, &call->events); - } + rxrpc_set_timer(call, rxrpc_timer_set_for_resend); /* other events may have been raised since we started checking */ - goto maybe_reschedule; - -send_ACK_with_skew: - ack.maxSkew = htons(call->ackr_skew); -send_ACK: - mtu = call->peer->if_mtu; - mtu -= call->peer->hdrsize; - ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(rxrpc_rx_window_size); - - /* permit the peer to send us jumbo packets if it wants to */ - ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max); - - serial = atomic_inc_return(&call->conn->serial); - whdr.serial = htonl(serial); - _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", - serial, - ntohs(ack.maxSkew), - ntohl(ack.firstPacket), - ntohl(ack.previousPacket), - ntohl(ack.serial), - rxrpc_acks(ack.reason), - ack.nAcks); - - del_timer_sync(&call->ack_timer); - if (ack.nAcks > 0) - set_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags); - goto send_message_2; - -send_message: - _debug("send message"); - - serial = atomic_inc_return(&call->conn->serial); - whdr.serial = htonl(serial); - _proto("Tx %s %%%u", rxrpc_pkts[whdr.type], serial); -send_message_2: - - len = iov[0].iov_len; - ioc = 1; - if (iov[4].iov_len) { - ioc = 5; - len += iov[4].iov_len; - len += iov[3].iov_len; - len += iov[2].iov_len; - len += iov[1].iov_len; - } else if (iov[3].iov_len) { - ioc = 4; - len += iov[3].iov_len; - len += iov[2].iov_len; - len += iov[1].iov_len; - } else if (iov[2].iov_len) { - ioc = 3; - len += iov[2].iov_len; - len += iov[1].iov_len; - } else if (iov[1].iov_len) { - ioc = 2; - len += iov[1].iov_len; - } - - ret = kernel_sendmsg(call->conn->params.local->socket, - &msg, iov, ioc, len); - if (ret < 0) { - _debug("sendmsg failed: %d", ret); - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_DEAD) - rxrpc_queue_call(call); - read_unlock_bh(&call->state_lock); - goto error; - } - - switch (genbit) { - case RXRPC_CALL_EV_ABORT: - clear_bit(genbit, &call->events); - clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); - goto kill_ACKs; - - case RXRPC_CALL_EV_ACK_FINAL: - rxrpc_call_completed(call); - goto kill_ACKs; - - default: - clear_bit(genbit, &call->events); - switch (call->state) { - case RXRPC_CALL_CLIENT_AWAIT_REPLY: - case RXRPC_CALL_CLIENT_RECV_REPLY: - case RXRPC_CALL_SERVER_RECV_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - _debug("start ACK timer"); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, - call->ackr_skew, call->ackr_serial, - false); - default: - break; - } - goto maybe_reschedule; - } - -kill_ACKs: - del_timer_sync(&call->ack_timer); - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events)) - rxrpc_put_call(call); - clear_bit(RXRPC_CALL_EV_ACK, &call->events); - -maybe_reschedule: - if (call->events || !skb_queue_empty(&call->rx_queue)) { - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_DEAD) - rxrpc_queue_call(call); - read_unlock_bh(&call->state_lock); - } - - /* don't leave aborted connections on the accept queue */ - if (call->state >= RXRPC_CALL_COMPLETE && - !list_empty(&call->accept_link)) { - _debug("X unlinking once-pending call %p { e=%lx f=%lx c=%x }", - call, call->events, call->flags, call->conn->proto.cid); - - read_lock_bh(&call->state_lock); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) - rxrpc_queue_call(call); - read_unlock_bh(&call->state_lock); - } - -error: - kfree(acks); - - /* because we don't want two CPUs both processing the work item for one - * call at the same time, we use a flag to note when it's busy; however - * this means there's a race between clearing the flag and setting the - * work pending bit and the work item being processed again */ - if (call->events && !work_pending(&call->processor)) { - _debug("jumpstart %x", call->conn->proto.cid); - rxrpc_queue_call(call); + if (call->events && call->state < RXRPC_CALL_COMPLETE) { + __rxrpc_queue_call(call); + goto out; } +out_put: + rxrpc_put_call(call, rxrpc_call_put); +out: _leave(""); - return; - -no_mem: - _debug("out of memory"); - goto maybe_reschedule; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6569174..d4b3293 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -24,18 +24,13 @@ */ unsigned int rxrpc_max_call_lifetime = 60 * HZ; -/* - * Time till dead call expires after last use (in jiffies). - */ -unsigned int rxrpc_dead_call_expiry = 2 * HZ; - const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_UNINITIALISED] = "Uninit ", [RXRPC_CALL_CLIENT_AWAIT_CONN] = "ClWtConn", [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", [RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl", - [RXRPC_CALL_CLIENT_FINAL_ACK] = "ClFnlACK", + [RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc", [RXRPC_CALL_SERVER_SECURING] = "SvSecure", [RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept", [RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq", @@ -43,27 +38,49 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", [RXRPC_CALL_SERVER_AWAIT_ACK] = "SvAwtACK", [RXRPC_CALL_COMPLETE] = "Complete", - [RXRPC_CALL_DEAD] = "Dead ", }; const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { [RXRPC_CALL_SUCCEEDED] = "Complete", - [RXRPC_CALL_SERVER_BUSY] = "SvBusy ", [RXRPC_CALL_REMOTELY_ABORTED] = "RmtAbort", [RXRPC_CALL_LOCALLY_ABORTED] = "LocAbort", [RXRPC_CALL_LOCAL_ERROR] = "LocError", [RXRPC_CALL_NETWORK_ERROR] = "NetError", }; +const char rxrpc_call_traces[rxrpc_call__nr_trace][4] = { + [rxrpc_call_new_client] = "NWc", + [rxrpc_call_new_service] = "NWs", + [rxrpc_call_queued] = "QUE", + [rxrpc_call_queued_ref] = "QUR", + [rxrpc_call_connected] = "CON", + [rxrpc_call_release] = "RLS", + [rxrpc_call_seen] = "SEE", + [rxrpc_call_got] = "GOT", + [rxrpc_call_got_userid] = "Gus", + [rxrpc_call_got_kernel] = "Gke", + [rxrpc_call_put] = "PUT", + [rxrpc_call_put_userid] = "Pus", + [rxrpc_call_put_kernel] = "Pke", + [rxrpc_call_put_noqueue] = "PNQ", + [rxrpc_call_error] = "*E*", +}; + struct kmem_cache *rxrpc_call_jar; LIST_HEAD(rxrpc_calls); DEFINE_RWLOCK(rxrpc_call_lock); -static void rxrpc_destroy_call(struct work_struct *work); -static void rxrpc_call_life_expired(unsigned long _call); -static void rxrpc_dead_call_expired(unsigned long _call); -static void rxrpc_ack_time_expired(unsigned long _call); -static void rxrpc_resend_time_expired(unsigned long _call); +static void rxrpc_call_timer_expired(unsigned long _call) +{ + struct rxrpc_call *call = (struct rxrpc_call *)_call; + + _enter("%d", call->debug_id); + + if (call->state < RXRPC_CALL_COMPLETE) { + trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies); + rxrpc_queue_call(call); + } +} /* * find an extant server call @@ -96,7 +113,7 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, return NULL; found_extant_call: - rxrpc_get_call(call); + rxrpc_get_call(call, rxrpc_call_got); read_unlock(&rx->call_lock); _leave(" = %p [%d]", call, atomic_read(&call->usage)); return call; @@ -105,7 +122,7 @@ found_extant_call: /* * allocate a new call */ -static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) +struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) { struct rxrpc_call *call; @@ -113,30 +130,24 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) if (!call) return NULL; - call->acks_winsz = 16; - call->acks_window = kmalloc(call->acks_winsz * sizeof(unsigned long), + call->rxtx_buffer = kcalloc(RXRPC_RXTX_BUFF_SIZE, + sizeof(struct sk_buff *), gfp); - if (!call->acks_window) { - kmem_cache_free(rxrpc_call_jar, call); - return NULL; - } + if (!call->rxtx_buffer) + goto nomem; + + call->rxtx_annotations = kcalloc(RXRPC_RXTX_BUFF_SIZE, sizeof(u8), gfp); + if (!call->rxtx_annotations) + goto nomem_2; - setup_timer(&call->lifetimer, &rxrpc_call_life_expired, - (unsigned long) call); - setup_timer(&call->deadspan, &rxrpc_dead_call_expired, - (unsigned long) call); - setup_timer(&call->ack_timer, &rxrpc_ack_time_expired, - (unsigned long) call); - setup_timer(&call->resend_timer, &rxrpc_resend_time_expired, - (unsigned long) call); - INIT_WORK(&call->destroyer, &rxrpc_destroy_call); + setup_timer(&call->timer, rxrpc_call_timer_expired, + (unsigned long)call); INIT_WORK(&call->processor, &rxrpc_process_call); INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->chan_wait_link); INIT_LIST_HEAD(&call->accept_link); - skb_queue_head_init(&call->rx_queue); - skb_queue_head_init(&call->rx_oos_queue); - skb_queue_head_init(&call->knlrecv_queue); + INIT_LIST_HEAD(&call->recvmsg_link); + INIT_LIST_HEAD(&call->sock_link); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); rwlock_init(&call->state_lock); @@ -145,65 +156,65 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) memset(&call->sock_node, 0xed, sizeof(call->sock_node)); - call->rx_data_expect = 1; - call->rx_data_eaten = 0; - call->rx_first_oos = 0; - call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size; - call->creation_jif = jiffies; + /* Leave space in the ring to handle a maxed-out jumbo packet */ + call->rx_winsize = rxrpc_rx_window_size; + call->tx_winsize = 16; + call->rx_expect_next = 1; + + if (RXRPC_TX_SMSS > 2190) + call->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + call->cong_cwnd = 3; + else + call->cong_cwnd = 4; + call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; return call; + +nomem_2: + kfree(call->rxtx_buffer); +nomem: + kmem_cache_free(rxrpc_call_jar, call); + return NULL; } /* * Allocate a new client call. */ -static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, - struct sockaddr_rxrpc *srx, +static struct rxrpc_call *rxrpc_alloc_client_call(struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_call *call; + ktime_t now; _enter(""); - ASSERT(rx->local != NULL); - call = rxrpc_alloc_call(gfp); if (!call) return ERR_PTR(-ENOMEM); call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; - - sock_hold(&rx->sk); - call->socket = rx; - call->rx_data_post = 1; call->service_id = srx->srx_service; + call->tx_phase = true; + now = ktime_get_real(); + call->acks_latest_ts = now; + call->cong_tstamp = now; _leave(" = %p", call); return call; } /* - * Begin client call. + * Initiate the call ack/resend/expiry timer. */ -static int rxrpc_begin_client_call(struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +static void rxrpc_start_call_timer(struct rxrpc_call *call) { - int ret; - - /* Set up or get a connection record and set the protocol parameters, - * including channel number and call ID. - */ - ret = rxrpc_connect_call(call, cp, srx, gfp); - if (ret < 0) - return ret; - - spin_lock(&call->conn->params.peer->lock); - hlist_add_head(&call->error_link, &call->conn->params.peer->error_targets); - spin_unlock(&call->conn->params.peer->lock); - - call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; - add_timer(&call->lifetimer); - return 0; + unsigned long expire_at; + + expire_at = jiffies + rxrpc_max_call_lifetime; + call->expire_at = expire_at; + call->ack_at = expire_at; + call->resend_at = expire_at; + call->timer.expires = expire_at + 1; + rxrpc_set_timer(call, rxrpc_timer_begin); } /* @@ -223,19 +234,16 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, _enter("%p,%lx", rx, user_call_ID); - call = rxrpc_alloc_client_call(rx, srx, gfp); + call = rxrpc_alloc_client_call(srx, gfp); if (IS_ERR(call)) { _leave(" = %ld", PTR_ERR(call)); return call; } - trace_rxrpc_call(call, 0, atomic_read(&call->usage), 0, here, - (const void *)user_call_ID); + trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + here, (const void *)user_call_ID); /* Publish the call, even though it is incompletely set up as yet */ - call->user_call_ID = user_call_ID; - __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); - write_lock(&rx->call_lock); pp = &rx->calls.rb_node; @@ -249,192 +257,138 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else - goto found_user_ID_now_present; + goto error_dup_user_ID; } - rxrpc_get_call(call); - + rcu_assign_pointer(call->socket, rx); + call->user_call_ID = user_call_ID; + __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); + rxrpc_get_call(call, rxrpc_call_got_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); + list_add(&call->sock_link, &rx->sock_calls); + write_unlock(&rx->call_lock); - write_lock_bh(&rxrpc_call_lock); + write_lock(&rxrpc_call_lock); list_add_tail(&call->link, &rxrpc_calls); - write_unlock_bh(&rxrpc_call_lock); + write_unlock(&rxrpc_call_lock); - ret = rxrpc_begin_client_call(call, cp, srx, gfp); + /* Set up or get a connection record and set the protocol parameters, + * including channel number and call ID. + */ + ret = rxrpc_connect_call(call, cp, srx, gfp); if (ret < 0) goto error; - _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); + trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), + here, ERR_PTR(ret)); - _leave(" = %p [new]", call); - return call; + spin_lock_bh(&call->conn->params.peer->lock); + hlist_add_head(&call->error_link, + &call->conn->params.peer->error_targets); + spin_unlock_bh(&call->conn->params.peer->lock); -error: - write_lock(&rx->call_lock); - rb_erase(&call->sock_node, &rx->calls); - write_unlock(&rx->call_lock); - rxrpc_put_call(call); + rxrpc_start_call_timer(call); - write_lock_bh(&rxrpc_call_lock); - list_del_init(&call->link); - write_unlock_bh(&rxrpc_call_lock); + _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); - set_bit(RXRPC_CALL_RELEASED, &call->flags); - call->state = RXRPC_CALL_DEAD; - rxrpc_put_call(call); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = %p [new]", call); + return call; /* We unexpectedly found the user ID in the list after taking * the call_lock. This shouldn't happen unless the user races * with itself and tries to add the same user ID twice at the * same time in different threads. */ -found_user_ID_now_present: +error_dup_user_ID: write_unlock(&rx->call_lock); - set_bit(RXRPC_CALL_RELEASED, &call->flags); - call->state = RXRPC_CALL_DEAD; - rxrpc_put_call(call); - _leave(" = -EEXIST [%p]", call); - return ERR_PTR(-EEXIST); + ret = -EEXIST; + +error: + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), + here, ERR_PTR(ret)); + rxrpc_release_call(rx, call); + rxrpc_put_call(call, rxrpc_call_put); + _leave(" = %d", ret); + return ERR_PTR(ret); } /* - * set up an incoming call - * - called in process context with IRQs enabled + * Set up an incoming call. call->conn points to the connection. + * This is called in BH context and isn't allowed to fail. */ -struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, - struct rxrpc_connection *conn, - struct sk_buff *skb) +void rxrpc_incoming_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct sk_buff *skb) { + struct rxrpc_connection *conn = call->conn; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_call *call, *candidate; - const void *here = __builtin_return_address(0); - u32 call_id, chan; - - _enter(",%d", conn->debug_id); - - ASSERT(rx != NULL); - - candidate = rxrpc_alloc_call(GFP_NOIO); - if (!candidate) - return ERR_PTR(-EBUSY); - - trace_rxrpc_call(candidate, 1, atomic_read(&candidate->usage), - 0, here, NULL); - - chan = sp->hdr.cid & RXRPC_CHANNELMASK; - candidate->socket = rx; - candidate->conn = conn; - candidate->peer = conn->params.peer; - candidate->cid = sp->hdr.cid; - candidate->call_id = sp->hdr.callNumber; - candidate->rx_data_post = 0; - candidate->state = RXRPC_CALL_SERVER_ACCEPTING; - candidate->flags |= (1 << RXRPC_CALL_IS_SERVICE); - if (conn->security_ix > 0) - candidate->state = RXRPC_CALL_SERVER_SECURING; - - spin_lock(&conn->channel_lock); - - /* set the channel for this call */ - call = rcu_dereference_protected(conn->channels[chan].call, - lockdep_is_held(&conn->channel_lock)); - - _debug("channel[%u] is %p", candidate->cid & RXRPC_CHANNELMASK, call); - if (call && call->call_id == sp->hdr.callNumber) { - /* already set; must've been a duplicate packet */ - _debug("extant call [%d]", call->state); - ASSERTCMP(call->conn, ==, conn); - - read_lock(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_LOCALLY_ABORTED: - if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) - rxrpc_queue_call(call); - case RXRPC_CALL_REMOTELY_ABORTED: - read_unlock(&call->state_lock); - goto aborted_call; - default: - rxrpc_get_call(call); - read_unlock(&call->state_lock); - goto extant_call; - } - } - - if (call) { - /* it seems the channel is still in use from the previous call - * - ditch the old binding if its call is now complete */ - _debug("CALL: %u { %s }", - call->debug_id, rxrpc_call_states[call->state]); - - if (call->state == RXRPC_CALL_COMPLETE) { - __rxrpc_disconnect_call(conn, call); - } else { - spin_unlock(&conn->channel_lock); - kmem_cache_free(rxrpc_call_jar, candidate); - _leave(" = -EBUSY"); - return ERR_PTR(-EBUSY); - } - } - - /* check the call number isn't duplicate */ - _debug("check dup"); - call_id = sp->hdr.callNumber; - - /* We just ignore calls prior to the current call ID. Terminated calls - * are handled via the connection. + u32 chan; + + _enter(",%d", call->conn->debug_id); + + rcu_assign_pointer(call->socket, rx); + call->call_id = sp->hdr.callNumber; + call->service_id = sp->hdr.serviceId; + call->cid = sp->hdr.cid; + call->state = RXRPC_CALL_SERVER_ACCEPTING; + if (sp->hdr.securityIndex > 0) + call->state = RXRPC_CALL_SERVER_SECURING; + call->cong_tstamp = skb->tstamp; + + /* Set the channel for this call. We don't get channel_lock as we're + * only defending against the data_ready handler (which we're called + * from) and the RESPONSE packet parser (which is only really + * interested in call_counter and can cope with a disagreement with the + * call pointer). */ - if (call_id <= conn->channels[chan].call_counter) - goto old_call; /* TODO: Just drop packet */ - - /* make the call available */ - _debug("new call"); - call = candidate; - candidate = NULL; - conn->channels[chan].call_counter = call_id; + chan = sp->hdr.cid & RXRPC_CHANNELMASK; + conn->channels[chan].call_counter = call->call_id; + conn->channels[chan].call_id = call->call_id; rcu_assign_pointer(conn->channels[chan].call, call); - sock_hold(&rx->sk); - rxrpc_get_connection(conn); - rxrpc_get_peer(call->peer); - spin_unlock(&conn->channel_lock); spin_lock(&conn->params.peer->lock); hlist_add_head(&call->error_link, &conn->params.peer->error_targets); spin_unlock(&conn->params.peer->lock); - write_lock_bh(&rxrpc_call_lock); - list_add_tail(&call->link, &rxrpc_calls); - write_unlock_bh(&rxrpc_call_lock); - - call->service_id = conn->params.service_id; - _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); - call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; - add_timer(&call->lifetimer); - _leave(" = %p {%d} [new]", call, call->debug_id); - return call; + rxrpc_start_call_timer(call); + _leave(""); +} -extant_call: - spin_unlock(&conn->channel_lock); - kmem_cache_free(rxrpc_call_jar, candidate); - _leave(" = %p {%d} [extant]", call, call ? call->debug_id : -1); - return call; +/* + * Queue a call's work processor, getting a ref to pass to the work queue. + */ +bool rxrpc_queue_call(struct rxrpc_call *call) +{ + const void *here = __builtin_return_address(0); + int n = __atomic_add_unless(&call->usage, 1, 0); + if (n == 0) + return false; + if (rxrpc_queue_work(&call->processor)) + trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + else + rxrpc_put_call(call, rxrpc_call_put_noqueue); + return true; +} -aborted_call: - spin_unlock(&conn->channel_lock); - kmem_cache_free(rxrpc_call_jar, candidate); - _leave(" = -ECONNABORTED"); - return ERR_PTR(-ECONNABORTED); - -old_call: - spin_unlock(&conn->channel_lock); - kmem_cache_free(rxrpc_call_jar, candidate); - _leave(" = -ECONNRESET [old]"); - return ERR_PTR(-ECONNRESET); +/* + * Queue a call's work processor, passing the callers ref to the work queue. + */ +bool __rxrpc_queue_call(struct rxrpc_call *call) +{ + const void *here = __builtin_return_address(0); + int n = atomic_read(&call->usage); + ASSERTCMP(n, >=, 1); + if (rxrpc_queue_work(&call->processor)) + trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + else + rxrpc_put_call(call, rxrpc_call_put_noqueue); + return true; } /* @@ -445,157 +399,88 @@ void rxrpc_see_call(struct rxrpc_call *call) const void *here = __builtin_return_address(0); if (call) { int n = atomic_read(&call->usage); - int m = atomic_read(&call->skb_count); - trace_rxrpc_call(call, 2, n, m, here, 0); + trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); } } /* * Note the addition of a ref on a call. */ -void rxrpc_get_call(struct rxrpc_call *call) +void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - int m = atomic_read(&call->skb_count); - trace_rxrpc_call(call, 3, n, m, here, 0); + trace_rxrpc_call(call, op, n, here, NULL); } /* - * Note the addition of a ref on a call for a socket buffer. + * Detach a call from its owning socket. */ -void rxrpc_get_call_for_skb(struct rxrpc_call *call, struct sk_buff *skb) +void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(&call->usage); - int m = atomic_inc_return(&call->skb_count); - - trace_rxrpc_call(call, 4, n, m, here, skb); -} - -/* - * detach a call from a socket and set up for release - */ -void rxrpc_release_call(struct rxrpc_call *call) -{ struct rxrpc_connection *conn = call->conn; - struct rxrpc_sock *rx = call->socket; + bool put = false; + int i; - _enter("{%d,%d,%d,%d}", - call->debug_id, atomic_read(&call->usage), - atomic_read(&call->ackr_not_idle), - call->rx_first_oos); + _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - rxrpc_see_call(call); + trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + here, (const void *)call->flags); + + ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); spin_lock_bh(&call->lock); if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); spin_unlock_bh(&call->lock); - /* dissociate from the socket - * - the socket's ref on the call is passed to the death timer - */ - _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); + del_timer_sync(&call->timer); - spin_lock(&conn->params.peer->lock); - hlist_del_init(&call->error_link); - spin_unlock(&conn->params.peer->lock); + /* Make sure we don't get any more notifications */ + write_lock_bh(&rx->recvmsg_lock); - write_lock_bh(&rx->call_lock); - if (!list_empty(&call->accept_link)) { + if (!list_empty(&call->recvmsg_link)) { _debug("unlinking once-pending call %p { e=%lx f=%lx }", call, call->events, call->flags); - ASSERT(!test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); - list_del_init(&call->accept_link); - sk_acceptq_removed(&rx->sk); - } else if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { - rb_erase(&call->sock_node, &rx->calls); - memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); - clear_bit(RXRPC_CALL_HAS_USERID, &call->flags); + list_del(&call->recvmsg_link); + put = true; } - write_unlock_bh(&rx->call_lock); - /* free up the channel for reuse */ - write_lock_bh(&call->state_lock); + /* list_empty() must return false in rxrpc_notify_socket() */ + call->recvmsg_link.next = NULL; + call->recvmsg_link.prev = NULL; - if (call->state < RXRPC_CALL_COMPLETE && - call->state != RXRPC_CALL_CLIENT_FINAL_ACK) { - _debug("+++ ABORTING STATE %d +++\n", call->state); - __rxrpc_abort_call(call, RX_CALL_DEAD, ECONNRESET); - } - write_unlock_bh(&call->state_lock); - - rxrpc_disconnect_call(call); - - /* clean up the Rx queue */ - if (!skb_queue_empty(&call->rx_queue) || - !skb_queue_empty(&call->rx_oos_queue)) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - - _debug("purge Rx queues"); - - spin_lock_bh(&call->lock); - while ((skb = skb_dequeue(&call->rx_queue)) || - (skb = skb_dequeue(&call->rx_oos_queue))) { - spin_unlock_bh(&call->lock); - - sp = rxrpc_skb(skb); - _debug("- zap %s %%%u #%u", - rxrpc_pkts[sp->hdr.type], - sp->hdr.serial, sp->hdr.seq); - rxrpc_free_skb(skb); - spin_lock_bh(&call->lock); - } - spin_unlock_bh(&call->lock); - } + write_unlock_bh(&rx->recvmsg_lock); + if (put) + rxrpc_put_call(call, rxrpc_call_put); - del_timer_sync(&call->resend_timer); - del_timer_sync(&call->ack_timer); - del_timer_sync(&call->lifetimer); - call->deadspan.expires = jiffies + rxrpc_dead_call_expiry; - add_timer(&call->deadspan); + write_lock(&rx->call_lock); - _leave(""); -} + if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { + rb_erase(&call->sock_node, &rx->calls); + memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); + rxrpc_put_call(call, rxrpc_call_put_userid); + } -/* - * handle a dead call being ready for reaping - */ -static void rxrpc_dead_call_expired(unsigned long _call) -{ - struct rxrpc_call *call = (struct rxrpc_call *) _call; + list_del(&call->sock_link); + write_unlock(&rx->call_lock); - _enter("{%d}", call->debug_id); + _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - rxrpc_see_call(call); - write_lock_bh(&call->state_lock); - call->state = RXRPC_CALL_DEAD; - write_unlock_bh(&call->state_lock); - rxrpc_put_call(call); -} + if (conn) + rxrpc_disconnect_call(call); -/* - * mark a call as to be released, aborting it if it's still in progress - * - called with softirqs disabled - */ -static void rxrpc_mark_call_released(struct rxrpc_call *call) -{ - bool sched = false; - - rxrpc_see_call(call); - write_lock(&call->state_lock); - if (call->state < RXRPC_CALL_DEAD) { - sched = __rxrpc_abort_call(call, RX_CALL_DEAD, ECONNRESET); - if (!test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) - sched = true; + for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { + rxrpc_free_skb(call->rxtx_buffer[i], + (call->tx_phase ? rxrpc_skb_tx_cleaned : + rxrpc_skb_rx_cleaned)); + call->rxtx_buffer[i] = NULL; } - write_unlock(&call->state_lock); - if (sched) - rxrpc_queue_call(call); + + _leave(""); } /* @@ -604,70 +489,52 @@ static void rxrpc_mark_call_released(struct rxrpc_call *call) void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) { struct rxrpc_call *call; - struct rb_node *p; _enter("%p", rx); - read_lock_bh(&rx->call_lock); - - /* kill the not-yet-accepted incoming calls */ - list_for_each_entry(call, &rx->secureq, accept_link) { - rxrpc_mark_call_released(call); - } - - list_for_each_entry(call, &rx->acceptq, accept_link) { - rxrpc_mark_call_released(call); + while (!list_empty(&rx->to_be_accepted)) { + call = list_entry(rx->to_be_accepted.next, + struct rxrpc_call, accept_link); + list_del(&call->accept_link); + rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, ECONNRESET); + rxrpc_put_call(call, rxrpc_call_put); } - /* mark all the calls as no longer wanting incoming packets */ - for (p = rb_first(&rx->calls); p; p = rb_next(p)) { - call = rb_entry(p, struct rxrpc_call, sock_node); - rxrpc_mark_call_released(call); + while (!list_empty(&rx->sock_calls)) { + call = list_entry(rx->sock_calls.next, + struct rxrpc_call, sock_link); + rxrpc_get_call(call, rxrpc_call_got); + rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, ECONNRESET); + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_release_call(rx, call); + rxrpc_put_call(call, rxrpc_call_put); } - read_unlock_bh(&rx->call_lock); _leave(""); } /* * release a call */ -void rxrpc_put_call(struct rxrpc_call *call) +void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { const void *here = __builtin_return_address(0); - int n, m; + int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - m = atomic_read(&call->skb_count); - trace_rxrpc_call(call, 5, n, m, here, NULL); + trace_rxrpc_call(call, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); - WARN_ON(m != 0); - ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); - rxrpc_queue_work(&call->destroyer); - } -} + ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); -/* - * Release a call ref held by a socket buffer. - */ -void rxrpc_put_call_for_skb(struct rxrpc_call *call, struct sk_buff *skb) -{ - const void *here = __builtin_return_address(0); - int n, m; + write_lock(&rxrpc_call_lock); + list_del_init(&call->link); + write_unlock(&rxrpc_call_lock); - n = atomic_dec_return(&call->usage); - m = atomic_dec_return(&call->skb_count); - trace_rxrpc_call(call, 6, n, m, here, skb); - ASSERTCMP(n, >=, 0); - if (n == 0) { - _debug("call %d dead", call->debug_id); - WARN_ON(m != 0); - ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); - rxrpc_queue_work(&call->destroyer); + rxrpc_cleanup_call(call); } } @@ -678,99 +545,53 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) { struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); - rxrpc_purge_queue(&call->rx_queue); - rxrpc_purge_queue(&call->knlrecv_queue); rxrpc_put_peer(call->peer); + kfree(call->rxtx_buffer); + kfree(call->rxtx_annotations); kmem_cache_free(rxrpc_call_jar, call); } /* * clean up a call */ -static void rxrpc_cleanup_call(struct rxrpc_call *call) +void rxrpc_cleanup_call(struct rxrpc_call *call) { - _net("DESTROY CALL %d", call->debug_id); + int i; - ASSERT(call->socket); + _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); - del_timer_sync(&call->lifetimer); - del_timer_sync(&call->deadspan); - del_timer_sync(&call->ack_timer); - del_timer_sync(&call->resend_timer); + del_timer_sync(&call->timer); + ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - ASSERTCMP(call->events, ==, 0); - if (work_pending(&call->processor)) { - _debug("defer destroy"); - rxrpc_queue_work(&call->destroyer); - return; - } - ASSERTCMP(call->conn, ==, NULL); - if (call->acks_window) { - _debug("kill Tx window %d", - CIRC_CNT(call->acks_head, call->acks_tail, - call->acks_winsz)); - smp_mb(); - while (CIRC_CNT(call->acks_head, call->acks_tail, - call->acks_winsz) > 0) { - struct rxrpc_skb_priv *sp; - unsigned long _skb; - - _skb = call->acks_window[call->acks_tail] & ~1; - sp = rxrpc_skb((struct sk_buff *)_skb); - _debug("+++ clear Tx %u", sp->hdr.seq); - rxrpc_free_skb((struct sk_buff *)_skb); - call->acks_tail = - (call->acks_tail + 1) & (call->acks_winsz - 1); - } - - kfree(call->acks_window); - } + /* Clean up the Rx/Tx buffer */ + for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) + rxrpc_free_skb(call->rxtx_buffer[i], + (call->tx_phase ? rxrpc_skb_tx_cleaned : + rxrpc_skb_rx_cleaned)); - rxrpc_free_skb(call->tx_pending); + rxrpc_free_skb(call->tx_pending, rxrpc_skb_tx_cleaned); - rxrpc_purge_queue(&call->rx_queue); - ASSERT(skb_queue_empty(&call->rx_oos_queue)); - rxrpc_purge_queue(&call->knlrecv_queue); - sock_put(&call->socket->sk); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } /* - * destroy a call - */ -static void rxrpc_destroy_call(struct work_struct *work) -{ - struct rxrpc_call *call = - container_of(work, struct rxrpc_call, destroyer); - - _enter("%p{%d,%x,%p}", - call, atomic_read(&call->usage), call->cid, call->conn); - - ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); - - write_lock_bh(&rxrpc_call_lock); - list_del_init(&call->link); - write_unlock_bh(&rxrpc_call_lock); - - rxrpc_cleanup_call(call); - _leave(""); -} - -/* - * preemptively destroy all the call records from a transport endpoint rather - * than waiting for them to time out + * Make sure that all calls are gone. */ void __exit rxrpc_destroy_all_calls(void) { struct rxrpc_call *call; _enter(""); - write_lock_bh(&rxrpc_call_lock); + + if (list_empty(&rxrpc_calls)) + return; + + write_lock(&rxrpc_call_lock); while (!list_empty(&rxrpc_calls)) { call = list_entry(rxrpc_calls.next, struct rxrpc_call, link); @@ -779,87 +600,15 @@ void __exit rxrpc_destroy_all_calls(void) rxrpc_see_call(call); list_del_init(&call->link); - switch (atomic_read(&call->usage)) { - case 0: - ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); - break; - case 1: - if (del_timer_sync(&call->deadspan) != 0 && - call->state != RXRPC_CALL_DEAD) - rxrpc_dead_call_expired((unsigned long) call); - if (call->state != RXRPC_CALL_DEAD) - break; - default: - pr_err("Call %p still in use (%d,%d,%s,%lx,%lx)!\n", - call, atomic_read(&call->usage), - atomic_read(&call->ackr_not_idle), - rxrpc_call_states[call->state], - call->flags, call->events); - if (!skb_queue_empty(&call->rx_queue)) - pr_err("Rx queue occupied\n"); - if (!skb_queue_empty(&call->rx_oos_queue)) - pr_err("OOS queue occupied\n"); - break; - } - - write_unlock_bh(&rxrpc_call_lock); + pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", + call, atomic_read(&call->usage), + rxrpc_call_states[call->state], + call->flags, call->events); + + write_unlock(&rxrpc_call_lock); cond_resched(); - write_lock_bh(&rxrpc_call_lock); + write_lock(&rxrpc_call_lock); } - write_unlock_bh(&rxrpc_call_lock); - _leave(""); -} - -/* - * handle call lifetime being exceeded - */ -static void rxrpc_call_life_expired(unsigned long _call) -{ - struct rxrpc_call *call = (struct rxrpc_call *) _call; - - _enter("{%d}", call->debug_id); - - rxrpc_see_call(call); - if (call->state >= RXRPC_CALL_COMPLETE) - return; - - set_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); - rxrpc_queue_call(call); -} - -/* - * handle resend timer expiry - * - may not take call->state_lock as this can deadlock against del_timer_sync() - */ -static void rxrpc_resend_time_expired(unsigned long _call) -{ - struct rxrpc_call *call = (struct rxrpc_call *) _call; - - _enter("{%d}", call->debug_id); - - rxrpc_see_call(call); - if (call->state >= RXRPC_CALL_COMPLETE) - return; - - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) - rxrpc_queue_call(call); -} - -/* - * handle ACK timer expiry - */ -static void rxrpc_ack_time_expired(unsigned long _call) -{ - struct rxrpc_call *call = (struct rxrpc_call *) _call; - - _enter("{%d}", call->debug_id); - - rxrpc_see_call(call); - if (call->state >= RXRPC_CALL_COMPLETE) - return; - - if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) - rxrpc_queue_call(call); + write_unlock(&rxrpc_call_lock); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 82de1ae..c76a125 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -105,6 +105,14 @@ static void rxrpc_discard_expired_client_conns(struct work_struct *); static DECLARE_DELAYED_WORK(rxrpc_client_conn_reap, rxrpc_discard_expired_client_conns); +const char rxrpc_conn_cache_states[RXRPC_CONN__NR_CACHE_STATES][5] = { + [RXRPC_CONN_CLIENT_INACTIVE] = "Inac", + [RXRPC_CONN_CLIENT_WAITING] = "Wait", + [RXRPC_CONN_CLIENT_ACTIVE] = "Actv", + [RXRPC_CONN_CLIENT_CULLED] = "Cull", + [RXRPC_CONN_CLIENT_IDLE] = "Idle", +}; + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -220,6 +228,9 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) rxrpc_get_local(conn->params.local); key_get(conn->params.key); + trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage), + __builtin_return_address(0)); + trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); return conn; @@ -348,6 +359,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, if (cp->exclusive) { call->conn = candidate; + call->security_ix = candidate->security_ix; _leave(" = 0 [exclusive %d]", candidate->debug_id); return 0; } @@ -384,6 +396,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, rb_replace_node(&conn->client_node, &candidate->client_node, &local->client_conns); + trace_rxrpc_client(conn, -1, rxrpc_client_replace); goto candidate_published; } } @@ -395,6 +408,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call, candidate_published: set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); call->conn = candidate; + call->security_ix = candidate->security_ix; spin_unlock(&local->client_conns_lock); _leave(" = 0 [new %d]", candidate->debug_id); return 0; @@ -407,11 +421,15 @@ found_extant_conn: _debug("found conn"); spin_unlock(&local->client_conns_lock); - rxrpc_put_connection(candidate); - candidate = NULL; + if (candidate) { + trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); + rxrpc_put_connection(candidate); + candidate = NULL; + } spin_lock(&conn->channel_lock); call->conn = conn; + call->security_ix = conn->security_ix; list_add(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); _leave(" = 0 [extant %d]", conn->debug_id); @@ -430,6 +448,7 @@ error: */ static void rxrpc_activate_conn(struct rxrpc_connection *conn) { + trace_rxrpc_client(conn, -1, rxrpc_client_to_active); conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; rxrpc_nr_active_client_conns++; list_move_tail(&conn->cache_link, &rxrpc_active_client_conns); @@ -459,8 +478,10 @@ static void rxrpc_animate_client_conn(struct rxrpc_connection *conn) spin_lock(&rxrpc_client_conn_cache_lock); nr_conns = rxrpc_nr_client_conns; - if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) + if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) { + trace_rxrpc_client(conn, -1, rxrpc_client_count); rxrpc_nr_client_conns = nr_conns + 1; + } switch (conn->cache_state) { case RXRPC_CONN_CLIENT_ACTIVE: @@ -491,6 +512,7 @@ activate_conn: wait_for_capacity: _debug("wait"); + trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); conn->cache_state = RXRPC_CONN_CLIENT_WAITING; list_move_tail(&conn->cache_link, &rxrpc_waiting_client_conns); goto out_unlock; @@ -521,6 +543,8 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, struct rxrpc_call, chan_wait_link); u32 call_id = chan->call_counter + 1; + trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate); + write_lock_bh(&call->state_lock); call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; write_unlock_bh(&call->state_lock); @@ -560,6 +584,8 @@ static void rxrpc_activate_channels(struct rxrpc_connection *conn) _enter("%d", conn->debug_id); + trace_rxrpc_client(conn, -1, rxrpc_client_activate_chans); + if (conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE || conn->active_chans == RXRPC_ACTIVE_CHANS_MASK) return; @@ -654,10 +680,13 @@ int rxrpc_connect_call(struct rxrpc_call *call, * had a chance at re-use (the per-connection security negotiation is * expensive). */ -static void rxrpc_expose_client_conn(struct rxrpc_connection *conn) +static void rxrpc_expose_client_conn(struct rxrpc_connection *conn, + unsigned int channel) { - if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) + if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { + trace_rxrpc_client(conn, channel, rxrpc_client_exposed); rxrpc_get_connection(conn); + } } /* @@ -666,9 +695,9 @@ static void rxrpc_expose_client_conn(struct rxrpc_connection *conn) */ void rxrpc_expose_client_call(struct rxrpc_call *call) { + unsigned int channel = call->cid & RXRPC_CHANNELMASK; struct rxrpc_connection *conn = call->conn; - struct rxrpc_channel *chan = - &conn->channels[call->cid & RXRPC_CHANNELMASK]; + struct rxrpc_channel *chan = &conn->channels[channel]; if (!test_and_set_bit(RXRPC_CALL_EXPOSED, &call->flags)) { /* Mark the call ID as being used. If the callNumber counter @@ -679,7 +708,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) chan->call_counter++; if (chan->call_counter >= INT_MAX) set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_expose_client_conn(conn); + rxrpc_expose_client_conn(conn, channel); } } @@ -692,6 +721,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) struct rxrpc_connection *conn = call->conn; struct rxrpc_channel *chan = &conn->channels[channel]; + trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); call->conn = NULL; spin_lock(&conn->channel_lock); @@ -706,6 +736,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); list_del_init(&call->chan_wait_link); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_unstarted); + /* We must deactivate or idle the connection if it's now * waiting for nothing. */ @@ -718,7 +750,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) } ASSERTCMP(rcu_access_pointer(chan->call), ==, call); - ASSERTCMP(atomic_read(&conn->usage), >=, 2); /* If a client call was exposed to the world, we save the result for * retransmission. @@ -737,7 +768,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) /* See if we can pass the channel directly to another call. */ if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE && !list_empty(&conn->waiting_calls)) { - _debug("pass chan"); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); goto out_2; } @@ -760,7 +791,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) goto out; } - _debug("pass chan 2"); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); goto out; @@ -792,7 +823,7 @@ idle_connection: * immediately or moved to the idle list for a short while. */ if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - _debug("make idle"); + trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); conn->idle_timestamp = jiffies; conn->cache_state = RXRPC_CONN_CLIENT_IDLE; list_move_tail(&conn->cache_link, &rxrpc_idle_client_conns); @@ -802,7 +833,7 @@ idle_connection: &rxrpc_client_conn_reap, rxrpc_conn_idle_client_expiry); } else { - _debug("make inactive"); + trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive); conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_del_init(&conn->cache_link); } @@ -815,10 +846,12 @@ idle_connection: static struct rxrpc_connection * rxrpc_put_one_client_conn(struct rxrpc_connection *conn) { - struct rxrpc_connection *next; + struct rxrpc_connection *next = NULL; struct rxrpc_local *local = conn->params.local; unsigned int nr_conns; + trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); + if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) { spin_lock(&local->client_conns_lock); if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, @@ -831,24 +864,23 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE); - if (!test_bit(RXRPC_CONN_COUNTED, &conn->flags)) - return NULL; - - spin_lock(&rxrpc_client_conn_cache_lock); - nr_conns = --rxrpc_nr_client_conns; + if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) { + trace_rxrpc_client(conn, -1, rxrpc_client_uncount); + spin_lock(&rxrpc_client_conn_cache_lock); + nr_conns = --rxrpc_nr_client_conns; + + if (nr_conns < rxrpc_max_client_connections && + !list_empty(&rxrpc_waiting_client_conns)) { + next = list_entry(rxrpc_waiting_client_conns.next, + struct rxrpc_connection, cache_link); + rxrpc_get_connection(next); + rxrpc_activate_conn(next); + } - next = NULL; - if (nr_conns < rxrpc_max_client_connections && - !list_empty(&rxrpc_waiting_client_conns)) { - next = list_entry(rxrpc_waiting_client_conns.next, - struct rxrpc_connection, cache_link); - rxrpc_get_connection(next); - rxrpc_activate_conn(next); + spin_unlock(&rxrpc_client_conn_cache_lock); } - spin_unlock(&rxrpc_client_conn_cache_lock); rxrpc_kill_connection(conn); - if (next) rxrpc_activate_channels(next); @@ -863,20 +895,18 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) */ void rxrpc_put_client_conn(struct rxrpc_connection *conn) { - struct rxrpc_connection *next; + const void *here = __builtin_return_address(0); + int n; do { - _enter("%p{u=%d,d=%d}", - conn, atomic_read(&conn->usage), conn->debug_id); - - next = rxrpc_put_one_client_conn(conn); - - if (!next) - break; - conn = next; - } while (atomic_dec_and_test(&conn->usage)); - - _leave(""); + n = atomic_dec_return(&conn->usage); + trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here); + if (n > 0) + return; + ASSERTCMP(n, >=, 0); + + conn = rxrpc_put_one_client_conn(conn); + } while (conn); } /* @@ -907,9 +937,11 @@ static void rxrpc_cull_active_client_conns(void) ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_ACTIVE); if (list_empty(&conn->waiting_calls)) { + trace_rxrpc_client(conn, -1, rxrpc_client_to_culled); conn->cache_state = RXRPC_CONN_CLIENT_CULLED; list_del_init(&conn->cache_link); } else { + trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); conn->cache_state = RXRPC_CONN_CLIENT_WAITING; list_move_tail(&conn->cache_link, &rxrpc_waiting_client_conns); @@ -983,7 +1015,7 @@ next: goto not_yet_expired; } - _debug("discard conn %d", conn->debug_id); + trace_rxrpc_client(conn, -1, rxrpc_client_discard); if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) BUG(); conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 9db90f4..37609ce 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -15,10 +15,6 @@ #include <linux/net.h> #include <linux/skbuff.h> #include <linux/errqueue.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> @@ -101,6 +97,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.info.maxMTU = htonl(mtu); pkt.info.rwind = htonl(rxrpc_rx_window_size); pkt.info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + pkt.whdr.flags |= RXRPC_SLOW_START_OK; len += sizeof(pkt.ack) + sizeof(pkt.info); break; } @@ -123,6 +120,8 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); break; case RXRPC_PACKET_TYPE_ACK: + trace_rxrpc_tx_ack(NULL, serial, chan->last_seq, 0, + RXRPC_ACK_DUPLICATE, 0); _proto("Tx ACK %%%u [re]", serial); break; } @@ -140,16 +139,10 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, u32 abort_code, int error) { struct rxrpc_call *call; - bool queue; - int i, bit; + int i; _enter("{%d},%x", conn->debug_id, abort_code); - if (compl == RXRPC_CALL_LOCALLY_ABORTED) - bit = RXRPC_CALL_EV_CONN_ABORT; - else - bit = RXRPC_CALL_EV_RCVD_ABORT; - spin_lock(&conn->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { @@ -157,16 +150,13 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, conn->channels[i].call, lockdep_is_held(&conn->channel_lock)); if (call) { - rxrpc_see_call(call); - write_lock_bh(&call->state_lock); - if (rxrpc_set_call_completion(call, compl, abort_code, - error)) { - set_bit(bit, &call->events); - queue = true; - } - write_unlock_bh(&call->state_lock); - if (queue) - rxrpc_queue_call(call); + if (compl == RXRPC_CALL_LOCALLY_ABORTED) + trace_rxrpc_abort("CON", call->cid, + call->call_id, 0, + abort_code, error); + if (rxrpc_set_call_completion(call, compl, + abort_code, error)) + rxrpc_notify_socket(call); } } @@ -245,17 +235,18 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, /* * mark a call as being on a now-secured channel - * - must be called with softirqs disabled + * - must be called with BH's disabled. */ static void rxrpc_call_is_secure(struct rxrpc_call *call) { _enter("%p", call); if (call) { - read_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE && - !test_and_set_bit(RXRPC_CALL_EV_SECURED, &call->events)) - rxrpc_queue_call(call); - read_unlock(&call->state_lock); + write_lock_bh(&call->state_lock); + if (call->state == RXRPC_CALL_SERVER_SECURING) { + call->state = RXRPC_CALL_SERVER_ACCEPTING; + rxrpc_notify_socket(call); + } + write_unlock_bh(&call->state_lock); } } @@ -272,7 +263,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, int loop, ret; if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - kleave(" = -ECONNABORTED [%u]", conn->state); + _leave(" = -ECONNABORTED [%u]", conn->state); return -ECONNABORTED; } @@ -285,14 +276,14 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return 0; case RXRPC_PACKET_TYPE_ABORT: - if (skb_copy_bits(skb, 0, &wtmp, sizeof(wtmp)) < 0) + if (skb_copy_bits(skb, sp->offset, &wtmp, sizeof(wtmp)) < 0) return -EPROTO; abort_code = ntohl(wtmp); _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, 0, RXRPC_CALL_REMOTELY_ABORTED, - abort_code); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, + abort_code, ECONNABORTED); return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: @@ -317,14 +308,16 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; + spin_unlock(&conn->state_lock); for (loop = 0; loop < RXRPC_MAXCALLS; loop++) rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, lockdep_is_held(&conn->channel_lock))); + } else { + spin_unlock(&conn->state_lock); } - spin_unlock(&conn->state_lock); spin_unlock(&conn->channel_lock); return 0; @@ -387,7 +380,7 @@ void rxrpc_process_connection(struct work_struct *work) u32 abort_code = RX_PROTOCOL_ERROR; int ret; - _enter("{%d}", conn->debug_id); + rxrpc_see_connection(conn); if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) rxrpc_secure_connection(conn); @@ -395,7 +388,7 @@ void rxrpc_process_connection(struct work_struct *work) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - rxrpc_see_skb(skb); + rxrpc_see_skb(skb, rxrpc_skb_rx_seen); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -406,7 +399,7 @@ void rxrpc_process_connection(struct work_struct *work) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); break; } } @@ -423,92 +416,7 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, -ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); _leave(" [EPROTO]"); goto out; } - -/* - * put a packet up for transport-level abort - */ -void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) -{ - CHECK_SLAB_OKAY(&local->usage); - - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); -} - -/* - * reject packets through the local endpoint - */ -void rxrpc_reject_packets(struct rxrpc_local *local) -{ - union { - struct sockaddr sa; - struct sockaddr_in sin; - } sa; - struct rxrpc_skb_priv *sp; - struct rxrpc_wire_header whdr; - struct sk_buff *skb; - struct msghdr msg; - struct kvec iov[2]; - size_t size; - __be32 code; - - _enter("%d", local->debug_id); - - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = &code; - iov[1].iov_len = sizeof(code); - size = sizeof(whdr) + sizeof(code); - - msg.msg_name = &sa; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; - - memset(&sa, 0, sizeof(sa)); - sa.sa.sa_family = local->srx.transport.family; - switch (sa.sa.sa_family) { - case AF_INET: - msg.msg_namelen = sizeof(sa.sin); - break; - default: - msg.msg_namelen = 0; - break; - } - - memset(&whdr, 0, sizeof(whdr)); - whdr.type = RXRPC_PACKET_TYPE_ABORT; - - while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb); - sp = rxrpc_skb(skb); - switch (sa.sa.sa_family) { - case AF_INET: - sa.sin.sin_port = udp_hdr(skb)->source; - sa.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; - code = htonl(skb->priority); - - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.serviceId = htons(sp->hdr.serviceId); - whdr.flags = sp->hdr.flags; - whdr.flags ^= RXRPC_CLIENT_INITIATED; - whdr.flags &= RXRPC_CLIENT_INITIATED; - - kernel_sendmsg(local->socket, &msg, iov, 2, size); - break; - - default: - break; - } - - rxrpc_free_skb(skb); - } - - _leave(""); -} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 9c6685b..e1e83af 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -53,7 +53,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); conn->size_align = 4; - conn->header_size = sizeof(struct rxrpc_wire_header); conn->idle_timestamp = jiffies; } @@ -134,6 +133,16 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, srx.transport.sin.sin_addr.s_addr) goto not_found; break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + if (peer->srx.transport.sin6.sin6_port != + srx.transport.sin6.sin6_port || + memcmp(&peer->srx.transport.sin6.sin6_addr, + &srx.transport.sin6.sin6_addr, + sizeof(struct in6_addr)) != 0) + goto not_found; + break; +#endif default: BUG(); } @@ -169,7 +178,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, chan->last_abort = call->abort_code; chan->last_type = RXRPC_PACKET_TYPE_ABORT; } else { - chan->last_seq = call->rx_data_eaten; + chan->last_seq = call->rx_hard_ack; chan->last_type = RXRPC_PACKET_TYPE_ACK; } /* Sync with rxrpc_conn_retransmit(). */ @@ -191,6 +200,10 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; + spin_lock_bh(&conn->params.peer->lock); + hlist_del_init(&call->error_link); + spin_unlock_bh(&conn->params.peer->lock); + if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); @@ -232,11 +245,77 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) } /* - * release a virtual connection + * Queue a connection's work processor, getting a ref to pass to the work + * queue. */ -void __rxrpc_put_connection(struct rxrpc_connection *conn) +bool rxrpc_queue_conn(struct rxrpc_connection *conn) { - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); + const void *here = __builtin_return_address(0); + int n = __atomic_add_unless(&conn->usage, 1, 0); + if (n == 0) + return false; + if (rxrpc_queue_work(&conn->processor)) + trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here); + else + rxrpc_put_connection(conn); + return true; +} + +/* + * Note the re-emergence of a connection. + */ +void rxrpc_see_connection(struct rxrpc_connection *conn) +{ + const void *here = __builtin_return_address(0); + if (conn) { + int n = atomic_read(&conn->usage); + + trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here); + } +} + +/* + * Get a ref on a connection. + */ +void rxrpc_get_connection(struct rxrpc_connection *conn) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&conn->usage); + + trace_rxrpc_conn(conn, rxrpc_conn_got, n, here); +} + +/* + * Try to get a ref on a connection. + */ +struct rxrpc_connection * +rxrpc_get_connection_maybe(struct rxrpc_connection *conn) +{ + const void *here = __builtin_return_address(0); + + if (conn) { + int n = __atomic_add_unless(&conn->usage, 1, 0); + if (n > 0) + trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); + else + conn = NULL; + } + return conn; +} + +/* + * Release a service connection + */ +void rxrpc_put_service_conn(struct rxrpc_connection *conn) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&conn->usage); + trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here); + ASSERTCMP(n, >=, 0); + if (n == 0) + rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); } /* @@ -286,6 +365,8 @@ static void rxrpc_connection_reaper(struct work_struct *work) ASSERTCMP(atomic_read(&conn->usage), >, 0); if (likely(atomic_read(&conn->usage) > 1)) continue; + if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) + continue; idle_timestamp = READ_ONCE(conn->idle_timestamp); _debug("reap CONN %d { u=%d,t=%ld }", diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 316a921..eef551f 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -65,9 +65,8 @@ done: * Insert a service connection into a peer's tree, thereby making it a target * for incoming packets. */ -static struct rxrpc_connection * -rxrpc_publish_service_conn(struct rxrpc_peer *peer, - struct rxrpc_connection *conn) +static void rxrpc_publish_service_conn(struct rxrpc_peer *peer, + struct rxrpc_connection *conn) { struct rxrpc_connection *cursor = NULL; struct rxrpc_conn_proto k = conn->proto; @@ -96,7 +95,7 @@ conn_published: set_bit(RXRPC_CONN_IN_SERVICE_CONNS, &conn->flags); write_sequnlock_bh(&peer->service_conn_lock); _leave(" = %d [new]", conn->debug_id); - return conn; + return; found_extant_conn: if (atomic_read(&cursor->usage) == 0) @@ -119,106 +118,58 @@ replace_old_connection: } /* - * get a record of an incoming connection + * Preallocate a service connection. The connection is placed on the proc and + * reap lists so that we don't have to get the lock from BH context. */ -struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *local, - struct sockaddr_rxrpc *srx, - struct sk_buff *skb) +struct rxrpc_connection *rxrpc_prealloc_service_connection(gfp_t gfp) { - struct rxrpc_connection *conn; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_peer *peer; - const char *new = "old"; - - _enter(""); + struct rxrpc_connection *conn = rxrpc_alloc_connection(gfp); - peer = rxrpc_lookup_peer(local, srx, GFP_NOIO); - if (!peer) { - _debug("no peer"); - return ERR_PTR(-EBUSY); - } + if (conn) { + /* We maintain an extra ref on the connection whilst it is on + * the rxrpc_connections list. + */ + conn->state = RXRPC_CONN_SERVICE_PREALLOC; + atomic_set(&conn->usage, 2); - ASSERT(sp->hdr.flags & RXRPC_CLIENT_INITIATED); - - rcu_read_lock(); - peer = rxrpc_lookup_peer_rcu(local, srx); - if (peer) { - conn = rxrpc_find_service_conn_rcu(peer, skb); - if (conn) { - if (sp->hdr.securityIndex != conn->security_ix) - goto security_mismatch_rcu; - if (rxrpc_get_connection_maybe(conn)) - goto found_extant_connection_rcu; - - /* The conn has expired but we can't remove it without - * the appropriate lock, so we attempt to replace it - * when we have a new candidate. - */ - } + write_lock(&rxrpc_connection_lock); + list_add_tail(&conn->link, &rxrpc_connections); + list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); + write_unlock(&rxrpc_connection_lock); - if (!rxrpc_get_peer_maybe(peer)) - peer = NULL; + trace_rxrpc_conn(conn, rxrpc_conn_new_service, + atomic_read(&conn->usage), + __builtin_return_address(0)); } - rcu_read_unlock(); - if (!peer) { - peer = rxrpc_lookup_peer(local, srx, GFP_NOIO); - if (!peer) - goto enomem; - } + return conn; +} - /* We don't have a matching record yet. */ - conn = rxrpc_alloc_connection(GFP_NOIO); - if (!conn) - goto enomem_peer; +/* + * Set up an incoming connection. This is called in BH context with the RCU + * read lock held. + */ +void rxrpc_new_incoming_connection(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + _enter(""); conn->proto.epoch = sp->hdr.epoch; conn->proto.cid = sp->hdr.cid & RXRPC_CIDMASK; - conn->params.local = local; - conn->params.peer = peer; conn->params.service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; - conn->state = RXRPC_CONN_SERVICE; - if (conn->params.service_id) + if (conn->security_ix) conn->state = RXRPC_CONN_SERVICE_UNSECURED; - - rxrpc_get_local(local); - - /* We maintain an extra ref on the connection whilst it is on - * the rxrpc_connections list. - */ - atomic_set(&conn->usage, 2); - - write_lock(&rxrpc_connection_lock); - list_add_tail(&conn->link, &rxrpc_connections); - list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); - write_unlock(&rxrpc_connection_lock); + else + conn->state = RXRPC_CONN_SERVICE; /* Make the connection a target for incoming packets. */ - rxrpc_publish_service_conn(peer, conn); - - new = "new"; - -success: - _net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->proto.cid); - _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); - return conn; - -found_extant_connection_rcu: - rcu_read_unlock(); - goto success; - -security_mismatch_rcu: - rcu_read_unlock(); - _leave(" = -EKEYREJECTED"); - return ERR_PTR(-EKEYREJECTED); + rxrpc_publish_service_conn(conn->params.peer, conn); -enomem_peer: - rxrpc_put_peer(peer); -enomem: - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); + _net("CONNECTION new %d {%x}", conn->debug_id, conn->proto.cid); } /* diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 72f016c..094720d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1,6 +1,6 @@ /* RxRPC packet reception * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -27,545 +27,908 @@ #include <net/net_namespace.h> #include "ar-internal.h" +static void rxrpc_proto_abort(const char *why, + struct rxrpc_call *call, rxrpc_seq_t seq) +{ + if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, EBADMSG)) { + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + rxrpc_queue_call(call); + } +} + /* - * queue a packet for recvmsg to pass to userspace - * - the caller must hold a lock on call->lock - * - must not be called with interrupts disabled (sk_filter() disables BH's) - * - eats the packet whether successful or not - * - there must be just one reference to the packet, which the caller passes to - * this function + * Do TCP-style congestion management [RFC 5681]. */ -int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, - bool force, bool terminal) +static void rxrpc_congestion_management(struct rxrpc_call *call, + struct sk_buff *skb, + struct rxrpc_ack_summary *summary) { - struct rxrpc_skb_priv *sp; - struct rxrpc_sock *rx = call->socket; - struct sock *sk; - int ret; + enum rxrpc_congest_change change = rxrpc_cong_no_change; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + unsigned int cumulative_acks = call->cong_cumul_acks; + unsigned int cwnd = call->cong_cwnd; + bool resend = false; + + summary->flight_size = + (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + + if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { + summary->retrans_timeo = true; + call->cong_ssthresh = max_t(unsigned int, + summary->flight_size / 2, 2); + cwnd = 1; + if (cwnd > call->cong_ssthresh && + call->cong_mode == RXRPC_CALL_SLOW_START) { + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + call->cong_tstamp = skb->tstamp; + cumulative_acks = 0; + } + } - _enter(",,%d,%d", force, terminal); + cumulative_acks += summary->nr_new_acks; + cumulative_acks += summary->nr_rot_new_acks; + if (cumulative_acks > 255) + cumulative_acks = 255; + + summary->mode = call->cong_mode; + summary->cwnd = call->cong_cwnd; + summary->ssthresh = call->cong_ssthresh; + summary->cumulative_acks = cumulative_acks; + summary->dup_acks = call->cong_dup_acks; + + switch (call->cong_mode) { + case RXRPC_CALL_SLOW_START: + if (summary->nr_nacks > 0) + goto packet_loss_detected; + if (summary->cumulative_acks > 0) + cwnd += 1; + if (cwnd > call->cong_ssthresh) { + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + call->cong_tstamp = skb->tstamp; + } + goto out; - ASSERT(!irqs_disabled()); + case RXRPC_CALL_CONGEST_AVOIDANCE: + if (summary->nr_nacks > 0) + goto packet_loss_detected; - sp = rxrpc_skb(skb); - ASSERTCMP(sp->call, ==, call); - - /* if we've already posted the terminal message for a call, then we - * don't post any more */ - if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { - _debug("already terminated"); - ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE); - rxrpc_free_skb(skb); - return 0; - } - - sk = &rx->sk; - - if (!force) { - /* cast skb->rcvbuf to unsigned... It's pointless, but - * reduces number of warnings when compiling with -W - * --ANK */ -// ret = -ENOBUFS; -// if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= -// (unsigned int) sk->sk_rcvbuf) -// goto out; - - ret = sk_filter(sk, skb); - if (ret < 0) + /* We analyse the number of packets that get ACK'd per RTT + * period and increase the window if we managed to fill it. + */ + if (call->peer->rtt_usage == 0) goto out; - } + if (ktime_before(skb->tstamp, + ktime_add_ns(call->cong_tstamp, + call->peer->rtt))) + goto out_no_clear_ca; + change = rxrpc_cong_rtt_window_end; + call->cong_tstamp = skb->tstamp; + if (cumulative_acks >= cwnd) + cwnd++; + goto out; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags) && - !test_bit(RXRPC_CALL_RELEASED, &call->flags) && - call->socket->sk.sk_state != RXRPC_CLOSE) { - skb->destructor = rxrpc_packet_destructor; - skb->dev = NULL; - skb->sk = sk; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); + case RXRPC_CALL_PACKET_LOSS: + if (summary->nr_nacks == 0) + goto resume_normality; - if (terminal) { - _debug("<<<< TERMINAL MESSAGE >>>>"); - set_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags); + if (summary->new_low_nack) { + change = rxrpc_cong_new_low_nack; + call->cong_dup_acks = 1; + if (call->cong_extra > 1) + call->cong_extra = 1; + goto send_extra_data; } - /* allow interception by a kernel service */ - if (skb->mark == RXRPC_SKB_MARK_NEW_CALL && - rx->notify_new_call) { - spin_unlock_bh(&sk->sk_receive_queue.lock); - skb_queue_tail(&call->knlrecv_queue, skb); - rx->notify_new_call(&rx->sk); - } else if (call->notify_rx) { - spin_unlock_bh(&sk->sk_receive_queue.lock); - skb_queue_tail(&call->knlrecv_queue, skb); - call->notify_rx(&rx->sk, call, call->user_call_ID); - } else { - _net("post skb %p", skb); - __skb_queue_tail(&sk->sk_receive_queue, skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); + call->cong_dup_acks++; + if (call->cong_dup_acks < 3) + goto send_extra_data; + + change = rxrpc_cong_begin_retransmission; + call->cong_mode = RXRPC_CALL_FAST_RETRANSMIT; + call->cong_ssthresh = max_t(unsigned int, + summary->flight_size / 2, 2); + cwnd = call->cong_ssthresh + 3; + call->cong_extra = 0; + call->cong_dup_acks = 0; + resend = true; + goto out; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + case RXRPC_CALL_FAST_RETRANSMIT: + if (!summary->new_low_nack) { + if (summary->nr_new_acks == 0) + cwnd += 1; + call->cong_dup_acks++; + if (call->cong_dup_acks == 2) { + change = rxrpc_cong_retransmit_again; + call->cong_dup_acks = 0; + resend = true; + } + } else { + change = rxrpc_cong_progress; + cwnd = call->cong_ssthresh; + if (summary->nr_nacks == 0) + goto resume_normality; } - skb = NULL; - } else { - spin_unlock_bh(&sk->sk_receive_queue.lock); + goto out; + + default: + BUG(); + goto out; } - ret = 0; +resume_normality: + change = rxrpc_cong_cleared_nacks; + call->cong_dup_acks = 0; + call->cong_extra = 0; + call->cong_tstamp = skb->tstamp; + if (cwnd <= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_SLOW_START; + else + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; out: - rxrpc_free_skb(skb); + cumulative_acks = 0; +out_no_clear_ca: + if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) + cwnd = RXRPC_RXTX_BUFF_SIZE - 1; + call->cong_cwnd = cwnd; + call->cong_cumul_acks = cumulative_acks; + trace_rxrpc_congest(call, summary, sp->hdr.serial, change); + if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) + rxrpc_queue_call(call); + return; - _leave(" = %d", ret); - return ret; +packet_loss_detected: + change = rxrpc_cong_saw_nack; + call->cong_mode = RXRPC_CALL_PACKET_LOSS; + call->cong_dup_acks = 0; + goto send_extra_data; + +send_extra_data: + /* Send some previously unsent DATA if we have some to advance the ACK + * state. + */ + if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & + RXRPC_TX_ANNO_LAST || + summary->nr_acks != call->tx_top - call->tx_hard_ack) { + call->cong_extra++; + wake_up(&call->waitq); + } + goto out_no_clear_ca; } /* - * process a DATA packet, posting the packet to the appropriate queue - * - eats the packet if successful + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. */ -static int rxrpc_fast_process_data(struct rxrpc_call *call, - struct sk_buff *skb, u32 seq) +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, + int skew) { - struct rxrpc_skb_priv *sp; - bool terminal; - int ret, ackbit, ack; - u32 serial; - u16 skew; - u8 flags; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + ktime_t now = skb->tstamp; - _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); + if (call->peer->rtt_usage < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + true, true, + rxrpc_propose_ack_ping_for_params); +} - sp = rxrpc_skb(skb); - ASSERTCMP(sp->call, ==, NULL); - flags = sp->hdr.flags; - serial = sp->hdr.serial; - skew = skb->priority; +/* + * Apply a hard ACK by advancing the Tx window. + */ +static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, + struct rxrpc_ack_summary *summary) +{ + struct sk_buff *skb, *list = NULL; + int ix; + u8 annotation; + + if (call->acks_lowest_nak == call->tx_hard_ack) { + call->acks_lowest_nak = to; + } else if (before_eq(call->acks_lowest_nak, to)) { + summary->new_low_nack = true; + call->acks_lowest_nak = to; + } spin_lock(&call->lock); - if (call->state > RXRPC_CALL_COMPLETE) - goto discard; + while (before(call->tx_hard_ack, to)) { + call->tx_hard_ack++; + ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; + skb = call->rxtx_buffer[ix]; + annotation = call->rxtx_annotations[ix]; + rxrpc_see_skb(skb, rxrpc_skb_tx_rotated); + call->rxtx_buffer[ix] = NULL; + call->rxtx_annotations[ix] = 0; + skb->next = list; + list = skb; + + if (annotation & RXRPC_TX_ANNO_LAST) + set_bit(RXRPC_CALL_TX_LAST, &call->flags); + if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) + summary->nr_rot_new_acks++; + } - ASSERTCMP(call->rx_data_expect, >=, call->rx_data_post); - ASSERTCMP(call->rx_data_post, >=, call->rx_data_recv); - ASSERTCMP(call->rx_data_recv, >=, call->rx_data_eaten); + spin_unlock(&call->lock); - if (seq < call->rx_data_post) { - _debug("dup #%u [-%u]", seq, call->rx_data_post); - ack = RXRPC_ACK_DUPLICATE; - ret = -ENOBUFS; - goto discard_and_ack; - } + trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ? + rxrpc_transmit_rotate_last : + rxrpc_transmit_rotate)); + wake_up(&call->waitq); - /* we may already have the packet in the out of sequence queue */ - ackbit = seq - (call->rx_data_eaten + 1); - ASSERTCMP(ackbit, >=, 0); - if (__test_and_set_bit(ackbit, call->ackr_window)) { - _debug("dup oos #%u [%u,%u]", - seq, call->rx_data_eaten, call->rx_data_post); - ack = RXRPC_ACK_DUPLICATE; - goto discard_and_ack; + while (list) { + skb = list; + list = skb->next; + skb->next = NULL; + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } +} - if (seq >= call->ackr_win_top) { - _debug("exceed #%u [%u]", seq, call->ackr_win_top); - __clear_bit(ackbit, call->ackr_window); - ack = RXRPC_ACK_EXCEEDS_WINDOW; - goto discard_and_ack; - } +/* + * End the transmission phase of a call. + * + * This occurs when we get an ACKALL packet, the first DATA packet of a reply, + * or a final ACK packet. + */ +static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, + const char *abort_why) +{ - if (seq == call->rx_data_expect) { - clear_bit(RXRPC_CALL_EXPECT_OOS, &call->flags); - call->rx_data_expect++; - } else if (seq > call->rx_data_expect) { - _debug("oos #%u [%u]", seq, call->rx_data_expect); - call->rx_data_expect = seq + 1; - if (test_and_set_bit(RXRPC_CALL_EXPECT_OOS, &call->flags)) { - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - goto enqueue_and_ack; - } - goto enqueue_packet; - } + ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); - if (seq != call->rx_data_post) { - _debug("ahead #%u [%u]", seq, call->rx_data_post); - goto enqueue_packet; - } + write_lock(&call->state_lock); - if (test_bit(RXRPC_CALL_RCVD_LAST, &call->flags)) - goto protocol_error; + switch (call->state) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + if (reply_begun) + call->state = RXRPC_CALL_CLIENT_RECV_REPLY; + else + call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + break; - /* if the packet need security things doing to it, then it goes down - * the slow path */ - if (call->conn->security_ix) - goto enqueue_packet; + case RXRPC_CALL_SERVER_AWAIT_ACK: + __rxrpc_call_completed(call); + rxrpc_notify_socket(call); + break; - sp->call = call; - rxrpc_get_call_for_skb(call, skb); - terminal = ((flags & RXRPC_LAST_PACKET) && - !(flags & RXRPC_CLIENT_INITIATED)); - ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); - if (ret < 0) { - if (ret == -ENOMEM || ret == -ENOBUFS) { - __clear_bit(ackbit, call->ackr_window); - ack = RXRPC_ACK_NOSPACE; - goto discard_and_ack; - } - goto out; + default: + goto bad_state; } - skb = NULL; - sp = NULL; - - _debug("post #%u", seq); - ASSERTCMP(call->rx_data_post, ==, seq); - call->rx_data_post++; + write_unlock(&call->state_lock); + if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) { + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, 0, false, true, + rxrpc_propose_ack_client_tx_end); + trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); + } else { + trace_rxrpc_transmit(call, rxrpc_transmit_end); + } + _leave(" = ok"); + return true; + +bad_state: + write_unlock(&call->state_lock); + kdebug("end_tx %s", rxrpc_call_states[call->state]); + rxrpc_proto_abort(abort_why, call, call->tx_top); + return false; +} - if (flags & RXRPC_LAST_PACKET) - set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); +/* + * Begin the reply reception phase of a call. + */ +static bool rxrpc_receiving_reply(struct rxrpc_call *call) +{ + struct rxrpc_ack_summary summary = { 0 }; + rxrpc_seq_t top = READ_ONCE(call->tx_top); + + if (call->ackr_reason) { + spin_lock_bh(&call->lock); + call->ackr_reason = 0; + call->resend_at = call->expire_at; + call->ack_at = call->expire_at; + spin_unlock_bh(&call->lock); + rxrpc_set_timer(call, rxrpc_timer_init_for_reply); + } - /* if we've reached an out of sequence packet then we need to drain - * that queue into the socket Rx queue now */ - if (call->rx_data_post == call->rx_first_oos) { - _debug("drain rx oos now"); - read_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE && - !test_and_set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events)) - rxrpc_queue_call(call); - read_unlock(&call->state_lock); + if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + rxrpc_rotate_tx_window(call, top, &summary); + if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { + rxrpc_proto_abort("TXL", call, top); + return false; } + if (!rxrpc_end_tx_phase(call, true, "ETD")) + return false; + call->tx_phase = false; + return true; +} - spin_unlock(&call->lock); - atomic_inc(&call->ackr_not_idle); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, false); - _leave(" = 0 [posted]"); - return 0; +/* + * Scan a jumbo packet to validate its structure and to work out how many + * subpackets it contains. + * + * A jumbo packet is a collection of consecutive packets glued together with + * little headers between that indicate how to change the initial header for + * each subpacket. + * + * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but + * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any + * size. + */ +static bool rxrpc_validate_jumbo(struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + unsigned int offset = sp->offset; + unsigned int len = skb->len; + int nr_jumbo = 1; + u8 flags = sp->hdr.flags; -protocol_error: - ret = -EBADMSG; -out: - spin_unlock(&call->lock); - _leave(" = %d", ret); - return ret; + do { + nr_jumbo++; + if (len - offset < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (flags & RXRPC_LAST_PACKET) + goto protocol_error; + offset += RXRPC_JUMBO_DATALEN; + if (skb_copy_bits(skb, offset, &flags, 1) < 0) + goto protocol_error; + offset += sizeof(struct rxrpc_jumbo_header); + } while (flags & RXRPC_JUMBO_PACKET); -discard_and_ack: - _debug("discard and ACK packet %p", skb); - __rxrpc_propose_ACK(call, ack, skew, serial, true); -discard: - spin_unlock(&call->lock); - rxrpc_free_skb(skb); - _leave(" = 0 [discarded]"); - return 0; + sp->nr_jumbo = nr_jumbo; + return true; -enqueue_and_ack: - __rxrpc_propose_ACK(call, ack, skew, serial, true); -enqueue_packet: - _net("defer skb %p", skb); - spin_unlock(&call->lock); - skb_queue_tail(&call->rx_queue, skb); - atomic_inc(&call->ackr_not_idle); - read_lock(&call->state_lock); - if (call->state < RXRPC_CALL_DEAD) - rxrpc_queue_call(call); - read_unlock(&call->state_lock); - _leave(" = 0 [queued]"); - return 0; +protocol_error: + return false; } /* - * assume an implicit ACKALL of the transmission phase of a client socket upon - * reception of the first reply packet + * Handle reception of a duplicate packet. + * + * We have to take care to avoid an attack here whereby we're given a series of + * jumbograms, each with a sequence number one before the preceding one and + * filled up to maximum UDP size. If they never send us the first packet in + * the sequence, they can cause us to have to hold on to around 2MiB of kernel + * space until the call times out. + * + * We limit the space usage by only accepting three duplicate jumbo packets per + * call. After that, we tell the other side we're no longer accepting jumbos + * (that information is encoded in the ACK packet). */ -static void rxrpc_assume_implicit_ackall(struct rxrpc_call *call, u32 serial) +static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, + u8 annotation, bool *_jumbo_bad) { - write_lock_bh(&call->state_lock); - - switch (call->state) { - case RXRPC_CALL_CLIENT_AWAIT_REPLY: - call->state = RXRPC_CALL_CLIENT_RECV_REPLY; - call->acks_latest = serial; - - _debug("implicit ACKALL %%%u", call->acks_latest); - set_bit(RXRPC_CALL_EV_RCVD_ACKALL, &call->events); - write_unlock_bh(&call->state_lock); - - if (try_to_del_timer_sync(&call->resend_timer) >= 0) { - clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); - clear_bit(RXRPC_CALL_EV_RESEND, &call->events); - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - } - break; + /* Discard normal packets that are duplicates. */ + if (annotation == 0) + return; - default: - write_unlock_bh(&call->state_lock); - break; + /* Skip jumbo subpackets that are duplicates. When we've had three or + * more partially duplicate jumbo packets, we refuse to take any more + * jumbos for this call. + */ + if (!*_jumbo_bad) { + call->nr_jumbo_bad++; + *_jumbo_bad = true; } } /* - * post an incoming packet to the nominated call to deal with - * - must get rid of the sk_buff, either by freeing it or by queuing it + * Process a DATA packet, adding the packet to the Rx ring. */ -void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) +static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, + u16 skew) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - __be32 wtmp; - u32 abort_code; + unsigned int offset = sp->offset; + unsigned int ix; + rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; + rxrpc_seq_t seq = sp->hdr.seq, hard_ack; + bool immediate_ack = false, jumbo_bad = false, queued; + u16 len; + u8 ack = 0, flags, annotation = 0; - _enter("%p,%p", call, skb); + _enter("{%u,%u},{%u,%u}", + call->rx_hard_ack, call->rx_top, skb->len, seq); - ASSERT(!irqs_disabled()); + _proto("Rx DATA %%%u { #%u f=%02x }", + sp->hdr.serial, seq, sp->hdr.flags); -#if 0 // INJECT RX ERROR - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) { - static int skip = 0; - if (++skip == 3) { - printk("DROPPED 3RD PACKET!!!!!!!!!!!!!\n"); - skip = 0; - goto free_packet; - } + if (call->state >= RXRPC_CALL_COMPLETE) + return; + + /* Received data implicitly ACKs all of the request packets we sent + * when we're acting as a client. + */ + if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST || + call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && + !rxrpc_receiving_reply(call)) + return; + + call->ackr_prev_seq = seq; + + hard_ack = READ_ONCE(call->rx_hard_ack); + if (after(seq, hard_ack + call->rx_winsize)) { + ack = RXRPC_ACK_EXCEEDS_WINDOW; + ack_serial = serial; + goto ack; } -#endif - /* request ACK generation for any ACK or DATA packet that requests - * it */ - if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - _proto("ACK Requested on %%%u", sp->hdr.serial); - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - skb->priority, sp->hdr.serial, false); + flags = sp->hdr.flags; + if (flags & RXRPC_JUMBO_PACKET) { + if (call->nr_jumbo_bad > 3) { + ack = RXRPC_ACK_NOSPACE; + ack_serial = serial; + goto ack; + } + annotation = 1; } - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_ABORT: - _debug("abort"); +next_subpacket: + queued = false; + ix = seq & RXRPC_RXTX_BUFF_MASK; + len = skb->len; + if (flags & RXRPC_JUMBO_PACKET) + len = RXRPC_JUMBO_DATALEN; + + if (flags & RXRPC_LAST_PACKET) { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq != call->rx_top) + return rxrpc_proto_abort("LSN", call, seq); + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, call->rx_top)) + return rxrpc_proto_abort("LSA", call, seq); + } - if (skb_copy_bits(skb, 0, &wtmp, sizeof(wtmp)) < 0) - goto protocol_error; + if (before_eq(seq, hard_ack)) { + ack = RXRPC_ACK_DUPLICATE; + ack_serial = serial; + goto skip; + } - abort_code = ntohl(wtmp); - _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); + if (flags & RXRPC_REQUEST_ACK && !ack) { + ack = RXRPC_ACK_REQUESTED; + ack_serial = serial; + } - if (__rxrpc_set_call_completion(call, - RXRPC_CALL_REMOTELY_ABORTED, - abort_code, ECONNABORTED)) { - set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); - rxrpc_queue_call(call); + if (call->rxtx_buffer[ix]) { + rxrpc_input_dup_data(call, seq, annotation, &jumbo_bad); + if (ack != RXRPC_ACK_DUPLICATE) { + ack = RXRPC_ACK_DUPLICATE; + ack_serial = serial; } - goto free_packet; + immediate_ack = true; + goto skip; + } - case RXRPC_PACKET_TYPE_BUSY: - _proto("Rx BUSY %%%u", sp->hdr.serial); + /* Queue the packet. We use a couple of memory barriers here as need + * to make sure that rx_top is perceived to be set after the buffer + * pointer and that the buffer pointer is set after the annotation and + * the skb data. + * + * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() + * and also rxrpc_fill_out_ack(). + */ + rxrpc_get_skb(skb, rxrpc_skb_rx_got); + call->rxtx_annotations[ix] = annotation; + smp_wmb(); + call->rxtx_buffer[ix] = skb; + if (after(seq, call->rx_top)) { + smp_store_release(&call->rx_top, seq); + } else if (before(seq, call->rx_top)) { + /* Send an immediate ACK if we fill in a hole */ + if (!ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } + immediate_ack = true; + } + if (flags & RXRPC_LAST_PACKET) { + set_bit(RXRPC_CALL_RX_LAST, &call->flags); + trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + } else { + trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + } + queued = true; - if (rxrpc_conn_is_service(call->conn)) - goto protocol_error; + if (after_eq(seq, call->rx_expect_next)) { + if (after(seq, call->rx_expect_next)) { + _net("OOS %u > %u", seq, call->rx_expect_next); + ack = RXRPC_ACK_OUT_OF_SEQUENCE; + ack_serial = serial; + } + call->rx_expect_next = seq + 1; + } - write_lock_bh(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_CLIENT_SEND_REQUEST: - __rxrpc_set_call_completion(call, - RXRPC_CALL_SERVER_BUSY, - 0, EBUSY); - set_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events); - rxrpc_queue_call(call); - case RXRPC_CALL_SERVER_BUSY: - goto free_packet_unlock; - default: - goto protocol_error_locked; +skip: + offset += len; + if (flags & RXRPC_JUMBO_PACKET) { + if (skb_copy_bits(skb, offset, &flags, 1) < 0) + return rxrpc_proto_abort("XJF", call, seq); + offset += sizeof(struct rxrpc_jumbo_header); + seq++; + serial++; + annotation++; + if (flags & RXRPC_JUMBO_PACKET) + annotation |= RXRPC_RX_ANNO_JLAST; + if (after(seq, hard_ack + call->rx_winsize)) { + ack = RXRPC_ACK_EXCEEDS_WINDOW; + ack_serial = serial; + if (!jumbo_bad) { + call->nr_jumbo_bad++; + jumbo_bad = true; + } + goto ack; } - default: - _proto("Rx %s %%%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial); - goto protocol_error; + _proto("Rx DATA Jumbo %%%u", serial); + goto next_subpacket; + } - case RXRPC_PACKET_TYPE_DATA: - _proto("Rx DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); + if (queued && flags & RXRPC_LAST_PACKET && !ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } - if (sp->hdr.seq == 0) - goto protocol_error; +ack: + if (ack) + rxrpc_propose_ACK(call, ack, skew, ack_serial, + immediate_ack, true, + rxrpc_propose_ack_input_data); + + if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) + rxrpc_notify_socket(call); + _leave(" [queued]"); +} + +/* + * Process a requested ACK. + */ +static void rxrpc_input_requested_ack(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t orig_serial, + rxrpc_serial_t ack_serial) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + ktime_t sent_at; + int ix; + + for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { + skb = call->rxtx_buffer[ix]; + if (!skb) + continue; + + sp = rxrpc_skb(skb); + if (sp->hdr.serial != orig_serial) + continue; + smp_rmb(); + sent_at = skb->tstamp; + goto found; + } + return; - call->ackr_prev_seq = sp->hdr.seq; +found: + rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, + orig_serial, ack_serial, sent_at, resp_time); +} - /* received data implicitly ACKs all of the request packets we - * sent when we're acting as a client */ - if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - rxrpc_assume_implicit_ackall(call, sp->hdr.serial); +/* + * Process a ping response. + */ +static void rxrpc_input_ping_response(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t orig_serial, + rxrpc_serial_t ack_serial) +{ + rxrpc_serial_t ping_serial; + ktime_t ping_time; - switch (rxrpc_fast_process_data(call, skb, sp->hdr.seq)) { - case 0: - skb = NULL; - goto done; + ping_time = call->ackr_ping_time; + smp_rmb(); + ping_serial = call->ackr_ping; - default: - BUG(); + if (!test_bit(RXRPC_CALL_PINGING, &call->flags) || + before(orig_serial, ping_serial)) + return; + clear_bit(RXRPC_CALL_PINGING, &call->flags); + if (after(orig_serial, ping_serial)) + return; - /* data packet received beyond the last packet */ - case -EBADMSG: - goto protocol_error; - } + rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, + orig_serial, ack_serial, ping_time, resp_time); +} - case RXRPC_PACKET_TYPE_ACKALL: - case RXRPC_PACKET_TYPE_ACK: - /* ACK processing is done in process context */ - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_DEAD) { - skb_queue_tail(&call->rx_queue, skb); - rxrpc_queue_call(call); - skb = NULL; - } - read_unlock_bh(&call->state_lock); - goto free_packet; +/* + * Process the extra information that may be appended to an ACK packet + */ +static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_ackinfo *ackinfo) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_peer *peer; + unsigned int mtu; + u32 rwind = ntohl(ackinfo->rwind); + + _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", + sp->hdr.serial, + ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), + rwind, ntohl(ackinfo->jumbo_max)); + + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; + call->tx_winsize = rwind; + + mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + + peer = call->peer; + if (mtu < peer->maxdata) { + spin_lock_bh(&peer->lock); + peer->maxdata = mtu; + peer->mtu = mtu + peer->hdrsize; + spin_unlock_bh(&peer->lock); + _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata); } +} -protocol_error: - _debug("protocol error"); - write_lock_bh(&call->state_lock); -protocol_error_locked: - if (__rxrpc_abort_call(call, RX_PROTOCOL_ERROR, EPROTO)) - rxrpc_queue_call(call); -free_packet_unlock: - write_unlock_bh(&call->state_lock); -free_packet: - rxrpc_free_skb(skb); -done: - _leave(""); +/* + * Process individual soft ACKs. + * + * Each ACK in the array corresponds to one packet and can be either an ACK or + * a NAK. If we get find an explicitly NAK'd packet we resend immediately; + * packets that lie beyond the end of the ACK list are scheduled for resend by + * the timer on the basis that the peer might just not have processed them at + * the time the ACK was sent. + */ +static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, + rxrpc_seq_t seq, int nr_acks, + struct rxrpc_ack_summary *summary) +{ + int ix; + u8 annotation, anno_type; + + for (; nr_acks > 0; nr_acks--, seq++) { + ix = seq & RXRPC_RXTX_BUFF_MASK; + annotation = call->rxtx_annotations[ix]; + anno_type = annotation & RXRPC_TX_ANNO_MASK; + annotation &= ~RXRPC_TX_ANNO_MASK; + switch (*acks++) { + case RXRPC_ACK_TYPE_ACK: + summary->nr_acks++; + if (anno_type == RXRPC_TX_ANNO_ACK) + continue; + summary->nr_new_acks++; + call->rxtx_annotations[ix] = + RXRPC_TX_ANNO_ACK | annotation; + break; + case RXRPC_ACK_TYPE_NACK: + if (!summary->nr_nacks && + call->acks_lowest_nak != seq) { + call->acks_lowest_nak = seq; + summary->new_low_nack = true; + } + summary->nr_nacks++; + if (anno_type == RXRPC_TX_ANNO_NAK) + continue; + summary->nr_new_nacks++; + if (anno_type == RXRPC_TX_ANNO_RETRANS) + continue; + call->rxtx_annotations[ix] = + RXRPC_TX_ANNO_NAK | annotation; + break; + default: + return rxrpc_proto_abort("SFT", call, 0); + } + } } /* - * split up a jumbo data packet + * Process an ACK packet. + * + * ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet + * in the ACK array. Anything before that is hard-ACK'd and may be discarded. + * + * A hard-ACK means that a packet has been processed and may be discarded; a + * soft-ACK means that the packet may be discarded and retransmission + * requested. A phase is complete when all packets are hard-ACK'd. */ -static void rxrpc_process_jumbo_packet(struct rxrpc_call *call, - struct sk_buff *jumbo) +static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, + u16 skew) { - struct rxrpc_jumbo_header jhdr; - struct rxrpc_skb_priv *sp; - struct sk_buff *part; + struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + union { + struct rxrpc_ackpacket ack; + struct rxrpc_ackinfo info; + u8 acks[RXRPC_MAXACKS]; + } buf; + rxrpc_serial_t acked_serial; + rxrpc_seq_t first_soft_ack, hard_ack; + int nr_acks, offset; + + _enter(""); + + if (skb_copy_bits(skb, sp->offset, &buf.ack, sizeof(buf.ack)) < 0) { + _debug("extraction failure"); + return rxrpc_proto_abort("XAK", call, 0); + } + sp->offset += sizeof(buf.ack); + + acked_serial = ntohl(buf.ack.serial); + first_soft_ack = ntohl(buf.ack.firstPacket); + hard_ack = first_soft_ack - 1; + nr_acks = buf.ack.nAcks; + summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? + buf.ack.reason : RXRPC_ACK__INVALID); + + trace_rxrpc_rx_ack(call, first_soft_ack, summary.ack_reason, nr_acks); + + _proto("Rx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", + sp->hdr.serial, + ntohs(buf.ack.maxSkew), + first_soft_ack, + ntohl(buf.ack.previousPacket), + acked_serial, + rxrpc_ack_names[summary.ack_reason], + buf.ack.nAcks); + + if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) + rxrpc_input_ping_response(call, skb->tstamp, acked_serial, + sp->hdr.serial); + if (buf.ack.reason == RXRPC_ACK_REQUESTED) + rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, + sp->hdr.serial); + + if (buf.ack.reason == RXRPC_ACK_PING) { + _proto("Rx ACK %%%u PING Request", sp->hdr.serial); + rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, + skew, sp->hdr.serial, true, true, + rxrpc_propose_ack_respond_to_ping); + } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, + skew, sp->hdr.serial, true, true, + rxrpc_propose_ack_respond_to_ack); + } - _enter(",{%u,%u}", jumbo->data_len, jumbo->len); + offset = sp->offset + nr_acks + 3; + if (skb->len >= offset + sizeof(buf.info)) { + if (skb_copy_bits(skb, offset, &buf.info, sizeof(buf.info)) < 0) + return rxrpc_proto_abort("XAI", call, 0); + rxrpc_input_ackinfo(call, skb, &buf.info); + } - sp = rxrpc_skb(jumbo); + if (first_soft_ack == 0) + return rxrpc_proto_abort("AK0", call, 0); - do { - sp->hdr.flags &= ~RXRPC_JUMBO_PACKET; - - /* make a clone to represent the first subpacket in what's left - * of the jumbo packet */ - part = skb_clone(jumbo, GFP_ATOMIC); - if (!part) { - /* simply ditch the tail in the event of ENOMEM */ - pskb_trim(jumbo, RXRPC_JUMBO_DATALEN); - break; - } - rxrpc_new_skb(part); + /* Ignore ACKs unless we are or have just been transmitting. */ + switch (call->state) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + case RXRPC_CALL_SERVER_SEND_REPLY: + case RXRPC_CALL_SERVER_AWAIT_ACK: + break; + default: + return; + } - pskb_trim(part, RXRPC_JUMBO_DATALEN); + /* Discard any out-of-order or duplicate ACKs. */ + if (before_eq(sp->hdr.serial, call->acks_latest)) { + _debug("discard ACK %d <= %d", + sp->hdr.serial, call->acks_latest); + return; + } + call->acks_latest_ts = skb->tstamp; + call->acks_latest = sp->hdr.serial; + + if (before(hard_ack, call->tx_hard_ack) || + after(hard_ack, call->tx_top)) + return rxrpc_proto_abort("AKW", call, 0); + if (nr_acks > call->tx_top - hard_ack) + return rxrpc_proto_abort("AKN", call, 0); + + if (after(hard_ack, call->tx_hard_ack)) + rxrpc_rotate_tx_window(call, hard_ack, &summary); + + if (nr_acks > 0) { + if (skb_copy_bits(skb, sp->offset, buf.acks, nr_acks) < 0) + return rxrpc_proto_abort("XSA", call, 0); + rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, + &summary); + } - if (!pskb_pull(jumbo, RXRPC_JUMBO_DATALEN)) - goto protocol_error; + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { + rxrpc_end_tx_phase(call, false, "ETA"); + return; + } - if (skb_copy_bits(jumbo, 0, &jhdr, sizeof(jhdr)) < 0) - goto protocol_error; - if (!pskb_pull(jumbo, sizeof(jhdr))) - BUG(); + if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & + RXRPC_TX_ANNO_LAST && + summary.nr_acks == call->tx_top - hard_ack) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + false, true, + rxrpc_propose_ack_ping_for_lost_reply); - sp->hdr.seq += 1; - sp->hdr.serial += 1; - sp->hdr.flags = jhdr.flags; - sp->hdr._rsvd = ntohs(jhdr._rsvd); + return rxrpc_congestion_management(call, skb, &summary); +} - _proto("Rx DATA Jumbo %%%u", sp->hdr.serial - 1); +/* + * Process an ACKALL packet. + */ +static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_fast_process_packet(call, part); - part = NULL; + _proto("Rx ACKALL %%%u", sp->hdr.serial); - } while (sp->hdr.flags & RXRPC_JUMBO_PACKET); + rxrpc_rotate_tx_window(call, call->tx_top, &summary); + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + rxrpc_end_tx_phase(call, false, "ETL"); +} - rxrpc_fast_process_packet(call, jumbo); - _leave(""); - return; +/* + * Process an ABORT packet. + */ +static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + __be32 wtmp; + u32 abort_code = RX_CALL_DEAD; -protocol_error: - _debug("protocol error"); - rxrpc_free_skb(part); - rxrpc_free_skb(jumbo); - if (rxrpc_abort_call(call, RX_PROTOCOL_ERROR, EPROTO)) - rxrpc_queue_call(call); - _leave(""); + _enter(""); + + if (skb->len >= 4 && + skb_copy_bits(skb, sp->offset, &wtmp, sizeof(wtmp)) >= 0) + abort_code = ntohl(wtmp); + + _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); + + if (rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + abort_code, ECONNABORTED)) + rxrpc_notify_socket(call); } /* - * post an incoming packet to the appropriate call/socket to deal with - * - must get rid of the sk_buff, either by freeing it or by queuing it + * Process an incoming call packet. */ -static void rxrpc_post_packet_to_call(struct rxrpc_call *call, - struct sk_buff *skb) +static void rxrpc_input_call_packet(struct rxrpc_call *call, + struct sk_buff *skb, u16 skew) { - struct rxrpc_skb_priv *sp; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); _enter("%p,%p", call, skb); - sp = rxrpc_skb(skb); + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_DATA: + rxrpc_input_data(call, skb, skew); + break; - _debug("extant call [%d]", call->state); + case RXRPC_PACKET_TYPE_ACK: + rxrpc_input_ack(call, skb, skew); + break; - read_lock(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_DEAD: - goto dead_call; - - case RXRPC_CALL_COMPLETE: - switch (call->completion) { - case RXRPC_CALL_LOCALLY_ABORTED: - if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, - &call->events)) { - rxrpc_queue_call(call); - goto free_unlock; - } - default: - goto dead_call; - case RXRPC_CALL_SUCCEEDED: - if (rxrpc_conn_is_service(call->conn)) - goto dead_call; - goto resend_final_ack; - } + case RXRPC_PACKET_TYPE_BUSY: + _proto("Rx BUSY %%%u", sp->hdr.serial); - case RXRPC_CALL_CLIENT_FINAL_ACK: - goto resend_final_ack; + /* Just ignore BUSY packets from the server; the retry and + * lifespan timers will take care of business. BUSY packets + * from the client don't make sense. + */ + break; + + case RXRPC_PACKET_TYPE_ABORT: + rxrpc_input_abort(call, skb); + break; + + case RXRPC_PACKET_TYPE_ACKALL: + rxrpc_input_ackall(call, skb); + break; default: + _proto("Rx %s %%%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial); break; } - read_unlock(&call->state_lock); - rxrpc_get_call(call); - - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - sp->hdr.flags & RXRPC_JUMBO_PACKET) - rxrpc_process_jumbo_packet(call, skb); - else - rxrpc_fast_process_packet(call, skb); - - rxrpc_put_call(call); - goto done; - -resend_final_ack: - _debug("final ack again"); - rxrpc_get_call(call); - set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); - rxrpc_queue_call(call); - goto free_unlock; - -dead_call: - if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { - skb->priority = RX_CALL_DEAD; - rxrpc_reject_packet(call->conn->params.local, skb); - goto unlock; - } -free_unlock: - rxrpc_free_skb(skb); -unlock: - read_unlock(&call->state_lock); -done: _leave(""); } @@ -597,6 +960,17 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, } /* + * put a packet up for transport-level abort + */ +static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) +{ + CHECK_SLAB_OKAY(&local->usage); + + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); +} + +/* * Extract the wire header from a packet and translate the byte order. */ static noinline @@ -607,8 +981,6 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) /* dig out the RxRPC connection details */ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) return -EBADMSG; - if (!pskb_pull(skb, sizeof(whdr))) - BUG(); memset(sp, 0, sizeof(*sp)); sp->hdr.epoch = ntohl(whdr.epoch); @@ -622,6 +994,7 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); + sp->offset = sizeof(whdr); return 0; } @@ -633,19 +1006,22 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * shut down and the local endpoint from going away, thus sk_user_data will not * be cleared until this function returns. */ -void rxrpc_data_ready(struct sock *sk) +void rxrpc_data_ready(struct sock *udp_sk) { struct rxrpc_connection *conn; + struct rxrpc_channel *chan; + struct rxrpc_call *call; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local = sk->sk_user_data; + struct rxrpc_local *local = udp_sk->sk_user_data; struct sk_buff *skb; + unsigned int channel; int ret, skew; - _enter("%p", sk); + _enter("%p", udp_sk); ASSERT(!irqs_disabled()); - skb = skb_recv_datagram(sk, 0, 1, &ret); + skb = skb_recv_datagram(udp_sk, 0, 1, &ret); if (!skb) { if (ret == -EAGAIN) return; @@ -653,13 +1029,13 @@ void rxrpc_data_ready(struct sock *sk) return; } - rxrpc_new_skb(skb); + rxrpc_new_skb(skb, rxrpc_skb_rx_received); _net("recv skb %p", skb); /* we'll probably need to checksum it (didn't call sock_recvmsg) */ if (skb_checksum_complete(skb)) { - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0); _leave(" [CSUM failed]"); return; @@ -673,13 +1049,21 @@ void rxrpc_data_ready(struct sock *sk) skb_orphan(skb); sp = rxrpc_skb(skb); - _net("Rx UDP packet from %08x:%04hu", - ntohl(ip_hdr(skb)->saddr), ntohs(udp_hdr(skb)->source)); - /* dig out the RxRPC connection details */ if (rxrpc_extract_header(sp, skb) < 0) goto bad_message; + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { + static int lose; + if ((lose++ & 7) == 7) { + trace_rxrpc_rx_lose(sp); + rxrpc_lose_skb(skb, rxrpc_skb_rx_lost); + return; + } + } + + trace_rxrpc_rx_packet(sp); + _net("Rx RxRPC %s ep=%x call=%x:%x", sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient", sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber); @@ -690,110 +1074,125 @@ void rxrpc_data_ready(struct sock *sk) goto bad_message; } - if (sp->hdr.type == RXRPC_PACKET_TYPE_VERSION) { + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_VERSION: rxrpc_post_packet_to_local(local, skb); goto out; - } - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) - goto bad_message; + case RXRPC_PACKET_TYPE_BUSY: + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + goto discard; + + case RXRPC_PACKET_TYPE_DATA: + if (sp->hdr.callNumber == 0) + goto bad_message; + if (sp->hdr.flags & RXRPC_JUMBO_PACKET && + !rxrpc_validate_jumbo(skb)) + goto bad_message; + break; + } rcu_read_lock(); conn = rxrpc_find_connection_rcu(local, skb); - if (!conn) { - skb->priority = 0; - goto cant_route_call; - } + if (conn) { + if (sp->hdr.securityIndex != conn->security_ix) + goto wrong_security; - /* Note the serial number skew here */ - skew = (int)sp->hdr.serial - (int)conn->hi_serial; - if (skew >= 0) { - if (skew > 0) - conn->hi_serial = sp->hdr.serial; - skb->priority = 0; - } else { - skew = -skew; - skb->priority = min(skew, 65535); - } + if (sp->hdr.callNumber == 0) { + /* Connection-level packet */ + _debug("CONN %p {%d}", conn, conn->debug_id); + rxrpc_post_packet_to_conn(conn, skb); + goto out_unlock; + } + + /* Note the serial number skew here */ + skew = (int)sp->hdr.serial - (int)conn->hi_serial; + if (skew >= 0) { + if (skew > 0) + conn->hi_serial = sp->hdr.serial; + } else { + skew = -skew; + skew = min(skew, 65535); + } - if (sp->hdr.callNumber == 0) { - /* Connection-level packet */ - _debug("CONN %p {%d}", conn, conn->debug_id); - rxrpc_post_packet_to_conn(conn, skb); - goto out_unlock; - } else { /* Call-bound packets are routed by connection channel. */ - unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; - struct rxrpc_channel *chan = &conn->channels[channel]; - struct rxrpc_call *call; + channel = sp->hdr.cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) goto discard_unlock; if (sp->hdr.callNumber == chan->last_call) { - /* For the previous service call, if completed - * successfully, we discard all further packets. + /* For the previous service call, if completed successfully, we + * discard all further packets. */ if (rxrpc_conn_is_service(conn) && (chan->last_type == RXRPC_PACKET_TYPE_ACK || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)) goto discard_unlock; - /* But otherwise we need to retransmit the final packet - * from data cached in the connection record. + /* But otherwise we need to retransmit the final packet from + * data cached in the connection record. */ rxrpc_post_packet_to_conn(conn, skb); goto out_unlock; } call = rcu_dereference(chan->call); - if (!call || atomic_read(&call->usage) == 0) - goto cant_route_call; + } else { + skew = 0; + call = NULL; + } - rxrpc_see_call(call); - rxrpc_post_packet_to_call(call, skb); - goto out_unlock; + if (!call || atomic_read(&call->usage) == 0) { + if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) || + sp->hdr.callNumber == 0 || + sp->hdr.type != RXRPC_PACKET_TYPE_DATA) + goto bad_message_unlock; + if (sp->hdr.seq != 1) + goto discard_unlock; + call = rxrpc_new_incoming_call(local, conn, skb); + if (!call) { + rcu_read_unlock(); + goto reject_packet; + } + rxrpc_send_ping(call, skb, skew); } + rxrpc_input_call_packet(call, skb, skew); + goto discard_unlock; + discard_unlock: - rxrpc_free_skb(skb); -out_unlock: rcu_read_unlock(); +discard: + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); out: + trace_rxrpc_rx_done(0, 0); return; -cant_route_call: +out_unlock: rcu_read_unlock(); + goto out; - _debug("can't route call"); - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && - sp->hdr.type == RXRPC_PACKET_TYPE_DATA) { - if (sp->hdr.seq == 1) { - _debug("first packet"); - skb_queue_tail(&local->accept_queue, skb); - rxrpc_queue_work(&local->processor); - _leave(" [incoming]"); - return; - } - skb->priority = RX_INVALID_OPERATION; - } else { - skb->priority = RX_CALL_DEAD; - } - - if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { - _debug("reject type %d",sp->hdr.type); - rxrpc_reject_packet(local, skb); - } else { - rxrpc_free_skb(skb); - } - _leave(" [no call]"); - return; +wrong_security: + rcu_read_unlock(); + trace_rxrpc_abort("SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RXKADINCONSISTENCY, EBADMSG); + skb->priority = RXKADINCONSISTENCY; + goto post_abort; +bad_message_unlock: + rcu_read_unlock(); bad_message: + trace_rxrpc_abort("BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_PROTOCOL_ERROR, EBADMSG); skb->priority = RX_PROTOCOL_ERROR; +post_abort: + skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; +reject_packet: + trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); _leave(" [badmsg]"); } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index c21ad21..7d4375e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -23,31 +23,36 @@ static int none_prime_packet_security(struct rxrpc_connection *conn) } static int none_secure_packet(struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size, - void *sechdr) + struct sk_buff *skb, + size_t data_size, + void *sechdr) { return 0; } -static int none_verify_packet(struct rxrpc_call *call, - struct sk_buff *skb, - u32 *_abort_code) +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int offset, unsigned int len, + rxrpc_seq_t seq, u16 expected_cksum) { return 0; } +static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int *_offset, unsigned int *_len) +{ +} + static int none_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb, + u32 *_abort_code) { *_abort_code = RX_PROTOCOL_ERROR; return -EPROTO; } static int none_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb, + u32 *_abort_code) { *_abort_code = RX_PROTOCOL_ERROR; return -EPROTO; @@ -78,6 +83,7 @@ const struct rxrpc_security rxrpc_no_security = { .prime_packet_security = none_prime_packet_security, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, + .locate_data = none_locate_data, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index bcc6593..190f68b 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -15,8 +15,6 @@ #include <linux/net.h> #include <linux/skbuff.h> #include <linux/slab.h> -#include <linux/udp.h> -#include <linux/ip.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <generated/utsrelease.h> @@ -33,7 +31,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, { struct rxrpc_wire_header whdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct sockaddr_in sin; + struct sockaddr_rxrpc srx; struct msghdr msg; struct kvec iov[2]; size_t len; @@ -41,12 +39,11 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, _enter(""); - sin.sin_family = AF_INET; - sin.sin_port = udp_hdr(skb)->source; - sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) + return; - msg.msg_name = &sin; - msg.msg_namelen = sizeof(sin); + msg.msg_name = &srx.transport; + msg.msg_namelen = srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -93,12 +90,12 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_see_skb(skb); + rxrpc_see_skb(skb, rxrpc_skb_rx_seen); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: - if (skb_copy_bits(skb, 0, &v, 1) < 0) + if (skb_copy_bits(skb, sp->offset, &v, 1) < 0) return; _proto("Rx VERSION { %02x }", v); if (v == 0) @@ -110,7 +107,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) break; } - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); } _leave(""); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a753796..e3fad80 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -58,6 +58,17 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local, memcmp(&local->srx.transport.sin.sin_addr, &srx->transport.sin.sin_addr, sizeof(struct in_addr)); +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + /* If the choice of UDP6 port is left up to the transport, then + * the endpoint record doesn't match. + */ + return ((u16 __force)local->srx.transport.sin6.sin6_port - + (u16 __force)srx->transport.sin6.sin6_port) ?: + memcmp(&local->srx.transport.sin6.sin6_addr, + &srx->transport.sin6.sin6_addr, + sizeof(struct in6_addr)); +#endif default: BUG(); } @@ -75,9 +86,8 @@ static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx) atomic_set(&local->usage, 1); INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); - INIT_LIST_HEAD(&local->services); + INIT_HLIST_HEAD(&local->services); init_rwsem(&local->defrag_sem); - skb_queue_head_init(&local->accept_queue); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); local->client_conns = RB_ROOT; @@ -101,11 +111,12 @@ static int rxrpc_open_socket(struct rxrpc_local *local) struct sock *sock; int ret, opt; - _enter("%p{%d}", local, local->srx.transport_type); + _enter("%p{%d,%d}", + local, local->srx.transport_type, local->srx.transport.family); /* create a socket to represent the local endpoint */ - ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type, - IPPROTO_UDP, &local->socket); + ret = sock_create_kern(&init_net, local->srx.transport.family, + local->srx.transport_type, 0, &local->socket); if (ret < 0) { _leave(" = %d [socket]", ret); return ret; @@ -170,18 +181,8 @@ struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) long diff; int ret; - if (srx->transport.family == AF_INET) { - _enter("{%d,%u,%pI4+%hu}", - srx->transport_type, - srx->transport.family, - &srx->transport.sin.sin_addr, - ntohs(srx->transport.sin.sin_port)); - } else { - _enter("{%d,%u}", - srx->transport_type, - srx->transport.family); - return ERR_PTR(-EAFNOSUPPORT); - } + _enter("{%d,%d,%pISp}", + srx->transport_type, srx->transport.family, &srx->transport); mutex_lock(&rxrpc_local_mutex); @@ -234,13 +235,8 @@ struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx) found: mutex_unlock(&rxrpc_local_mutex); - _net("LOCAL %s %d {%d,%u,%pI4+%hu}", - age, - local->debug_id, - local->srx.transport_type, - local->srx.transport.family, - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port)); + _net("LOCAL %s %d {%pISp}", + age, local->debug_id, &local->srx.transport); _leave(" = %p", local); return local; @@ -296,7 +292,7 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) mutex_unlock(&rxrpc_local_mutex); ASSERT(RB_EMPTY_ROOT(&local->client_conns)); - ASSERT(list_empty(&local->services)); + ASSERT(hlist_empty(&local->services)); if (socket) { local->socket = NULL; @@ -308,7 +304,6 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) /* At this point, there should be no more packets coming in to the * local endpoint. */ - rxrpc_purge_queue(&local->accept_queue); rxrpc_purge_queue(&local->reject_queue); rxrpc_purge_queue(&local->event_queue); @@ -332,11 +327,6 @@ static void rxrpc_local_processor(struct work_struct *work) if (atomic_read(&local->usage) == 0) return rxrpc_local_destroyer(local); - if (!skb_queue_empty(&local->accept_queue)) { - rxrpc_accept_incoming_calls(local); - again = true; - } - if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); again = true; diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 39e7cc3..aedb897 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -50,7 +50,10 @@ unsigned int rxrpc_idle_ack_delay = 0.5 * HZ; * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further * packets. */ -unsigned int rxrpc_rx_window_size = 32; +unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE; +#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE +#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE +#endif /* * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet @@ -65,9 +68,9 @@ unsigned int rxrpc_rx_mtu = 5692; unsigned int rxrpc_rx_jumbo_max = 4; /* - * Time till packet resend (in jiffies). + * Time till packet resend (in milliseconds). */ -unsigned int rxrpc_resend_timeout = 4 * HZ; +unsigned int rxrpc_resend_timeout = 4 * 1000; const char *const rxrpc_pkts[] = { "?00", @@ -80,21 +83,153 @@ const s8 rxrpc_ack_priority[] = { [RXRPC_ACK_DELAY] = 1, [RXRPC_ACK_REQUESTED] = 2, [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_PING_RESPONSE] = 4, - [RXRPC_ACK_DUPLICATE] = 5, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 6, - [RXRPC_ACK_EXCEEDS_WINDOW] = 7, - [RXRPC_ACK_NOSPACE] = 8, -}; - -const char *rxrpc_acks(u8 reason) -{ - static const char *const str[] = { - "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", - "IDL", "-?-" - }; - - if (reason >= ARRAY_SIZE(str)) - reason = ARRAY_SIZE(str) - 1; - return str[reason]; -} + [RXRPC_ACK_DUPLICATE] = 4, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 5, + [RXRPC_ACK_EXCEEDS_WINDOW] = 6, + [RXRPC_ACK_NOSPACE] = 7, + [RXRPC_ACK_PING_RESPONSE] = 8, + [RXRPC_ACK_PING] = 9, +}; + +const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { + "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", + "IDL", "-?-" +}; + +const char rxrpc_skb_traces[rxrpc_skb__nr_trace][7] = { + [rxrpc_skb_rx_cleaned] = "Rx CLN", + [rxrpc_skb_rx_freed] = "Rx FRE", + [rxrpc_skb_rx_got] = "Rx GOT", + [rxrpc_skb_rx_lost] = "Rx *L*", + [rxrpc_skb_rx_received] = "Rx RCV", + [rxrpc_skb_rx_purged] = "Rx PUR", + [rxrpc_skb_rx_rotated] = "Rx ROT", + [rxrpc_skb_rx_seen] = "Rx SEE", + [rxrpc_skb_tx_cleaned] = "Tx CLN", + [rxrpc_skb_tx_freed] = "Tx FRE", + [rxrpc_skb_tx_got] = "Tx GOT", + [rxrpc_skb_tx_lost] = "Tx *L*", + [rxrpc_skb_tx_new] = "Tx NEW", + [rxrpc_skb_tx_rotated] = "Tx ROT", + [rxrpc_skb_tx_seen] = "Tx SEE", +}; + +const char rxrpc_conn_traces[rxrpc_conn__nr_trace][4] = { + [rxrpc_conn_new_client] = "NWc", + [rxrpc_conn_new_service] = "NWs", + [rxrpc_conn_queued] = "QUE", + [rxrpc_conn_seen] = "SEE", + [rxrpc_conn_got] = "GOT", + [rxrpc_conn_put_client] = "PTc", + [rxrpc_conn_put_service] = "PTs", +}; + +const char rxrpc_client_traces[rxrpc_client__nr_trace][7] = { + [rxrpc_client_activate_chans] = "Activa", + [rxrpc_client_alloc] = "Alloc ", + [rxrpc_client_chan_activate] = "ChActv", + [rxrpc_client_chan_disconnect] = "ChDisc", + [rxrpc_client_chan_pass] = "ChPass", + [rxrpc_client_chan_unstarted] = "ChUnst", + [rxrpc_client_cleanup] = "Clean ", + [rxrpc_client_count] = "Count ", + [rxrpc_client_discard] = "Discar", + [rxrpc_client_duplicate] = "Duplic", + [rxrpc_client_exposed] = "Expose", + [rxrpc_client_replace] = "Replac", + [rxrpc_client_to_active] = "->Actv", + [rxrpc_client_to_culled] = "->Cull", + [rxrpc_client_to_idle] = "->Idle", + [rxrpc_client_to_inactive] = "->Inac", + [rxrpc_client_to_waiting] = "->Wait", + [rxrpc_client_uncount] = "Uncoun", +}; + +const char rxrpc_transmit_traces[rxrpc_transmit__nr_trace][4] = { + [rxrpc_transmit_wait] = "WAI", + [rxrpc_transmit_queue] = "QUE", + [rxrpc_transmit_queue_last] = "QLS", + [rxrpc_transmit_rotate] = "ROT", + [rxrpc_transmit_rotate_last] = "RLS", + [rxrpc_transmit_await_reply] = "AWR", + [rxrpc_transmit_end] = "END", +}; + +const char rxrpc_receive_traces[rxrpc_receive__nr_trace][4] = { + [rxrpc_receive_incoming] = "INC", + [rxrpc_receive_queue] = "QUE", + [rxrpc_receive_queue_last] = "QLS", + [rxrpc_receive_front] = "FRN", + [rxrpc_receive_rotate] = "ROT", + [rxrpc_receive_end] = "END", +}; + +const char rxrpc_recvmsg_traces[rxrpc_recvmsg__nr_trace][5] = { + [rxrpc_recvmsg_enter] = "ENTR", + [rxrpc_recvmsg_wait] = "WAIT", + [rxrpc_recvmsg_dequeue] = "DEQU", + [rxrpc_recvmsg_hole] = "HOLE", + [rxrpc_recvmsg_next] = "NEXT", + [rxrpc_recvmsg_cont] = "CONT", + [rxrpc_recvmsg_full] = "FULL", + [rxrpc_recvmsg_data_return] = "DATA", + [rxrpc_recvmsg_terminal] = "TERM", + [rxrpc_recvmsg_to_be_accepted] = "TBAC", + [rxrpc_recvmsg_return] = "RETN", +}; + +const char rxrpc_rtt_tx_traces[rxrpc_rtt_tx__nr_trace][5] = { + [rxrpc_rtt_tx_ping] = "PING", + [rxrpc_rtt_tx_data] = "DATA", +}; + +const char rxrpc_rtt_rx_traces[rxrpc_rtt_rx__nr_trace][5] = { + [rxrpc_rtt_rx_ping_response] = "PONG", + [rxrpc_rtt_rx_requested_ack] = "RACK", +}; + +const char rxrpc_timer_traces[rxrpc_timer__nr_trace][8] = { + [rxrpc_timer_begin] = "Begin ", + [rxrpc_timer_expired] = "*EXPR*", + [rxrpc_timer_init_for_reply] = "IniRpl", + [rxrpc_timer_set_for_ack] = "SetAck", + [rxrpc_timer_set_for_send] = "SetTx ", + [rxrpc_timer_set_for_resend] = "SetRTx", +}; + +const char rxrpc_propose_ack_traces[rxrpc_propose_ack__nr_trace][8] = { + [rxrpc_propose_ack_client_tx_end] = "ClTxEnd", + [rxrpc_propose_ack_input_data] = "DataIn ", + [rxrpc_propose_ack_ping_for_lost_ack] = "LostAck", + [rxrpc_propose_ack_ping_for_lost_reply] = "LostRpl", + [rxrpc_propose_ack_ping_for_params] = "Params ", + [rxrpc_propose_ack_respond_to_ack] = "Rsp2Ack", + [rxrpc_propose_ack_respond_to_ping] = "Rsp2Png", + [rxrpc_propose_ack_retry_tx] = "RetryTx", + [rxrpc_propose_ack_rotate_rx] = "RxAck ", + [rxrpc_propose_ack_terminal_ack] = "ClTerm ", +}; + +const char *const rxrpc_propose_ack_outcomes[rxrpc_propose_ack__nr_outcomes] = { + [rxrpc_propose_ack_use] = "", + [rxrpc_propose_ack_update] = " Update", + [rxrpc_propose_ack_subsume] = " Subsume", +}; + +const char rxrpc_congest_modes[NR__RXRPC_CONGEST_MODES][10] = { + [RXRPC_CALL_SLOW_START] = "SlowStart", + [RXRPC_CALL_CONGEST_AVOIDANCE] = "CongAvoid", + [RXRPC_CALL_PACKET_LOSS] = "PktLoss ", + [RXRPC_CALL_FAST_RETRANSMIT] = "FastReTx ", +}; + +const char rxrpc_congest_changes[rxrpc_congest__nr_change][9] = { + [rxrpc_cong_begin_retransmission] = " Retrans", + [rxrpc_cong_cleared_nacks] = " Cleared", + [rxrpc_cong_new_low_nack] = " NewLowN", + [rxrpc_cong_no_change] = "", + [rxrpc_cong_progress] = " Progres", + [rxrpc_cong_retransmit_again] = " ReTxAgn", + [rxrpc_cong_rtt_window_end] = " RttWinE", + [rxrpc_cong_saw_nack] = " SawNack", +}; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 5b5508f..cf43a71 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -19,46 +19,319 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +struct rxrpc_pkt_buffer { + struct rxrpc_wire_header whdr; + union { + struct { + struct rxrpc_ackpacket ack; + u8 acks[255]; + u8 pad[3]; + }; + __be32 abort_code; + }; + struct rxrpc_ackinfo ackinfo; +}; + +/* + * Fill out an ACK packet. + */ +static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, + struct rxrpc_pkt_buffer *pkt, + rxrpc_seq_t *_hard_ack, + rxrpc_seq_t *_top) +{ + rxrpc_serial_t serial; + rxrpc_seq_t hard_ack, top, seq; + int ix; + u32 mtu, jmax; + u8 *ackp = pkt->acks; + + /* Barrier against rxrpc_input_data(). */ + serial = call->ackr_serial; + hard_ack = READ_ONCE(call->rx_hard_ack); + top = smp_load_acquire(&call->rx_top); + *_hard_ack = hard_ack; + *_top = top; + + pkt->ack.bufferSpace = htons(8); + pkt->ack.maxSkew = htons(call->ackr_skew); + pkt->ack.firstPacket = htonl(hard_ack + 1); + pkt->ack.previousPacket = htonl(call->ackr_prev_seq); + pkt->ack.serial = htonl(serial); + pkt->ack.reason = call->ackr_reason; + pkt->ack.nAcks = top - hard_ack; + + if (pkt->ack.reason == RXRPC_ACK_PING) + pkt->whdr.flags |= RXRPC_REQUEST_ACK; + + if (after(top, hard_ack)) { + seq = hard_ack + 1; + do { + ix = seq & RXRPC_RXTX_BUFF_MASK; + if (call->rxtx_buffer[ix]) + *ackp++ = RXRPC_ACK_TYPE_ACK; + else + *ackp++ = RXRPC_ACK_TYPE_NACK; + seq++; + } while (before_eq(seq, top)); + } + + mtu = call->conn->params.peer->if_mtu; + mtu -= call->conn->params.peer->hdrsize; + jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; + pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + pkt->ackinfo.maxMTU = htonl(mtu); + pkt->ackinfo.rwind = htonl(call->rx_winsize); + pkt->ackinfo.jumbo_max = htonl(jmax); + + *ackp++ = 0; + *ackp++ = 0; + *ackp++ = 0; + return top - hard_ack + 3; +} + +/* + * Send an ACK or ABORT call packet. + */ +int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) +{ + struct rxrpc_connection *conn = NULL; + struct rxrpc_pkt_buffer *pkt; + struct msghdr msg; + struct kvec iov[2]; + rxrpc_serial_t serial; + rxrpc_seq_t hard_ack, top; + size_t len, n; + bool ping = false; + int ioc, ret; + u32 abort_code; + + _enter("%u,%s", call->debug_id, rxrpc_pkts[type]); + + spin_lock_bh(&call->lock); + if (call->conn) + conn = rxrpc_get_connection_maybe(call->conn); + spin_unlock_bh(&call->lock); + if (!conn) + return -ECONNRESET; + + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) { + rxrpc_put_connection(conn); + return -ENOMEM; + } + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + pkt->whdr.epoch = htonl(conn->proto.epoch); + pkt->whdr.cid = htonl(call->cid); + pkt->whdr.callNumber = htonl(call->call_id); + pkt->whdr.seq = 0; + pkt->whdr.type = type; + pkt->whdr.flags = conn->out_clientflag; + pkt->whdr.userStatus = 0; + pkt->whdr.securityIndex = call->security_ix; + pkt->whdr._rsvd = 0; + pkt->whdr.serviceId = htons(call->service_id); + + iov[0].iov_base = pkt; + iov[0].iov_len = sizeof(pkt->whdr); + len = sizeof(pkt->whdr); + + switch (type) { + case RXRPC_PACKET_TYPE_ACK: + spin_lock_bh(&call->lock); + if (!call->ackr_reason) { + spin_unlock_bh(&call->lock); + ret = 0; + goto out; + } + ping = (call->ackr_reason == RXRPC_ACK_PING); + n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top); + call->ackr_reason = 0; + + spin_unlock_bh(&call->lock); + + + pkt->whdr.flags |= RXRPC_SLOW_START_OK; + + iov[0].iov_len += sizeof(pkt->ack) + n; + iov[1].iov_base = &pkt->ackinfo; + iov[1].iov_len = sizeof(pkt->ackinfo); + len += sizeof(pkt->ack) + n + sizeof(pkt->ackinfo); + ioc = 2; + break; + + case RXRPC_PACKET_TYPE_ABORT: + abort_code = call->abort_code; + pkt->abort_code = htonl(abort_code); + iov[0].iov_len += sizeof(pkt->abort_code); + len += sizeof(pkt->abort_code); + ioc = 1; + break; + + default: + BUG(); + ret = -ENOANO; + goto out; + } + + serial = atomic_inc_return(&conn->serial); + pkt->whdr.serial = htonl(serial); + switch (type) { + case RXRPC_PACKET_TYPE_ACK: + trace_rxrpc_tx_ack(call, serial, + ntohl(pkt->ack.firstPacket), + ntohl(pkt->ack.serial), + pkt->ack.reason, pkt->ack.nAcks); + break; + } + + if (ping) { + call->ackr_ping = serial; + smp_wmb(); + /* We need to stick a time in before we send the packet in case + * the reply gets back before kernel_sendmsg() completes - but + * asking UDP to send the packet can take a relatively long + * time, so we update the time after, on the assumption that + * the packet transmission is more likely to happen towards the + * end of the kernel_sendmsg() call. + */ + call->ackr_ping_time = ktime_get_real(); + set_bit(RXRPC_CALL_PINGING, &call->flags); + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); + } + ret = kernel_sendmsg(conn->params.local->socket, + &msg, iov, ioc, len); + if (ping) + call->ackr_ping_time = ktime_get_real(); + + if (type == RXRPC_PACKET_TYPE_ACK && + call->state < RXRPC_CALL_COMPLETE) { + if (ret < 0) { + clear_bit(RXRPC_CALL_PINGING, &call->flags); + rxrpc_propose_ACK(call, pkt->ack.reason, + ntohs(pkt->ack.maxSkew), + ntohl(pkt->ack.serial), + true, true, + rxrpc_propose_ack_retry_tx); + } else { + spin_lock_bh(&call->lock); + if (after(hard_ack, call->ackr_consumed)) + call->ackr_consumed = hard_ack; + if (after(top, call->ackr_seen)) + call->ackr_seen = top; + spin_unlock_bh(&call->lock); + } + } + +out: + rxrpc_put_connection(conn); + kfree(pkt); + return ret; +} + /* * send a packet through the transport endpoint */ -int rxrpc_send_data_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb) { - struct kvec iov[1]; + struct rxrpc_connection *conn = call->conn; + struct rxrpc_wire_header whdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; + struct kvec iov[2]; + rxrpc_serial_t serial; + size_t len; int ret, opt; _enter(",{%d}", skb->len); - iov[0].iov_base = skb->head; - iov[0].iov_len = skb->len; + /* Each transmission of a Tx packet needs a new serial number */ + serial = atomic_inc_return(&conn->serial); - msg.msg_name = &conn->params.peer->srx.transport; - msg.msg_namelen = conn->params.peer->srx.transport_len; + whdr.epoch = htonl(conn->proto.epoch); + whdr.cid = htonl(call->cid); + whdr.callNumber = htonl(call->call_id); + whdr.seq = htonl(sp->hdr.seq); + whdr.serial = htonl(serial); + whdr.type = RXRPC_PACKET_TYPE_DATA; + whdr.flags = sp->hdr.flags; + whdr.userStatus = 0; + whdr.securityIndex = call->security_ix; + whdr._rsvd = htons(sp->hdr._rsvd); + whdr.serviceId = htons(call->service_id); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = skb->head; + iov[1].iov_len = skb->len; + len = iov[0].iov_len + iov[1].iov_len; + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; + /* If our RTT cache needs working on, request an ACK. Also request + * ACKs if a DATA packet appears to have been lost. + */ + if (call->cong_mode == RXRPC_CALL_FAST_RETRANSMIT || + (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real())) + whdr.flags |= RXRPC_REQUEST_ACK; + + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { + static int lose; + if ((lose++ & 7) == 7) { + trace_rxrpc_tx_data(call, sp->hdr.seq, serial, + whdr.flags, true); + rxrpc_lose_skb(skb, rxrpc_skb_tx_lost); + _leave(" = 0 [lose]"); + return 0; + } + } + + _proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq); + /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (skb->len - sizeof(struct rxrpc_wire_header) < conn->params.peer->maxdata) { - down_read(&conn->params.local->defrag_sem); - /* send the packet by UDP - * - returns -EMSGSIZE if UDP would have to fragment the packet - * to go out of the interface - * - in which case, we'll have processed the ICMP error - * message and update the peer record - */ - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, - iov[0].iov_len); + if (iov[1].iov_len >= call->peer->maxdata) + goto send_fragmentable; + + down_read(&conn->params.local->defrag_sem); + /* send the packet by UDP + * - returns -EMSGSIZE if UDP would have to fragment the packet + * to go out of the interface + * - in which case, we'll have processed the ICMP error + * message and update the peer record + */ + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - up_read(&conn->params.local->defrag_sem); - if (ret == -EMSGSIZE) - goto send_fragmentable; + up_read(&conn->params.local->defrag_sem); + if (ret == -EMSGSIZE) + goto send_fragmentable; - _leave(" = %d [%u]", ret, conn->params.peer->maxdata); - return ret; +done: + trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, false); + if (ret >= 0) { + ktime_t now = ktime_get_real(); + skb->tstamp = now; + smp_wmb(); + sp->hdr.serial = serial; + if (whdr.flags & RXRPC_REQUEST_ACK) { + call->peer->rtt_last_req = now; + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); + } } + _leave(" = %d [%u]", ret, call->peer->maxdata); + return ret; send_fragmentable: /* attempt to send this message with fragmentation enabled */ @@ -73,8 +346,8 @@ send_fragmentable: SOL_IP, IP_MTU_DISCOVER, (char *)&opt, sizeof(opt)); if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, - iov[0].iov_len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 2, len); opt = IP_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, SOL_IP, @@ -82,9 +355,82 @@ send_fragmentable: (char *)&opt, sizeof(opt)); } break; + +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + opt = IPV6_PMTUDISC_DONT; + ret = kernel_setsockopt(conn->params.local->socket, + SOL_IPV6, IPV6_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + if (ret == 0) { + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 1, iov[0].iov_len); + + opt = IPV6_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, + SOL_IPV6, IPV6_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + } + break; +#endif } up_write(&conn->params.local->defrag_sem); - _leave(" = %d [frag %u]", ret, conn->params.peer->maxdata); - return ret; + goto done; +} + +/* + * reject packets through the local endpoint + */ +void rxrpc_reject_packets(struct rxrpc_local *local) +{ + struct sockaddr_rxrpc srx; + struct rxrpc_skb_priv *sp; + struct rxrpc_wire_header whdr; + struct sk_buff *skb; + struct msghdr msg; + struct kvec iov[2]; + size_t size; + __be32 code; + + _enter("%d", local->debug_id); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = &code; + iov[1].iov_len = sizeof(code); + size = sizeof(whdr) + sizeof(code); + + msg.msg_name = &srx.transport; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + memset(&whdr, 0, sizeof(whdr)); + whdr.type = RXRPC_PACKET_TYPE_ABORT; + + while ((skb = skb_dequeue(&local->reject_queue))) { + rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + sp = rxrpc_skb(skb); + + if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { + msg.msg_namelen = srx.transport_len; + + code = htonl(skb->priority); + + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.serviceId = htons(sp->hdr.serviceId); + whdr.flags = sp->hdr.flags; + whdr.flags ^= RXRPC_CLIENT_INITIATED; + whdr.flags &= RXRPC_CLIENT_INITIATED; + + kernel_sendmsg(local->socket, &msg, iov, 2, size); + } + + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } + + _leave(""); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 27b9eca..bf13b84 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -66,6 +66,32 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, } break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + srx.transport.sin6.sin6_port = serr->port; + srx.transport_len = sizeof(struct sockaddr_in6); + switch (serr->ee.ee_origin) { + case SO_EE_ORIGIN_ICMP6: + _net("Rx ICMP6"); + memcpy(&srx.transport.sin6.sin6_addr, + skb_network_header(skb) + serr->addr_offset, + sizeof(struct in6_addr)); + break; + case SO_EE_ORIGIN_ICMP: + _net("Rx ICMP on v6 sock"); + memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12, + skb_network_header(skb) + serr->addr_offset, + sizeof(struct in_addr)); + break; + default: + memcpy(&srx.transport.sin6.sin6_addr, + &ipv6_hdr(skb)->saddr, + sizeof(struct in6_addr)); + break; + } + break; +#endif + default: BUG(); } @@ -129,22 +155,21 @@ void rxrpc_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } + rxrpc_new_skb(skb, rxrpc_skb_rx_received); serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); - kfree_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); return; } - rxrpc_new_skb(skb); - rcu_read_lock(); peer = rxrpc_lookup_peer_icmp_rcu(local, skb); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; if (!peer) { rcu_read_unlock(); - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); _leave(" [no peer]"); return; } @@ -154,7 +179,7 @@ void rxrpc_error_report(struct sock *sk) serr->ee.ee_code == ICMP_FRAG_NEEDED)) { rxrpc_adjust_mtu(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); rxrpc_put_peer(peer); _leave(" [MTU update]"); return; @@ -162,7 +187,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_store_error(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); /* The ref we obtained is passed off to the work item */ rxrpc_queue_work(&peer->error_distributor); @@ -249,7 +274,6 @@ void rxrpc_peer_error_distributor(struct work_struct *work) container_of(work, struct rxrpc_peer, error_distributor); struct rxrpc_call *call; enum rxrpc_call_completion compl; - bool queue; int error; _enter(""); @@ -272,15 +296,8 @@ void rxrpc_peer_error_distributor(struct work_struct *work) hlist_del_init(&call->error_link); rxrpc_see_call(call); - queue = false; - write_lock(&call->state_lock); - if (__rxrpc_set_call_completion(call, compl, 0, error)) { - set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); - queue = true; - } - write_unlock(&call->state_lock); - if (queue) - rxrpc_queue_call(call); + if (rxrpc_set_call_completion(call, compl, 0, error)) + rxrpc_notify_socket(call); } spin_unlock_bh(&peer->lock); @@ -288,3 +305,44 @@ void rxrpc_peer_error_distributor(struct work_struct *work) rxrpc_put_peer(peer); _leave(""); } + +/* + * Add RTT information to cache. This is called in softirq mode and has + * exclusive access to the peer RTT data. + */ +void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, + ktime_t send_time, ktime_t resp_time) +{ + struct rxrpc_peer *peer = call->peer; + s64 rtt; + u64 sum = peer->rtt_sum, avg; + u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage; + + rtt = ktime_to_ns(ktime_sub(resp_time, send_time)); + if (rtt < 0) + return; + + /* Replace the oldest datum in the RTT buffer */ + sum -= peer->rtt_cache[cursor]; + sum += rtt; + peer->rtt_cache[cursor] = rtt; + peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1); + peer->rtt_sum = sum; + if (usage < RXRPC_RTT_CACHE_SIZE) { + usage++; + peer->rtt_usage = usage; + } + + /* Now recalculate the average */ + if (usage == RXRPC_RTT_CACHE_SIZE) { + avg = sum / RXRPC_RTT_CACHE_SIZE; + } else { + avg = sum; + do_div(avg, usage); + } + + peer->rtt = avg; + trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt, + usage, avg); +} diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index aebc73a..941b724 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -16,12 +16,14 @@ #include <linux/skbuff.h> #include <linux/udp.h> #include <linux/in.h> +#include <linux/in6.h> #include <linux/slab.h> #include <linux/hashtable.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> #include <net/route.h> +#include <net/ip6_route.h> #include "ar-internal.h" static DEFINE_HASHTABLE(rxrpc_peer_hash, 10); @@ -50,6 +52,13 @@ static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local, size = sizeof(srx->transport.sin.sin_addr); p = (u16 *)&srx->transport.sin.sin_addr; break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + hash_key += (u16 __force)srx->transport.sin.sin_port; + size = sizeof(srx->transport.sin6.sin6_addr); + p = (u16 *)&srx->transport.sin6.sin6_addr; + break; +#endif default: WARN(1, "AF_RXRPC: Unsupported transport address family\n"); return 0; @@ -93,6 +102,14 @@ static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer, memcmp(&peer->srx.transport.sin.sin_addr, &srx->transport.sin.sin_addr, sizeof(struct in_addr)); +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + return ((u16 __force)peer->srx.transport.sin6.sin6_port - + (u16 __force)srx->transport.sin6.sin6_port) ?: + memcmp(&peer->srx.transport.sin6.sin6_addr, + &srx->transport.sin6.sin6_addr, + sizeof(struct in6_addr)); +#endif default: BUG(); } @@ -130,17 +147,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); if (peer) { - switch (srx->transport.family) { - case AF_INET: - _net("PEER %d {%d,%u,%pI4+%hu}", - peer->debug_id, - peer->srx.transport_type, - peer->srx.transport.family, - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); - break; - } - + _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); } return peer; @@ -152,22 +159,53 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, */ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) { + struct dst_entry *dst; struct rtable *rt; - struct flowi4 fl4; + struct flowi fl; + struct flowi4 *fl4 = &fl.u.ip4; +#ifdef CONFIG_AF_RXRPC_IPV6 + struct flowi6 *fl6 = &fl.u.ip6; +#endif peer->if_mtu = 1500; - rt = ip_route_output_ports(&init_net, &fl4, NULL, - peer->srx.transport.sin.sin_addr.s_addr, 0, - htons(7000), htons(7001), - IPPROTO_UDP, 0, 0); - if (IS_ERR(rt)) { - _leave(" [route err %ld]", PTR_ERR(rt)); - return; + memset(&fl, 0, sizeof(fl)); + switch (peer->srx.transport.family) { + case AF_INET: + rt = ip_route_output_ports( + &init_net, fl4, NULL, + peer->srx.transport.sin.sin_addr.s_addr, 0, + htons(7000), htons(7001), IPPROTO_UDP, 0, 0); + if (IS_ERR(rt)) { + _leave(" [route err %ld]", PTR_ERR(rt)); + return; + } + dst = &rt->dst; + break; + +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + fl6->flowi6_iif = LOOPBACK_IFINDEX; + fl6->flowi6_scope = RT_SCOPE_UNIVERSE; + fl6->flowi6_proto = IPPROTO_UDP; + memcpy(&fl6->daddr, &peer->srx.transport.sin6.sin6_addr, + sizeof(struct in6_addr)); + fl6->fl6_dport = htons(7001); + fl6->fl6_sport = htons(7000); + dst = ip6_route_output(&init_net, NULL, fl6); + if (IS_ERR(dst)) { + _leave(" [route err %ld]", PTR_ERR(dst)); + return; + } + break; +#endif + + default: + BUG(); } - peer->if_mtu = dst_mtu(&rt->dst); - dst_release(&rt->dst); + peer->if_mtu = dst_mtu(dst); + dst_release(dst); _leave(" [if_mtu %u]", peer->if_mtu); } @@ -199,6 +237,41 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) } /* + * Initialise peer record. + */ +static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key) +{ + peer->hash_key = hash_key; + rxrpc_assess_MTU_size(peer); + peer->mtu = peer->if_mtu; + peer->rtt_last_req = ktime_get_real(); + + switch (peer->srx.transport.family) { + case AF_INET: + peer->hdrsize = sizeof(struct iphdr); + break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + peer->hdrsize = sizeof(struct ipv6hdr); + break; +#endif + default: + BUG(); + } + + switch (peer->srx.transport_type) { + case SOCK_DGRAM: + peer->hdrsize += sizeof(struct udphdr); + break; + default: + BUG(); + } + + peer->hdrsize += sizeof(struct rxrpc_wire_header); + peer->maxdata = peer->mtu - peer->hdrsize; +} + +/* * Set up a new peer. */ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, @@ -212,31 +285,40 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, peer = rxrpc_alloc_peer(local, gfp); if (peer) { - peer->hash_key = hash_key; memcpy(&peer->srx, srx, sizeof(*srx)); + rxrpc_init_peer(peer, hash_key); + } - rxrpc_assess_MTU_size(peer); - peer->mtu = peer->if_mtu; - - if (srx->transport.family == AF_INET) { - peer->hdrsize = sizeof(struct iphdr); - switch (srx->transport_type) { - case SOCK_DGRAM: - peer->hdrsize += sizeof(struct udphdr); - break; - default: - BUG(); - break; - } - } else { - BUG(); - } + _leave(" = %p", peer); + return peer; +} + +/* + * Set up a new incoming peer. The address is prestored in the preallocated + * peer. + */ +struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, + struct rxrpc_peer *prealloc) +{ + struct rxrpc_peer *peer; + unsigned long hash_key; + + hash_key = rxrpc_peer_hash_key(local, &prealloc->srx); + prealloc->local = local; + rxrpc_init_peer(prealloc, hash_key); - peer->hdrsize += sizeof(struct rxrpc_wire_header); - peer->maxdata = peer->mtu - peer->hdrsize; + spin_lock(&rxrpc_peer_hash_lock); + + /* Need to check that we aren't racing with someone else */ + peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + peer = prealloc; + hash_add_rcu(rxrpc_peer_hash, &peer->hash_link, hash_key); } - _leave(" = %p", peer); + spin_unlock(&rxrpc_peer_hash_lock); return peer; } @@ -249,11 +331,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, *candidate; unsigned long hash_key = rxrpc_peer_hash_key(local, srx); - _enter("{%d,%d,%pI4+%hu}", - srx->transport_type, - srx->transport_len, - &srx->transport.sin.sin_addr, - ntohs(srx->transport.sin.sin_port)); + _enter("{%pISp}", &srx->transport); /* search the peer list first */ rcu_read_lock(); @@ -272,7 +350,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, return NULL; } - spin_lock(&rxrpc_peer_hash_lock); + spin_lock_bh(&rxrpc_peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); @@ -282,7 +360,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, hash_add_rcu(rxrpc_peer_hash, &candidate->hash_link, hash_key); - spin_unlock(&rxrpc_peer_hash_lock); + spin_unlock_bh(&rxrpc_peer_hash_lock); if (peer) kfree(candidate); @@ -290,11 +368,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, peer = candidate; } - _net("PEER %d {%d,%pI4+%hu}", - peer->debug_id, - peer->srx.transport_type, - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); + _net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport); _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); return peer; @@ -307,9 +381,9 @@ void __rxrpc_put_peer(struct rxrpc_peer *peer) { ASSERT(hlist_empty(&peer->error_targets)); - spin_lock(&rxrpc_peer_hash_lock); + spin_lock_bh(&rxrpc_peer_hash_lock); hash_del_rcu(&peer->hash_link); - spin_unlock(&rxrpc_peer_hash_lock); + spin_unlock_bh(&rxrpc_peer_hash_lock); kfree_rcu(peer, rcu); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 82c6405..65cd980 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -17,6 +17,7 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_UNUSED] = "Unused ", [RXRPC_CONN_CLIENT] = "Client ", + [RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc", [RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ", [RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ", [RXRPC_CONN_SERVICE] = "SvSecure", @@ -29,6 +30,7 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { */ static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos) { + rcu_read_lock(); read_lock(&rxrpc_call_lock); return seq_list_start_head(&rxrpc_calls, *_pos); } @@ -41,6 +43,7 @@ static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) { read_unlock(&rxrpc_call_lock); + rcu_read_unlock(); } static int rxrpc_call_seq_show(struct seq_file *seq, void *v) @@ -49,11 +52,12 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_sock *rx; struct rxrpc_peer *peer; struct rxrpc_call *call; - char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; + char lbuff[50], rbuff[50]; if (v == &rxrpc_calls) { seq_puts(seq, - "Proto Local Remote " + "Proto Local " + " Remote " " SvID ConnID CallID End Use State Abort " " UserID\n"); return 0; @@ -61,13 +65,11 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call = list_entry(v, struct rxrpc_call, link); - rx = READ_ONCE(call->socket); + rx = rcu_dereference(call->socket); if (rx) { local = READ_ONCE(rx->local); if (local) - sprintf(lbuff, "%pI4:%u", - &local->srx.transport.sin.sin_addr, - ntohs(local->srx.transport.sin.sin_port)); + sprintf(lbuff, "%pISpc", &local->srx.transport); else strcpy(lbuff, "no_local"); } else { @@ -76,14 +78,12 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) peer = call->peer; if (peer) - sprintf(rbuff, "%pI4:%u", - &peer->srx.transport.sin.sin_addr, - ntohs(peer->srx.transport.sin.sin_port)); + sprintf(rbuff, "%pISpc", &peer->srx.transport); else strcpy(rbuff, "no_connection"); seq_printf(seq, - "UDP %-22.22s %-22.22s %4x %08x %08x %s %3u" + "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %lx\n", lbuff, rbuff, @@ -142,11 +142,12 @@ static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) { struct rxrpc_connection *conn; - char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; + char lbuff[50], rbuff[50]; if (v == &rxrpc_connection_proc_list) { seq_puts(seq, - "Proto Local Remote " + "Proto Local " + " Remote " " SvID ConnID End Use State Key " " Serial ISerial\n" ); @@ -154,17 +155,18 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) } conn = list_entry(v, struct rxrpc_connection, proc_link); + if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) { + strcpy(lbuff, "no_local"); + strcpy(rbuff, "no_connection"); + goto print; + } - sprintf(lbuff, "%pI4:%u", - &conn->params.local->srx.transport.sin.sin_addr, - ntohs(conn->params.local->srx.transport.sin.sin_port)); - - sprintf(rbuff, "%pI4:%u", - &conn->params.peer->srx.transport.sin.sin_addr, - ntohs(conn->params.peer->srx.transport.sin.sin_port)); + sprintf(lbuff, "%pISpc", &conn->params.local->srx.transport); + sprintf(rbuff, "%pISpc", &conn->params.peer->srx.transport); +print: seq_printf(seq, - "UDP %-22.22s %-22.22s %4x %08x %s %3u" + "UDP %-47.47s %-47.47s %4x %08x %s %3u" " %s %08x %08x %08x\n", lbuff, rbuff, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 0ab7b33..038ae62 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -19,427 +19,545 @@ #include "ar-internal.h" /* - * removal a call's user ID from the socket tree to make the user ID available - * again and so that it won't be seen again in association with that call + * Post a call for attention by the socket or kernel service. Further + * notifications are suppressed by putting recvmsg_link on a dummy queue. */ -void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call) +void rxrpc_notify_socket(struct rxrpc_call *call) { - _debug("RELEASE CALL %d", call->debug_id); + struct rxrpc_sock *rx; + struct sock *sk; - if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { - write_lock_bh(&rx->call_lock); - rb_erase(&call->sock_node, &call->socket->calls); - clear_bit(RXRPC_CALL_HAS_USERID, &call->flags); - write_unlock_bh(&rx->call_lock); + _enter("%d", call->debug_id); + + if (!list_empty(&call->recvmsg_link)) + return; + + rcu_read_lock(); + + rx = rcu_dereference(call->socket); + sk = &rx->sk; + if (rx && sk->sk_state < RXRPC_CLOSE) { + if (call->notify_rx) { + call->notify_rx(sk, call, call->user_call_ID); + } else { + write_lock_bh(&rx->recvmsg_lock); + if (list_empty(&call->recvmsg_link)) { + rxrpc_get_call(call, rxrpc_call_got); + list_add_tail(&call->recvmsg_link, &rx->recvmsg_q); + } + write_unlock_bh(&rx->recvmsg_lock); + + if (!sock_flag(sk, SOCK_DEAD)) { + _debug("call %ps", sk->sk_data_ready); + sk->sk_data_ready(sk); + } + } } - read_lock_bh(&call->state_lock); - if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && - !test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) - rxrpc_queue_call(call); - read_unlock_bh(&call->state_lock); + rcu_read_unlock(); + _leave(""); } /* - * receive a message from an RxRPC socket - * - we need to be careful about two or more threads calling recvmsg - * simultaneously + * Pass a call terminating message to userspace. */ -int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) { - struct rxrpc_skb_priv *sp; - struct rxrpc_call *call = NULL, *continue_call = NULL; - struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - struct sk_buff *skb; - long timeo; - int copy, ret, ullen, offset, copied = 0; - u32 abort_code; + u32 tmp = 0; + int ret; - DEFINE_WAIT(wait); + switch (call->completion) { + case RXRPC_CALL_SUCCEEDED: + ret = 0; + if (rxrpc_is_service_call(call)) + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ACK, 0, &tmp); + break; + case RXRPC_CALL_REMOTELY_ABORTED: + tmp = call->abort_code; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp); + break; + case RXRPC_CALL_LOCALLY_ABORTED: + tmp = call->abort_code; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp); + break; + case RXRPC_CALL_NETWORK_ERROR: + tmp = call->error; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &tmp); + break; + case RXRPC_CALL_LOCAL_ERROR: + tmp = call->error; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp); + break; + default: + pr_err("Invalid terminal call state %u\n", call->state); + BUG(); + break; + } - _enter(",,,%zu,%d", len, flags); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, + call->rx_pkt_offset, call->rx_pkt_len, ret); + return ret; +} - if (flags & (MSG_OOB | MSG_TRUNC)) - return -EOPNOTSUPP; +/* + * Pass back notification of a new call. The call is added to the + * to-be-accepted list. This means that the next call to be accepted might not + * be the last call seen awaiting acceptance, but unless we leave this on the + * front of the queue and block all other messages until someone gives us a + * user_ID for it, there's not a lot we can do. + */ +static int rxrpc_recvmsg_new_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct msghdr *msg, int flags) +{ + int tmp = 0, ret; - ullen = msg->msg_flags & MSG_CMSG_COMPAT ? 4 : sizeof(unsigned long); + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &tmp); - timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT); - msg->msg_flags |= MSG_MORE; + if (ret == 0 && !(flags & MSG_PEEK)) { + _debug("to be accepted"); + write_lock_bh(&rx->recvmsg_lock); + list_del_init(&call->recvmsg_link); + write_unlock_bh(&rx->recvmsg_lock); - lock_sock(&rx->sk); + rxrpc_get_call(call, rxrpc_call_got); + write_lock(&rx->call_lock); + list_add_tail(&call->accept_link, &rx->to_be_accepted); + write_unlock(&rx->call_lock); + } - for (;;) { - /* return immediately if a client socket has no outstanding - * calls */ - if (RB_EMPTY_ROOT(&rx->calls)) { - if (copied) - goto out; - if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) { - release_sock(&rx->sk); - if (continue_call) - rxrpc_put_call(continue_call); - return -ENODATA; - } - } + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_to_be_accepted, 1, 0, 0, ret); + return ret; +} - /* get the next message on the Rx queue */ - skb = skb_peek(&rx->sk.sk_receive_queue); - if (!skb) { - /* nothing remains on the queue */ - if (copied && - (flags & MSG_PEEK || timeo == 0)) - goto out; +/* + * End the packet reception phase. + */ +static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) +{ + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - /* wait for a message to turn up */ - release_sock(&rx->sk); - prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait, - TASK_INTERRUPTIBLE); - ret = sock_error(&rx->sk); - if (ret) - goto wait_error; - - if (skb_queue_empty(&rx->sk.sk_receive_queue)) { - if (signal_pending(current)) - goto wait_interrupted; - timeo = schedule_timeout(timeo); - } - finish_wait(sk_sleep(&rx->sk), &wait); - lock_sock(&rx->sk); - continue; - } + trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); + ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); - peek_next_packet: - rxrpc_see_skb(skb); - sp = rxrpc_skb(skb); - call = sp->call; - ASSERT(call != NULL); - rxrpc_see_call(call); - - _debug("next pkt %s", rxrpc_pkts[sp->hdr.type]); - - /* make sure we wait for the state to be updated in this call */ - spin_lock_bh(&call->lock); - spin_unlock_bh(&call->lock); - - if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { - _debug("packet from released call"); - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - rxrpc_free_skb(skb); - continue; - } + if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false, + rxrpc_propose_ack_terminal_ack); + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + } - /* determine whether to continue last data receive */ - if (continue_call) { - _debug("maybe cont"); - if (call != continue_call || - skb->mark != RXRPC_SKB_MARK_DATA) { - release_sock(&rx->sk); - rxrpc_put_call(continue_call); - _leave(" = %d [noncont]", copied); - return copied; - } - } + write_lock_bh(&call->state_lock); - rxrpc_get_call(call); + switch (call->state) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + __rxrpc_call_completed(call); + break; - /* copy the peer address and timestamp */ - if (!continue_call) { - if (msg->msg_name) { - size_t len = - sizeof(call->conn->params.peer->srx); - memcpy(msg->msg_name, - &call->conn->params.peer->srx, len); - msg->msg_namelen = len; - } - sock_recv_timestamp(msg, &rx->sk, skb); - } + case RXRPC_CALL_SERVER_RECV_REQUEST: + call->tx_phase = true; + call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + break; + default: + break; + } - /* receive the message */ - if (skb->mark != RXRPC_SKB_MARK_DATA) - goto receive_non_data_message; + write_unlock_bh(&call->state_lock); +} - _debug("recvmsg DATA #%u { %d, %d }", - sp->hdr.seq, skb->len, sp->offset); +/* + * Discard a packet we've used up and advance the Rx window by one. + */ +static void rxrpc_rotate_rx_window(struct rxrpc_call *call) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + rxrpc_serial_t serial; + rxrpc_seq_t hard_ack, top; + u8 flags; + int ix; - if (!continue_call) { - /* only set the control data once per recvmsg() */ - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, - ullen, &call->user_call_ID); - if (ret < 0) - goto copy_error; - ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); - } + _enter("%d", call->debug_id); - ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); - ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); - call->rx_data_recv = sp->hdr.seq; + hard_ack = call->rx_hard_ack; + top = smp_load_acquire(&call->rx_top); + ASSERT(before(hard_ack, top)); - ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); + hard_ack++; + ix = hard_ack & RXRPC_RXTX_BUFF_MASK; + skb = call->rxtx_buffer[ix]; + rxrpc_see_skb(skb, rxrpc_skb_rx_rotated); + sp = rxrpc_skb(skb); + flags = sp->hdr.flags; + serial = sp->hdr.serial; + if (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) + serial += (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - 1; + + call->rxtx_buffer[ix] = NULL; + call->rxtx_annotations[ix] = 0; + /* Barrier against rxrpc_input_data(). */ + smp_store_release(&call->rx_hard_ack, hard_ack); + + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + + _debug("%u,%u,%02x", hard_ack, top, flags); + trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); + if (flags & RXRPC_LAST_PACKET) { + rxrpc_end_rx_phase(call, serial); + } else { + /* Check to see if there's an ACK that needs sending. */ + if (after_eq(hard_ack, call->ackr_consumed + 2) || + after_eq(top, call->ackr_seen + 2) || + (hard_ack == top && after(hard_ack, call->ackr_consumed))) + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, + true, false, + rxrpc_propose_ack_rotate_rx); + if (call->ackr_reason) + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + } +} - offset = sp->offset; - copy = skb->len - offset; - if (copy > len - copied) - copy = len - copied; +/* + * Decrypt and verify a (sub)packet. The packet's length may be changed due to + * padding, but if this is the case, the packet length will be resident in the + * socket buffer. Note that we can't modify the master skb info as the skb may + * be the home to multiple subpackets. + */ +static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, + u8 annotation, + unsigned int offset, unsigned int len) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + rxrpc_seq_t seq = sp->hdr.seq; + u16 cksum = sp->hdr.cksum; + + _enter(""); + + /* For all but the head jumbo subpacket, the security checksum is in a + * jumbo header immediately prior to the data. + */ + if ((annotation & RXRPC_RX_ANNO_JUMBO) > 1) { + __be16 tmp; + if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) + BUG(); + cksum = ntohs(tmp); + seq += (annotation & RXRPC_RX_ANNO_JUMBO) - 1; + } - ret = skb_copy_datagram_msg(skb, offset, msg, copy); + return call->conn->security->verify_packet(call, skb, offset, len, + seq, cksum); +} +/* + * Locate the data within a packet. This is complicated by: + * + * (1) An skb may contain a jumbo packet - so we have to find the appropriate + * subpacket. + * + * (2) The (sub)packets may be encrypted and, if so, the encrypted portion + * contains an extra header which includes the true length of the data, + * excluding any encrypted padding. + */ +static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, + u8 *_annotation, + unsigned int *_offset, unsigned int *_len) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + unsigned int offset = *_offset; + unsigned int len = *_len; + int ret; + u8 annotation = *_annotation; + + /* Locate the subpacket */ + offset = sp->offset; + len = skb->len - sp->offset; + if ((annotation & RXRPC_RX_ANNO_JUMBO) > 0) { + offset += (((annotation & RXRPC_RX_ANNO_JUMBO) - 1) * + RXRPC_JUMBO_SUBPKTLEN); + len = (annotation & RXRPC_RX_ANNO_JLAST) ? + skb->len - offset : RXRPC_JUMBO_SUBPKTLEN; + } + + if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { + ret = rxrpc_verify_packet(call, skb, annotation, offset, len); if (ret < 0) - goto copy_error; + return ret; + *_annotation |= RXRPC_RX_ANNO_VERIFIED; + } + + *_offset = offset; + *_len = len; + call->conn->security->locate_data(call, skb, _offset, _len); + return 0; +} - /* handle piecemeal consumption of data packets */ - _debug("copied %d+%d", copy, copied); +/* + * Deliver messages to a call. This keeps processing packets until the buffer + * is filled and we find either more DATA (returns 0) or the end of the DATA + * (returns 1). If more packets are required, it returns -EAGAIN. + */ +static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, + struct msghdr *msg, struct iov_iter *iter, + size_t len, int flags, size_t *_offset) +{ + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + rxrpc_seq_t hard_ack, top, seq; + size_t remain; + bool last; + unsigned int rx_pkt_offset, rx_pkt_len; + int ix, copy, ret = -EAGAIN, ret2; - offset += copy; - copied += copy; + rx_pkt_offset = call->rx_pkt_offset; + rx_pkt_len = call->rx_pkt_len; - if (!(flags & MSG_PEEK)) - sp->offset = offset; + if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { + seq = call->rx_hard_ack; + ret = 1; + goto done; + } - if (sp->offset < skb->len) { - _debug("buffer full"); - ASSERTCMP(copied, ==, len); + /* Barriers against rxrpc_input_data(). */ + hard_ack = call->rx_hard_ack; + top = smp_load_acquire(&call->rx_top); + for (seq = hard_ack + 1; before_eq(seq, top); seq++) { + ix = seq & RXRPC_RXTX_BUFF_MASK; + skb = call->rxtx_buffer[ix]; + if (!skb) { + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, + rx_pkt_offset, rx_pkt_len, 0); break; } + smp_rmb(); + rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + sp = rxrpc_skb(skb); - /* we transferred the whole data packet */ if (!(flags & MSG_PEEK)) - rxrpc_kernel_data_consumed(call, skb); - - if (sp->hdr.flags & RXRPC_LAST_PACKET) { - _debug("last"); - if (rxrpc_conn_is_client(call->conn)) { - /* last byte of reply received */ - ret = copied; - goto terminal_message; + trace_rxrpc_receive(call, rxrpc_receive_front, + sp->hdr.serial, seq); + + if (msg) + sock_recv_timestamp(msg, sock->sk, skb); + + if (rx_pkt_offset == 0) { + ret2 = rxrpc_locate_data(call, skb, + &call->rxtx_annotations[ix], + &rx_pkt_offset, &rx_pkt_len); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, + rx_pkt_offset, rx_pkt_len, ret2); + if (ret2 < 0) { + ret = ret2; + goto out; } + } else { + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq, + rx_pkt_offset, rx_pkt_len, 0); + } - /* last bit of request received */ - if (!(flags & MSG_PEEK)) { - _debug("eat packet"); - if (skb_dequeue(&rx->sk.sk_receive_queue) != - skb) - BUG(); - rxrpc_free_skb(skb); + /* We have to handle short, empty and used-up DATA packets. */ + remain = len - *_offset; + copy = rx_pkt_len; + if (copy > remain) + copy = remain; + if (copy > 0) { + ret2 = skb_copy_datagram_iter(skb, rx_pkt_offset, iter, + copy); + if (ret2 < 0) { + ret = ret2; + goto out; } - msg->msg_flags &= ~MSG_MORE; - break; - } - /* move on to the next data message */ - _debug("next"); - if (!continue_call) - continue_call = sp->call; - else - rxrpc_put_call(call); - call = NULL; - - if (flags & MSG_PEEK) { - _debug("peek next"); - skb = skb->next; - if (skb == (struct sk_buff *) &rx->sk.sk_receive_queue) - break; - goto peek_next_packet; + /* handle piecemeal consumption of data packets */ + rx_pkt_offset += copy; + rx_pkt_len -= copy; + *_offset += copy; } - _debug("eat packet"); - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - rxrpc_free_skb(skb); - } - - /* end of non-terminal data packet reception for the moment */ - _debug("end rcv data"); -out: - release_sock(&rx->sk); - if (call) - rxrpc_put_call(call); - if (continue_call) - rxrpc_put_call(continue_call); - _leave(" = %d [data]", copied); - return copied; - - /* handle non-DATA messages such as aborts, incoming connections and - * final ACKs */ -receive_non_data_message: - _debug("non-data"); - - if (skb->mark == RXRPC_SKB_MARK_NEW_CALL) { - _debug("RECV NEW CALL"); - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &abort_code); - if (ret < 0) - goto copy_error; - if (!(flags & MSG_PEEK)) { - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - rxrpc_free_skb(skb); + if (rx_pkt_len > 0) { + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq, + rx_pkt_offset, rx_pkt_len, 0); + ASSERTCMP(*_offset, ==, len); + ret = 0; + break; } - goto out; - } - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, - ullen, &call->user_call_ID); - if (ret < 0) - goto copy_error; - ASSERT(test_bit(RXRPC_CALL_HAS_USERID, &call->flags)); + /* The whole packet has been transferred. */ + last = sp->hdr.flags & RXRPC_LAST_PACKET; + if (!(flags & MSG_PEEK)) + rxrpc_rotate_rx_window(call); + rx_pkt_offset = 0; + rx_pkt_len = 0; - switch (skb->mark) { - case RXRPC_SKB_MARK_DATA: - BUG(); - case RXRPC_SKB_MARK_FINAL_ACK: - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ACK, 0, &abort_code); - break; - case RXRPC_SKB_MARK_BUSY: - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_BUSY, 0, &abort_code); - break; - case RXRPC_SKB_MARK_REMOTE_ABORT: - abort_code = call->abort_code; - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); - break; - case RXRPC_SKB_MARK_LOCAL_ABORT: - abort_code = call->abort_code; - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); - if (call->error) { - abort_code = call->error; - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, - &abort_code); + if (last) { + ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); + ret = 1; + goto out; } - break; - case RXRPC_SKB_MARK_NET_ERROR: - _debug("RECV NET ERROR %d", sp->error); - abort_code = sp->error; - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &abort_code); - break; - case RXRPC_SKB_MARK_LOCAL_ERROR: - _debug("RECV LOCAL ERROR %d", sp->error); - abort_code = sp->error; - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, - &abort_code); - break; - default: - pr_err("Unknown packet mark %u\n", skb->mark); - BUG(); - break; } - if (ret < 0) - goto copy_error; - -terminal_message: - _debug("terminal"); - msg->msg_flags &= ~MSG_MORE; - msg->msg_flags |= MSG_EOR; - +out: if (!(flags & MSG_PEEK)) { - _net("free terminal skb %p", skb); - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - rxrpc_free_skb(skb); - rxrpc_remove_user_ID(rx, call); + call->rx_pkt_offset = rx_pkt_offset; + call->rx_pkt_len = rx_pkt_len; } - - release_sock(&rx->sk); - rxrpc_put_call(call); - if (continue_call) - rxrpc_put_call(continue_call); - _leave(" = %d", ret); +done: + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, + rx_pkt_offset, rx_pkt_len, ret); return ret; - -copy_error: - _debug("copy error"); - release_sock(&rx->sk); - rxrpc_put_call(call); - if (continue_call) - rxrpc_put_call(continue_call); - _leave(" = %d", ret); - return ret; - -wait_interrupted: - ret = sock_intr_errno(timeo); -wait_error: - finish_wait(sk_sleep(&rx->sk), &wait); - if (continue_call) - rxrpc_put_call(continue_call); - if (copied) - copied = ret; - _leave(" = %d [waitfail %d]", copied, ret); - return copied; - } /* - * Deliver messages to a call. This keeps processing packets until the buffer - * is filled and we find either more DATA (returns 0) or the end of the DATA - * (returns 1). If more packets are required, it returns -EAGAIN. - * - * TODO: Note that this is hacked in at the moment and will be replaced. + * Receive a message from an RxRPC socket + * - we need to be careful about two or more threads calling recvmsg + * simultaneously */ -static int temp_deliver_data(struct socket *sock, struct rxrpc_call *call, - struct iov_iter *iter, size_t size, - size_t *_offset) +int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - size_t remain; - int ret, copy; + struct rxrpc_call *call; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + struct list_head *l; + size_t copied = 0; + long timeo; + int ret; - _enter("%d", call->debug_id); + DEFINE_WAIT(wait); -next: - local_bh_disable(); - skb = skb_dequeue(&call->knlrecv_queue); - local_bh_enable(); - if (!skb) { - if (test_bit(RXRPC_CALL_RX_NO_MORE, &call->flags)) - return 1; - _leave(" = -EAGAIN [empty]"); - return -EAGAIN; + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0); + + if (flags & (MSG_OOB | MSG_TRUNC)) + return -EOPNOTSUPP; + + timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT); + +try_again: + lock_sock(&rx->sk); + + /* Return immediately if a client socket has no outstanding calls */ + if (RB_EMPTY_ROOT(&rx->calls) && + list_empty(&rx->recvmsg_q) && + rx->sk.sk_state != RXRPC_SERVER_LISTENING) { + release_sock(&rx->sk); + return -ENODATA; } - sp = rxrpc_skb(skb); - _debug("dequeued %p %u/%zu", skb, sp->offset, size); - - switch (skb->mark) { - case RXRPC_SKB_MARK_DATA: - remain = size - *_offset; - if (remain > 0) { - copy = skb->len - sp->offset; - if (copy > remain) - copy = remain; - ret = skb_copy_datagram_iter(skb, sp->offset, iter, - copy); - if (ret < 0) - goto requeue_and_leave; + if (list_empty(&rx->recvmsg_q)) { + ret = -EWOULDBLOCK; + if (timeo == 0) { + call = NULL; + goto error_no_call; + } - /* handle piecemeal consumption of data packets */ - sp->offset += copy; - *_offset += copy; + release_sock(&rx->sk); + + /* Wait for something to happen */ + prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait, + TASK_INTERRUPTIBLE); + ret = sock_error(&rx->sk); + if (ret) + goto wait_error; + + if (list_empty(&rx->recvmsg_q)) { + if (signal_pending(current)) + goto wait_interrupted; + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, + 0, 0, 0, 0); + timeo = schedule_timeout(timeo); } + finish_wait(sk_sleep(&rx->sk), &wait); + goto try_again; + } - if (sp->offset < skb->len) - goto partially_used_skb; + /* Find the next call and dequeue it if we're not just peeking. If we + * do dequeue it, that comes with a ref that we will need to release. + */ + write_lock_bh(&rx->recvmsg_lock); + l = rx->recvmsg_q.next; + call = list_entry(l, struct rxrpc_call, recvmsg_link); + if (!(flags & MSG_PEEK)) + list_del_init(&call->recvmsg_link); + else + rxrpc_get_call(call, rxrpc_call_got); + write_unlock_bh(&rx->recvmsg_lock); + + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) + BUG(); - /* We consumed the whole packet */ - ASSERTCMP(sp->offset, ==, skb->len); - if (sp->hdr.flags & RXRPC_LAST_PACKET) - set_bit(RXRPC_CALL_RX_NO_MORE, &call->flags); - rxrpc_kernel_data_consumed(call, skb); - rxrpc_free_skb(skb); - goto next; + if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { + if (flags & MSG_CMSG_COMPAT) { + unsigned int id32 = call->user_call_ID; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + sizeof(unsigned int), &id32); + } else { + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + sizeof(unsigned long), + &call->user_call_ID); + } + if (ret < 0) + goto error; + } + + if (msg->msg_name) { + size_t len = sizeof(call->conn->params.peer->srx); + memcpy(msg->msg_name, &call->conn->params.peer->srx, len); + msg->msg_namelen = len; + } + + switch (call->state) { + case RXRPC_CALL_SERVER_ACCEPTING: + ret = rxrpc_recvmsg_new_call(rx, call, msg, flags); + break; + case RXRPC_CALL_CLIENT_RECV_REPLY: + case RXRPC_CALL_SERVER_RECV_REQUEST: + case RXRPC_CALL_SERVER_ACK_REQUEST: + ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len, + flags, &copied); + if (ret == -EAGAIN) + ret = 0; + + if (after(call->rx_top, call->rx_hard_ack) && + call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) + rxrpc_notify_socket(call); + break; default: - rxrpc_free_skb(skb); - goto next; + ret = 0; + break; + } + + if (ret < 0) + goto error; + + if (call->state == RXRPC_CALL_COMPLETE) { + ret = rxrpc_recvmsg_term(call, msg); + if (ret < 0) + goto error; + if (!(flags & MSG_PEEK)) + rxrpc_release_call(rx, call); + msg->msg_flags |= MSG_EOR; + ret = 1; } -partially_used_skb: - ASSERTCMP(*_offset, ==, size); - ret = 0; -requeue_and_leave: - skb_queue_head(&call->knlrecv_queue, skb); + if (ret == 0) + msg->msg_flags |= MSG_MORE; + else + msg->msg_flags &= ~MSG_MORE; + ret = copied; + +error: + rxrpc_put_call(call, rxrpc_call_put); +error_no_call: + release_sock(&rx->sk); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; + +wait_interrupted: + ret = sock_intr_errno(timeo); +wait_error: + finish_wait(sk_sleep(&rx->sk), &wait); + call = NULL; + goto error_no_call; } /** @@ -474,8 +592,9 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, struct kvec iov; int ret; - _enter("{%d,%s},%zu,%d", - call->debug_id, rxrpc_call_states[call->state], size, want_more); + _enter("{%d,%s},%zu/%zu,%d", + call->debug_id, rxrpc_call_states[call->state], + *_offset, size, want_more); ASSERTCMP(*_offset, <=, size); ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); @@ -490,7 +609,8 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = temp_deliver_data(sock, call, &iter, size, _offset); + ret = rxrpc_recvmsg_data(sock, call, NULL, &iter, size, 0, + _offset); if (ret < 0) goto out; @@ -515,7 +635,6 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, goto call_complete; default: - *_offset = 0; ret = -EINPROGRESS; goto out; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 89f475f..88d080a 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -80,12 +80,10 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn) case RXRPC_SECURITY_AUTH: conn->size_align = 8; conn->security_size = sizeof(struct rxkad_level1_hdr); - conn->header_size += sizeof(struct rxkad_level1_hdr); break; case RXRPC_SECURITY_ENCRYPT: conn->size_align = 8; conn->security_size = sizeof(struct rxkad_level2_hdr); - conn->header_size += sizeof(struct rxkad_level2_hdr); break; default: ret = -EKEYREJECTED; @@ -161,7 +159,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ sp->hdr.callNumber; + check = sp->hdr.seq ^ call->call_id; data_size |= (u32)check << 16; hdr.data_size = htonl(data_size); @@ -205,7 +203,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ sp->hdr.callNumber; + check = sp->hdr.seq ^ call->call_id; rxkhdr.data_size = htonl(data_size | (u32)check << 16); rxkhdr.checksum = 0; @@ -277,7 +275,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, /* calculate the security checksum */ x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= sp->hdr.seq & 0x3fffffff; - call->crypto_buf[0] = htonl(sp->hdr.callNumber); + call->crypto_buf[0] = htonl(call->call_id); call->crypto_buf[1] = htonl(x); sg_init_one(&sg, call->crypto_buf, 8); @@ -316,12 +314,11 @@ static int rxkad_secure_packet(struct rxrpc_call *call, /* * decrypt partial encryption on a packet (level 1 security) */ -static int rxkad_verify_packet_auth(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 *_abort_code) +static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int offset, unsigned int len, + rxrpc_seq_t seq) { struct rxkad_level1_hdr sechdr; - struct rxrpc_skb_priv *sp; SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; struct scatterlist sg[16]; @@ -332,15 +329,20 @@ static int rxkad_verify_packet_auth(const struct rxrpc_call *call, _enter(""); - sp = rxrpc_skb(skb); + if (len < 8) { + rxrpc_abort_call("V1H", call, seq, RXKADSEALEDINCON, EPROTO); + goto protocol_error; + } - /* we want to decrypt the skbuff in-place */ + /* Decrypt the skbuff in-place. TODO: We really want to decrypt + * directly into the target buffer. + */ nsg = skb_cow_data(skb, 0, &trailer); if (nsg < 0 || nsg > 16) goto nomem; sg_init_table(sg, nsg); - skb_to_sgvec(skb, sg, 0, 8); + skb_to_sgvec(skb, sg, offset, 8); /* start the decryption afresh */ memset(&iv, 0, sizeof(iv)); @@ -351,35 +353,35 @@ static int rxkad_verify_packet_auth(const struct rxrpc_call *call, crypto_skcipher_decrypt(req); skcipher_request_zero(req); - /* remove the decrypted packet length */ - if (skb_copy_bits(skb, 0, &sechdr, sizeof(sechdr)) < 0) - goto datalen_error; - if (!skb_pull(skb, sizeof(sechdr))) - BUG(); + /* Extract the decrypted packet length */ + if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + rxrpc_abort_call("XV1", call, seq, RXKADDATALEN, EPROTO); + goto protocol_error; + } + offset += sizeof(sechdr); + len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; check = buf >> 16; - check ^= sp->hdr.seq ^ sp->hdr.callNumber; + check ^= seq ^ call->call_id; check &= 0xffff; if (check != 0) { - *_abort_code = RXKADSEALEDINCON; + rxrpc_abort_call("V1C", call, seq, RXKADSEALEDINCON, EPROTO); goto protocol_error; } - /* shorten the packet to remove the padding */ - if (data_size > skb->len) - goto datalen_error; - else if (data_size < skb->len) - skb->len = data_size; + if (data_size > len) { + rxrpc_abort_call("V1L", call, seq, RXKADDATALEN, EPROTO); + goto protocol_error; + } _leave(" = 0 [dlen=%x]", data_size); return 0; -datalen_error: - *_abort_code = RXKADDATALEN; protocol_error: + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); _leave(" = -EPROTO"); return -EPROTO; @@ -391,13 +393,12 @@ nomem: /* * wholly decrypt a packet (level 2 security) */ -static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 *_abort_code) +static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int offset, unsigned int len, + rxrpc_seq_t seq) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; - struct rxrpc_skb_priv *sp; SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; @@ -408,9 +409,14 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, _enter(",{%d}", skb->len); - sp = rxrpc_skb(skb); + if (len < 8) { + rxrpc_abort_call("V2H", call, seq, RXKADSEALEDINCON, EPROTO); + goto protocol_error; + } - /* we want to decrypt the skbuff in-place */ + /* Decrypt the skbuff in-place. TODO: We really want to decrypt + * directly into the target buffer. + */ nsg = skb_cow_data(skb, 0, &trailer); if (nsg < 0) goto nomem; @@ -423,7 +429,7 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, } sg_init_table(sg, nsg); - skb_to_sgvec(skb, sg, 0, skb->len); + skb_to_sgvec(skb, sg, offset, len); /* decrypt from the session key */ token = call->conn->params.key->payload.data[0]; @@ -431,41 +437,41 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, skcipher_request_set_tfm(req, call->conn->cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, skb->len, iv.x); + skcipher_request_set_crypt(req, sg, sg, len, iv.x); crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); - /* remove the decrypted packet length */ - if (skb_copy_bits(skb, 0, &sechdr, sizeof(sechdr)) < 0) - goto datalen_error; - if (!skb_pull(skb, sizeof(sechdr))) - BUG(); + /* Extract the decrypted packet length */ + if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + rxrpc_abort_call("XV2", call, seq, RXKADDATALEN, EPROTO); + goto protocol_error; + } + offset += sizeof(sechdr); + len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; check = buf >> 16; - check ^= sp->hdr.seq ^ sp->hdr.callNumber; + check ^= seq ^ call->call_id; check &= 0xffff; if (check != 0) { - *_abort_code = RXKADSEALEDINCON; + rxrpc_abort_call("V2C", call, seq, RXKADSEALEDINCON, EPROTO); goto protocol_error; } - /* shorten the packet to remove the padding */ - if (data_size > skb->len) - goto datalen_error; - else if (data_size < skb->len) - skb->len = data_size; + if (data_size > len) { + rxrpc_abort_call("V2L", call, seq, RXKADDATALEN, EPROTO); + goto protocol_error; + } _leave(" = 0 [dlen=%x]", data_size); return 0; -datalen_error: - *_abort_code = RXKADDATALEN; protocol_error: + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); _leave(" = -EPROTO"); return -EPROTO; @@ -475,40 +481,31 @@ nomem: } /* - * verify the security on a received packet + * Verify the security on a received packet or subpacket (if part of a + * jumbo packet). */ -static int rxkad_verify_packet(struct rxrpc_call *call, - struct sk_buff *skb, - u32 *_abort_code) +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int offset, unsigned int len, + rxrpc_seq_t seq, u16 expected_cksum) { SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); - struct rxrpc_skb_priv *sp; struct rxrpc_crypt iv; struct scatterlist sg; u16 cksum; u32 x, y; - int ret; - - sp = rxrpc_skb(skb); _enter("{%d{%x}},{#%u}", - call->debug_id, key_serial(call->conn->params.key), sp->hdr.seq); + call->debug_id, key_serial(call->conn->params.key), seq); if (!call->conn->cipher) return 0; - if (sp->hdr.securityIndex != RXRPC_SECURITY_RXKAD) { - *_abort_code = RXKADINCONSISTENCY; - _leave(" = -EPROTO [not rxkad]"); - return -EPROTO; - } - /* continue encrypting from where we left off */ memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); /* validate the security checksum */ x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); - x |= sp->hdr.seq & 0x3fffffff; + x |= seq & 0x3fffffff; call->crypto_buf[0] = htonl(call->call_id); call->crypto_buf[1] = htonl(x); @@ -524,29 +521,69 @@ static int rxkad_verify_packet(struct rxrpc_call *call, if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ - if (sp->hdr.cksum != cksum) { - *_abort_code = RXKADSEALEDINCON; + if (cksum != expected_cksum) { + rxrpc_abort_call("VCK", call, seq, RXKADSEALEDINCON, EPROTO); + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); _leave(" = -EPROTO [csum failed]"); return -EPROTO; } switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: - ret = 0; - break; + return 0; case RXRPC_SECURITY_AUTH: - ret = rxkad_verify_packet_auth(call, skb, _abort_code); - break; + return rxkad_verify_packet_1(call, skb, offset, len, seq); case RXRPC_SECURITY_ENCRYPT: - ret = rxkad_verify_packet_encrypt(call, skb, _abort_code); - break; + return rxkad_verify_packet_2(call, skb, offset, len, seq); default: - ret = -ENOANO; - break; + return -ENOANO; } +} - _leave(" = %d", ret); - return ret; +/* + * Locate the data contained in a packet that was partially encrypted. + */ +static void rxkad_locate_data_1(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int *_offset, unsigned int *_len) +{ + struct rxkad_level1_hdr sechdr; + + if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) + BUG(); + *_offset += sizeof(sechdr); + *_len = ntohl(sechdr.data_size) & 0xffff; +} + +/* + * Locate the data contained in a packet that was completely encrypted. + */ +static void rxkad_locate_data_2(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int *_offset, unsigned int *_len) +{ + struct rxkad_level2_hdr sechdr; + + if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) + BUG(); + *_offset += sizeof(sechdr); + *_len = ntohl(sechdr.data_size) & 0xffff; +} + +/* + * Locate the data contained in an already decrypted packet. + */ +static void rxkad_locate_data(struct rxrpc_call *call, struct sk_buff *skb, + unsigned int *_offset, unsigned int *_len) +{ + switch (call->conn->params.security_level) { + case RXRPC_SECURITY_AUTH: + rxkad_locate_data_1(call, skb, _offset, _len); + return; + case RXRPC_SECURITY_ENCRYPT: + rxkad_locate_data_2(call, skb, _offset, _len); + return; + default: + return; + } } /* @@ -716,7 +753,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, struct rxkad_challenge challenge; struct rxkad_response resp __attribute__((aligned(8))); /* must be aligned for crypto */ - struct rxrpc_skb_priv *sp; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); u32 version, nonce, min_level, abort_code; int ret; @@ -734,8 +771,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, } abort_code = RXKADPACKETSHORT; - sp = rxrpc_skb(skb); - if (skb_copy_bits(skb, 0, &challenge, sizeof(challenge)) < 0) + if (skb_copy_bits(skb, sp->offset, &challenge, sizeof(challenge)) < 0) goto protocol_error; version = ntohl(challenge.version); @@ -981,7 +1017,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, { struct rxkad_response response __attribute__((aligned(8))); /* must be aligned for crypto */ - struct rxrpc_skb_priv *sp; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt session_key; time_t expiry; void *ticket; @@ -992,7 +1028,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); abort_code = RXKADPACKETSHORT; - if (skb_copy_bits(skb, 0, &response, sizeof(response)) < 0) + if (skb_copy_bits(skb, sp->offset, &response, sizeof(response)) < 0) goto protocol_error; if (!pskb_pull(skb, sizeof(response))) BUG(); @@ -1000,7 +1036,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, version = ntohl(response.version); ticket_len = ntohl(response.ticket_len); kvno = ntohl(response.kvno); - sp = rxrpc_skb(skb); _proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }", sp->hdr.serial, version, kvno, ticket_len); @@ -1022,7 +1057,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, return -ENOMEM; abort_code = RXKADPACKETSHORT; - if (skb_copy_bits(skb, 0, ticket, ticket_len) < 0) + if (skb_copy_bits(skb, sp->offset, ticket, ticket_len) < 0) goto protocol_error_free; ret = rxkad_decrypt_ticket(conn, ticket, ticket_len, &session_key, @@ -1147,6 +1182,7 @@ const struct rxrpc_security rxkad = { .prime_packet_security = rxkad_prime_packet_security, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, + .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 814d285..82d8134 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -130,20 +130,20 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) } /* find the service */ - read_lock_bh(&local->services_lock); - list_for_each_entry(rx, &local->services, listen_link) { + read_lock(&local->services_lock); + hlist_for_each_entry(rx, &local->services, listen_link) { if (rx->srx.srx_service == conn->params.service_id) goto found_service; } /* the service appears to have died */ - read_unlock_bh(&local->services_lock); + read_unlock(&local->services_lock); _leave(" = -ENOENT"); return -ENOENT; found_service: if (!rx->securities) { - read_unlock_bh(&local->services_lock); + read_unlock(&local->services_lock); _leave(" = -ENOKEY"); return -ENOKEY; } @@ -152,13 +152,13 @@ found_service: kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc); if (IS_ERR(kref)) { - read_unlock_bh(&local->services_lock); + read_unlock(&local->services_lock); _leave(" = %ld [search]", PTR_ERR(kref)); return PTR_ERR(kref); } key = key_ref_to_ptr(kref); - read_unlock_bh(&local->services_lock); + read_unlock(&local->services_lock); conn->server_key = key; conn->security = sec; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 7376794..1f8040d 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -15,7 +15,6 @@ #include <linux/gfp.h> #include <linux/skbuff.h> #include <linux/export.h> -#include <linux/circ_buf.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" @@ -38,24 +37,28 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%d},%ld", - CIRC_SPACE(call->acks_head, ACCESS_ONCE(call->acks_tail), - call->acks_winsz), - *timeo); + _enter(",{%u,%u,%u}", + call->tx_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); for (;;) { set_current_state(TASK_INTERRUPTIBLE); ret = 0; - if (CIRC_SPACE(call->acks_head, ACCESS_ONCE(call->acks_tail), - call->acks_winsz) > 0) + if (call->tx_top - call->tx_hard_ack < + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) break; + if (call->state >= RXRPC_CALL_COMPLETE) { + ret = -call->error; + break; + } if (signal_pending(current)) { ret = sock_intr_errno(*timeo); break; } + trace_rxrpc_transmit(call, rxrpc_transmit_wait); release_sock(&rx->sk); *timeo = schedule_timeout(*timeo); lock_sock(&rx->sk); @@ -68,36 +71,55 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, } /* - * attempt to schedule an instant Tx resend + * Schedule an instant Tx resend. */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call) +static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) { - read_lock_bh(&call->state_lock); - if (try_to_del_timer_sync(&call->resend_timer) >= 0) { - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - if (call->state < RXRPC_CALL_COMPLETE && - !test_and_set_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events)) + spin_lock_bh(&call->lock); + + if (call->state < RXRPC_CALL_COMPLETE) { + call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS; + if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } - read_unlock_bh(&call->state_lock); + + spin_unlock_bh(&call->lock); } /* - * queue a packet for transmission, set the resend timer and attempt - * to send the packet immediately + * Queue a DATA packet for transmission, set the resend timeout and send the + * packet immediately */ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, bool last) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - int ret; + rxrpc_seq_t seq = sp->hdr.seq; + int ret, ix; + u8 annotation = RXRPC_TX_ANNO_UNACK; - _net("queue skb %p [%d]", skb, call->acks_head); + _net("queue skb %p [%d]", skb, seq); - ASSERT(call->acks_window != NULL); - call->acks_window[call->acks_head] = (unsigned long) skb; + ASSERTCMP(seq, ==, call->tx_top + 1); + + if (last) + annotation |= RXRPC_TX_ANNO_LAST; + + /* We have to set the timestamp before queueing as the retransmit + * algorithm can see the packet as soon as we queue it. + */ + skb->tstamp = ktime_get_real(); + + ix = seq & RXRPC_RXTX_BUFF_MASK; + rxrpc_get_skb(skb, rxrpc_skb_tx_got); + call->rxtx_annotations[ix] = annotation; smp_wmb(); - call->acks_head = (call->acks_head + 1) & (call->acks_winsz - 1); + call->rxtx_buffer[ix] = skb; + call->tx_top = seq; + if (last) + trace_rxrpc_transmit(call, rxrpc_transmit_queue_last); + else + trace_rxrpc_transmit(call, rxrpc_transmit_queue); if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); @@ -119,60 +141,26 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, write_unlock_bh(&call->state_lock); } - _proto("Tx DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq); - - sp->need_resend = false; - sp->resend_at = jiffies + rxrpc_resend_timeout; - if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) { - _debug("run timer"); - call->resend_timer.expires = sp->resend_at; - add_timer(&call->resend_timer); - } - - /* attempt to cancel the rx-ACK timer, deferring reply transmission if - * we're ACK'ing the request phase of an incoming call */ - ret = -EAGAIN; - if (try_to_del_timer_sync(&call->ack_timer) >= 0) { - /* the packet may be freed by rxrpc_process_call() before this - * returns */ - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - ret = rxrpc_send_data_packet(call->conn, skb); - _net("sent skb %p", skb); - } else { - _debug("failed to delete ACK timer"); - } + if (seq == 1 && rxrpc_is_client_call(call)) + rxrpc_expose_client_call(call); + ret = rxrpc_send_data_packet(call, skb); if (ret < 0) { _debug("need instant resend %d", ret); - sp->need_resend = true; - rxrpc_instant_resend(call); - } + rxrpc_instant_resend(call, ix); + } else { + unsigned long resend_at; - _leave(""); -} + resend_at = jiffies + msecs_to_jiffies(rxrpc_resend_timeout); -/* - * Convert a host-endian header into a network-endian header. - */ -static void rxrpc_insert_header(struct sk_buff *skb) -{ - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + if (time_before(resend_at, call->resend_at)) { + call->resend_at = resend_at; + rxrpc_set_timer(call, rxrpc_timer_set_for_send); + } + } - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = htonl(sp->hdr.serial); - whdr.type = sp->hdr.type; - whdr.flags = sp->hdr.flags; - whdr.userStatus = sp->hdr.userStatus; - whdr.securityIndex = sp->hdr.securityIndex; - whdr._rsvd = htons(sp->hdr._rsvd); - whdr.serviceId = htons(sp->hdr.serviceId); - - memcpy(skb->head, &whdr, sizeof(whdr)); + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + _leave(""); } /* @@ -203,18 +191,22 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb); + rxrpc_see_skb(skb, rxrpc_skb_tx_seen); copied = 0; do { + /* Check to see if there's a ping ACK to reply to. */ + if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + if (!skb) { size_t size, chunk, max, space; _debug("alloc"); - if (CIRC_SPACE(call->acks_head, - ACCESS_ONCE(call->acks_tail), - call->acks_winsz) <= 0) { + if (call->tx_top - call->tx_hard_ack >= + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) { ret = -EAGAIN; if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; @@ -224,7 +216,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, goto maybe_error; } - max = call->conn->params.peer->maxdata; + max = RXRPC_JUMBO_DATALEN; max -= call->conn->security_size; max &= ~(call->conn->size_align - 1UL); @@ -235,7 +227,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, space = chunk + call->conn->size_align; space &= ~(call->conn->size_align - 1UL); - size = space + call->conn->header_size; + size = space + call->conn->security_size; _debug("SIZE: %zu/%zu/%zu", chunk, space, size); @@ -245,15 +237,15 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (!skb) goto maybe_error; - rxrpc_new_skb(skb); + rxrpc_new_skb(skb, rxrpc_skb_tx_new); _debug("ALLOC SEND %p", skb); ASSERTCMP(skb->mark, ==, 0); - _debug("HS: %u", call->conn->header_size); - skb_reserve(skb, call->conn->header_size); - skb->len += call->conn->header_size; + _debug("HS: %u", call->conn->security_size); + skb_reserve(skb, call->conn->security_size); + skb->len += call->conn->security_size; sp = rxrpc_skb(skb); sp->remain = chunk; @@ -313,36 +305,23 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, memset(skb_put(skb, pad), 0, pad); } - seq = atomic_inc_return(&call->sequence); + seq = call->tx_top + 1; - sp->hdr.epoch = conn->proto.epoch; - sp->hdr.cid = call->cid; - sp->hdr.callNumber = call->call_id; sp->hdr.seq = seq; - sp->hdr.serial = atomic_inc_return(&conn->serial); - sp->hdr.type = RXRPC_PACKET_TYPE_DATA; - sp->hdr.userStatus = 0; - sp->hdr.securityIndex = conn->security_ix; sp->hdr._rsvd = 0; - sp->hdr.serviceId = call->service_id; + sp->hdr.flags = conn->out_clientflag; - sp->hdr.flags = conn->out_clientflag; if (msg_data_left(msg) == 0 && !more) sp->hdr.flags |= RXRPC_LAST_PACKET; - else if (CIRC_SPACE(call->acks_head, - ACCESS_ONCE(call->acks_tail), - call->acks_winsz) > 1) + else if (call->tx_top - call->tx_hard_ack < + call->tx_winsize) sp->hdr.flags |= RXRPC_MORE_PACKETS; - if (more && seq & 1) - sp->hdr.flags |= RXRPC_REQUEST_ACK; ret = conn->security->secure_packet( - call, skb, skb->mark, - skb->head + sizeof(struct rxrpc_wire_header)); + call, skb, skb->mark, skb->head); if (ret < 0) goto out; - rxrpc_insert_header(skb); rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more); skb = NULL; } @@ -356,9 +335,9 @@ out: return ret; call_terminated: - rxrpc_free_skb(skb); + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); _leave(" = %d", -call->error); - return ret; + return -call->error; maybe_error: if (copied) @@ -452,28 +431,6 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, } /* - * abort a call, sending an ABORT packet to the peer - */ -static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) -{ - if (call->state >= RXRPC_CALL_COMPLETE) - return; - - write_lock_bh(&call->state_lock); - - if (__rxrpc_abort_call(call, abort_code, ECONNABORTED)) { - del_timer_sync(&call->resend_timer); - del_timer_sync(&call->ack_timer); - clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); - clear_bit(RXRPC_CALL_EV_ACK, &call->events); - clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); - rxrpc_queue_call(call); - } - - write_unlock_bh(&call->state_lock); -} - -/* * Create a new client call for sendmsg(). */ static struct rxrpc_call * @@ -534,7 +491,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) call = rxrpc_accept_call(rx, user_call_ID, NULL); if (IS_ERR(call)) return PTR_ERR(call); - rxrpc_put_call(call); + rxrpc_put_call(call, rxrpc_call_put); return 0; } @@ -548,7 +505,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); } - rxrpc_see_call(call); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); @@ -556,8 +512,10 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) /* it's too late for this call */ ret = -ESHUTDOWN; } else if (cmd == RXRPC_CMD_SEND_ABORT) { - rxrpc_send_abort(call, abort_code); ret = 0; + if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED)) + ret = rxrpc_send_call_packet(call, + RXRPC_PACKET_TYPE_ABORT); } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && @@ -573,7 +531,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = rxrpc_send_data(rx, call, msg, len); } - rxrpc_put_call(call); + rxrpc_put_call(call, rxrpc_call_put); _leave(" = %d", ret); return ret; } @@ -626,20 +584,20 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data); * @sock: The socket the call is on * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet + * @error: Local error value + * @why: 3-char string indicating why. * * Allow a kernel service to abort a call, if it's still in an abortable state. */ void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, - u32 abort_code) + u32 abort_code, int error, const char *why) { - _enter("{%d},%d", call->debug_id, abort_code); + _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); lock_sock(sock->sk); - _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, call->state, call->conn); - - rxrpc_send_abort(call, abort_code); + if (rxrpc_abort_call(why, call, 0, abort_code, error)) + rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); release_sock(sock->sk); _leave(""); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 9752f8b..5154cbf 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -18,198 +18,77 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -/* - * set up for the ACK at the end of the receive phase when we discard the final - * receive phase data packet - * - called with softirqs disabled - */ -static void rxrpc_request_final_ACK(struct rxrpc_call *call) -{ - /* the call may be aborted before we have a chance to ACK it */ - write_lock(&call->state_lock); - - switch (call->state) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - call->state = RXRPC_CALL_CLIENT_FINAL_ACK; - _debug("request final ACK"); - - /* get an extra ref on the call for the final-ACK generator to - * release */ - rxrpc_get_call(call); - set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); - if (try_to_del_timer_sync(&call->ack_timer) >= 0) - rxrpc_queue_call(call); - break; - - case RXRPC_CALL_SERVER_RECV_REQUEST: - call->state = RXRPC_CALL_SERVER_ACK_REQUEST; - default: - break; - } - - write_unlock(&call->state_lock); -} - -/* - * drop the bottom ACK off of the call ACK window and advance the window - */ -static void rxrpc_hard_ACK_data(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - int loop; - u32 seq; - - spin_lock_bh(&call->lock); - - _debug("hard ACK #%u", sp->hdr.seq); - - for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) { - call->ackr_window[loop] >>= 1; - call->ackr_window[loop] |= - call->ackr_window[loop + 1] << (BITS_PER_LONG - 1); - } - - seq = sp->hdr.seq; - ASSERTCMP(seq, ==, call->rx_data_eaten + 1); - call->rx_data_eaten = seq; - - if (call->ackr_win_top < UINT_MAX) - call->ackr_win_top++; - - ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE, - call->rx_data_post, >=, call->rx_data_recv); - ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE, - call->rx_data_recv, >=, call->rx_data_eaten); - - if (sp->hdr.flags & RXRPC_LAST_PACKET) { - rxrpc_request_final_ACK(call); - } else if (atomic_dec_and_test(&call->ackr_not_idle) && - test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) { - /* We previously soft-ACK'd some received packets that have now - * been consumed, so send a hard-ACK if no more packets are - * immediately forthcoming to allow the transmitter to free up - * its Tx bufferage. - */ - _debug("send Rx idle ACK"); - __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, - skb->priority, sp->hdr.serial, false); - } - - spin_unlock_bh(&call->lock); -} - -/** - * rxrpc_kernel_data_consumed - Record consumption of data message - * @call: The call to which the message pertains. - * @skb: Message holding data - * - * Record the consumption of a data message and generate an ACK if appropriate. - * The call state is shifted if this was the final packet. The caller must be - * in process context with no spinlocks held. - * - * TODO: Actually generate the ACK here rather than punting this to the - * workqueue. - */ -void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - _enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq); - - ASSERTCMP(sp->call, ==, call); - ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA); - - /* TODO: Fix the sequence number tracking */ - ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); - ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); - ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); - - call->rx_data_recv = sp->hdr.seq; - rxrpc_hard_ACK_data(call, skb); -} +#define select_skb_count(op) (op >= rxrpc_skb_tx_cleaned ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) /* - * Destroy a packet that has an RxRPC control buffer + * Note the allocation or reception of a socket buffer. */ -void rxrpc_packet_destructor(struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_call *call = sp->call; - - _enter("%p{%p}", skb, call); - - if (call) { - rxrpc_put_call_for_skb(call, skb); - sp->call = NULL; - } - - if (skb->sk) - sock_rfree(skb); - _leave(""); -} - -/** - * rxrpc_kernel_free_skb - Free an RxRPC socket buffer - * @skb: The socket buffer to be freed - * - * Let RxRPC free its own socket buffer, permitting it to maintain debug - * accounting. - */ -void rxrpc_kernel_free_skb(struct sk_buff *skb) -{ - rxrpc_free_skb(skb); -} -EXPORT_SYMBOL(rxrpc_kernel_free_skb); - -/* - * Note the existence of a new-to-us socket buffer (allocated or dequeued). - */ -void rxrpc_new_skb(struct sk_buff *skb) +void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(&rxrpc_n_skbs); - trace_rxrpc_skb(skb, 0, atomic_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ -void rxrpc_see_skb(struct sk_buff *skb) +void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); if (skb) { - int n = atomic_read(&rxrpc_n_skbs); - trace_rxrpc_skb(skb, 1, atomic_read(&skb->users), n, here); + int n = atomic_read(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); } } /* * Note the addition of a ref on a socket buffer. */ -void rxrpc_get_skb(struct sk_buff *skb) +void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(&rxrpc_n_skbs); - trace_rxrpc_skb(skb, 2, atomic_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); skb_get(skb); } /* * Note the destruction of a socket buffer. */ -void rxrpc_free_skb(struct sk_buff *skb) +void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); if (skb) { int n; CHECK_SLAB_OKAY(&skb->users); - n = atomic_dec_return(&rxrpc_n_skbs); - trace_rxrpc_skb(skb, 3, atomic_read(&skb->users), n, here); + n = atomic_dec_return(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); kfree_skb(skb); } } /* + * Note the injected loss of a socket buffer. + */ +void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +{ + const void *here = __builtin_return_address(0); + if (skb) { + int n; + CHECK_SLAB_OKAY(&skb->users); + if (op == rxrpc_skb_tx_lost) { + n = atomic_read(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + } else { + n = atomic_dec_return(select_skb_count(op)); + trace_rxrpc_skb(skb, op, atomic_read(&skb->users), n, here); + kfree_skb(skb); + } + } +} + +/* * Clear a queue of socket buffers. */ void rxrpc_purge_queue(struct sk_buff_head *list) @@ -217,8 +96,9 @@ void rxrpc_purge_queue(struct sk_buff_head *list) const void *here = __builtin_return_address(0); struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { - int n = atomic_dec_return(&rxrpc_n_skbs); - trace_rxrpc_skb(skb, 4, atomic_read(&skb->users), n, here); + int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged)); + trace_rxrpc_skb(skb, rxrpc_skb_rx_purged, + atomic_read(&skb->users), n, here); kfree_skb(skb); } } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index dc380af..13d1df03 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -20,7 +20,7 @@ static const unsigned int one = 1; static const unsigned int four = 4; static const unsigned int thirtytwo = 32; static const unsigned int n_65535 = 65535; -static const unsigned int n_max_acks = RXRPC_MAXACKS; +static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; /* * RxRPC operating parameters. @@ -59,7 +59,7 @@ static struct ctl_table rxrpc_sysctl_table[] = { .data = &rxrpc_resend_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, + .proc_handler = proc_dointvec, .extra1 = (void *)&one, }, { @@ -88,14 +88,6 @@ static struct ctl_table rxrpc_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, .extra1 = (void *)&one, }, - { - .procname = "dead_call_expiry", - .data = &rxrpc_dead_call_expiry, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - .extra1 = (void *)&one, - }, /* Non-time values */ { diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c index b88914d..ff7af71 100644 --- a/net/rxrpc/utils.c +++ b/net/rxrpc/utils.c @@ -30,6 +30,7 @@ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb) srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; return 0; +#ifdef CONFIG_AF_RXRPC_IPV6 case ETH_P_IPV6: srx->transport_type = SOCK_DGRAM; srx->transport_len = sizeof(srx->transport.sin6); @@ -37,6 +38,7 @@ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb) srx->transport.sin6.sin6_port = udp_hdr(skb)->source; srx->transport.sin6.sin6_addr = ipv6_hdr(skb)->saddr; return 0; +#endif default: pr_warn_ratelimited("AF_RXRPC: Unknown eth protocol %u\n", diff --git a/net/sched/Kconfig b/net/sched/Kconfig index ccf931b..87956a7 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -749,6 +749,17 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_SKBMOD + tristate "skb data modification action" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow modification of skb data + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_skbmod. + config NET_ACT_IFE tristate "Inter-FE action based on IETF ForCES InterFE LFB" depends on NET_CLS_ACT @@ -761,6 +772,17 @@ config NET_ACT_IFE To compile this code as a module, choose M here: the module will be called act_ife. +config NET_ACT_TUNNEL_KEY + tristate "IP tunnel metadata manipulation" + depends on NET_CLS_ACT + ---help--- + Say Y here to set/release ip tunnel metadata. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_tunnel_key. + config NET_IFE_SKBMARK tristate "Support to encoding decoding skb mark on IFE action" depends on NET_ACT_IFE @@ -771,6 +793,11 @@ config NET_IFE_SKBPRIO depends on NET_ACT_IFE ---help--- +config NET_IFE_SKBTCINDEX + tristate "Support to encoding decoding skb tcindex on IFE action" + depends on NET_ACT_IFE + ---help--- + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index ae088a5..4bdda36 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -19,9 +19,12 @@ obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o +obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o +obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d09d068..c910217 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -592,9 +592,19 @@ err_out: return ERR_PTR(err); } -int tcf_action_init(struct net *net, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, - int bind, struct list_head *actions) +static void cleanup_a(struct list_head *actions, int ovr) +{ + struct tc_action *a; + + if (!ovr) + return; + + list_for_each_entry(a, actions, list) + a->tcfa_refcnt--; +} + +int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind, struct list_head *actions) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; @@ -612,8 +622,15 @@ int tcf_action_init(struct net *net, struct nlattr *nla, goto err; } act->order = i; + if (ovr) + act->tcfa_refcnt++; list_add_tail(&act->list, actions); } + + /* Remove the temp refcnt which was necessary to protect against + * destroying an existing action which was being replaced + */ + cleanup_a(actions, ovr); return 0; err: @@ -883,6 +900,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, goto err; } act->order = i; + if (event == RTM_GETACTION) + act->tcfa_refcnt++; list_add_tail(&act->list, &actions); } @@ -923,9 +942,8 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, return err; } -static int -tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 portid, int ovr) +static int tcf_action_add(struct net *net, struct nlattr *nla, + struct nlmsghdr *n, u32 portid, int ovr) { int ret = 0; LIST_HEAD(actions); @@ -988,8 +1006,7 @@ replay: return ret; } -static struct nlattr * -find_dump_kind(const struct nlmsghdr *n) +static struct nlattr *find_dump_kind(const struct nlmsghdr *n) { struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; @@ -1016,8 +1033,7 @@ find_dump_kind(const struct nlmsghdr *n) return kind; } -static int -tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) +static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index bfa8707..1d39600 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -39,13 +39,10 @@ static struct tc_action_ops act_bpf_ops; static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { + bool at_ingress = skb_at_tc_ingress(skb); struct tcf_bpf *prog = to_bpf(act); struct bpf_prog *filter; int action, filter_res; - bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS; - - if (unlikely(!skb_mac_header_was_set(skb))) - return TC_ACT_UNSPEC; tcf_lastuse_update(&prog->tcf_tm); bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b5dbf63..e0defce 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -116,8 +116,8 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, return (void *)(skb_network_header(skb) + ihl); } -static int tcf_csum_ipv4_icmp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl) +static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl) { struct icmphdr *icmph; @@ -152,8 +152,8 @@ static int tcf_csum_ipv4_igmp(struct sk_buff *skb, return 1; } -static int tcf_csum_ipv6_icmp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl) +static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl) { struct icmp6hdr *icmp6h; const struct ipv6hdr *ip6h; @@ -174,8 +174,8 @@ static int tcf_csum_ipv6_icmp(struct sk_buff *skb, return 1; } -static int tcf_csum_ipv4_tcp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl) +static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl) { struct tcphdr *tcph; const struct iphdr *iph; @@ -195,8 +195,8 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb, return 1; } -static int tcf_csum_ipv6_tcp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl) +static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl) { struct tcphdr *tcph; const struct ipv6hdr *ip6h; @@ -217,8 +217,8 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb, return 1; } -static int tcf_csum_ipv4_udp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl, int udplite) +static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl, int udplite) { struct udphdr *udph; const struct iphdr *iph; @@ -270,8 +270,8 @@ ignore_obscure_skb: return 1; } -static int tcf_csum_ipv6_udp(struct sk_buff *skb, - unsigned int ihl, unsigned int ipl, int udplite) +static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl, int udplite) { struct udphdr *udph; const struct ipv6hdr *ip6h; @@ -380,8 +380,8 @@ fail: return 0; } -static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, - unsigned int ixhl, unsigned int *pl) +static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl, + unsigned int *pl) { int off, len, optlen; unsigned char *xh = (void *)ip6xh; @@ -494,8 +494,8 @@ fail: return 0; } -static int tcf_csum(struct sk_buff *skb, - const struct tc_action *a, struct tcf_result *res) +static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); int action; @@ -531,8 +531,8 @@ drop: return TC_ACT_SHOT; } -static int tcf_csum_dump(struct sk_buff *skb, - struct tc_action *a, int bind, int ref) +static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, + int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_csum *p = to_tcf_csum(a); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index e24a409..e0aa30f 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -156,7 +156,8 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, int action = READ_ONCE(gact->tcf_action); struct tcf_t *tm = &gact->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes, packets); + _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes, + packets); if (action == TC_ACT_SHOT) this_cpu_ptr(gact->common.cpu_qstats)->drops += packets; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index e87cd81..ccf7b4b 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -63,6 +63,23 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) } EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); +int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi) +{ + u16 edata = 0; + + if (mi->metaval) + edata = *(u16 *)mi->metaval; + else if (metaval) + edata = metaval; + + if (!edata) /* will not encode */ + return 0; + + edata = htons(edata); + return ife_tlv_meta_encode(skbdata, mi->metaid, 2, &edata); +} +EXPORT_SYMBOL_GPL(ife_encode_meta_u16); + int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi) { if (mi->metaval) @@ -81,6 +98,15 @@ int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi) } EXPORT_SYMBOL_GPL(ife_check_meta_u32); +int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi) +{ + if (metaval || mi->metaval) + return 8; /* T+L+(V) == 2+2+(2+2bytepad) */ + + return 0; +} +EXPORT_SYMBOL_GPL(ife_check_meta_u16); + int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi) { u32 edata = metaval; diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c new file mode 100644 index 0000000..3b35774 --- /dev/null +++ b/net/sched/act_meta_skbtcindex.c @@ -0,0 +1,79 @@ +/* + * net/sched/act_meta_tc_index.c IFE skb->tc_index metadata module + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * copyright Jamal Hadi Salim (2016) + * +*/ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/module.h> +#include <linux/init.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <uapi/linux/tc_act/tc_ife.h> +#include <net/tc_act/tc_ife.h> +#include <linux/rtnetlink.h> + +static int skbtcindex_encode(struct sk_buff *skb, void *skbdata, + struct tcf_meta_info *e) +{ + u32 ifetc_index = skb->tc_index; + + return ife_encode_meta_u16(ifetc_index, skbdata, e); +} + +static int skbtcindex_decode(struct sk_buff *skb, void *data, u16 len) +{ + u16 ifetc_index = *(u16 *)data; + + skb->tc_index = ntohs(ifetc_index); + return 0; +} + +static int skbtcindex_check(struct sk_buff *skb, struct tcf_meta_info *e) +{ + return ife_check_meta_u16(skb->tc_index, e); +} + +static struct tcf_meta_ops ife_skbtcindex_ops = { + .metaid = IFE_META_TCINDEX, + .metatype = NLA_U16, + .name = "tc_index", + .synopsis = "skb tc_index 16 bit metadata", + .check_presence = skbtcindex_check, + .encode = skbtcindex_encode, + .decode = skbtcindex_decode, + .get = ife_get_meta_u16, + .alloc = ife_alloc_meta_u16, + .release = ife_release_meta_gen, + .validate = ife_validate_meta_u16, + .owner = THIS_MODULE, +}; + +static int __init ifetc_index_init_module(void) +{ + return register_ife_op(&ife_skbtcindex_ops); +} + +static void __exit ifetc_index_cleanup_module(void) +{ + unregister_ife_op(&ife_skbtcindex_ops); +} + +module_init(ifetc_index_init_module); +module_exit(ifetc_index_cleanup_module); + +MODULE_AUTHOR("Jamal Hadi Salim(2016)"); +MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6038c85..667dc38 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -204,7 +204,15 @@ out: return retval; } -static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, + u64 lastuse) +{ + tcf_lastuse_update(&a->tcfa_tm); + _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); +} + +static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, + int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); @@ -280,6 +288,7 @@ static struct tc_action_ops act_mirred_ops = { .type = TCA_ACT_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred, + .stats_update = tcf_stats_update, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8a3be1d..d1bd248 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -249,6 +249,8 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; + if (police->tcfp_result == TC_ACT_SHOT) + police->tcf_qstats.drops++; spin_unlock(&police->tcf_lock); return police->tcfp_result; } @@ -261,8 +263,8 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, return police->tcf_action; } -static int -tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); @@ -347,14 +349,12 @@ static struct pernet_operations police_net_ops = { .size = sizeof(struct tc_action_net), }; -static int __init -police_init_module(void) +static int __init police_init_module(void) { return tcf_register_action(&act_police_ops, &police_net_ops); } -static void __exit -police_cleanup_module(void) +static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops, &police_net_ops); } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c new file mode 100644 index 0000000..e7d9638 --- /dev/null +++ b/net/sched/act_skbmod.c @@ -0,0 +1,301 @@ +/* + * net/sched/act_skbmod.c skb data modifier + * + * Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. +*/ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> + +#include <linux/tc_act/tc_skbmod.h> +#include <net/tc_act/tc_skbmod.h> + +#define SKBMOD_TAB_MASK 15 + +static int skbmod_net_id; +static struct tc_action_ops act_skbmod_ops; + +#define MAX_EDIT_LEN ETH_HLEN +static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_skbmod *d = to_skbmod(a); + int action; + struct tcf_skbmod_params *p; + u64 flags; + int err; + + tcf_lastuse_update(&d->tcf_tm); + bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + + /* XXX: if you are going to edit more fields beyond ethernet header + * (example when you add IP header replacement or vlan swap) + * then MAX_EDIT_LEN needs to change appropriately + */ + err = skb_ensure_writable(skb, MAX_EDIT_LEN); + if (unlikely(err)) { /* best policy is to drop on the floor */ + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; + } + + rcu_read_lock(); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) { + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + rcu_read_unlock(); + return action; + } + + p = rcu_dereference(d->skbmod_p); + flags = p->flags; + if (flags & SKBMOD_F_DMAC) + ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); + if (flags & SKBMOD_F_SMAC) + ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); + if (flags & SKBMOD_F_ETYPE) + eth_hdr(skb)->h_proto = p->eth_type; + rcu_read_unlock(); + + if (flags & SKBMOD_F_SWAPMAC) { + u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ + /*XXX: I am sure we can come up with more efficient swapping*/ + ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest); + ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source); + ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); + } + + return action; +} + +static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { + [TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) }, + [TCA_SKBMOD_DMAC] = { .len = ETH_ALEN }, + [TCA_SKBMOD_SMAC] = { .len = ETH_ALEN }, + [TCA_SKBMOD_ETYPE] = { .type = NLA_U16 }, +}; + +static int tcf_skbmod_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + struct nlattr *tb[TCA_SKBMOD_MAX + 1]; + struct tcf_skbmod_params *p, *p_old; + struct tc_skbmod *parm; + struct tcf_skbmod *d; + bool exists = false; + u8 *daddr = NULL; + u8 *saddr = NULL; + u16 eth_type = 0; + u32 lflags = 0; + int ret = 0, err; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy); + if (err < 0) + return err; + + if (!tb[TCA_SKBMOD_PARMS]) + return -EINVAL; + + if (tb[TCA_SKBMOD_DMAC]) { + daddr = nla_data(tb[TCA_SKBMOD_DMAC]); + lflags |= SKBMOD_F_DMAC; + } + + if (tb[TCA_SKBMOD_SMAC]) { + saddr = nla_data(tb[TCA_SKBMOD_SMAC]); + lflags |= SKBMOD_F_SMAC; + } + + if (tb[TCA_SKBMOD_ETYPE]) { + eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]); + lflags |= SKBMOD_F_ETYPE; + } + + parm = nla_data(tb[TCA_SKBMOD_PARMS]); + if (parm->flags & SKBMOD_F_SWAPMAC) + lflags = SKBMOD_F_SWAPMAC; + + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + if (!lflags) + return -EINVAL; + + if (!exists) { + ret = tcf_hash_create(tn, parm->index, est, a, + &act_skbmod_ops, bind, true); + if (ret) + return ret; + + ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; + } + + d = to_skbmod(*a); + + ASSERT_RTNL(); + p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); + if (unlikely(!p)) { + if (ovr) + tcf_hash_release(*a, bind); + return -ENOMEM; + } + + p->flags = lflags; + d->tcf_action = parm->action; + + p_old = rtnl_dereference(d->skbmod_p); + + if (ovr) + spin_lock_bh(&d->tcf_lock); + + if (lflags & SKBMOD_F_DMAC) + ether_addr_copy(p->eth_dst, daddr); + if (lflags & SKBMOD_F_SMAC) + ether_addr_copy(p->eth_src, saddr); + if (lflags & SKBMOD_F_ETYPE) + p->eth_type = htons(eth_type); + + rcu_assign_pointer(d->skbmod_p, p); + if (ovr) + spin_unlock_bh(&d->tcf_lock); + + if (p_old) + kfree_rcu(p_old, rcu); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, *a); + return ret; +} + +static void tcf_skbmod_cleanup(struct tc_action *a, int bind) +{ + struct tcf_skbmod *d = to_skbmod(a); + struct tcf_skbmod_params *p; + + p = rcu_dereference_protected(d->skbmod_p, 1); + kfree_rcu(p, rcu); +} + +static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + struct tcf_skbmod *d = to_skbmod(a); + unsigned char *b = skb_tail_pointer(skb); + struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p); + struct tc_skbmod opt = { + .index = d->tcf_index, + .refcnt = d->tcf_refcnt - ref, + .bindcnt = d->tcf_bindcnt - bind, + .action = d->tcf_action, + }; + struct tcf_t t; + + opt.flags = p->flags; + if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_DMAC) && + nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_SMAC) && + nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src)) + goto nla_put_failure; + if ((p->flags & SKBMOD_F_ETYPE) && + nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type))) + goto nla_put_failure; + + tcf_tm_dump(&t, &d->tcf_tm); + if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD)) + goto nla_put_failure; + + return skb->len; +nla_put_failure: + rcu_read_unlock(); + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops); +} + +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_skbmod_ops = { + .kind = "skbmod", + .type = TCA_ACT_SKBMOD, + .owner = THIS_MODULE, + .act = tcf_skbmod_run, + .dump = tcf_skbmod_dump, + .init = tcf_skbmod_init, + .cleanup = tcf_skbmod_cleanup, + .walk = tcf_skbmod_walker, + .lookup = tcf_skbmod_search, + .size = sizeof(struct tcf_skbmod), +}; + +static __net_init int skbmod_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tc_action_net_init(tn, &act_skbmod_ops, SKBMOD_TAB_MASK); +} + +static void __net_exit skbmod_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations skbmod_net_ops = { + .init = skbmod_init_net, + .exit = skbmod_exit_net, + .id = &skbmod_net_id, + .size = sizeof(struct tc_action_net), +}; + +MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>"); +MODULE_DESCRIPTION("SKB data mod-ing"); +MODULE_LICENSE("GPL"); + +static int __init skbmod_init_module(void) +{ + return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops); +} + +static void __exit skbmod_cleanup_module(void) +{ + tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops); +} + +module_init(skbmod_init_module); +module_exit(skbmod_cleanup_module); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c new file mode 100644 index 0000000..af47bdf --- /dev/null +++ b/net/sched/act_tunnel_key.c @@ -0,0 +1,342 @@ +/* + * Copyright (c) 2016, Amir Vadai <amir@vadai.me> + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/dst.h> +#include <net/dst_metadata.h> + +#include <linux/tc_act/tc_tunnel_key.h> +#include <net/tc_act/tc_tunnel_key.h> + +#define TUNNEL_KEY_TAB_MASK 15 + +static int tunnel_key_net_id; +static struct tc_action_ops act_tunnel_key_ops; + +static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + int action; + + rcu_read_lock(); + + params = rcu_dereference(t->params); + + tcf_lastuse_update(&t->tcf_tm); + bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); + action = params->action; + + switch (params->tcft_action) { + case TCA_TUNNEL_KEY_ACT_RELEASE: + skb_dst_drop(skb); + break; + case TCA_TUNNEL_KEY_ACT_SET: + skb_dst_drop(skb); + skb_dst_set(skb, dst_clone(¶ms->tcft_enc_metadata->dst)); + break; + default: + WARN_ONCE(1, "Bad tunnel_key action %d.\n", + params->tcft_action); + break; + } + + rcu_read_unlock(); + + return action; +} + +static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { + [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, + [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, +}; + +static int tunnel_key_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; + struct tcf_tunnel_key_params *params_old; + struct tcf_tunnel_key_params *params_new; + struct metadata_dst *metadata = NULL; + struct tc_tunnel_key *parm; + struct tcf_tunnel_key *t; + bool exists = false; + __be64 key_id; + int ret = 0; + int err; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + switch (parm->t_action) { + case TCA_TUNNEL_KEY_ACT_RELEASE: + break; + case TCA_TUNNEL_KEY_ACT_SET: + if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { + ret = -EINVAL; + goto err_out; + } + + key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && + tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { + __be32 saddr; + __be32 daddr; + + saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); + daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); + + metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, + TUNNEL_KEY, key_id, 0); + } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && + tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { + struct in6_addr saddr; + struct in6_addr daddr; + + saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); + daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); + + metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0, + TUNNEL_KEY, key_id, 0); + } + + if (!metadata) { + ret = -EINVAL; + goto err_out; + } + + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; + break; + default: + goto err_out; + } + + if (!exists) { + ret = tcf_hash_create(tn, parm->index, est, a, + &act_tunnel_key_ops, bind, true); + if (ret) + return ret; + + ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; + } + + t = to_tunnel_key(*a); + + ASSERT_RTNL(); + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + if (ret == ACT_P_CREATED) + tcf_hash_release(*a, bind); + return -ENOMEM; + } + + params_old = rtnl_dereference(t->params); + + params_new->action = parm->action; + params_new->tcft_action = parm->t_action; + params_new->tcft_enc_metadata = metadata; + + rcu_assign_pointer(t->params, params_new); + + if (params_old) + kfree_rcu(params_old, rcu); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, *a); + + return ret; + +err_out: + if (exists) + tcf_hash_release(*a, bind); + return ret; +} + +static void tunnel_key_release(struct tc_action *a, int bind) +{ + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + + params = rcu_dereference_protected(t->params, 1); + + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(¶ms->tcft_enc_metadata->dst); + + kfree_rcu(params, rcu); +} + +static int tunnel_key_dump_addresses(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + unsigned short family = ip_tunnel_info_af(info); + + if (family == AF_INET) { + __be32 saddr = info->key.u.ipv4.src; + __be32 daddr = info->key.u.ipv4.dst; + + if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) && + !nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr)) + return 0; + } + + if (family == AF_INET6) { + const struct in6_addr *saddr6 = &info->key.u.ipv6.src; + const struct in6_addr *daddr6 = &info->key.u.ipv6.dst; + + if (!nla_put_in6_addr(skb, + TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) && + !nla_put_in6_addr(skb, + TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6)) + return 0; + } + + return -EINVAL; +} + +static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params; + struct tc_tunnel_key opt = { + .index = t->tcf_index, + .refcnt = t->tcf_refcnt - ref, + .bindcnt = t->tcf_bindcnt - bind, + }; + struct tcf_t tm; + + params = rtnl_dereference(t->params); + + opt.t_action = params->tcft_action; + opt.action = params->action; + + if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { + struct ip_tunnel_key *key = + ¶ms->tcft_enc_metadata->u.tun_info.key; + __be32 key_id = tunnel_id_to_key32(key->tun_id); + + if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || + tunnel_key_dump_addresses(skb, + ¶ms->tcft_enc_metadata->u.tun_info)) + goto nla_put_failure; + } + + tcf_tm_dump(&tm, &t->tcf_tm); + if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), + &tm, TCA_TUNNEL_KEY_PAD)) + goto nla_put_failure; + + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int tunnel_key_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops); +} + +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_tunnel_key_ops = { + .kind = "tunnel_key", + .type = TCA_ACT_TUNNEL_KEY, + .owner = THIS_MODULE, + .act = tunnel_key_act, + .dump = tunnel_key_dump, + .init = tunnel_key_init, + .cleanup = tunnel_key_release, + .walk = tunnel_key_walker, + .lookup = tunnel_key_search, + .size = sizeof(struct tcf_tunnel_key), +}; + +static __net_init int tunnel_key_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tc_action_net_init(tn, &act_tunnel_key_ops, TUNNEL_KEY_TAB_MASK); +} + +static void __net_exit tunnel_key_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations tunnel_key_net_ops = { + .init = tunnel_key_init_net, + .exit = tunnel_key_exit_net, + .id = &tunnel_key_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init tunnel_key_init_module(void) +{ + return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops); +} + +static void __exit tunnel_key_cleanup_module(void) +{ + tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops); +} + +module_init(tunnel_key_init_module); +module_exit(tunnel_key_cleanup_module); + +MODULE_AUTHOR("Amir Vadai <amir@vadai.me>"); +MODULE_DESCRIPTION("ip tunnel manipulation actions"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 59a8d31..a95c00b 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -30,6 +30,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, struct tcf_vlan *v = to_vlan(a); int action; int err; + u16 tci; spin_lock(&v->tcf_lock); tcf_lastuse_update(&v->tcf_tm); @@ -48,6 +49,30 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (err) goto drop; break; + case TCA_VLAN_ACT_MODIFY: + /* No-op if no vlan tag (either hw-accel or in-payload) */ + if (!skb_vlan_tagged(skb)) + goto unlock; + /* extract existing tag (and guarantee no hw-accel tag) */ + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + skb->vlan_tci = 0; + } else { + /* in-payload vlan tag, pop it */ + err = __skb_vlan_pop(skb, &tci); + if (err) + goto drop; + } + /* replace the vid */ + tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid; + /* replace prio bits, if tcfv_push_prio specified */ + if (v->tcfv_push_prio) { + tci &= ~VLAN_PRIO_MASK; + tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT; + } + /* put updated tci as hwaccel tag */ + __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci); + break; default: BUG(); } @@ -102,6 +127,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, case TCA_VLAN_ACT_POP: break; case TCA_VLAN_ACT_PUSH: + case TCA_VLAN_ACT_MODIFY: if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) tcf_hash_release(*a, bind); @@ -185,7 +211,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if (v->tcfv_action == TCA_VLAN_ACT_PUSH && + if ((v->tcfv_action == TCA_VLAN_ACT_PUSH || + v->tcfv_action == TCA_VLAN_ACT_MODIFY) && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto) || diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a7c5645..11da7da 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -344,13 +344,15 @@ replay: if (err == 0) { struct tcf_proto *next = rtnl_dereference(tp->next); - tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); + tfilter_notify(net, skb, n, tp, fh, + RTM_DELTFILTER); if (tcf_destroy(tp, false)) RCU_INIT_POINTER(*back, next); } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER); + err = tfilter_notify(net, skb, n, tp, fh, + RTM_NEWTFILTER); goto errout; default: err = -EINVAL; @@ -448,7 +450,8 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, struct net *net = sock_net(a->skb->sk); return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, - a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); + a->cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWTFILTER); } /* called with RTNL */ @@ -552,7 +555,7 @@ void tcf_exts_destroy(struct tcf_exts *exts) EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr) + struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr) { #ifdef CONFIG_NET_CLS_ACT { @@ -560,8 +563,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tb[exts->police], rate_tlv, - "police", ovr, - TCA_ACT_BIND); + "police", ovr, TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); @@ -573,8 +575,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, int err, i = 0; err = tcf_action_init(net, tb[exts->action], rate_tlv, - NULL, ovr, - TCA_ACT_BIND, &actions); + NULL, ovr, TCA_ACT_BIND, + &actions); if (err) return err; list_for_each_entry(act, &actions, list) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 4742f41..bb1d5a4 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -27,6 +27,8 @@ MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_DESCRIPTION("TC BPF based classifier"); #define CLS_BPF_NAME_LEN 256 +#define CLS_BPF_SUPPORTED_GEN_FLAGS \ + (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW) struct cls_bpf_head { struct list_head plist; @@ -39,6 +41,8 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; + bool offloaded; + u32 gen_flags; struct tcf_exts exts; u32 handle; union { @@ -54,8 +58,10 @@ struct cls_bpf_prog { static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, [TCA_BPF_FLAGS] = { .type = NLA_U32 }, + [TCA_BPF_FLAGS_GEN] = { .type = NLA_U32 }, [TCA_BPF_FD] = { .type = NLA_U32 }, - [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, + [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, + .len = CLS_BPF_NAME_LEN }, [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, @@ -83,9 +89,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_bpf_prog *prog; int ret = -1; - if (unlikely(!skb_mac_header_was_set(skb))) - return -1; - /* Needed here for accessing maps. */ rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { @@ -93,7 +96,9 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, qdisc_skb_cb(skb)->tc_classid = prog->res.classid; - if (at_ingress) { + if (tc_skip_sw(prog->gen_flags)) { + filter_res = prog->exts_integrated ? TC_ACT_UNSPEC : 0; + } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); bpf_compute_data_end(skb); @@ -140,6 +145,91 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) return !prog->bpf_ops; } +static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, + enum tc_clsbpf_command cmd) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_bpf_offload bpf_offload = {}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSBPF; + offload.cls_bpf = &bpf_offload; + + bpf_offload.command = cmd; + bpf_offload.exts = &prog->exts; + bpf_offload.prog = prog->filter; + bpf_offload.name = prog->bpf_name; + bpf_offload.exts_integrated = prog->exts_integrated; + bpf_offload.gen_flags = prog->gen_flags; + + return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); +} + +static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, + struct cls_bpf_prog *oldprog) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct cls_bpf_prog *obj = prog; + enum tc_clsbpf_command cmd; + bool skip_sw; + int ret; + + skip_sw = tc_skip_sw(prog->gen_flags) || + (oldprog && tc_skip_sw(oldprog->gen_flags)); + + if (oldprog && oldprog->offloaded) { + if (tc_should_offload(dev, tp, prog->gen_flags)) { + cmd = TC_CLSBPF_REPLACE; + } else if (!tc_skip_sw(prog->gen_flags)) { + obj = oldprog; + cmd = TC_CLSBPF_DESTROY; + } else { + return -EINVAL; + } + } else { + if (!tc_should_offload(dev, tp, prog->gen_flags)) + return skip_sw ? -EINVAL : 0; + cmd = TC_CLSBPF_ADD; + } + + ret = cls_bpf_offload_cmd(tp, obj, cmd); + if (ret) + return skip_sw ? ret : 0; + + obj->offloaded = true; + if (oldprog) + oldprog->offloaded = false; + + return 0; +} + +static void cls_bpf_stop_offload(struct tcf_proto *tp, + struct cls_bpf_prog *prog) +{ + int err; + + if (!prog->offloaded) + return; + + err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + if (err) { + pr_err("Stopping hardware offload failed: %d\n", err); + return; + } + + prog->offloaded = false; +} + +static void cls_bpf_offload_update_stats(struct tcf_proto *tp, + struct cls_bpf_prog *prog) +{ + if (!prog->offloaded) + return; + + cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_STATS); +} + static int cls_bpf_init(struct tcf_proto *tp) { struct cls_bpf_head *head; @@ -179,6 +269,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) arg; + cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); @@ -195,6 +286,7 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(prog, tmp, &head->plist, link) { + cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); @@ -304,6 +396,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, { bool is_bpf, is_ebpf, have_exts = false; struct tcf_exts exts; + u32 gen_flags = 0; int ret; is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; @@ -328,8 +421,17 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout; + } + } prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : cls_bpf_prog_from_efd(tb, prog, tp); @@ -412,10 +514,17 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; } - ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr); + ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], + ovr); if (ret < 0) goto errout; + ret = cls_bpf_offload(tp, prog, oldprog); + if (ret) { + cls_bpf_delete_prog(tp, prog); + return ret; + } + if (oldprog) { list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); @@ -477,6 +586,8 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, tm->tcm_handle = prog->handle; + cls_bpf_offload_update_stats(tp, prog); + nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -499,6 +610,9 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT; if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags)) goto nla_put_failure; + if (prog->gen_flags && + nla_put_u32(skb, TCA_BPF_FLAGS_GEN, prog->gen_flags)) + goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2c1ae54..e396723 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -29,7 +29,7 @@ #include <net/route.h> #include <net/flow_dissector.h> -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif @@ -87,12 +87,14 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } -static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_proto(const struct sk_buff *skb, + const struct flow_keys *flow) { return flow->basic.ip_proto; } -static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_proto_src(const struct sk_buff *skb, + const struct flow_keys *flow) { if (flow->ports.ports) return ntohs(flow->ports.src); @@ -100,7 +102,8 @@ static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys return addr_fold(skb->sk); } -static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_proto_dst(const struct sk_buff *skb, + const struct flow_keys *flow) { if (flow->ports.ports) return ntohs(flow->ports.dst); @@ -125,14 +128,14 @@ static u32 flow_get_mark(const struct sk_buff *skb) static u32 flow_get_nfct(const struct sk_buff *skb) { -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) return addr_fold(skb->nfct); #else return 0; #endif } -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #define CTTUPLE(skb, member) \ ({ \ enum ip_conntrack_info ctinfo; \ @@ -149,7 +152,8 @@ static u32 flow_get_nfct(const struct sk_buff *skb) }) #endif -static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_nfct_src(const struct sk_buff *skb, + const struct flow_keys *flow) { switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): @@ -161,7 +165,8 @@ fallback: return flow_get_src(skb, flow); } -static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_nfct_dst(const struct sk_buff *skb, + const struct flow_keys *flow) { switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): @@ -173,14 +178,16 @@ fallback: return flow_get_dst(skb, flow); } -static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, + const struct flow_keys *flow) { return ntohs(CTTUPLE(skb, src.u.all)); fallback: return flow_get_proto_src(skb, flow); } -static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow) +static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, + const struct flow_keys *flow) { return ntohs(CTTUPLE(skb, dst.u.all)); fallback: diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index cf9ad5b..2af09c8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -23,18 +23,26 @@ #include <net/ip.h> #include <net/flow_dissector.h> +#include <net/dst.h> +#include <net/dst_metadata.h> + struct fl_flow_key { int indev_ifindex; struct flow_dissector_key_control control; + struct flow_dissector_key_control enc_control; struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; struct flow_dissector_key_vlan vlan; - struct flow_dissector_key_addrs ipaddrs; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_ports tp; + struct flow_dissector_key_keyid enc_key_id; + union { + struct flow_dissector_key_ipv4_addrs enc_ipv4; + struct flow_dissector_key_ipv6_addrs enc_ipv6; + }; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -124,11 +132,31 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; + struct ip_tunnel_info *info; if (!atomic_read(&head->ht.nelems)) return -1; fl_clear_masked_range(&skb_key, &head->mask); + + info = skb_tunnel_info(skb); + if (info) { + struct ip_tunnel_key *key = &info->key; + + switch (ip_tunnel_info_af(info)) { + case AF_INET: + skb_key.enc_ipv4.src = key->u.ipv4.src; + skb_key.enc_ipv4.dst = key->u.ipv4.dst; + break; + case AF_INET6: + skb_key.enc_ipv6.src = key->u.ipv6.src; + skb_key.enc_ipv6.dst = key->u.ipv6.dst; + break; + } + + skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); + } + skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, * so do it rather here. @@ -213,7 +241,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, tc.type = TC_SETUP_CLSFLOWER; tc.cls_flower = &offload; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); + err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, + &tc); if (tc_skip_sw(flags)) return err; @@ -297,7 +326,19 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_VLAN_ID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_VLAN_PRIO] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_VLAN_ETH_TYPE] = { .type = NLA_U16 }, - + [TCA_FLOWER_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) }, + [TCA_FLOWER_KEY_TCP_SRC_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -395,20 +436,54 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (key->basic.ip_proto == IPPROTO_TCP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK, sizeof(key->tp.src)); fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, sizeof(key->tp.dst)); } else if (key->basic.ip_proto == IPPROTO_UDP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK, sizeof(key->tp.src)); fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)); } + if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || + tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) { + key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + fl_set_key_val(tb, &key->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC, + &mask->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK, + sizeof(key->enc_ipv4.src)); + fl_set_key_val(tb, &key->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST, + &mask->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK, + sizeof(key->enc_ipv4.dst)); + } + + if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] || + tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) { + key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + fl_set_key_val(tb, &key->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC, + &mask->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK, + sizeof(key->enc_ipv6.src)); + fl_set_key_val(tb, &key->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST, + &mask->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK, + sizeof(key->enc_ipv6.dst)); + } + + fl_set_key_val(tb, &key->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID, + &mask->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID, + sizeof(key->enc_key_id.keyid)); + return 0; } @@ -806,21 +881,48 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (key->basic.ip_proto == IPPROTO_TCP && (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_TCP_SRC_MASK, sizeof(key->tp.src)) || fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_TCP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; else if (key->basic.ip_proto == IPPROTO_UDP && (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC, - &mask->tp.src, TCA_FLOWER_UNSPEC, + &mask->tp.src, TCA_FLOWER_KEY_UDP_SRC_MASK, sizeof(key->tp.src)) || fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST, - &mask->tp.dst, TCA_FLOWER_UNSPEC, + &mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK, sizeof(key->tp.dst)))) goto nla_put_failure; + if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && + (fl_dump_key_val(skb, &key->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src, + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK, + sizeof(key->enc_ipv4.src)) || + fl_dump_key_val(skb, &key->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST, &mask->enc_ipv4.dst, + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK, + sizeof(key->enc_ipv4.dst)))) + goto nla_put_failure; + else if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS && + (fl_dump_key_val(skb, &key->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src, + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK, + sizeof(key->enc_ipv6.src)) || + fl_dump_key_val(skb, &key->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST, + &mask->enc_ipv6.dst, + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK, + sizeof(key->enc_ipv6.dst)))) + goto nla_put_failure; + + if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID, + &mask->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID, + sizeof(key->enc_key_id))) + goto nla_put_failure; + nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags); if (tcf_exts_dump(skb, &f->exts)) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index cc0bda9..9dc63d5 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -57,7 +57,7 @@ static u32 fw_hash(u32 handle) } static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) + struct tcf_result *res) { struct fw_head *head = rcu_dereference_bh(tp->root); struct fw_filter *f; @@ -188,7 +188,8 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { static int fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, - struct nlattr **tb, struct nlattr **tca, unsigned long base, bool ovr) + struct nlattr **tb, struct nlattr **tca, unsigned long base, + bool ovr) { struct fw_head *head = rtnl_dereference(tp->root); struct tcf_exts e; @@ -237,9 +238,8 @@ errout: static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - unsigned long *arg, bool ovr) + u32 handle, struct nlattr **tca, unsigned long *arg, + bool ovr) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = (struct fw_filter *) *arg; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index c91e65d..455fc8f 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -268,8 +268,7 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static void -route4_delete_filter(struct rcu_head *head) +static void route4_delete_filter(struct rcu_head *head) { struct route4_filter *f = container_of(head, struct route4_filter, rcu); @@ -474,10 +473,8 @@ errout: } static int route4_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - unsigned long *arg, bool ovr) + struct tcf_proto *tp, unsigned long base, u32 handle, + struct nlattr **tca, unsigned long *arg, bool ovr) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -562,7 +559,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, return 0; errout: - tcf_exts_destroy(&f->exts); + if (f) + tcf_exts_destroy(&f->exts); kfree(f); return err; } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index d950070..96144bd 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -50,14 +50,13 @@ struct tcindex_data { struct rcu_head rcu; }; -static inline int -tcindex_filter_is_set(struct tcindex_filter_result *r) +static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) { return tcf_exts_is_predicative(&r->exts) || r->res.classid; } -static struct tcindex_filter_result * -tcindex_lookup(struct tcindex_data *p, u16 key) +static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, + u16 key) { if (p->perfect) { struct tcindex_filter_result *f = p->perfect + key; @@ -144,7 +143,8 @@ static void tcindex_destroy_rexts(struct rcu_head *head) static void tcindex_destroy_fexts(struct rcu_head *head) { - struct tcindex_filter *f = container_of(head, struct tcindex_filter, rcu); + struct tcindex_filter *f = container_of(head, struct tcindex_filter, + rcu); tcf_exts_destroy(&f->result.exts); kfree(f); @@ -550,7 +550,7 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force) static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a29263a..ae83c3ae 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -104,7 +104,8 @@ static inline unsigned int u32_hash_fold(__be32 key, return h; } -static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) +static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) { struct { struct tc_u_knode *knode; @@ -256,8 +257,7 @@ deadloop: return -1; } -static struct tc_u_hnode * -u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) +static struct tc_u_hnode *u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; @@ -270,8 +270,7 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) return ht; } -static struct tc_u_knode * -u32_lookup_key(struct tc_u_hnode *ht, u32 handle) +static struct tc_u_knode *u32_lookup_key(struct tc_u_hnode *ht, u32 handle) { unsigned int sel; struct tc_u_knode *n = NULL; @@ -360,8 +359,7 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tcf_proto *tp, - struct tc_u_knode *n, +static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, bool free_pf) { tcf_exts_destroy(&n->exts); @@ -448,9 +446,8 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) } } -static int u32_replace_hw_hnode(struct tcf_proto *tp, - struct tc_u_hnode *h, - u32 flags) +static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -496,9 +493,8 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) } } -static int u32_replace_hw_knode(struct tcf_proto *tp, - struct tc_u_knode *n, - u32 flags) +static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -763,8 +759,7 @@ errout: return err; } -static void u32_replace_knode(struct tcf_proto *tp, - struct tc_u_common *tp_c, +static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, struct tc_u_knode *n) { struct tc_u_knode __rcu **ins; @@ -845,8 +840,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, - unsigned long *arg, bool ovr) + struct nlattr **tca, unsigned long *arg, bool ovr) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -1088,7 +1082,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t) { struct tc_u_knode *n = (struct tc_u_knode *)fh; struct tc_u_hnode *ht_up, *ht_down; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d677b34..206dc24 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -389,7 +389,8 @@ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) static struct qdisc_rate_table *qdisc_rtab_list; -struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab) +struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, + struct nlattr *tab) { struct qdisc_rate_table *rtab; @@ -541,7 +542,8 @@ nla_put_failure: return -1; } -void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) +void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab) { int pkt_len, slot; @@ -888,10 +890,10 @@ static struct lock_class_key qdisc_rx_lock; Parameters are passed via opt. */ -static struct Qdisc * -qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, - struct Qdisc *p, u32 parent, u32 handle, - struct nlattr **tca, int *errp) +static struct Qdisc *qdisc_create(struct net_device *dev, + struct netdev_queue *dev_queue, + struct Qdisc *p, u32 parent, u32 handle, + struct nlattr **tca, int *errp) { int err; struct nlattr *kind = tca[TCA_KIND]; @@ -1073,7 +1075,8 @@ struct check_loop_arg { int depth; }; -static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w); +static int check_loop_fn(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w); static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth) { @@ -1450,7 +1453,8 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, } else { if (!tc_qdisc_dump_ignore(q) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) + cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWQDISC) <= 0) goto done; q_idx++; } @@ -1471,7 +1475,8 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, } if (!tc_qdisc_dump_ignore(q) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) + cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWQDISC) <= 0) goto done; q_idx++; } @@ -1505,7 +1510,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_q_idx = 0; q_idx = 0; - if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, true) < 0) + if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, + true) < 0) goto done; dev_queue = dev_ingress_queue(dev); @@ -1640,7 +1646,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n) if (cops->delete) err = cops->delete(q, cl); if (err == 0) - tclass_notify(net, skb, n, q, cl, RTM_DELTCLASS); + tclass_notify(net, skb, n, q, cl, + RTM_DELTCLASS); goto out; case RTM_GETTCLASS: err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS); @@ -1738,12 +1745,14 @@ struct qdisc_dump_args { struct netlink_callback *cb; }; -static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) +static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *arg) { struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg; return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, - a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS); + a->cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWTCLASS); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, @@ -1976,10 +1985,12 @@ static int __init pktsched_init(void) rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, NULL); + rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, + NULL); rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL); rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, NULL); + rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, + NULL); return 0; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 4002df3..5bfa79e 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -69,7 +69,7 @@ struct codel_sched_data { static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) { struct Qdisc *sch = ctx; - struct sk_buff *skb = __skb_dequeue(&sch->q); + struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (skb) sch->qstats.backlog -= qdisc_pkt_len(skb); @@ -172,7 +172,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __skb_dequeue(&sch->q); + struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index baeed6a..1e37247 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -31,7 +31,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - if (likely(skb_queue_len(&sch->q) < sch->limit)) + if (likely(sch->q.qlen < sch->limit)) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); @@ -42,7 +42,7 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, { unsigned int prev_backlog; - if (likely(skb_queue_len(&sch->q) < sch->limit)) + if (likely(sch->q.qlen < sch->limit)) return qdisc_enqueue_tail(skb, sch); prev_backlog = sch->qstats.backlog; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index e5458b9..18e7524 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -86,6 +86,7 @@ struct fq_sched_data { struct rb_root delayed; /* for rate limited flows */ u64 time_next_delayed_flow; + unsigned long unthrottle_latency_ns; struct fq_flow internal; /* for non classified or high prio packets */ u32 quantum; @@ -94,6 +95,7 @@ struct fq_sched_data { u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ u32 orphan_mask; /* mask for orphaned skb */ + u32 low_rate_threshold; struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; @@ -407,11 +409,19 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, static void fq_check_throttled(struct fq_sched_data *q, u64 now) { + unsigned long sample; struct rb_node *p; if (q->time_next_delayed_flow > now) return; + /* Update unthrottle latency EWMA. + * This is cheap and can help diagnosing timer/latency problems. + */ + sample = (unsigned long)(now - q->time_next_delayed_flow); + q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3; + q->unthrottle_latency_ns += sample >> 3; + q->time_next_delayed_flow = ~0ULL; while ((p = rb_first(&q->delayed)) != NULL) { struct fq_flow *f = container_of(p, struct fq_flow, rate_node); @@ -433,7 +443,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; - u32 rate; + u32 rate, plen; skb = fq_dequeue_head(sch, &q->internal); if (skb) @@ -482,7 +492,7 @@ begin: prefetch(&skb->end); f->credit -= qdisc_pkt_len(skb); - if (f->credit > 0 || !q->rate_enable) + if (!q->rate_enable) goto out; /* Do not pace locally generated ack packets */ @@ -493,8 +503,15 @@ begin: if (skb->sk) rate = min(skb->sk->sk_pacing_rate, rate); + if (rate <= q->low_rate_threshold) { + f->credit = 0; + plen = qdisc_pkt_len(skb); + } else { + plen = max(qdisc_pkt_len(skb), q->quantum); + if (f->credit > 0) + goto out; + } if (rate != ~0U) { - u32 plen = max(qdisc_pkt_len(skb), q->quantum); u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) @@ -507,7 +524,12 @@ begin: len = NSEC_PER_SEC; q->stat_pkts_too_long++; } - + /* Account for schedule/timers drifts. + * f->time_next_packet was set when prior packet was sent, + * and current time (@now) can be too late by tens of us. + */ + if (f->time_next_packet) + len -= min(len/2, now - f->time_next_packet); f->time_next_packet = now + len; } out: @@ -662,6 +684,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt) @@ -716,6 +739,10 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_FQ_FLOW_MAX_RATE]) q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) + q->low_rate_threshold = + nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); + if (tb[TCA_FQ_RATE_ENABLE]) { u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]); @@ -774,6 +801,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0U; + q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; q->new_flows.first = NULL; q->old_flows.first = NULL; @@ -781,6 +809,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->fq_root = NULL; q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; + q->low_rate_threshold = 550000 / 8; qdisc_watchdog_init(&q->watchdog, sch); if (opt) @@ -811,6 +840,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, jiffies_to_usecs(q->flow_refill_delay)) || nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || + nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, + q->low_rate_threshold) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; @@ -823,20 +854,24 @@ nla_put_failure: static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_sched_data *q = qdisc_priv(sch); - u64 now = ktime_get_ns(); - struct tc_fq_qd_stats st = { - .gc_flows = q->stat_gc_flows, - .highprio_packets = q->stat_internal_packets, - .tcp_retrans = q->stat_tcp_retrans, - .throttled = q->stat_throttled, - .flows_plimit = q->stat_flows_plimit, - .pkts_too_long = q->stat_pkts_too_long, - .allocation_errors = q->stat_allocation_errors, - .flows = q->flows, - .inactive_flows = q->inactive_flows, - .throttled_flows = q->throttled_flows, - .time_next_delayed_flow = q->time_next_delayed_flow - now, - }; + struct tc_fq_qd_stats st; + + sch_tree_lock(sch); + + st.gc_flows = q->stat_gc_flows; + st.highprio_packets = q->stat_internal_packets; + st.tcp_retrans = q->stat_tcp_retrans; + st.throttled = q->stat_throttled; + st.flows_plimit = q->stat_flows_plimit; + st.pkts_too_long = q->stat_pkts_too_long; + st.allocation_errors = q->stat_allocation_errors; + st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_ns(); + st.flows = q->flows; + st.inactive_flows = q->inactive_flows; + st.throttled_flows = q->throttled_flows; + st.unthrottle_latency_ns = min_t(unsigned long, + q->unthrottle_latency_ns, ~0U); + sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 0d21b56..6cfb6e9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -466,7 +466,7 @@ static const u8 prio2band[TC_PRIO_MAX + 1] = { */ struct pfifo_fast_priv { u32 bitmap; - struct sk_buff_head q[PFIFO_FAST_BANDS]; + struct qdisc_skb_head q[PFIFO_FAST_BANDS]; }; /* @@ -477,7 +477,7 @@ struct pfifo_fast_priv { */ static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0}; -static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv, +static inline struct qdisc_skb_head *band2list(struct pfifo_fast_priv *priv, int band) { return priv->q + band; @@ -486,10 +486,10 @@ static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv, static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { - if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) { + if (qdisc->q.qlen < qdisc_dev(qdisc)->tx_queue_len) { int band = prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); - struct sk_buff_head *list = band2list(priv, band); + struct qdisc_skb_head *list = band2list(priv, band); priv->bitmap |= (1 << band); qdisc->q.qlen++; @@ -505,11 +505,16 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) int band = bitmap2band[priv->bitmap]; if (likely(band >= 0)) { - struct sk_buff_head *list = band2list(priv, band); - struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list); + struct qdisc_skb_head *qh = band2list(priv, band); + struct sk_buff *skb = __qdisc_dequeue_head(qh); + + if (likely(skb != NULL)) { + qdisc_qstats_backlog_dec(qdisc, skb); + qdisc_bstats_update(qdisc, skb); + } qdisc->q.qlen--; - if (skb_queue_empty(list)) + if (qh->qlen == 0) priv->bitmap &= ~(1 << band); return skb; @@ -524,9 +529,9 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) int band = bitmap2band[priv->bitmap]; if (band >= 0) { - struct sk_buff_head *list = band2list(priv, band); + struct qdisc_skb_head *qh = band2list(priv, band); - return skb_peek(list); + return qh->head; } return NULL; @@ -564,7 +569,7 @@ static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - __skb_queue_head_init(band2list(priv, prio)); + qdisc_skb_head_init(band2list(priv, prio)); /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; @@ -612,7 +617,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); sch->padded = (char *) sch - (char *) p; } - skb_queue_head_init(&sch->q); + qdisc_skb_head_init(&sch->q); + spin_lock_init(&sch->q.lock); spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 53dbfa1..c798d0d 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -162,7 +162,7 @@ struct htb_sched { struct work_struct work; /* non shaped skbs; let them go directly thru */ - struct sk_buff_head direct_queue; + struct qdisc_skb_head direct_queue; long direct_pkts; struct qdisc_watchdog watchdog; @@ -570,6 +570,22 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) list_del_init(&cl->un.leaf.drop_list); } +static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, + struct qdisc_skb_head *qh) +{ + struct sk_buff *last = qh->tail; + + if (last) { + skb->next = NULL; + last->next = skb; + qh->tail = skb; + } else { + qh->tail = skb; + qh->head = skb; + } + qh->qlen++; +} + static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -580,7 +596,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - __skb_queue_tail(&q->direct_queue, skb); + htb_enqueue_tail(skb, sch, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -888,7 +904,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) unsigned long start_at; /* try to dequeue direct packets as high prio (!) to minimize cpu work */ - skb = __skb_dequeue(&q->direct_queue); + skb = __qdisc_dequeue_head(&q->direct_queue); if (skb != NULL) { ok: qdisc_bstats_update(sch, skb); @@ -1019,7 +1035,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); INIT_WORK(&q->work, htb_work_func); - __skb_queue_head_init(&q->direct_queue); + qdisc_skb_head_init(&q->direct_queue); if (tb[TCA_HTB_DIRECT_QLEN]) q->direct_qlen = nla_get_u32(tb[TCA_HTB_DIRECT_QLEN]); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index aaaf021..9f7b380 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -413,6 +413,16 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } +static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) +{ + skb->next = qh->head; + + if (!qh->head) + qh->tail = skb; + qh->head = skb; + qh->qlen++; +} + /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -502,7 +512,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<(prandom_u32() % 8); } - if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) + if (unlikely(sch->q.qlen >= sch->limit)) return qdisc_drop(skb, sch, to_free); qdisc_qstats_backlog_inc(sch, skb); @@ -522,8 +532,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (q->rate) { struct sk_buff *last; - if (!skb_queue_empty(&sch->q)) - last = skb_peek_tail(&sch->q); + if (sch->q.qlen) + last = sch->q.tail; else last = netem_rb_to_skb(rb_last(&q->t_root)); if (last) { @@ -552,7 +562,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = psched_get_time(); q->counter = 0; - __skb_queue_head(&sch->q, skb); + netem_enqueue_skb_head(&sch->q, skb); sch->qstats.requeues++; } @@ -587,7 +597,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) struct rb_node *p; tfifo_dequeue: - skb = __skb_dequeue(&sch->q); + skb = __qdisc_dequeue_head(&sch->q); if (skb) { qdisc_qstats_backlog_dec(sch, skb); deliver: diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index a570b0b..5c3a99d 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -231,7 +231,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __skb_dequeue(&sch->q); + struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); @@ -511,7 +511,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { struct sk_buff *skb; - skb = __qdisc_dequeue_head(sch, &sch->q); + skb = qdisc_dequeue_head(sch); if (!skb) return NULL; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 1c23060..f10d339 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1408,7 +1408,7 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) transports) { if (t->pmtu_pending && t->dst) { sctp_transport_update_pmtu(sk, t, - WORD_TRUNC(dst_mtu(t->dst))); + SCTP_TRUNC4(dst_mtu(t->dst))); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 912eb16..f99d485 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -48,7 +48,7 @@ static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = { /* id 2 is reserved as well */ .hmac_id = SCTP_AUTH_HMAC_ID_RESERVED_2, }, -#if defined (CONFIG_CRYPTO_SHA256) || defined (CONFIG_CRYPTO_SHA256_MODULE) +#if IS_ENABLED(CONFIG_CRYPTO_SHA256) { .hmac_id = SCTP_AUTH_HMAC_ID_SHA256, .hmac_name = "hmac(sha256)", diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index a55e547..8afe2e9 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -70,6 +70,19 @@ static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) return msg; } +void sctp_datamsg_free(struct sctp_datamsg *msg) +{ + struct sctp_chunk *chunk; + + /* This doesn't have to be a _safe vairant because + * sctp_chunk_free() only drops the refs. + */ + list_for_each_entry(chunk, &msg->chunks, frag_list) + sctp_chunk_free(chunk); + + sctp_datamsg_put(msg); +} + /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { @@ -182,9 +195,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, /* This is the biggest possible DATA chunk that can fit into * the packet */ - max_data = (asoc->pathmtu - - sctp_sk(asoc->base.sk)->pf->af->net_header_len - - sizeof(struct sctphdr) - sizeof(struct sctp_data_chunk)) & ~3; + max_data = asoc->pathmtu - + sctp_sk(asoc->base.sk)->pf->af->net_header_len - + sizeof(struct sctphdr) - sizeof(struct sctp_data_chunk); + max_data = SCTP_TRUNC4(max_data); max = asoc->frag_point; /* If the the peer requested that we authenticate DATA chunks @@ -195,8 +209,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) - max_data -= WORD_ROUND(sizeof(sctp_auth_chunk_t) + - hmac_desc->hmac_len); + max_data -= SCTP_PAD4(sizeof(sctp_auth_chunk_t) + + hmac_desc->hmac_len); } /* Now, check if we need to reduce our max */ @@ -216,7 +230,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, asoc->outqueue.out_qlen == 0 && list_empty(&asoc->outqueue.retransmit) && msg_len > max) - max_data -= WORD_ROUND(sizeof(sctp_sack_chunk_t)); + max_data -= SCTP_PAD4(sizeof(sctp_sack_chunk_t)); /* Encourage Cookie-ECHO bundling. */ if (asoc->state < SCTP_STATE_COOKIE_ECHOED) diff --git a/net/sctp/input.c b/net/sctp/input.c index 69444d3..a2ea1d1 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -605,7 +605,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) /* PMTU discovery (RFC1191) */ if (ICMP_FRAG_NEEDED == code) { sctp_icmp_frag_needed(sk, asoc, transport, - WORD_TRUNC(info)); + SCTP_TRUNC4(info)); goto out_unlock; } else { if (ICMP_PROT_UNREACH == code) { @@ -673,7 +673,7 @@ static int sctp_rcv_ootb(struct sk_buff *skb) if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) break; - ch_end = offset + WORD_ROUND(ntohs(ch->length)); + ch_end = offset + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb->len) break; @@ -796,27 +796,34 @@ struct sctp_hash_cmp_arg { static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { + struct sctp_transport *t = (struct sctp_transport *)ptr; const struct sctp_hash_cmp_arg *x = arg->key; - const struct sctp_transport *t = ptr; - struct sctp_association *asoc = t->asoc; - const struct net *net = x->net; + struct sctp_association *asoc; + int err = 1; if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) - return 1; - if (!net_eq(sock_net(asoc->base.sk), net)) - return 1; + return err; + if (!sctp_transport_hold(t)) + return err; + + asoc = t->asoc; + if (!net_eq(sock_net(asoc->base.sk), x->net)) + goto out; if (x->ep) { if (x->ep != asoc->ep) - return 1; + goto out; } else { if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) - return 1; + goto out; if (!sctp_bind_addr_match(&asoc->base.bind_addr, x->laddr, sctp_sk(asoc->base.sk))) - return 1; + goto out; } - return 0; + err = 0; +out: + sctp_transport_put(t); + return err; } static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed) @@ -1121,7 +1128,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) break; - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) break; @@ -1190,7 +1197,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, * that the chunk length doesn't cause overflow. Otherwise, we'll * walk off the end. */ - if (WORD_ROUND(ntohs(ch->length)) > skb->len) + if (SCTP_PAD4(ntohs(ch->length)) > skb->len) return NULL; /* If this is INIT/INIT-ACK look inside the chunk too. */ diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 6437aa9..f731de3 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -213,7 +213,7 @@ new_skb: } chunk->chunk_hdr = ch; - chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ diff --git a/net/sctp/output.c b/net/sctp/output.c index 1f1682b..2a5c189 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -180,7 +180,6 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, int one_packet, gfp_t gfp) { sctp_xmit_t retval; - int error = 0; pr_debug("%s: packet:%p size:%Zu chunk:%p size:%d\n", __func__, packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1); @@ -188,6 +187,8 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) { case SCTP_XMIT_PMTU_FULL: if (!packet->has_cookie_echo) { + int error = 0; + error = sctp_packet_transmit(packet, gfp); if (error < 0) chunk->skb->sk->sk_err = -error; @@ -296,7 +297,7 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, struct sctp_chunk *chunk) { sctp_xmit_t retval = SCTP_XMIT_OK; - __u16 chunk_len = WORD_ROUND(ntohs(chunk->chunk_hdr->length)); + __u16 chunk_len = SCTP_PAD4(ntohs(chunk->chunk_hdr->length)); /* Check to see if this chunk will fit into the packet */ retval = sctp_packet_will_fit(packet, chunk, chunk_len); @@ -441,14 +442,14 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * time. Application may notice this error. */ pr_err_once("Trying to GSO but underlying device doesn't support it."); - goto nomem; + goto err; } } else { pkt_size = packet->size; } head = alloc_skb(pkt_size + MAX_HEADER, gfp); if (!head) - goto nomem; + goto err; if (gso) { NAPI_GRO_CB(head)->last = head; skb_shinfo(head)->gso_type = sk->sk_gso_type; @@ -469,8 +470,12 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) } } dst = dst_clone(tp->dst); - if (!dst) - goto no_route; + if (!dst) { + if (asoc) + IP_INC_STATS(sock_net(asoc->base.sk), + IPSTATS_MIB_OUTNOROUTES); + goto nodst; + } skb_dst_set(head, dst); /* Build the SCTP header. */ @@ -503,7 +508,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) if (gso) { pkt_size = packet->overhead; list_for_each_entry(chunk, &packet->chunk_list, list) { - int padded = WORD_ROUND(chunk->skb->len); + int padded = SCTP_PAD4(chunk->skb->len); if (pkt_size + padded > tp->pathmtu) break; @@ -533,7 +538,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * included in the chunk length field. The sender should * never pad with more than 3 bytes. * - * [This whole comment explains WORD_ROUND() below.] + * [This whole comment explains SCTP_PAD4() below.] */ pkt_size -= packet->overhead; @@ -555,7 +560,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) has_data = 1; } - padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len; + padding = SCTP_PAD4(chunk->skb->len) - chunk->skb->len; if (padding) memset(skb_put(chunk->skb, padding), 0, padding); @@ -582,7 +587,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * acknowledged or have failed. * Re-queue auth chunks if needed. */ - pkt_size -= WORD_ROUND(chunk->skb->len); + pkt_size -= SCTP_PAD4(chunk->skb->len); if (!sctp_chunk_is_data(chunk) && chunk != packet->auth) sctp_chunk_free(chunk); @@ -621,8 +626,10 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) if (!gso) break; - if (skb_gro_receive(&head, nskb)) + if (skb_gro_receive(&head, nskb)) { + kfree_skb(nskb); goto nomem; + } nskb = NULL; if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >= sk->sk_gso_max_segs)) @@ -716,18 +723,13 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) } head->ignore_df = packet->ipfragok; tp->af_specific->sctp_xmit(head, tp); + goto out; -out: - sctp_packet_reset(packet); - return err; -no_route: - kfree_skb(head); - if (nskb != head) - kfree_skb(nskb); - - if (asoc) - IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); +nomem: + if (packet->auth && list_empty(&packet->auth->list)) + sctp_chunk_free(packet->auth); +nodst: /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the * association is unreachable. @@ -736,22 +738,18 @@ no_route: * required. */ /* err = -EHOSTUNREACH; */ -err: - /* Control chunks are unreliable so just drop them. DATA chunks - * will get resent or dropped later. - */ + kfree_skb(head); +err: list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { list_del_init(&chunk->list); if (!sctp_chunk_is_data(chunk)) sctp_chunk_free(chunk); } - goto out; -nomem: - if (packet->auth && list_empty(&packet->auth->list)) - sctp_chunk_free(packet->auth); - err = -ENOMEM; - goto err; + +out: + sctp_packet_reset(packet); + return err; } /******************************************************************** @@ -878,7 +876,7 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, struct sctp_chunk *chunk, u16 chunk_len) { - size_t psize, pmtu; + size_t psize, pmtu, maxsize; sctp_xmit_t retval = SCTP_XMIT_OK; psize = packet->size; @@ -906,6 +904,17 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, goto out; } + /* Similarly, if this chunk was built before a PMTU + * reduction, we have to fragment it at IP level now. So + * if the packet already contains something, we need to + * flush. + */ + maxsize = pmtu - packet->overhead; + if (packet->auth) + maxsize -= SCTP_PAD4(packet->auth->skb->len); + if (chunk_len > maxsize) + retval = SCTP_XMIT_PMTU_FULL; + /* It is also okay to fragment if the chunk we are * adding is a control chunk, but only if current packet * is not a GSO one otherwise it causes fragmentation of diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 72e54a4..3ec6da8b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -68,7 +68,7 @@ static void sctp_mark_missing(struct sctp_outq *q, static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); -static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); +static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, @@ -285,10 +285,9 @@ void sctp_outq_free(struct sctp_outq *q) } /* Put a new chunk in an sctp_outq. */ -int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) +void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = sock_net(q->asoc->base.sk); - int error = 0; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? @@ -299,54 +298,26 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) * immediately. */ if (sctp_chunk_is_data(chunk)) { - /* Is it OK to queue data chunks? */ - /* From 9. Termination of Association - * - * When either endpoint performs a shutdown, the - * association on each peer will stop accepting new - * data from its user and only deliver data in queue - * at the time of sending or receiving the SHUTDOWN - * chunk. - */ - switch (q->asoc->state) { - case SCTP_STATE_CLOSED: - case SCTP_STATE_SHUTDOWN_PENDING: - case SCTP_STATE_SHUTDOWN_SENT: - case SCTP_STATE_SHUTDOWN_RECEIVED: - case SCTP_STATE_SHUTDOWN_ACK_SENT: - /* Cannot send after transport endpoint shutdown */ - error = -ESHUTDOWN; - break; - - default: - pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", - __func__, q, chunk, chunk && chunk->chunk_hdr ? - sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : - "illegal chunk"); - - sctp_chunk_hold(chunk); - sctp_outq_tail_data(q, chunk); - if (chunk->asoc->prsctp_enable && - SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) - chunk->asoc->sent_cnt_removable++; - if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) - SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); - else - SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); - break; - } + pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", + __func__, q, chunk, chunk && chunk->chunk_hdr ? + sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : + "illegal chunk"); + + sctp_outq_tail_data(q, chunk); + if (chunk->asoc->prsctp_enable && + SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) + chunk->asoc->sent_cnt_removable++; + if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) + SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); + else + SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); } else { list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } - if (error < 0) - return error; - if (!q->cork) - error = sctp_outq_flush(q, 0, gfp); - - return error; + sctp_outq_flush(q, 0, gfp); } /* Insert a chunk into the sorted list based on the TSNs. The retransmit list @@ -559,7 +530,6 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, sctp_retransmit_reason_t reason) { struct net *net = sock_net(q->asoc->base.sk); - int error = 0; switch (reason) { case SCTP_RTXR_T3_RTX: @@ -603,10 +573,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) - error = sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); - - if (error) - q->asoc->base.sk->sk_err = -error; + sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); } /* @@ -778,12 +745,12 @@ redo: } /* Cork the outqueue so queued chunks are really queued. */ -int sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) +void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; - return sctp_outq_flush(q, 0, gfp); + sctp_outq_flush(q, 0, gfp); } @@ -796,7 +763,7 @@ int sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) * locking concerns must be made. Today we use the sock lock to protect * this function. */ -static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) +static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_packet *packet; struct sctp_packet singleton; @@ -919,8 +886,10 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) sctp_packet_config(&singleton, vtag, 0); sctp_packet_append_chunk(&singleton, chunk); error = sctp_packet_transmit(&singleton, gfp); - if (error < 0) - return error; + if (error < 0) { + asoc->base.sk->sk_err = -error; + return; + } break; case SCTP_CID_ABORT: @@ -1018,6 +987,8 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) retran: error = sctp_outq_flush_rtx(q, packet, rtx_timeout, &start_timer); + if (error < 0) + asoc->base.sk->sk_err = -error; if (start_timer) { sctp_transport_reset_t3_rtx(transport); @@ -1192,14 +1163,15 @@ sctp_flush_out: struct sctp_transport, send_ready); packet = &t->packet; - if (!sctp_packet_empty(packet)) + if (!sctp_packet_empty(packet)) { error = sctp_packet_transmit(packet, gfp); + if (error < 0) + asoc->base.sk->sk_err = -error; + } /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); } - - return error; } /* Update unack_data based on the incoming SACK chunk */ @@ -1747,7 +1719,7 @@ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) { int i; sctp_sack_variable_t *frags; - __u16 gap; + __u16 tsn_offset, blocks; __u32 ctsn = ntohl(sack->cum_tsn_ack); if (TSN_lte(tsn, ctsn)) @@ -1766,10 +1738,11 @@ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) */ frags = sack->variable; - gap = tsn - ctsn; - for (i = 0; i < ntohs(sack->num_gap_ack_blocks); ++i) { - if (TSN_lte(ntohs(frags[i].gab.start), gap) && - TSN_lte(gap, ntohs(frags[i].gab.end))) + blocks = ntohs(sack->num_gap_ack_blocks); + tsn_offset = tsn - ctsn; + for (i = 0; i < blocks; ++i) { + if (tsn_offset >= ntohs(frags[i].gab.start) && + tsn_offset <= ntohs(frags[i].gab.end)) goto pass; } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index f3508aa..807158e3 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -106,7 +106,8 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, int portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct list_head *addr_list; @@ -133,7 +134,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, r->idiag_retrans = 0; } - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) { @@ -203,6 +204,7 @@ struct sctp_comm_param { struct netlink_callback *cb; const struct inet_diag_req_v2 *r; const struct nlmsghdr *nlh; + bool net_admin; }; static size_t inet_assoc_attr_size(struct sctp_association *asoc) @@ -219,6 +221,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) @@ -256,7 +259,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + commp->net_admin); release_sock(sk); if (err < 0) { WARN_ON(err == -EMSGSIZE); @@ -310,7 +314,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->nlh) < 0) { + NLM_F_MULTI, cb->nlh, + commp->net_admin) < 0) { cb->args[3] = 1; err = 2; goto release; @@ -320,7 +325,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) if (inet_sctp_diag_fill(sk, assoc, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, cb->nlh) < 0) { + cb->nlh->nlmsg_seq, 0, cb->nlh, + commp->net_admin) < 0) { err = 2; goto release; } @@ -375,7 +381,7 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh) < 0) { + cb->nlh, commp->net_admin) < 0) { err = 2; goto out; } @@ -412,6 +418,7 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, .skb = in_skb, .r = req, .nlh = nlh, + .net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN), }; if (req->sdiag_family == AF_INET) { @@ -447,6 +454,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, .skb = skb, .cb = cb, .r = r, + .net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN), }; /* eps hashtable dumps diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 8c77b87..79dd660 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -253,7 +253,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, num_types = sp->pf->supported_addrs(sp, types); chunksize = sizeof(init) + addrs_len; - chunksize += WORD_ROUND(SCTP_SAT_LEN(num_types)); + chunksize += SCTP_PAD4(SCTP_SAT_LEN(num_types)); chunksize += sizeof(ecap_param); if (asoc->prsctp_enable) @@ -283,14 +283,14 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, /* Add HMACS parameter length if any were defined */ auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; if (auth_hmacs->length) - chunksize += WORD_ROUND(ntohs(auth_hmacs->length)); + chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; if (auth_chunks->length) - chunksize += WORD_ROUND(ntohs(auth_chunks->length)); + chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; @@ -300,8 +300,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, /* If we have any extensions to report, account for that */ if (num_ext) - chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) + - num_ext); + chunksize += SCTP_PAD4(sizeof(sctp_supported_ext_param_t) + + num_ext); /* RFC 2960 3.3.2 Initiation (INIT) (1) * @@ -443,13 +443,13 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; if (auth_hmacs->length) - chunksize += WORD_ROUND(ntohs(auth_hmacs->length)); + chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; if (auth_chunks->length) - chunksize += WORD_ROUND(ntohs(auth_chunks->length)); + chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; @@ -458,8 +458,8 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, } if (num_ext) - chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) + - num_ext); + chunksize += SCTP_PAD4(sizeof(sctp_supported_ext_param_t) + + num_ext); /* Now allocate and fill out the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_INIT_ACK, 0, chunksize, gfp); @@ -1390,7 +1390,7 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, struct sock *sk; /* No need to allocate LL here, as this is only a chunk. */ - skb = alloc_skb(WORD_ROUND(sizeof(sctp_chunkhdr_t) + paylen), gfp); + skb = alloc_skb(SCTP_PAD4(sizeof(sctp_chunkhdr_t) + paylen), gfp); if (!skb) goto nodata; @@ -1482,7 +1482,7 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) void *target; void *padding; int chunklen = ntohs(chunk->chunk_hdr->length); - int padlen = WORD_ROUND(chunklen) - chunklen; + int padlen = SCTP_PAD4(chunklen) - chunklen; padding = skb_put(chunk->skb, padlen); target = skb_put(chunk->skb, len); @@ -1900,7 +1900,7 @@ static int sctp_process_missing_param(const struct sctp_association *asoc, struct __sctp_missing report; __u16 len; - len = WORD_ROUND(sizeof(report)); + len = SCTP_PAD4(sizeof(report)); /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. @@ -2098,9 +2098,9 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, if (*errp) { if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, - WORD_ROUND(ntohs(param.p->length)))) + SCTP_PAD4(ntohs(param.p->length)))) sctp_addto_chunk_fixed(*errp, - WORD_ROUND(ntohs(param.p->length)), + SCTP_PAD4(ntohs(param.p->length)), param.v); } else { /* If there is no memory for generating the ERROR diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 12d4519..c345bf1 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1020,19 +1020,13 @@ static void sctp_cmd_t1_timer_update(struct sctp_association *asoc, * This way the whole message is queued up and bundling if * encouraged for small fragments. */ -static int sctp_cmd_send_msg(struct sctp_association *asoc, - struct sctp_datamsg *msg, gfp_t gfp) +static void sctp_cmd_send_msg(struct sctp_association *asoc, + struct sctp_datamsg *msg, gfp_t gfp) { struct sctp_chunk *chunk; - int error = 0; - - list_for_each_entry(chunk, &msg->chunks, frag_list) { - error = sctp_outq_tail(&asoc->outqueue, chunk, gfp); - if (error) - break; - } - return error; + list_for_each_entry(chunk, &msg->chunks, frag_list) + sctp_outq_tail(&asoc->outqueue, chunk, gfp); } @@ -1427,8 +1421,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, local_cork = 1; } /* Send a chunk to our peer. */ - error = sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk, - gfp); + sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk, gfp); break; case SCTP_CMD_SEND_PKT: @@ -1682,7 +1675,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_FORCE_PRIM_RETRAN: t = asoc->peer.retran_path; asoc->peer.retran_path = asoc->peer.primary_path; - error = sctp_outq_uncork(&asoc->outqueue, gfp); + sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; asoc->peer.retran_path = t; break; @@ -1709,7 +1702,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_outq_cork(&asoc->outqueue); local_cork = 1; } - error = sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); + sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); break; case SCTP_CMD_SEND_NEXT_ASCONF: sctp_cmd_send_asconf(asoc); @@ -1739,9 +1732,9 @@ out: */ if (asoc && SCTP_EVENT_T_CHUNK == event_type && chunk) { if (chunk->end_of_packet || chunk->singleton) - error = sctp_outq_uncork(&asoc->outqueue, gfp); + sctp_outq_uncork(&asoc->outqueue, gfp); } else if (local_cork) - error = sctp_outq_uncork(&asoc->outqueue, gfp); + sctp_outq_uncork(&asoc->outqueue, gfp); if (sp->data_ready_signalled) sp->data_ready_signalled = 0; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index d88bb2b..026e3bc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3454,7 +3454,7 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, } /* Report violation if chunk len overflows */ - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4185,7 +4185,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length)), + SCTP_PAD4(ntohs(hdr->length)), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, @@ -4203,7 +4203,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length)), + SCTP_PAD4(ntohs(hdr->length)), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9fc417a..6cdc61c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1958,6 +1958,8 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* Now send the (possibly) fragmented message. */ list_for_each_entry(chunk, &datamsg->chunks, frag_list) { + sctp_chunk_hold(chunk); + /* Do accounting for the write space. */ sctp_set_owner_w(chunk); @@ -1970,13 +1972,15 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) * breaks. */ err = sctp_primitive_SEND(net, asoc, datamsg); - sctp_datamsg_put(datamsg); /* Did the lower layer accept the chunk? */ - if (err) + if (err) { + sctp_datamsg_free(datamsg); goto out_free; + } pr_debug("%s: we sent primitively\n", __func__); + sctp_datamsg_put(datamsg); err = msg_len; if (unlikely(wait_connect)) { diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 81b8667..ce54dce 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -233,7 +233,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) } if (transport->dst) { - transport->pathmtu = WORD_TRUNC(dst_mtu(transport->dst)); + transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); } else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -287,7 +287,7 @@ void sctp_transport_route(struct sctp_transport *transport, return; } if (transport->dst) { - transport->pathmtu = WORD_TRUNC(dst_mtu(transport->dst)); + transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); /* Initialize sk->sk_rcv_saddr, if the transport is the * association's active path for getsockname(). diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index d85b803..bea0005 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -383,7 +383,7 @@ sctp_ulpevent_make_remote_error(const struct sctp_association *asoc, ch = (sctp_errhdr_t *)(chunk->skb->data); cause = ch->cause; - elen = WORD_ROUND(ntohs(ch->length)) - sizeof(sctp_errhdr_t); + elen = SCTP_PAD4(ntohs(ch->length)) - sizeof(sctp_errhdr_t); /* Pull off the ERROR header. */ skb_pull(chunk->skb, sizeof(sctp_errhdr_t)); @@ -688,7 +688,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, * MUST ignore the padding bytes. */ len = ntohs(chunk->chunk_hdr->length); - padding = WORD_ROUND(len) - len; + padding = SCTP_PAD4(len) - len; /* Fixup cloned skb with just this chunks data. */ skb_trim(skb, chunk->chunk_end - padding - skb->data); diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 877e550..84d0fda 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -140,11 +140,8 @@ int sctp_clear_pd(struct sock *sk, struct sctp_association *asoc) * we can go ahead and clear out the lobby in one shot */ if (!skb_queue_empty(&sp->pd_lobby)) { - struct list_head *list; skb_queue_splice_tail_init(&sp->pd_lobby, &sk->sk_receive_queue); - list = (struct list_head *)&sctp_sk(sk)->pd_lobby; - INIT_LIST_HEAD(list); return 1; } } else { diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 1d28181..d858202 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -569,9 +569,10 @@ gss_svc_searchbyctx(struct cache_detail *cd, struct xdr_netobj *handle) struct rsc *found; memset(&rsci, 0, sizeof(rsci)); - rsci.handle.data = handle->data; - rsci.handle.len = handle->len; + if (dup_to_netobj(&rsci.handle, handle->data, handle->len)) + return NULL; found = rsc_lookup(cd, &rsci); + rsc_free(&rsci); if (!found) return NULL; if (cache_check(cd, &found->h, NULL)) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 7f79fb7..66f23b3 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -453,7 +453,7 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt_switch *xps; if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xps = args->bc_xprt->xpt_bc_xps; xprt_switch_get(xps); } else { @@ -520,7 +520,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) char servername[48]; if (args->bc_xprt) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xprt = args->bc_xprt->xpt_bc_xprt; if (xprt) { xprt_get(xprt); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 536d0be..799cce6 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -51,6 +51,7 @@ #include <linux/slab.h> #include <linux/prefetch.h> #include <linux/sunrpc/addr.h> +#include <linux/sunrpc/svc_rdma.h> #include <asm/bitops.h> #include <linux/module.h> /* try_module_get()/module_put() */ @@ -923,7 +924,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) } INIT_LIST_HEAD(&buf->rb_recv_bufs); - for (i = 0; i < buf->rb_max_requests; i++) { + for (i = 0; i < buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; i++) { struct rpcrdma_rep *rep; rep = rpcrdma_create_rep(r_xprt); @@ -1018,6 +1019,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) rep = rpcrdma_buffer_get_rep_locked(buf); rpcrdma_destroy_rep(ia, rep); } + buf->rb_send_count = 0; spin_lock(&buf->rb_reqslock); while (!list_empty(&buf->rb_allreqs)) { @@ -1032,6 +1034,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) spin_lock(&buf->rb_reqslock); } spin_unlock(&buf->rb_reqslock); + buf->rb_recv_count = 0; rpcrdma_destroy_mrs(buf); } @@ -1074,8 +1077,27 @@ rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw) spin_unlock(&buf->rb_mwlock); } +static struct rpcrdma_rep * +rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers) +{ + /* If an RPC previously completed without a reply (say, a + * credential problem or a soft timeout occurs) then hold off + * on supplying more Receive buffers until the number of new + * pending RPCs catches up to the number of posted Receives. + */ + if (unlikely(buffers->rb_send_count < buffers->rb_recv_count)) + return NULL; + + if (unlikely(list_empty(&buffers->rb_recv_bufs))) + return NULL; + buffers->rb_recv_count++; + return rpcrdma_buffer_get_rep_locked(buffers); +} + /* * Get a set of request/reply buffers. + * + * Reply buffer (if available) is attached to send buffer upon return. */ struct rpcrdma_req * rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) @@ -1085,21 +1107,15 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) spin_lock(&buffers->rb_lock); if (list_empty(&buffers->rb_send_bufs)) goto out_reqbuf; + buffers->rb_send_count++; req = rpcrdma_buffer_get_req_locked(buffers); - if (list_empty(&buffers->rb_recv_bufs)) - goto out_repbuf; - req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers); + req->rl_reply = rpcrdma_buffer_get_rep(buffers); spin_unlock(&buffers->rb_lock); return req; out_reqbuf: spin_unlock(&buffers->rb_lock); - pr_warn("rpcrdma: out of request buffers (%p)\n", buffers); - return NULL; -out_repbuf: - list_add(&req->rl_free, &buffers->rb_send_bufs); - spin_unlock(&buffers->rb_lock); - pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers); + pr_warn("RPC: %s: out of request buffers\n", __func__); return NULL; } @@ -1117,9 +1133,12 @@ rpcrdma_buffer_put(struct rpcrdma_req *req) req->rl_reply = NULL; spin_lock(&buffers->rb_lock); + buffers->rb_send_count--; list_add_tail(&req->rl_free, &buffers->rb_send_bufs); - if (rep) + if (rep) { + buffers->rb_recv_count--; list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); + } spin_unlock(&buffers->rb_lock); } @@ -1133,8 +1152,7 @@ rpcrdma_recv_buffer_get(struct rpcrdma_req *req) struct rpcrdma_buffer *buffers = req->rl_buffer; spin_lock(&buffers->rb_lock); - if (!list_empty(&buffers->rb_recv_bufs)) - req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers); + req->rl_reply = rpcrdma_buffer_get_rep(buffers); spin_unlock(&buffers->rb_lock); } @@ -1148,6 +1166,7 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf; spin_lock(&buffers->rb_lock); + buffers->rb_recv_count--; list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); spin_unlock(&buffers->rb_lock); } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 670fad5..a71b0f5 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -321,6 +321,7 @@ struct rpcrdma_buffer { char *rb_pool; spinlock_t rb_lock; /* protect buf lists */ + int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; u32 rb_max_requests; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8ede3bc..bf16883 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1074,7 +1074,7 @@ static void xs_udp_data_receive(struct sock_xprt *transport) skb = skb_recv_datagram(sk, 0, 1, &err); if (skb != NULL) { xs_udp_data_read_skb(&transport->xprt, sk, skb); - skb_free_datagram(sk, skb); + skb_free_datagram_locked(sk, skb); continue; } if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 6b626a6..a04fe9b 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -62,6 +62,8 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message + * + * The buffer returned is of size INT_H_SIZE + payload size */ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) @@ -141,9 +143,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list, struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) * - ITEM_SIZE; - uint msg_rem = msg_dsz; + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + u32 msg_rem = msg_dsz; list_for_each_entry(publ, pls, local_list) { /* Prepare next buffer: */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index dd27468..d80cd3f 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -665,7 +665,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) { pr_err("Invalid UDP bearer configuration"); - return -EINVAL; + err = -EINVAL; + goto err; } err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_LOCAL], &local, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f1dffe8..8309687 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -661,11 +661,11 @@ static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - if (mutex_lock_interruptible(&u->readlock)) + if (mutex_lock_interruptible(&u->iolock)) return -EINTR; sk->sk_peek_off = val; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); return 0; } @@ -779,7 +779,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) spin_lock_init(&u->lock); atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); - mutex_init(&u->readlock); /* single task reading lock */ + mutex_init(&u->iolock); /* single task reading lock */ + mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound(sk), sk); @@ -848,7 +849,7 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) return err; @@ -895,7 +896,7 @@ retry: spin_unlock(&unix_table_lock); err = 0; -out: mutex_unlock(&u->readlock); +out: mutex_unlock(&u->bindlock); return err; } @@ -954,20 +955,32 @@ fail: return NULL; } -static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode, - struct path *res) +static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) { - int err; + struct dentry *dentry; + struct path path; + int err = 0; + /* + * Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + return err; - err = security_path_mknod(path, dentry, mode, 0); + /* + * All right, let's create it. + */ + err = security_path_mknod(&path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0); + err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); if (!err) { - res->mnt = mntget(path->mnt); + res->mnt = mntget(path.mnt); res->dentry = dget(dentry); } } - + done_path_create(&path, dentry); return err; } @@ -978,12 +991,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err, name_err; + int err; unsigned int hash; struct unix_address *addr; struct hlist_head *list; - struct path path; - struct dentry *dentry; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -999,34 +1010,14 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - name_err = 0; - dentry = NULL; - if (sun_path[0]) { - /* Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - - if (IS_ERR(dentry)) { - /* delay report until after 'already bound' check */ - name_err = PTR_ERR(dentry); - dentry = NULL; - } - } - - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) - goto out_path; + goto out; err = -EINVAL; if (u->addr) goto out_up; - if (name_err) { - err = name_err == -EEXIST ? -EADDRINUSE : name_err; - goto out_up; - } - err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1037,11 +1028,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr->hash = hash ^ sk->sk_type; atomic_set(&addr->refcnt, 1); - if (dentry) { - struct path u_path; + if (sun_path[0]) { + struct path path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(dentry, &path, mode, &u_path); + err = unix_mknod(sun_path, mode, &path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1049,9 +1040,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = u_path; + u->path = path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1073,11 +1064,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) out_unlock: spin_unlock(&unix_table_lock); out_up: - mutex_unlock(&u->readlock); -out_path: - if (dentry) - done_path_create(&path, dentry); - + mutex_unlock(&u->bindlock); out: return err; } @@ -1969,17 +1956,17 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, &err, 0); if (!newskb) goto err; } - /* we must acquire readlock as we modify already present + /* we must acquire iolock as we modify already present * skbs in the sk_receive_queue and mess with skb->len */ - err = mutex_lock_interruptible(&unix_sk(other)->readlock); + err = mutex_lock_interruptible(&unix_sk(other)->iolock); if (err) { err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; goto err; @@ -2046,7 +2033,7 @@ alloc_skb: } unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); other->sk_data_ready(other); scm_destroy(&scm); @@ -2055,7 +2042,7 @@ alloc_skb: err_state_unlock: unix_state_unlock(other); err_unlock: - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); err: kfree_skb(newskb); if (send_sigpipe && !(flags & MSG_NOSIGNAL)) @@ -2123,7 +2110,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err, @@ -2131,14 +2118,14 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (skb) break; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (err != -EAGAIN) break; } while (timeo && !__skb_wait_for_more_packets(sk, &err, &timeo, last)); - if (!skb) { /* implies readlock unlocked */ + if (!skb) { /* implies iolock unlocked */ unix_state_lock(sk); /* Signal EOF on disconnected non-blocking SEQPACKET socket. */ if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN && @@ -2203,7 +2190,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, out_free: skb_free_datagram(sk, skb); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); out: return err; } @@ -2298,7 +2285,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2340,7 +2327,7 @@ again: break; } - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, last_len); @@ -2351,7 +2338,7 @@ again: goto out; } - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); @@ -2454,7 +2441,7 @@ unlock: } } while (size); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (state->msg) scm_recv(sock, state->msg, &scm, flags); else @@ -2495,9 +2482,9 @@ static ssize_t skb_unix_socket_splice(struct sock *sk, int ret; struct unix_sock *u = unix_sk(sk); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); ret = splice_to_pipe(pipe, spd); - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); return ret; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 2029b49..4911cd9 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1252,7 +1252,7 @@ static int __init cfg80211_init(void) if (err) goto out_fail_reg; - cfg80211_wq = create_singlethread_workqueue("cfg80211"); + cfg80211_wq = alloc_ordered_workqueue("cfg80211", WQ_MEM_RECLAIM); if (!cfg80211_wq) { err = -ENOMEM; goto out_fail_wq; diff --git a/net/wireless/core.h b/net/wireless/core.h index eee9144..5555e3c 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -249,9 +249,9 @@ struct cfg80211_event { }; struct cfg80211_cached_keys { - struct key_params params[6]; - u8 data[6][WLAN_MAX_KEY_LEN]; - int def, defmgmt; + struct key_params params[4]; + u8 data[4][WLAN_KEY_LEN_WEP104]; + int def; }; enum cfg80211_chan_mode { diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 4a4dda5..eafdfa5 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -114,6 +114,9 @@ static int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, } } + if (WARN_ON(connkeys && connkeys->def < 0)) + return -EINVAL; + if (WARN_ON(wdev->connect_keys)) kzfree(wdev->connect_keys); wdev->connect_keys = connkeys; @@ -284,18 +287,16 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, if (!netif_running(wdev->netdev)) return 0; - if (wdev->wext.keys) { + if (wdev->wext.keys) wdev->wext.keys->def = wdev->wext.default_key; - wdev->wext.keys->defmgmt = wdev->wext.default_mgmt_key; - } wdev->wext.ibss.privacy = wdev->wext.default_key != -1; - if (wdev->wext.keys) { + if (wdev->wext.keys && wdev->wext.keys->def != -1) { ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); if (!ck) return -ENOMEM; - for (i = 0; i < 6; i++) + for (i = 0; i < 4; i++) ck->params[i].key = ck->data[i]; } err = __cfg80211_join_ibss(rdev, wdev->netdev, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index c284d88..d6abb07 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -222,7 +222,7 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, ASSERT_WDEV_LOCK(wdev); if (auth_type == NL80211_AUTHTYPE_SHARED_KEY) - if (!key || !key_len || key_idx < 0 || key_idx > 4) + if (!key || !key_len || key_idx < 0 || key_idx > 3) return -EINVAL; if (wdev->current_bss && diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4997857..fd111e2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -848,13 +848,21 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, struct nlattr *key; struct cfg80211_cached_keys *result; int rem, err, def = 0; + bool have_key = false; + + nla_for_each_nested(key, keys, rem) { + have_key = true; + break; + } + + if (!have_key) + return NULL; result = kzalloc(sizeof(*result), GFP_KERNEL); if (!result) return ERR_PTR(-ENOMEM); result->def = -1; - result->defmgmt = -1; nla_for_each_nested(key, keys, rem) { memset(&parse, 0, sizeof(parse)); @@ -866,7 +874,7 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, err = -EINVAL; if (!parse.p.key) goto error; - if (parse.idx < 0 || parse.idx > 4) + if (parse.idx < 0 || parse.idx > 3) goto error; if (parse.def) { if (def) @@ -881,16 +889,24 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, parse.idx, false, NULL); if (err) goto error; + if (parse.p.cipher != WLAN_CIPHER_SUITE_WEP40 && + parse.p.cipher != WLAN_CIPHER_SUITE_WEP104) { + err = -EINVAL; + goto error; + } result->params[parse.idx].cipher = parse.p.cipher; result->params[parse.idx].key_len = parse.p.key_len; result->params[parse.idx].key = result->data[parse.idx]; memcpy(result->data[parse.idx], parse.p.key, parse.p.key_len); - if (parse.p.cipher == WLAN_CIPHER_SUITE_WEP40 || - parse.p.cipher == WLAN_CIPHER_SUITE_WEP104) { - if (no_ht) - *no_ht = true; - } + /* must be WEP key if we got here */ + if (no_ht) + *no_ht = true; + } + + if (result->def < 0) { + err = -EINVAL; + goto error; } return result; @@ -2525,10 +2541,35 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * int if_idx = 0; int wp_start = cb->args[0]; int if_start = cb->args[1]; + int filter_wiphy = -1; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; rtnl_lock(); + if (!cb->args[2]) { + struct nl80211_dump_wiphy_state state = { + .filter_wiphy = -1, + }; + int ret; + + ret = nl80211_dump_wiphy_parse(skb, cb, &state); + if (ret) + return ret; + + filter_wiphy = state.filter_wiphy; + + /* + * if filtering, set cb->args[2] to +1 since 0 is the default + * value needed to determine that parsing is necessary. + */ + if (filter_wiphy >= 0) + cb->args[2] = filter_wiphy + 1; + else + cb->args[2] = -1; + } else if (cb->args[2] > 0) { + filter_wiphy = cb->args[2] - 1; + } + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { if (!net_eq(wiphy_net(&rdev->wiphy), sock_net(skb->sk))) continue; @@ -2536,6 +2577,10 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * wp_idx++; continue; } + + if (filter_wiphy >= 0 && filter_wiphy != rdev->wiphy_idx) + continue; + if_idx = 0; list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { @@ -6969,7 +7014,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) params.n_counter_offsets_presp = len / sizeof(u16); if (rdev->wiphy.max_num_csa_counters && - (params.n_counter_offsets_beacon > + (params.n_counter_offsets_presp > rdev->wiphy.max_num_csa_counters)) return -EINVAL; @@ -7359,7 +7404,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) (key.p.cipher != WLAN_CIPHER_SUITE_WEP104 || key.p.key_len != WLAN_KEY_LEN_WEP104)) return -EINVAL; - if (key.idx > 4) + if (key.idx > 3) return -EINVAL; } else { key.p.key_len = 0; @@ -7977,6 +8022,8 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, } data = nla_nest_start(skb, attr); + if (!data) + goto nla_put_failure; ((void **)skb->cb)[0] = rdev; ((void **)skb->cb)[1] = hdr; @@ -9406,18 +9453,27 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (!freqs) return -ENOBUFS; - for (i = 0; i < req->n_channels; i++) - nla_put_u32(msg, i, req->channels[i]->center_freq); + for (i = 0; i < req->n_channels; i++) { + if (nla_put_u32(msg, i, req->channels[i]->center_freq)) + return -ENOBUFS; + } nla_nest_end(msg, freqs); if (req->n_match_sets) { matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH); + if (!matches) + return -ENOBUFS; + for (i = 0; i < req->n_match_sets; i++) { match = nla_nest_start(msg, i); - nla_put(msg, NL80211_SCHED_SCAN_MATCH_ATTR_SSID, - req->match_sets[i].ssid.ssid_len, - req->match_sets[i].ssid.ssid); + if (!match) + return -ENOBUFS; + + if (nla_put(msg, NL80211_SCHED_SCAN_MATCH_ATTR_SSID, + req->match_sets[i].ssid.ssid_len, + req->match_sets[i].ssid.ssid)) + return -ENOBUFS; nla_nest_end(msg, match); } nla_nest_end(msg, matches); @@ -9429,6 +9485,9 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, for (i = 0; i < req->n_scan_plans; i++) { scan_plan = nla_nest_start(msg, i + 1); + if (!scan_plan) + return -ENOBUFS; + if (!scan_plan || nla_put_u32(msg, NL80211_SCHED_SCAN_PLAN_INTERVAL, req->scan_plans[i].interval) || diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0358e12..b5bd58d 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -352,52 +352,48 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *rdev) __cfg80211_bss_expire(rdev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE); } -const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len) +const u8 *cfg80211_find_ie_match(u8 eid, const u8 *ies, int len, + const u8 *match, int match_len, + int match_offset) { - while (len > 2 && ies[0] != eid) { + /* match_offset can't be smaller than 2, unless match_len is + * zero, in which case match_offset must be zero as well. + */ + if (WARN_ON((match_len && match_offset < 2) || + (!match_len && match_offset))) + return NULL; + + while (len >= 2 && len >= ies[1] + 2) { + if ((ies[0] == eid) && + (ies[1] + 2 >= match_offset + match_len) && + !memcmp(ies + match_offset, match, match_len)) + return ies; + len -= ies[1] + 2; ies += ies[1] + 2; } - if (len < 2) - return NULL; - if (len < 2 + ies[1]) - return NULL; - return ies; + + return NULL; } -EXPORT_SYMBOL(cfg80211_find_ie); +EXPORT_SYMBOL(cfg80211_find_ie_match); const u8 *cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, int len) { - struct ieee80211_vendor_ie *ie; - const u8 *pos = ies, *end = ies + len; - int ie_oui; + const u8 *ie; + u8 match[] = { oui >> 16, oui >> 8, oui, oui_type }; + int match_len = (oui_type < 0) ? 3 : sizeof(match); if (WARN_ON(oui_type > 0xff)) return NULL; - while (pos < end) { - pos = cfg80211_find_ie(WLAN_EID_VENDOR_SPECIFIC, pos, - end - pos); - if (!pos) - return NULL; - - ie = (struct ieee80211_vendor_ie *)pos; - - /* make sure we can access ie->len */ - BUILD_BUG_ON(offsetof(struct ieee80211_vendor_ie, len) != 1); + ie = cfg80211_find_ie_match(WLAN_EID_VENDOR_SPECIFIC, ies, len, + match, match_len, 2); - if (ie->len < sizeof(*ie)) - goto cont; + if (ie && (ie[1] < 4)) + return NULL; - ie_oui = ie->oui[0] << 16 | ie->oui[1] << 8 | ie->oui[2]; - if (ie_oui == oui && - (oui_type < 0 || ie->oui_type == oui_type)) - return pos; -cont: - pos += 2 + ie->len; - } - return NULL; + return ie; } EXPORT_SYMBOL(cfg80211_find_vendor_ie); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index add6824..c08a3b5 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1043,6 +1043,9 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, connect->crypto.ciphers_pairwise[0] = cipher; } } + } else { + if (WARN_ON(connkeys)) + return -EINVAL; } wdev->connect_keys = connkeys; diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index e46469b..0082f4b 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -57,7 +57,7 @@ static ssize_t addresses_show(struct device *dev, return sprintf(buf, "%pM\n", wiphy->perm_addr); for (i = 0; i < wiphy->n_addresses; i++) - buf += sprintf(buf, "%pM\n", &wiphy->addresses[i].addr); + buf += sprintf(buf, "%pM\n", wiphy->addresses[i].addr); return buf - start; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 0675f51..9e6e2aa 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -218,7 +218,7 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx > 5) + if (key_idx < 0 || key_idx > 5) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) @@ -249,7 +249,13 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, /* Disallow BIP (group-only) cipher as pairwise cipher */ if (pairwise) return -EINVAL; + if (key_idx < 4) + return -EINVAL; break; + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + if (key_idx > 3) + return -EINVAL; default: break; } @@ -906,7 +912,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) if (!wdev->connect_keys) return; - for (i = 0; i < 6; i++) { + for (i = 0; i < 4; i++) { if (!wdev->connect_keys->params[i].cipher) continue; if (rdev_add_key(rdev, dev, i, false, NULL, @@ -919,9 +925,6 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) netdev_err(dev, "failed to set defkey %d\n", i); continue; } - if (wdev->connect_keys->defmgmt == i) - if (rdev_set_default_mgmt_key(rdev, dev, i)) - netdev_err(dev, "failed to set mgtdef %d\n", i); } kzfree(wdev->connect_keys); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 9f27221..7b97d43 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -408,10 +408,10 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (!wdev->wext.keys) { wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), - GFP_KERNEL); + GFP_KERNEL); if (!wdev->wext.keys) return -ENOMEM; - for (i = 0; i < 6; i++) + for (i = 0; i < 4; i++) wdev->wext.keys->params[i].key = wdev->wext.keys->data[i]; } @@ -460,7 +460,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (err == -ENOENT) err = 0; if (!err) { - if (!addr) { + if (!addr && idx < 4) { memset(wdev->wext.keys->data[idx], 0, sizeof(wdev->wext.keys->data[idx])); wdev->wext.keys->params[idx].key_len = 0; @@ -487,6 +487,9 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, err = 0; if (wdev->current_bss) err = rdev_add_key(rdev, dev, idx, pairwise, addr, params); + else if (params->cipher != WLAN_CIPHER_SUITE_WEP40 && + params->cipher != WLAN_CIPHER_SUITE_WEP104) + return -EINVAL; if (err) return err; diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index dbb2738e..6250b1c 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -958,29 +958,8 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, return private(dev, iwr, cmd, info, handler); } /* Old driver API : call driver ioctl handler */ - if (dev->netdev_ops->ndo_do_ioctl) { -#ifdef CONFIG_COMPAT - if (info->flags & IW_REQUEST_FLAG_COMPAT) { - int ret = 0; - struct iwreq iwr_lcl; - struct compat_iw_point *iwp_compat = (void *) &iwr->u.data; - - memcpy(&iwr_lcl, iwr, sizeof(struct iwreq)); - iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer); - iwr_lcl.u.data.length = iwp_compat->length; - iwr_lcl.u.data.flags = iwp_compat->flags; - - ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd); - - iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer); - iwp_compat->length = iwr_lcl.u.data.length; - iwp_compat->flags = iwr_lcl.u.data.flags; - - return ret; - } else -#endif - return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); - } + if (dev->netdev_ops->ndo_do_ioctl) + return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); return -EOPNOTSUPP; } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index a4e8af3..88f1f69 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -35,7 +35,6 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, if (wdev->wext.keys) { wdev->wext.keys->def = wdev->wext.default_key; - wdev->wext.keys->defmgmt = wdev->wext.default_mgmt_key; if (wdev->wext.default_key != -1) wdev->wext.connect.privacy = true; } @@ -43,11 +42,11 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, if (!wdev->wext.connect.ssid_len) return 0; - if (wdev->wext.keys) { + if (wdev->wext.keys && wdev->wext.keys->def != -1) { ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); if (!ck) return -ENOMEM; - for (i = 0; i < 6; i++) + for (i = 0; i < 4; i++) ck->params[i].key = ck->data[i]; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a750f33..f83b74d 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1500,12 +1500,8 @@ out_fac_release: goto out_dtefac_release; if (dtefacs.calling_len > X25_MAX_AE_LEN) goto out_dtefac_release; - if (dtefacs.calling_ae == NULL) - goto out_dtefac_release; if (dtefacs.called_len > X25_MAX_AE_LEN) goto out_dtefac_release; - if (dtefacs.called_ae == NULL) - goto out_dtefac_release; x25->dte_facilities = dtefacs; rc = 0; out_dtefac_release: diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 250e567..44ac85f 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -17,7 +17,7 @@ #include <linux/crypto.h> #include <linux/scatterlist.h> #include <net/xfrm.h> -#if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE) +#if IS_ENABLED(CONFIG_INET_ESP) || IS_ENABLED(CONFIG_INET6_ESP) #include <net/esp.h> #endif diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1c4ad47..6e3f025 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -207,15 +207,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) family = XFRM_SPI_SKB_CB(skb)->family; /* if tunnel is present override skb->mark value with tunnel i_key */ - if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) { - switch (family) { - case AF_INET: + switch (family) { + case AF_INET: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); - break; - case AF_INET6: + break; + case AF_INET6: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); - break; - } + break; } /* Allocate new secpath or COW existing one. */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b5e665b..fd69866 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -49,6 +49,7 @@ static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; static struct kmem_cache *xfrm_dst_cache __read_mostly; +static __read_mostly seqcount_t xfrm_policy_hash_generation; static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); @@ -59,6 +60,11 @@ static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); +static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) +{ + return atomic_inc_not_zero(&policy->refcnt); +} + static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { @@ -385,9 +391,11 @@ static struct hlist_head *policy_hash_bysel(struct net *net, __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __sel_hash(sel, family, hmask, dbits, sbits); - return (hash == hmask + 1 ? - &net->xfrm.policy_inexact[dir] : - net->xfrm.policy_bydst[dir].table + hash); + if (hash == hmask + 1) + return &net->xfrm.policy_inexact[dir]; + + return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, + lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static struct hlist_head *policy_hash_direct(struct net *net, @@ -403,7 +411,8 @@ static struct hlist_head *policy_hash_direct(struct net *net, __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits); - return net->xfrm.policy_bydst[dir].table + hash; + return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, + lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static void xfrm_dst_hash_transfer(struct net *net, @@ -426,14 +435,14 @@ redo: h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask, dbits, sbits); if (!entry0) { - hlist_del(&pol->bydst); - hlist_add_head(&pol->bydst, ndsttable+h); + hlist_del_rcu(&pol->bydst); + hlist_add_head_rcu(&pol->bydst, ndsttable + h); h0 = h; } else { if (h != h0) continue; - hlist_del(&pol->bydst); - hlist_add_behind(&pol->bydst, entry0); + hlist_del_rcu(&pol->bydst); + hlist_add_behind_rcu(&pol->bydst, entry0); } entry0 = &pol->bydst; } @@ -468,22 +477,32 @@ static void xfrm_bydst_resize(struct net *net, int dir) unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); - struct hlist_head *odst = net->xfrm.policy_bydst[dir].table; struct hlist_head *ndst = xfrm_hash_alloc(nsize); + struct hlist_head *odst; int i; if (!ndst) return; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); + write_seqcount_begin(&xfrm_policy_hash_generation); + + odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, + lockdep_is_held(&net->xfrm.xfrm_policy_lock)); + + odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, + lockdep_is_held(&net->xfrm.xfrm_policy_lock)); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir); - net->xfrm.policy_bydst[dir].table = ndst; + rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + write_seqcount_end(&xfrm_policy_hash_generation); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + + synchronize_rcu(); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } @@ -500,7 +519,7 @@ static void xfrm_byidx_resize(struct net *net, int total) if (!nidx) return; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); @@ -508,7 +527,7 @@ static void xfrm_byidx_resize(struct net *net, int total) net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } @@ -541,7 +560,6 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total) void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { - read_lock_bh(&net->xfrm.xfrm_policy_lock); si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; @@ -550,7 +568,6 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; - read_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_spd_getinfo); @@ -600,7 +617,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) rbits6 = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); /* reset the bydst and inexact table in all directions */ for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { @@ -626,6 +643,10 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + /* skip socket policies */ + continue; + } newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, @@ -642,7 +663,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) hlist_add_head(&policy->bydst, chain); } - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); } @@ -753,7 +774,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct hlist_head *chain; struct hlist_node *newpos; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; @@ -764,7 +785,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) { - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return -EEXIST; } delpol = pol; @@ -800,7 +821,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); @@ -820,7 +841,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, struct hlist_head *chain; *err = 0; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; hlist_for_each_entry(pol, chain, bydst) { @@ -833,7 +854,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -842,7 +863,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -861,7 +882,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, return NULL; *err = 0; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { @@ -872,7 +893,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -881,7 +902,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -939,7 +960,7 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) @@ -955,14 +976,14 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again1; } @@ -974,13 +995,13 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again2; } } @@ -989,7 +1010,7 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) if (!cnt) err = -ESRCH; out: - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); @@ -1009,7 +1030,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else @@ -1037,7 +1058,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, } list_del_init(&walk->walk.all); out: - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); @@ -1056,9 +1077,9 @@ void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) if (list_empty(&walk->walk.all)) return; - write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ + spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); @@ -1096,17 +1117,24 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, struct xfrm_policy *pol, *ret; const xfrm_address_t *daddr, *saddr; struct hlist_head *chain; - u32 priority = ~0U; + unsigned int sequence; + u32 priority; daddr = xfrm_flowi_daddr(fl, family); saddr = xfrm_flowi_saddr(fl, family); if (unlikely(!daddr || !saddr)) return NULL; - read_lock_bh(&net->xfrm.xfrm_policy_lock); - chain = policy_hash_direct(net, daddr, saddr, family, dir); + rcu_read_lock(); + retry: + do { + sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + chain = policy_hash_direct(net, daddr, saddr, family, dir); + } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + + priority = ~0U; ret = NULL; - hlist_for_each_entry(pol, chain, bydst) { + hlist_for_each_entry_rcu(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -1122,7 +1150,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } } chain = &net->xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, chain, bydst) { + hlist_for_each_entry_rcu(pol, chain, bydst) { if ((pol->priority >= priority) && ret) break; @@ -1140,9 +1168,13 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } } - xfrm_pol_hold(ret); + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + goto retry; + + if (ret && !xfrm_pol_hold_rcu(ret)) + goto retry; fail: - read_unlock_bh(&net->xfrm.xfrm_policy_lock); + rcu_read_unlock(); return ret; } @@ -1219,10 +1251,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl) { struct xfrm_policy *pol; - struct net *net = sock_net(sk); rcu_read_lock(); - read_lock_bh(&net->xfrm.xfrm_policy_lock); + again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { bool match = xfrm_selector_match(&pol->selector, fl, @@ -1237,8 +1268,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, policy_to_flow_dir(dir)); - if (!err) - xfrm_pol_hold(pol); + if (!err && !xfrm_pol_hold_rcu(pol)) + goto again; else if (err == -ESRCH) pol = NULL; else @@ -1247,7 +1278,6 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, pol = NULL; } out: - read_unlock_bh(&net->xfrm.xfrm_policy_lock); rcu_read_unlock(); return pol; } @@ -1271,7 +1301,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { - hlist_del(&pol->bydst); + hlist_del_rcu(&pol->bydst); hlist_del(&pol->byidx); } @@ -1295,9 +1325,9 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; @@ -1316,7 +1346,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return -EINVAL; #endif - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { @@ -1334,7 +1364,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) */ xfrm_sk_policy_unlink(old_pol, dir); } - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); @@ -1364,9 +1394,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->type = old->type; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); - write_lock_bh(&net->xfrm.xfrm_policy_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); xfrm_sk_policy_link(newp, dir); - write_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; @@ -3048,7 +3078,7 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); - rwlock_init(&net->xfrm.xfrm_policy_lock); + spin_lock_init(&net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); return 0; @@ -3082,6 +3112,7 @@ static struct pernet_operations __net_initdata xfrm_net_ops = { void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); + seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); } @@ -3179,7 +3210,7 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * struct hlist_head *chain; u32 priority = ~0U; - read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/ + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && @@ -3203,7 +3234,7 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * xfrm_pol_hold(ret); - read_unlock_bh(&net->xfrm.xfrm_policy_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 4fd725a..cdc2e2e 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -558,7 +558,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) x->repl->notify(x, XFRM_REPLAY_UPDATE); } -static struct xfrm_replay xfrm_replay_legacy = { +static const struct xfrm_replay xfrm_replay_legacy = { .advance = xfrm_replay_advance, .check = xfrm_replay_check, .recheck = xfrm_replay_check, @@ -566,7 +566,7 @@ static struct xfrm_replay xfrm_replay_legacy = { .overflow = xfrm_replay_overflow, }; -static struct xfrm_replay xfrm_replay_bmp = { +static const struct xfrm_replay xfrm_replay_bmp = { .advance = xfrm_replay_advance_bmp, .check = xfrm_replay_check_bmp, .recheck = xfrm_replay_check_bmp, @@ -574,7 +574,7 @@ static struct xfrm_replay xfrm_replay_bmp = { .overflow = xfrm_replay_overflow_bmp, }; -static struct xfrm_replay xfrm_replay_esn = { +static const struct xfrm_replay xfrm_replay_esn = { .advance = xfrm_replay_advance_esn, .check = xfrm_replay_check_esn, .recheck = xfrm_replay_recheck_esn, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9895a8c..419bf5d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -28,6 +28,11 @@ #include "xfrm_hash.h" +#define xfrm_state_deref_prot(table, net) \ + rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) + +static void xfrm_state_gc_task(struct work_struct *work); + /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) @@ -36,6 +41,15 @@ */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; +static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); + +static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); +static HLIST_HEAD(xfrm_state_gc_list); + +static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) +{ + return atomic_inc_not_zero(&x->refcnt); +} static inline unsigned int xfrm_dst_hash(struct net *net, const xfrm_address_t *daddr, @@ -76,18 +90,18 @@ static void xfrm_hash_transfer(struct hlist_head *list, h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); - hlist_add_head(&x->bydst, ndsttable+h); + hlist_add_head_rcu(&x->bydst, ndsttable + h); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); - hlist_add_head(&x->bysrc, nsrctable+h); + hlist_add_head_rcu(&x->bysrc, nsrctable + h); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); - hlist_add_head(&x->byspi, nspitable+h); + hlist_add_head_rcu(&x->byspi, nspitable + h); } } } @@ -122,25 +136,29 @@ static void xfrm_hash_resize(struct work_struct *work) } spin_lock_bh(&net->xfrm.xfrm_state_lock); + write_seqcount_begin(&xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; + odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) - xfrm_hash_transfer(net->xfrm.state_bydst+i, ndst, nsrc, nspi, - nhashmask); + xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask); - odst = net->xfrm.state_bydst; - osrc = net->xfrm.state_bysrc; - ospi = net->xfrm.state_byspi; + osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); + ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); ohashmask = net->xfrm.state_hmask; - net->xfrm.state_bydst = ndst; - net->xfrm.state_bysrc = nsrc; - net->xfrm.state_byspi = nspi; + rcu_assign_pointer(net->xfrm.state_bydst, ndst); + rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); + rcu_assign_pointer(net->xfrm.state_byspi, nspi); net->xfrm.state_hmask = nhashmask; + write_seqcount_end(&xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); + + synchronize_rcu(); + xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); @@ -332,6 +350,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); + kfree(x->aead); kfree(x->aalg); kfree(x->ealg); kfree(x->calg); @@ -355,15 +374,16 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) static void xfrm_state_gc_task(struct work_struct *work) { - struct net *net = container_of(work, struct net, xfrm.state_gc_work); struct xfrm_state *x; struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); - hlist_move_list(&net->xfrm.state_gc_list, &gc_list); + hlist_move_list(&xfrm_state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); + synchronize_rcu(); + hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); } @@ -500,14 +520,12 @@ EXPORT_SYMBOL(xfrm_state_alloc); void __xfrm_state_destroy(struct xfrm_state *x) { - struct net *net = xs_net(x); - WARN_ON(x->km.state != XFRM_STATE_DEAD); spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &net->xfrm.state_gc_list); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&net->xfrm.state_gc_work); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -520,10 +538,10 @@ int __xfrm_state_delete(struct xfrm_state *x) x->km.state = XFRM_STATE_DEAD; spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); - hlist_del(&x->bydst); - hlist_del(&x->bysrc); + hlist_del_rcu(&x->bydst); + hlist_del_rcu(&x->bysrc); if (x->id.spi) - hlist_del(&x->byspi); + hlist_del_rcu(&x->byspi); net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); @@ -659,7 +677,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; - hlist_for_each_entry(x, net->xfrm.state_byspi+h, byspi) { + hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || @@ -668,7 +686,8 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, if ((mark & x->mark.m) != x->mark.v) continue; - xfrm_state_hold(x); + if (!xfrm_state_hold_rcu(x)) + continue; return x; } @@ -683,7 +702,7 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; - hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || @@ -692,7 +711,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, if ((mark & x->mark.m) != x->mark.v) continue; - xfrm_state_hold(x); + if (!xfrm_state_hold_rcu(x)) + continue; return x; } @@ -775,13 +795,16 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; + unsigned int sequence; struct km_event c; to_put = NULL; - spin_lock_bh(&net->xfrm.xfrm_state_lock); + sequence = read_seqcount_begin(&xfrm_state_hash_generation); + + rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -797,7 +820,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, goto found; h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); - hlist_for_each_entry(x, net->xfrm.state_bydst+h_wildcard, bydst) { + hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -850,19 +873,21 @@ found: } if (km_query(x, tmpl, pol) == 0) { + spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); - hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); + hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, daddr, saddr, encap_family); - hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); + hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); - hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); + hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { x->km.state = XFRM_STATE_DEAD; to_put = x; @@ -871,13 +896,26 @@ found: } } out: - if (x) - xfrm_state_hold(x); - else + if (x) { + if (!xfrm_state_hold_rcu(x)) { + *err = -EAGAIN; + x = NULL; + } + } else { *err = acquire_in_progress ? -EAGAIN : error; - spin_unlock_bh(&net->xfrm.xfrm_state_lock); + } + rcu_read_unlock(); if (to_put) xfrm_state_put(to_put); + + if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) { + *err = -EAGAIN; + if (x) { + xfrm_state_put(x); + x = NULL; + } + } + return x; } @@ -945,16 +983,16 @@ static void __xfrm_state_insert(struct xfrm_state *x) h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); - hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); + hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); - hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); + hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); + hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL); @@ -1063,9 +1101,9 @@ static struct xfrm_state *__find_acq_core(struct net *net, xfrm_state_hold(x); tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); list_add(&x->km.all, &net->xfrm.state_all); - hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); + hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, daddr, saddr, family); - hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); + hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); net->xfrm.state_num++; @@ -1394,9 +1432,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 { struct xfrm_state *x; - spin_lock_bh(&net->xfrm.xfrm_state_lock); + rcu_read_lock(); x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); - spin_unlock_bh(&net->xfrm.xfrm_state_lock); + rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup); @@ -1581,7 +1619,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) if (x->id.spi) { spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); + hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; @@ -2099,8 +2137,6 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); - INIT_HLIST_HEAD(&net->xfrm.state_gc_list); - INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task); spin_lock_init(&net->xfrm.xfrm_state_lock); return 0; @@ -2118,7 +2154,7 @@ void xfrm_state_fini(struct net *net) flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, IPSEC_PROTO_ANY, false); - flush_work(&net->xfrm.state_gc_work); + flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 05a6e3d..35a7e79 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -17,13 +17,13 @@ static struct ctl_table xfrm_table[] = { .procname = "xfrm_aevent_etime", .maxlen = sizeof(u32), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_douintvec }, { .procname = "xfrm_aevent_rseqth", .maxlen = sizeof(u32), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_douintvec }, { .procname = "xfrm_larval_drop", diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d516845..0889209 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -581,9 +581,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (err) goto error; - if (attrs[XFRMA_SEC_CTX] && - security_xfrm_state_alloc(x, nla_data(attrs[XFRMA_SEC_CTX]))) - goto error; + if (attrs[XFRMA_SEC_CTX]) { + err = security_xfrm_state_alloc(x, + nla_data(attrs[XFRMA_SEC_CTX])); + if (err) + goto error; + } if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn, attrs[XFRMA_REPLAY_ESN_VAL]))) @@ -896,7 +899,8 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) struct sock *sk = cb->skb->sk; struct net *net = sock_net(sk); - xfrm_state_walk_done(walk, net); + if (cb->args[0]) + xfrm_state_walk_done(walk, net); return 0; } @@ -921,8 +925,6 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) u8 proto = 0; int err; - cb->args[0] = 1; - err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy); if (err < 0) @@ -939,6 +941,7 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) proto = nla_get_u8(attrs[XFRMA_PROTO]); xfrm_state_walk_init(walk, proto, filter); + cb->args[0] = 1; } (void) xfrm_state_walk(net, walk, dump_one_state, &info); @@ -2051,9 +2054,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (up->hard) { xfrm_policy_delete(xp, p->dir); xfrm_audit_policy_delete(xp, 1, true); - } else { - // reset the timers here? - WARN(1, "Don't know what to do with soft policy expire\n"); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); @@ -2117,7 +2117,7 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, err = verify_newpolicy_info(&ua->policy); if (err) - goto bad_policy; + goto free_state; /* build an XP */ xp = xfrm_policy_construct(net, &ua->policy, attrs, &err); @@ -2149,8 +2149,6 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; -bad_policy: - WARN(1, "BAD policy passed\n"); free_state: kfree(x); nomem: |