diff options
Diffstat (limited to 'net')
203 files changed, 7500 insertions, 4090 deletions
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5704ed9c3a23..9d010a09ab98 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -38,9 +38,9 @@ struct vlan_info { static inline unsigned int vlan_proto_idx(__be16 proto) { switch (proto) { - case __constant_htons(ETH_P_8021Q): + case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: BUG(); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 6ee48aac776f..35b3c192d7b9 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -22,11 +22,11 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; - if (skb->pkt_type == PACKET_OTHERHOST) { + if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ - if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 566adbf5c506..4f3e9073cb49 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -538,6 +538,9 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; + if (saddr == NULL) + saddr = dev->dev_addr; + return dev_hard_header(skb, real_dev, type, daddr, saddr, len); } @@ -675,13 +678,13 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { - start = u64_stats_fetch_begin_bh(&p->syncp); + start = u64_stats_fetch_begin_irq(&p->syncp); rxpackets = p->rx_packets; rxbytes = p->rx_bytes; rxmulticast = p->rx_multicast; txpackets = p->tx_packets; txbytes = p->tx_bytes; - } while (u64_stats_fetch_retry_bh(&p->syncp, start)); + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c7e634af8516..8ac8a5cc2143 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -56,8 +56,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_PROTOCOL]) { switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) { - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): break; default: return -EPROTONOSUPPORT; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index adb3ea04adaa..73492b91105a 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -27,7 +27,7 @@ #include "6lowpan.h" -#include "../ieee802154/6lowpan.h" /* for the compression support */ +#include <net/6lowpan.h> /* for the compression support */ #define IFACE_NAME_TEMPLATE "bt%d" #define EUI64_ADDR_LEN 8 diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index efcd108822c4..f986b9968bdb 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -235,7 +235,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) + if (chan->scid == L2CAP_CID_A2MP) continue; l2cap_chan_lock(chan); @@ -726,7 +726,11 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) BT_DBG("chan %p", chan); - chan->chan_type = L2CAP_CHAN_CONN_FIX_A2MP; + chan->chan_type = L2CAP_CHAN_FIXED; + chan->scid = L2CAP_CID_A2MP; + chan->dcid = L2CAP_CID_A2MP; + chan->omtu = L2CAP_A2MP_DEFAULT_MTU; + chan->imtu = L2CAP_A2MP_DEFAULT_MTU; chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; chan->ops = &a2mp_chan_ops; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 0c5866bb49b6..2021c481cdb6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -31,7 +31,7 @@ #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> -#define VERSION "2.18" +#define VERSION "2.19" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ba5366c320da..7c713c4675ba 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -225,13 +225,13 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, cp.conn_interval_max = cpu_to_le16(max); cp.conn_latency = cpu_to_le16(latency); cp.supervision_timeout = cpu_to_le16(to_multiplier); - cp.min_ce_len = __constant_cpu_to_le16(0x0001); - cp.max_ce_len = __constant_cpu_to_le16(0x0001); + cp.min_ce_len = __constant_cpu_to_le16(0x0000); + cp.max_ce_len = __constant_cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); } -void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], +void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16]) { struct hci_dev *hdev = conn->hdev; @@ -242,9 +242,9 @@ void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); - memcpy(cp.ltk, ltk, sizeof(cp.ltk)); + cp.rand = rand; cp.ediv = ediv; - memcpy(cp.rand, rand, sizeof(cp.rand)); + memcpy(cp.ltk, ltk, sizeof(cp.ltk)); hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } @@ -363,6 +363,16 @@ static void hci_conn_auto_accept(struct work_struct *work) &conn->dst); } +static void le_conn_timeout(struct work_struct *work) +{ + struct hci_conn *conn = container_of(work, struct hci_conn, + le_conn_timeout.work); + + BT_DBG(""); + + hci_le_create_connection_cancel(conn); +} + struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) { struct hci_conn *conn; @@ -410,6 +420,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout); INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); + INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); atomic_set(&conn->refcnt, 0); @@ -442,6 +453,8 @@ int hci_conn_del(struct hci_conn *conn) /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { + cancel_delayed_work_sync(&conn->le_conn_timeout); + if (hdev->le_pkts) hdev->le_cnt += conn->sent; else @@ -514,6 +527,26 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) } EXPORT_SYMBOL(hci_get_route); +/* This function requires the caller holds hdev->lock */ +void hci_le_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + conn->state = BT_CLOSED; + + mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, + status); + + hci_proto_connect_cfm(conn, status); + + hci_conn_del(conn); + + /* Since we may have temporarily stopped the background scanning in + * favor of connection establishment, we should restart it. + */ + hci_update_background_scan(hdev); +} + static void create_le_conn_complete(struct hci_dev *hdev, u8 status) { struct hci_conn *conn; @@ -530,55 +563,55 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status) if (!conn) goto done; - conn->state = BT_CLOSED; - - mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, - status); - - hci_proto_connect_cfm(conn, status); - - hci_conn_del(conn); + hci_le_conn_failed(conn, status); done: hci_dev_unlock(hdev); } -static int hci_create_le_conn(struct hci_conn *conn) +static void hci_req_add_le_create_conn(struct hci_request *req, + struct hci_conn *conn) { - struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_conn cp; - struct hci_request req; - int err; - - hci_req_init(&req, hdev); + struct hci_dev *hdev = conn->hdev; + u8 own_addr_type; memset(&cp, 0, sizeof(cp)); + + /* Update random address, but set require_privacy to false so + * that we never connect with an unresolvable address. + */ + if (hci_update_random_address(req, false, &own_addr_type)) + return; + + /* Save the address type used for this connnection attempt so we able + * to retrieve this information if we need it. + */ + conn->src_type = own_addr_type; + cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); cp.scan_window = cpu_to_le16(hdev->le_scan_window); bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; - cp.own_address_type = conn->src_type; - cp.conn_interval_min = cpu_to_le16(hdev->le_conn_min_interval); - cp.conn_interval_max = cpu_to_le16(hdev->le_conn_max_interval); + cp.own_address_type = own_addr_type; + cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); cp.supervision_timeout = __constant_cpu_to_le16(0x002a); cp.min_ce_len = __constant_cpu_to_le16(0x0000); cp.max_ce_len = __constant_cpu_to_le16(0x0000); - hci_req_add(&req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); - - err = hci_req_run(&req, create_le_conn_complete); - if (err) { - hci_conn_del(conn); - return err; - } + hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); - return 0; + conn->state = BT_CONNECT; } -static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, - u8 dst_type, u8 sec_level, u8 auth_type) +struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, + u8 dst_type, u8 sec_level, u8 auth_type) { + struct hci_conn_params *params; struct hci_conn *conn; + struct smp_irk *irk; + struct hci_request req; int err; if (test_bit(HCI_ADVERTISING, &hdev->flags)) @@ -607,35 +640,74 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (conn) return ERR_PTR(-EBUSY); + /* When given an identity address with existing identity + * resolving key, the connection needs to be established + * to a resolvable random address. + * + * This uses the cached random resolvable address from + * a previous scan. When no cached address is available, + * try connecting to the identity address instead. + * + * Storing the resolvable random address is required here + * to handle connection failures. The address will later + * be resolved back into the original identity address + * from the connect request. + */ + irk = hci_find_irk_by_addr(hdev, dst, dst_type); + if (irk && bacmp(&irk->rpa, BDADDR_ANY)) { + dst = &irk->rpa; + dst_type = ADDR_LE_DEV_RANDOM; + } + conn = hci_conn_add(hdev, LE_LINK, dst); if (!conn) return ERR_PTR(-ENOMEM); - if (dst_type == BDADDR_LE_PUBLIC) - conn->dst_type = ADDR_LE_DEV_PUBLIC; - else - conn->dst_type = ADDR_LE_DEV_RANDOM; - - conn->src_type = hdev->own_addr_type; + conn->dst_type = dst_type; - conn->state = BT_CONNECT; conn->out = true; conn->link_mode |= HCI_LM_MASTER; conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; conn->auth_type = auth_type; - err = hci_create_le_conn(conn); - if (err) + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + conn->le_conn_min_interval = params->conn_min_interval; + conn->le_conn_max_interval = params->conn_max_interval; + } else { + conn->le_conn_min_interval = hdev->le_conn_min_interval; + conn->le_conn_max_interval = hdev->le_conn_max_interval; + } + + hci_req_init(&req, hdev); + + /* If controller is scanning, we stop it since some controllers are + * not able to scan and connect at the same time. Also set the + * HCI_LE_SCAN_INTERRUPTED flag so that the command complete + * handler for scan disabling knows to set the correct discovery + * state. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + hci_req_add_le_scan_disable(&req); + set_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags); + } + + hci_req_add_le_create_conn(&req, conn); + + err = hci_req_run(&req, create_le_conn_complete); + if (err) { + hci_conn_del(conn); return ERR_PTR(err); + } done: hci_conn_hold(conn); return conn; } -static struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, - u8 sec_level, u8 auth_type) +struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, + u8 sec_level, u8 auth_type) { struct hci_conn *acl; @@ -704,22 +776,6 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, return sco; } -/* Create SCO, ACL or LE connection. */ -struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u8 dst_type, __u8 sec_level, __u8 auth_type) -{ - BT_DBG("%s dst %pMR type 0x%x", hdev->name, dst, type); - - switch (type) { - case LE_LINK: - return hci_connect_le(hdev, dst, dst_type, sec_level, auth_type); - case ACL_LINK: - return hci_connect_acl(hdev, dst, sec_level, auth_type); - } - - return ERR_PTR(-EINVAL); -} - /* Check link security requirement */ int hci_conn_check_link_mode(struct hci_conn *conn) { @@ -800,14 +856,23 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!(conn->link_mode & HCI_LM_AUTH)) goto auth; - /* An authenticated combination key has sufficient security for any - security level. */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION) + /* An authenticated FIPS approved combination key has sufficient + * security for security level 4. */ + if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 && + sec_level == BT_SECURITY_FIPS) + goto encrypt; + + /* An authenticated combination key has sufficient security for + security level 3. */ + if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 || + conn->key_type == HCI_LK_AUTH_COMBINATION_P256) && + sec_level == BT_SECURITY_HIGH) goto encrypt; /* An unauthenticated combination key has sufficient security for security level 1 and 2. */ - if (conn->key_type == HCI_LK_UNAUTH_COMBINATION && + if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 || + conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) && (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) goto encrypt; @@ -816,7 +881,8 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) is generated using maximum PIN code length (16). For pre 2.1 units. */ if (conn->key_type == HCI_LK_COMBINATION && - (sec_level != BT_SECURITY_HIGH || conn->pin_length == 16)) + (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW || + conn->pin_length == 16)) goto encrypt; auth: @@ -840,13 +906,17 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) { BT_DBG("hcon %p", conn); - if (sec_level != BT_SECURITY_HIGH) - return 1; /* Accept if non-secure is required */ + /* Accept if non-secure or higher security level is required */ + if (sec_level != BT_SECURITY_HIGH && sec_level != BT_SECURITY_FIPS) + return 1; - if (conn->sec_level == BT_SECURITY_HIGH) + /* Accept if secure or higher security level is already present */ + if (conn->sec_level == BT_SECURITY_HIGH || + conn->sec_level == BT_SECURITY_FIPS) return 1; - return 0; /* Reject not secure link */ + /* Reject not secure link */ + return 0; } EXPORT_SYMBOL(hci_conn_check_secure); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5e8663c194c1..8bbfdea9cbec 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -29,11 +29,14 @@ #include <linux/idr.h> #include <linux/rfkill.h> #include <linux/debugfs.h> +#include <linux/crypto.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include "smp.h" + static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); @@ -285,24 +288,6 @@ static const struct file_operations link_keys_fops = { .release = single_release, }; -static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[3]; - - buf[0] = test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) ? 'Y': 'N'; - buf[1] = '\n'; - buf[2] = '\0'; - return simple_read_from_buffer(user_buf, count, ppos, buf, 2); -} - -static const struct file_operations use_debug_keys_fops = { - .open = simple_open, - .read = use_debug_keys_read, - .llseek = default_llseek, -}; - static int dev_class_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -415,6 +400,70 @@ static int ssp_debug_mode_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(ssp_debug_mode_fops, ssp_debug_mode_get, ssp_debug_mode_set, "%llu\n"); +static ssize_t force_sc_support_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_FORCE_SC, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t force_sc_support_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + bool enable; + + if (test_bit(HCI_UP, &hdev->flags)) + return -EBUSY; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) + return -EINVAL; + + if (enable == test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + return -EALREADY; + + change_bit(HCI_FORCE_SC, &hdev->dev_flags); + + return count; +} + +static const struct file_operations force_sc_support_fops = { + .open = simple_open, + .read = force_sc_support_read, + .write = force_sc_support_write, + .llseek = default_llseek, +}; + +static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_SC_ONLY, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static const struct file_operations sc_only_mode_fops = { + .open = simple_open, + .read = sc_only_mode_read, + .llseek = default_llseek, +}; + static int idle_timeout_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -443,6 +492,37 @@ static int idle_timeout_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(idle_timeout_fops, idle_timeout_get, idle_timeout_set, "%llu\n"); +static int rpa_timeout_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + /* Require the RPA timeout to be at least 30 seconds and at most + * 24 hours. + */ + if (val < 30 || val > (60 * 60 * 24)) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->rpa_timeout = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int rpa_timeout_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->rpa_timeout; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(rpa_timeout_fops, rpa_timeout_get, + rpa_timeout_set, "%llu\n"); + static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -499,6 +579,59 @@ static int sniff_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get, sniff_max_interval_set, "%llu\n"); +static int identity_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + bdaddr_t addr; + u8 addr_type; + + hci_dev_lock(hdev); + + hci_copy_identity_address(hdev, &addr, &addr_type); + + seq_printf(f, "%pMR (type %u) %*phN %pMR\n", &addr, addr_type, + 16, hdev->irk, &hdev->rpa); + + hci_dev_unlock(hdev); + + return 0; +} + +static int identity_open(struct inode *inode, struct file *file) +{ + return single_open(file, identity_show, inode->i_private); +} + +static const struct file_operations identity_fops = { + .open = identity_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int random_address_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + + hci_dev_lock(hdev); + seq_printf(f, "%pMR\n", &hdev->random_addr); + hci_dev_unlock(hdev); + + return 0; +} + +static int random_address_open(struct inode *inode, struct file *file) +{ + return single_open(file, random_address_show, inode->i_private); +} + +static const struct file_operations random_address_fops = { + .open = random_address_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int static_address_show(struct seq_file *f, void *p) { struct hci_dev *hdev = f->private; @@ -522,33 +655,107 @@ static const struct file_operations static_address_fops = { .release = single_release, }; -static int own_address_type_set(void *data, u64 val) +static ssize_t force_static_address_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) { - struct hci_dev *hdev = data; + struct hci_dev *hdev = file->private_data; + char buf[3]; - if (val != 0 && val != 1) + buf[0] = test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t force_static_address_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + bool enable; + + if (test_bit(HCI_UP, &hdev->flags)) + return -EBUSY; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) return -EINVAL; + if (enable == test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags)) + return -EALREADY; + + change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags); + + return count; +} + +static const struct file_operations force_static_address_fops = { + .open = simple_open, + .read = force_static_address_read, + .write = force_static_address_write, + .llseek = default_llseek, +}; + +static int white_list_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct bdaddr_list *b; + hci_dev_lock(hdev); - hdev->own_addr_type = val; + list_for_each_entry(b, &hdev->le_white_list, list) + seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); return 0; } -static int own_address_type_get(void *data, u64 *val) +static int white_list_open(struct inode *inode, struct file *file) { - struct hci_dev *hdev = data; + return single_open(file, white_list_show, inode->i_private); +} + +static const struct file_operations white_list_fops = { + .open = white_list_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int identity_resolving_keys_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct list_head *p, *n; hci_dev_lock(hdev); - *val = hdev->own_addr_type; + list_for_each_safe(p, n, &hdev->identity_resolving_keys) { + struct smp_irk *irk = list_entry(p, struct smp_irk, list); + seq_printf(f, "%pMR (type %u) %*phN %pMR\n", + &irk->bdaddr, irk->addr_type, + 16, irk->val, &irk->rpa); + } hci_dev_unlock(hdev); return 0; } -DEFINE_SIMPLE_ATTRIBUTE(own_address_type_fops, own_address_type_get, - own_address_type_set, "%llu\n"); +static int identity_resolving_keys_open(struct inode *inode, struct file *file) +{ + return single_open(file, identity_resolving_keys_show, + inode->i_private); +} + +static const struct file_operations identity_resolving_keys_fops = { + .open = identity_resolving_keys_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; static int long_term_keys_show(struct seq_file *f, void *ptr) { @@ -556,12 +763,12 @@ static int long_term_keys_show(struct seq_file *f, void *ptr) struct list_head *p, *n; hci_dev_lock(hdev); - list_for_each_safe(p, n, &hdev->link_keys) { + list_for_each_safe(p, n, &hdev->long_term_keys) { struct smp_ltk *ltk = list_entry(p, struct smp_ltk, list); - seq_printf(f, "%pMR (type %u) %u %u %u %.4x %*phN %*phN\\n", + seq_printf(f, "%pMR (type %u) %u 0x%02x %u %.4x %.16llx %*phN\n", <k->bdaddr, ltk->bdaddr_type, ltk->authenticated, ltk->type, ltk->enc_size, __le16_to_cpu(ltk->ediv), - 8, ltk->rand, 16, ltk->val); + __le64_to_cpu(ltk->rand), 16, ltk->val); } hci_dev_unlock(hdev); @@ -636,6 +843,34 @@ static int conn_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, conn_max_interval_set, "%llu\n"); +static int adv_channel_map_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val < 0x01 || val > 0x07) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_adv_channel_map = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int adv_channel_map_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->le_adv_channel_map; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, + adv_channel_map_set, "%llu\n"); + static ssize_t lowpan_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -679,6 +914,115 @@ static const struct file_operations lowpan_debugfs_fops = { .llseek = default_llseek, }; +static int le_auto_conn_show(struct seq_file *sf, void *ptr) +{ + struct hci_dev *hdev = sf->private; + struct hci_conn_params *p; + + hci_dev_lock(hdev); + + list_for_each_entry(p, &hdev->le_conn_params, list) { + seq_printf(sf, "%pMR %u %u\n", &p->addr, p->addr_type, + p->auto_connect); + } + + hci_dev_unlock(hdev); + + return 0; +} + +static int le_auto_conn_open(struct inode *inode, struct file *file) +{ + return single_open(file, le_auto_conn_show, inode->i_private); +} + +static ssize_t le_auto_conn_write(struct file *file, const char __user *data, + size_t count, loff_t *offset) +{ + struct seq_file *sf = file->private_data; + struct hci_dev *hdev = sf->private; + u8 auto_connect = 0; + bdaddr_t addr; + u8 addr_type; + char *buf; + int err = 0; + int n; + + /* Don't allow partial write */ + if (*offset != 0) + return -EINVAL; + + if (count < 3) + return -EINVAL; + + buf = kzalloc(count, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, data, count)) { + err = -EFAULT; + goto done; + } + + if (memcmp(buf, "add", 3) == 0) { + n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu %hhu", + &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], + &addr.b[1], &addr.b[0], &addr_type, + &auto_connect); + + if (n < 7) { + err = -EINVAL; + goto done; + } + + hci_dev_lock(hdev); + err = hci_conn_params_add(hdev, &addr, addr_type, auto_connect, + hdev->le_conn_min_interval, + hdev->le_conn_max_interval); + hci_dev_unlock(hdev); + + if (err) + goto done; + } else if (memcmp(buf, "del", 3) == 0) { + n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", + &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], + &addr.b[1], &addr.b[0], &addr_type); + + if (n < 7) { + err = -EINVAL; + goto done; + } + + hci_dev_lock(hdev); + hci_conn_params_del(hdev, &addr, addr_type); + hci_dev_unlock(hdev); + } else if (memcmp(buf, "clr", 3) == 0) { + hci_dev_lock(hdev); + hci_conn_params_clear(hdev); + hci_pend_le_conns_clear(hdev); + hci_update_background_scan(hdev); + hci_dev_unlock(hdev); + } else { + err = -EINVAL; + } + +done: + kfree(buf); + + if (err) + return err; + else + return count; +} + +static const struct file_operations le_auto_conn_fops = { + .open = le_auto_conn_open, + .read = seq_read, + .write = le_auto_conn_write, + .llseek = seq_lseek, + .release = single_release, +}; + /* ---- HCI requests ---- */ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result) @@ -1027,14 +1371,17 @@ static void le_setup(struct hci_request *req) /* Read LE Local Supported Features */ hci_req_add(req, HCI_OP_LE_READ_LOCAL_FEATURES, 0, NULL); + /* Read LE Supported States */ + hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL); + /* Read LE Advertising Channel TX Power */ hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); /* Read LE White List Size */ hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, 0, NULL); - /* Read LE Supported States */ - hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL); + /* Clear LE White List */ + hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); /* LE-only controllers have LE implicitly enabled */ if (!lmp_bredr_capable(hdev)) @@ -1288,6 +1635,10 @@ static void hci_set_event_mask_page_2(struct hci_request *req) events[2] |= 0x08; /* Truncated Page Complete */ } + /* Enable Authenticated Payload Timeout Expired event if supported */ + if (lmp_ping_capable(hdev)) + events[2] |= 0x80; + hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events); } @@ -1322,21 +1673,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[5] & 0x10) hci_setup_link_policy(req); - if (lmp_le_capable(hdev)) { - if (test_bit(HCI_SETUP, &hdev->dev_flags)) { - /* If the controller has a public BD_ADDR, then - * by default use that one. If this is a LE only - * controller without a public address, default - * to the random address. - */ - if (bacmp(&hdev->bdaddr, BDADDR_ANY)) - hdev->own_addr_type = ADDR_LE_DEV_PUBLIC; - else - hdev->own_addr_type = ADDR_LE_DEV_RANDOM; - } - + if (lmp_le_capable(hdev)) hci_set_le_support(req); - } /* Read features beyond page 1 if available */ for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) { @@ -1359,6 +1697,15 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) /* Check for Synchronization Train support */ if (lmp_sync_train_capable(hdev)) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); + + /* Enable Secure Connections if supported and configured */ + if ((lmp_sc_capable(hdev) || + test_bit(HCI_FORCE_SC, &hdev->dev_flags)) && + test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) { + u8 support = 0x01; + hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT, + sizeof(support), &support); + } } static int __hci_init(struct hci_dev *hdev) @@ -1417,8 +1764,6 @@ static int __hci_init(struct hci_dev *hdev) hdev, &inquiry_cache_fops); debugfs_create_file("link_keys", 0400, hdev->debugfs, hdev, &link_keys_fops); - debugfs_create_file("use_debug_keys", 0444, hdev->debugfs, - hdev, &use_debug_keys_fops); debugfs_create_file("dev_class", 0444, hdev->debugfs, hdev, &dev_class_fops); debugfs_create_file("voice_setting", 0444, hdev->debugfs, @@ -1430,6 +1775,10 @@ static int __hci_init(struct hci_dev *hdev) hdev, &auto_accept_delay_fops); debugfs_create_file("ssp_debug_mode", 0644, hdev->debugfs, hdev, &ssp_debug_mode_fops); + debugfs_create_file("force_sc_support", 0644, hdev->debugfs, + hdev, &force_sc_support_fops); + debugfs_create_file("sc_only_mode", 0444, hdev->debugfs, + hdev, &sc_only_mode_fops); } if (lmp_sniff_capable(hdev)) { @@ -1442,20 +1791,43 @@ static int __hci_init(struct hci_dev *hdev) } if (lmp_le_capable(hdev)) { + debugfs_create_file("identity", 0400, hdev->debugfs, + hdev, &identity_fops); + debugfs_create_file("rpa_timeout", 0644, hdev->debugfs, + hdev, &rpa_timeout_fops); + debugfs_create_file("random_address", 0444, hdev->debugfs, + hdev, &random_address_fops); + debugfs_create_file("static_address", 0444, hdev->debugfs, + hdev, &static_address_fops); + + /* For controllers with a public address, provide a debug + * option to force the usage of the configured static + * address. By default the public address is used. + */ + if (bacmp(&hdev->bdaddr, BDADDR_ANY)) + debugfs_create_file("force_static_address", 0644, + hdev->debugfs, hdev, + &force_static_address_fops); + debugfs_create_u8("white_list_size", 0444, hdev->debugfs, &hdev->le_white_list_size); - debugfs_create_file("static_address", 0444, hdev->debugfs, - hdev, &static_address_fops); - debugfs_create_file("own_address_type", 0644, hdev->debugfs, - hdev, &own_address_type_fops); + debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, + &white_list_fops); + debugfs_create_file("identity_resolving_keys", 0400, + hdev->debugfs, hdev, + &identity_resolving_keys_fops); debugfs_create_file("long_term_keys", 0400, hdev->debugfs, hdev, &long_term_keys_fops); debugfs_create_file("conn_min_interval", 0644, hdev->debugfs, hdev, &conn_min_interval_fops); debugfs_create_file("conn_max_interval", 0644, hdev->debugfs, hdev, &conn_max_interval_fops); + debugfs_create_file("adv_channel_map", 0644, hdev->debugfs, + hdev, &adv_channel_map_fops); debugfs_create_file("6lowpan", 0644, hdev->debugfs, hdev, &lowpan_debugfs_fops); + debugfs_create_file("le_auto_conn", 0644, hdev->debugfs, hdev, + &le_auto_conn_fops); } return 0; @@ -1548,6 +1920,8 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) switch (state) { case DISCOVERY_STOPPED: + hci_update_background_scan(hdev); + if (hdev->discovery.state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; @@ -1876,10 +2250,15 @@ static int hci_dev_do_open(struct hci_dev *hdev) * be able to determine if there is a public address * or not. * + * In case of user channel usage, it is not important + * if a public address or static random address is + * available. + * * This check is only valid for BR/EDR controllers * since AMP controllers do not have an address. */ - if (hdev->dev_type == HCI_BREDR && + if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) && + hdev->dev_type == HCI_BREDR && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY)) { ret = -EADDRNOTAVAIL; @@ -1916,6 +2295,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (!ret) { hci_dev_hold(hdev); + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); set_bit(HCI_UP, &hdev->flags); hci_notify(hdev, HCI_DEV_UP); if (!test_bit(HCI_SETUP, &hdev->dev_flags) && @@ -2014,9 +2394,13 @@ static int hci_dev_do_close(struct hci_dev *hdev) cancel_delayed_work_sync(&hdev->le_scan_disable); + if (test_bit(HCI_MGMT, &hdev->dev_flags)) + cancel_delayed_work_sync(&hdev->rpa_expired); + hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); + hci_pend_le_conns_clear(hdev); hci_dev_unlock(hdev); hci_notify(hdev, HCI_DEV_DOWN); @@ -2074,6 +2458,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); + bacpy(&hdev->random_addr, BDADDR_ANY); hci_req_unlock(hdev); @@ -2437,7 +2822,7 @@ static void hci_discov_off(struct work_struct *work) mgmt_discoverable_timeout(hdev); } -int hci_uuids_clear(struct hci_dev *hdev) +void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; @@ -2445,11 +2830,9 @@ int hci_uuids_clear(struct hci_dev *hdev) list_del(&uuid->list); kfree(uuid); } - - return 0; } -int hci_link_keys_clear(struct hci_dev *hdev) +void hci_link_keys_clear(struct hci_dev *hdev) { struct list_head *p, *n; @@ -2461,11 +2844,9 @@ int hci_link_keys_clear(struct hci_dev *hdev) list_del(p); kfree(key); } - - return 0; } -int hci_smp_ltks_clear(struct hci_dev *hdev) +void hci_smp_ltks_clear(struct hci_dev *hdev) { struct smp_ltk *k, *tmp; @@ -2473,8 +2854,16 @@ int hci_smp_ltks_clear(struct hci_dev *hdev) list_del(&k->list); kfree(k); } +} - return 0; +void hci_smp_irks_clear(struct hci_dev *hdev) +{ + struct smp_irk *k, *tmp; + + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { + list_del(&k->list); + kfree(k); + } } struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -2524,13 +2913,24 @@ static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, return false; } -struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) +static bool ltk_type_master(u8 type) +{ + if (type == HCI_SMP_STK || type == HCI_SMP_LTK) + return true; + + return false; +} + +struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand, + bool master) { struct smp_ltk *k; list_for_each_entry(k, &hdev->long_term_keys, list) { - if (k->ediv != ediv || - memcmp(rand, k->rand, sizeof(k->rand))) + if (k->ediv != ediv || k->rand != rand) + continue; + + if (ltk_type_master(k->type) != master) continue; return k; @@ -2540,18 +2940,56 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) } struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 addr_type) + u8 addr_type, bool master) { struct smp_ltk *k; list_for_each_entry(k, &hdev->long_term_keys, list) if (addr_type == k->bdaddr_type && - bacmp(bdaddr, &k->bdaddr) == 0) + bacmp(bdaddr, &k->bdaddr) == 0 && + ltk_type_master(k->type) == master) return k; return NULL; } +struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) +{ + struct smp_irk *irk; + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (!bacmp(&irk->rpa, rpa)) + return irk; + } + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (smp_irk_matches(hdev->tfm_aes, irk->val, rpa)) { + bacpy(&irk->rpa, rpa); + return irk; + } + } + + return NULL; +} + +struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type) +{ + struct smp_irk *irk; + + /* Identity Address must be public or static random */ + if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0) + return NULL; + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (addr_type == irk->addr_type && + bacmp(bdaddr, &irk->bdaddr) == 0) + return irk; + } + + return NULL; +} + int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) { @@ -2565,7 +3003,7 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, key = old_key; } else { old_key_type = conn ? conn->key_type : 0xff; - key = kzalloc(sizeof(*key), GFP_ATOMIC); + key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return -ENOMEM; list_add(&key->list, &hdev->link_keys); @@ -2605,22 +3043,20 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, return 0; } -int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, - int new_key, u8 authenticated, u8 tk[16], u8 enc_size, __le16 - ediv, u8 rand[8]) +struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type, u8 type, u8 authenticated, + u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; + bool master = ltk_type_master(type); - if (!(type & HCI_SMP_STK) && !(type & HCI_SMP_LTK)) - return 0; - - old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type); + old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, master); if (old_key) key = old_key; else { - key = kzalloc(sizeof(*key), GFP_ATOMIC); + key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) - return -ENOMEM; + return NULL; list_add(&key->list, &hdev->long_term_keys); } @@ -2629,17 +3065,34 @@ int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, memcpy(key->val, tk, sizeof(key->val)); key->authenticated = authenticated; key->ediv = ediv; + key->rand = rand; key->enc_size = enc_size; key->type = type; - memcpy(key->rand, rand, sizeof(key->rand)); - if (!new_key) - return 0; + return key; +} + +struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type, u8 val[16], bdaddr_t *rpa) +{ + struct smp_irk *irk; - if (type & HCI_SMP_LTK) - mgmt_new_ltk(hdev, key, 1); + irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type); + if (!irk) { + irk = kzalloc(sizeof(*irk), GFP_KERNEL); + if (!irk) + return NULL; - return 0; + bacpy(&irk->bdaddr, bdaddr); + irk->addr_type = addr_type; + + list_add(&irk->list, &hdev->identity_resolving_keys); + } + + memcpy(irk->val, val, 16); + bacpy(&irk->rpa, rpa); + + return irk; } int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -2658,21 +3111,38 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) return 0; } -int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr) +int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct smp_ltk *k, *tmp; + int removed = 0; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { - if (bacmp(bdaddr, &k->bdaddr)) + if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del(&k->list); kfree(k); + removed++; } - return 0; + return removed ? 0 : -ENOENT; +} + +void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) +{ + struct smp_irk *k, *tmp; + + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { + if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) + continue; + + BT_DBG("%s removing %pMR", hdev->name, bdaddr); + + list_del(&k->list); + kfree(k); + } } /* HCI command timer function */ @@ -2721,7 +3191,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr) return 0; } -int hci_remote_oob_data_clear(struct hci_dev *hdev) +void hci_remote_oob_data_clear(struct hci_dev *hdev) { struct oob_data *data, *n; @@ -2729,19 +3199,43 @@ int hci_remote_oob_data_clear(struct hci_dev *hdev) list_del(&data->list); kfree(data); } +} + +int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *hash, u8 *randomizer) +{ + struct oob_data *data; + + data = hci_find_remote_oob_data(hdev, bdaddr); + if (!data) { + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + bacpy(&data->bdaddr, bdaddr); + list_add(&data->list, &hdev->remote_oob_data); + } + + memcpy(data->hash192, hash, sizeof(data->hash192)); + memcpy(data->randomizer192, randomizer, sizeof(data->randomizer192)); + + memset(data->hash256, 0, sizeof(data->hash256)); + memset(data->randomizer256, 0, sizeof(data->randomizer256)); + + BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } -int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, - u8 *randomizer) +int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *hash192, u8 *randomizer192, + u8 *hash256, u8 *randomizer256) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr); - if (!data) { - data = kmalloc(sizeof(*data), GFP_ATOMIC); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -2749,8 +3243,11 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, list_add(&data->list, &hdev->remote_oob_data); } - memcpy(data->hash, hash, sizeof(data->hash)); - memcpy(data->randomizer, randomizer, sizeof(data->randomizer)); + memcpy(data->hash192, hash192, sizeof(data->hash192)); + memcpy(data->randomizer192, randomizer192, sizeof(data->randomizer192)); + + memcpy(data->hash256, hash256, sizeof(data->hash256)); + memcpy(data->randomizer256, randomizer256, sizeof(data->randomizer256)); BT_DBG("%s for %pMR", hdev->name, bdaddr); @@ -2770,7 +3267,7 @@ struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, return NULL; } -int hci_blacklist_clear(struct hci_dev *hdev) +static void hci_blacklist_clear(struct hci_dev *hdev) { struct list_head *p, *n; @@ -2780,8 +3277,6 @@ int hci_blacklist_clear(struct hci_dev *hdev) list_del(p); kfree(b); } - - return 0; } int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) @@ -2810,8 +3305,10 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; - if (!bacmp(bdaddr, BDADDR_ANY)) - return hci_blacklist_clear(hdev); + if (!bacmp(bdaddr, BDADDR_ANY)) { + hci_blacklist_clear(hdev); + return 0; + } entry = hci_blacklist_lookup(hdev, bdaddr, type); if (!entry) @@ -2823,6 +3320,262 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) return mgmt_device_unblocked(hdev, bdaddr, type); } +struct bdaddr_list *hci_white_list_lookup(struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *b; + + list_for_each_entry(b, &hdev->le_white_list, list) { + if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) + return b; + } + + return NULL; +} + +void hci_white_list_clear(struct hci_dev *hdev) +{ + struct list_head *p, *n; + + list_for_each_safe(p, n, &hdev->le_white_list) { + struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list); + + list_del(p); + kfree(b); + } +} + +int hci_white_list_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) + return -EBADF; + + entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + bacpy(&entry->bdaddr, bdaddr); + entry->bdaddr_type = type; + + list_add(&entry->list, &hdev->le_white_list); + + return 0; +} + +int hci_white_list_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) + return -EBADF; + + entry = hci_white_list_lookup(hdev, bdaddr, type); + if (!entry) + return -ENOENT; + + list_del(&entry->list); + kfree(entry); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, + bdaddr_t *addr, u8 addr_type) +{ + struct hci_conn_params *params; + + list_for_each_entry(params, &hdev->le_conn_params, list) { + if (bacmp(¶ms->addr, addr) == 0 && + params->addr_type == addr_type) { + return params; + } + } + + return NULL; +} + +static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) +{ + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr); + if (!conn) + return false; + + if (conn->dst_type != type) + return false; + + if (conn->state != BT_CONNECTED) + return false; + + return true; +} + +static bool is_identity_address(bdaddr_t *addr, u8 addr_type) +{ + if (addr_type == ADDR_LE_DEV_PUBLIC) + return true; + + /* Check for Random Static address type */ + if ((addr->b[5] & 0xc0) == 0xc0) + return true; + + return false; +} + +/* This function requires the caller holds hdev->lock */ +int hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, + u8 auto_connect, u16 conn_min_interval, + u16 conn_max_interval) +{ + struct hci_conn_params *params; + + if (!is_identity_address(addr, addr_type)) + return -EINVAL; + + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (params) + goto update; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) { + BT_ERR("Out of memory"); + return -ENOMEM; + } + + bacpy(¶ms->addr, addr); + params->addr_type = addr_type; + + list_add(¶ms->list, &hdev->le_conn_params); + +update: + params->conn_min_interval = conn_min_interval; + params->conn_max_interval = conn_max_interval; + params->auto_connect = auto_connect; + + switch (auto_connect) { + case HCI_AUTO_CONN_DISABLED: + case HCI_AUTO_CONN_LINK_LOSS: + hci_pend_le_conn_del(hdev, addr, addr_type); + break; + case HCI_AUTO_CONN_ALWAYS: + if (!is_connected(hdev, addr, addr_type)) + hci_pend_le_conn_add(hdev, addr, addr_type); + break; + } + + BT_DBG("addr %pMR (type %u) auto_connect %u conn_min_interval 0x%.4x " + "conn_max_interval 0x%.4x", addr, addr_type, auto_connect, + conn_min_interval, conn_max_interval); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct hci_conn_params *params; + + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (!params) + return; + + hci_pend_le_conn_del(hdev, addr, addr_type); + + list_del(¶ms->list); + kfree(params); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); +} + +/* This function requires the caller holds hdev->lock */ +void hci_conn_params_clear(struct hci_dev *hdev) +{ + struct hci_conn_params *params, *tmp; + + list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { + list_del(¶ms->list); + kfree(params); + } + + BT_DBG("All LE connection parameters were removed"); +} + +/* This function requires the caller holds hdev->lock */ +struct bdaddr_list *hci_pend_le_conn_lookup(struct hci_dev *hdev, + bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + list_for_each_entry(entry, &hdev->pend_le_conns, list) { + if (bacmp(&entry->bdaddr, addr) == 0 && + entry->bdaddr_type == addr_type) + return entry; + } + + return NULL; +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conn_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); + if (entry) + goto done; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + BT_ERR("Out of memory"); + return; + } + + bacpy(&entry->bdaddr, addr); + entry->bdaddr_type = addr_type; + + list_add(&entry->list, &hdev->pend_le_conns); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); + +done: + hci_update_background_scan(hdev); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conn_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); + if (!entry) + goto done; + + list_del(&entry->list); + kfree(entry); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); + +done: + hci_update_background_scan(hdev); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conns_clear(struct hci_dev *hdev) +{ + struct bdaddr_list *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->pend_le_conns, list) { + list_del(&entry->list); + kfree(entry); + } + + BT_DBG("All LE pending connections cleared"); +} + static void inquiry_complete(struct hci_dev *hdev, u8 status) { if (status) { @@ -2882,7 +3635,6 @@ static void le_scan_disable_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, le_scan_disable.work); - struct hci_cp_le_set_scan_enable cp; struct hci_request req; int err; @@ -2890,15 +3642,128 @@ static void le_scan_disable_work(struct work_struct *work) hci_req_init(&req, hdev); - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + hci_req_add_le_scan_disable(&req); err = hci_req_run(&req, le_scan_disable_work_complete); if (err) BT_ERR("Disable LE scanning request failed: err %d", err); } +static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) +{ + struct hci_dev *hdev = req->hdev; + + /* If we're advertising or initiating an LE connection we can't + * go ahead and change the random address at this time. This is + * because the eventual initiator address used for the + * subsequently created connection will be undefined (some + * controllers use the new address and others the one we had + * when the operation started). + * + * In this kind of scenario skip the update and let the random + * address be updated at the next cycle. + */ + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) || + hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { + BT_DBG("Deferring random address update"); + return; + } + + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa); +} + +int hci_update_random_address(struct hci_request *req, bool require_privacy, + u8 *own_addr_type) +{ + struct hci_dev *hdev = req->hdev; + int err; + + /* If privacy is enabled use a resolvable private address. If + * current RPA has expired or there is something else than + * the current RPA in use, then generate a new one. + */ + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + int to; + + *own_addr_type = ADDR_LE_DEV_RANDOM; + + if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) && + !bacmp(&hdev->random_addr, &hdev->rpa)) + return 0; + + err = smp_generate_rpa(hdev->tfm_aes, hdev->irk, &hdev->rpa); + if (err < 0) { + BT_ERR("%s failed to generate new RPA", hdev->name); + return err; + } + + set_random_addr(req, &hdev->rpa); + + to = msecs_to_jiffies(hdev->rpa_timeout * 1000); + queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to); + + return 0; + } + + /* In case of required privacy without resolvable private address, + * use an unresolvable private address. This is useful for active + * scanning and non-connectable advertising. + */ + if (require_privacy) { + bdaddr_t urpa; + + get_random_bytes(&urpa, 6); + urpa.b[5] &= 0x3f; /* Clear two most significant bits */ + + *own_addr_type = ADDR_LE_DEV_RANDOM; + set_random_addr(req, &urpa); + return 0; + } + + /* If forcing static address is in use or there is no public + * address use the static address as random address (but skip + * the HCI command if the current random address is already the + * static one. + */ + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + !bacmp(&hdev->bdaddr, BDADDR_ANY)) { + *own_addr_type = ADDR_LE_DEV_RANDOM; + if (bacmp(&hdev->static_addr, &hdev->random_addr)) + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, + &hdev->static_addr); + return 0; + } + + /* Neither privacy nor static address is being used so use a + * public address. + */ + *own_addr_type = ADDR_LE_DEV_PUBLIC; + + return 0; +} + +/* Copy the Identity Address of the controller. + * + * If the controller has a public BD_ADDR, then by default use that one. + * If this is a LE only controller without a public address, default to + * the static random address. + * + * For debugging purposes it is possible to force controllers with a + * public address to use the static random address instead. + */ +void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *bdaddr_type) +{ + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + !bacmp(&hdev->bdaddr, BDADDR_ANY)) { + bacpy(bdaddr, &hdev->static_addr); + *bdaddr_type = ADDR_LE_DEV_RANDOM; + } else { + bacpy(bdaddr, &hdev->bdaddr); + *bdaddr_type = ADDR_LE_DEV_PUBLIC; + } +} + /* Alloc HCI device */ struct hci_dev *hci_alloc_dev(void) { @@ -2919,11 +3784,14 @@ struct hci_dev *hci_alloc_dev(void) hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; + hdev->le_adv_channel_map = 0x07; hdev->le_scan_interval = 0x0060; hdev->le_scan_window = 0x0030; hdev->le_conn_min_interval = 0x0028; hdev->le_conn_max_interval = 0x0038; + hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; + mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); @@ -2932,7 +3800,11 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); + INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); + INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_conn_params); + INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_WORK(&hdev->rx_work, hci_rx_work); @@ -3017,9 +3889,18 @@ int hci_register_dev(struct hci_dev *hdev) dev_set_name(&hdev->dev, "%s", hdev->name); + hdev->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, + CRYPTO_ALG_ASYNC); + if (IS_ERR(hdev->tfm_aes)) { + BT_ERR("Unable to create crypto context"); + error = PTR_ERR(hdev->tfm_aes); + hdev->tfm_aes = NULL; + goto err_wqueue; + } + error = device_add(&hdev->dev); if (error < 0) - goto err_wqueue; + goto err_tfm; hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, @@ -3055,6 +3936,8 @@ int hci_register_dev(struct hci_dev *hdev) return id; +err_tfm: + crypto_free_blkcipher(hdev->tfm_aes); err_wqueue: destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); @@ -3105,6 +3988,9 @@ void hci_unregister_dev(struct hci_dev *hdev) rfkill_destroy(hdev->rfkill); } + if (hdev->tfm_aes) + crypto_free_blkcipher(hdev->tfm_aes); + device_del(&hdev->dev); debugfs_remove_recursive(hdev->debugfs); @@ -3117,7 +4003,11 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); + hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); + hci_white_list_clear(hdev); + hci_conn_params_clear(hdev); + hci_pend_le_conns_clear(hdev); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -4345,3 +5235,102 @@ static void hci_cmd_work(struct work_struct *work) } } } + +void hci_req_add_le_scan_disable(struct hci_request *req) +{ + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); +} + +void hci_req_add_le_passive_scan(struct hci_request *req) +{ + struct hci_cp_le_set_scan_param param_cp; + struct hci_cp_le_set_scan_enable enable_cp; + struct hci_dev *hdev = req->hdev; + u8 own_addr_type; + + /* Set require_privacy to true to avoid identification from + * unknown peer devices. Since this is passive scanning, no + * SCAN_REQ using the local identity should be sent. Mandating + * privacy is just an extra precaution. + */ + if (hci_update_random_address(req, true, &own_addr_type)) + return; + + memset(¶m_cp, 0, sizeof(param_cp)); + param_cp.type = LE_SCAN_PASSIVE; + param_cp.interval = cpu_to_le16(hdev->le_scan_interval); + param_cp.window = cpu_to_le16(hdev->le_scan_window); + param_cp.own_address_type = own_addr_type; + hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), + ¶m_cp); + + memset(&enable_cp, 0, sizeof(enable_cp)); + enable_cp.enable = LE_SCAN_ENABLE; + enable_cp.filter_dup = LE_SCAN_FILTER_DUP_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), + &enable_cp); +} + +static void update_background_scan_complete(struct hci_dev *hdev, u8 status) +{ + if (status) + BT_DBG("HCI request failed to update background scanning: " + "status 0x%2.2x", status); +} + +/* This function controls the background scanning based on hdev->pend_le_conns + * list. If there are pending LE connection we start the background scanning, + * otherwise we stop it. + * + * This function requires the caller holds hdev->lock. + */ +void hci_update_background_scan(struct hci_dev *hdev) +{ + struct hci_request req; + struct hci_conn *conn; + int err; + + hci_req_init(&req, hdev); + + if (list_empty(&hdev->pend_le_conns)) { + /* If there is no pending LE connections, we should stop + * the background scanning. + */ + + /* If controller is not scanning we are done. */ + if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + return; + + hci_req_add_le_scan_disable(&req); + + BT_DBG("%s stopping background scanning", hdev->name); + } else { + /* If there is at least one pending LE connection, we should + * keep the background scan running. + */ + + /* If controller is already scanning we are done. */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + return; + + /* If controller is connecting, we should not start scanning + * since some controllers are not able to scan and connect at + * the same time. + */ + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + if (conn) + return; + + hci_req_add_le_passive_scan(&req); + + BT_DBG("%s starting background scanning", hdev->name); + } + + err = hci_req_run(&req, update_background_scan_complete); + if (err) + BT_ERR("Failed to run HCI request: err %d", err); +} diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 5f812455a450..c3b0a08f5ab4 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -461,6 +461,34 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) } } +static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb) +{ + u8 status = *((u8 *) skb->data); + struct hci_cp_write_sc_support *sent; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SC_SUPPORT); + if (!sent) + return; + + if (!status) { + if (sent->support) + hdev->features[1][0] |= LMP_HOST_SC; + else + hdev->features[1][0] &= ~LMP_HOST_SC; + } + + if (test_bit(HCI_MGMT, &hdev->dev_flags)) + mgmt_sc_enable_complete(hdev, sent->support, status); + else if (!status) { + if (sent->support) + set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + else + clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + } +} + static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_local_version *rp = (void *) skb->data; @@ -904,16 +932,50 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, hci_dev_unlock(hdev); } -static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_read_local_oob_data(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_rp_read_local_oob_data *rp = (void *) skb->data; BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); - mgmt_read_local_oob_data_reply_complete(hdev, rp->hash, - rp->randomizer, rp->status); + mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->randomizer, + NULL, NULL, rp->status); + hci_dev_unlock(hdev); +} + +static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + hci_dev_lock(hdev); + mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->randomizer192, + rp->hash256, rp->randomizer256, + rp->status); + hci_dev_unlock(hdev); +} + + +static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + bdaddr_t *sent; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_RANDOM_ADDR); + if (!sent) + return; + + hci_dev_lock(hdev); + + if (!status) + bacpy(&hdev->random_addr, sent); + hci_dev_unlock(hdev); } @@ -929,12 +991,8 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (!status) { - if (*sent) - set_bit(HCI_ADVERTISING, &hdev->dev_flags); - else - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); - } + if (!status) + mgmt_advertising(hdev, *sent); hci_dev_unlock(hdev); } @@ -960,7 +1018,19 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, break; case LE_SCAN_DISABLE: + /* Cancel this timer so that we don't try to disable scanning + * when it's already disabled. + */ + cancel_delayed_work(&hdev->le_scan_disable); + clear_bit(HCI_LE_SCAN, &hdev->dev_flags); + /* The HCI_LE_SCAN_INTERRUPTED flag indicates that we + * interrupted scanning due to a connect request. Mark + * therefore discovery as stopped. + */ + if (test_and_clear_bit(HCI_LE_SCAN_INTERRUPTED, + &hdev->dev_flags)) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); break; default: @@ -980,6 +1050,49 @@ static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, hdev->le_white_list_size = rp->size; } +static void hci_cc_le_clear_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (!status) + hci_white_list_clear(hdev); +} + +static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_add_to_white_list *sent; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST); + if (!sent) + return; + + if (!status) + hci_white_list_add(hdev, &sent->bdaddr, sent->bdaddr_type); +} + +static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_del_from_white_list *sent; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST); + if (!sent) + return; + + if (!status) + hci_white_list_del(hdev, &sent->bdaddr, sent->bdaddr_type); +} + static void hci_cc_le_read_supported_states(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1020,6 +1133,25 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, } } +static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_cp_le_set_adv_param *cp; + u8 status = *((u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_PARAM); + if (!cp) + return; + + hci_dev_lock(hdev); + hdev->adv_addr_type = cp->own_address_type; + hci_dev_unlock(hdev); +} + static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1185,9 +1317,12 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, return 0; /* Only request authentication for SSP connections or non-SSP - * devices with sec_level HIGH or if MITM protection is requested */ + * devices with sec_level MEDIUM or HIGH or if MITM protection + * is requested. + */ if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) && - conn->pending_sec_level != BT_SECURITY_HIGH) + conn->pending_sec_level != BT_SECURITY_HIGH && + conn->pending_sec_level != BT_SECURITY_MEDIUM) return 0; return 1; @@ -1518,6 +1653,57 @@ static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status) amp_write_remote_assoc(hdev, cp->phy_handle); } +static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_create_conn *cp; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + /* All connection failure handling is taken care of by the + * hci_le_conn_failed function which is triggered by the HCI + * request completion callbacks used for connecting. + */ + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN); + if (!cp) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->peer_addr); + if (!conn) + goto unlock; + + /* Store the initiator and responder address information which + * is needed for SMP. These values will not change during the + * lifetime of the connection. + */ + conn->init_addr_type = cp->own_address_type; + if (cp->own_address_type == ADDR_LE_DEV_RANDOM) + bacpy(&conn->init_addr, &hdev->random_addr); + else + bacpy(&conn->init_addr, &hdev->bdaddr); + + conn->resp_addr_type = cp->peer_addr_type; + bacpy(&conn->resp_addr, &cp->peer_addr); + + /* We don't want the connection attempt to stick around + * indefinitely since LE doesn't have a page timeout concept + * like BR/EDR. Set a timer for any connection that doesn't use + * the white list for connecting. + */ + if (cp->filter_policy == HCI_LE_USE_PEER_ADDR) + queue_delayed_work(conn->hdev->workqueue, + &conn->le_conn_timeout, + HCI_LE_CONN_TIMEOUT); + +unlock: + hci_dev_unlock(hdev); +} + static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1659,7 +1845,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) } else { conn->state = BT_CLOSED; if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &ev->bdaddr, conn->type, + mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, ev->status); } @@ -1780,7 +1966,9 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_disconn_complete *ev = (void *) skb->data; u8 reason = hci_to_mgmt_reason(ev->reason); + struct hci_conn_params *params; struct hci_conn *conn; + bool mgmt_connected; u8 type; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -1799,13 +1987,30 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->state = BT_CLOSED; - if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_disconnected(hdev, &conn->dst, conn->type, - conn->dst_type, reason); + mgmt_connected = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags); + mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, + reason, mgmt_connected); if (conn->type == ACL_LINK && conn->flush_key) hci_remove_link_key(hdev, &conn->dst); + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + switch (params->auto_connect) { + case HCI_AUTO_CONN_LINK_LOSS: + if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) + break; + /* Fall through */ + + case HCI_AUTO_CONN_ALWAYS: + hci_pend_le_conn_add(hdev, &conn->dst, conn->dst_type); + break; + + default: + break; + } + } + type = conn->type; hci_proto_disconn_cfm(conn, ev->reason); @@ -1943,35 +2148,46 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); - if (conn) { - if (!ev->status) { - if (ev->encrypt) { - /* Encryption implies authentication */ - conn->link_mode |= HCI_LM_AUTH; - conn->link_mode |= HCI_LM_ENCRYPT; - conn->sec_level = conn->pending_sec_level; - } else - conn->link_mode &= ~HCI_LM_ENCRYPT; - } + if (!conn) + goto unlock; - clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + if (!ev->status) { + if (ev->encrypt) { + /* Encryption implies authentication */ + conn->link_mode |= HCI_LM_AUTH; + conn->link_mode |= HCI_LM_ENCRYPT; + conn->sec_level = conn->pending_sec_level; - if (ev->status && conn->state == BT_CONNECTED) { - hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); - hci_conn_drop(conn); - goto unlock; + /* P-256 authentication key implies FIPS */ + if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256) + conn->link_mode |= HCI_LM_FIPS; + + if ((conn->type == ACL_LINK && ev->encrypt == 0x02) || + conn->type == LE_LINK) + set_bit(HCI_CONN_AES_CCM, &conn->flags); + } else { + conn->link_mode &= ~HCI_LM_ENCRYPT; + clear_bit(HCI_CONN_AES_CCM, &conn->flags); } + } - if (conn->state == BT_CONFIG) { - if (!ev->status) - conn->state = BT_CONNECTED; + clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - hci_proto_connect_cfm(conn, ev->status); - hci_conn_drop(conn); - } else - hci_encrypt_cfm(conn, ev->status, ev->encrypt); + if (ev->status && conn->state == BT_CONNECTED) { + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; } + if (conn->state == BT_CONFIG) { + if (!ev->status) + conn->state = BT_CONNECTED; + + hci_proto_connect_cfm(conn, ev->status); + hci_conn_drop(conn); + } else + hci_encrypt_cfm(conn, ev->status, ev->encrypt); + unlock: hci_dev_unlock(hdev); } @@ -2144,6 +2360,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_ssp_mode(hdev, skb); break; + case HCI_OP_WRITE_SC_SUPPORT: + hci_cc_write_sc_support(hdev, skb); + break; + case HCI_OP_READ_LOCAL_VERSION: hci_cc_read_local_version(hdev, skb); break; @@ -2213,7 +2433,11 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) break; case HCI_OP_READ_LOCAL_OOB_DATA: - hci_cc_read_local_oob_data_reply(hdev, skb); + hci_cc_read_local_oob_data(hdev, skb); + break; + + case HCI_OP_READ_LOCAL_OOB_EXT_DATA: + hci_cc_read_local_oob_ext_data(hdev, skb); break; case HCI_OP_LE_READ_BUFFER_SIZE: @@ -2244,6 +2468,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_user_passkey_neg_reply(hdev, skb); break; + case HCI_OP_LE_SET_RANDOM_ADDR: + hci_cc_le_set_random_addr(hdev, skb); + break; + case HCI_OP_LE_SET_ADV_ENABLE: hci_cc_le_set_adv_enable(hdev, skb); break; @@ -2256,6 +2484,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_le_read_white_list_size(hdev, skb); break; + case HCI_OP_LE_CLEAR_WHITE_LIST: + hci_cc_le_clear_white_list(hdev, skb); + break; + + case HCI_OP_LE_ADD_TO_WHITE_LIST: + hci_cc_le_add_to_white_list(hdev, skb); + break; + + case HCI_OP_LE_DEL_FROM_WHITE_LIST: + hci_cc_le_del_from_white_list(hdev, skb); + break; + case HCI_OP_LE_READ_SUPPORTED_STATES: hci_cc_le_read_supported_states(hdev, skb); break; @@ -2264,6 +2504,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_le_host_supported(hdev, skb); break; + case HCI_OP_LE_SET_ADV_PARAM: + hci_cc_set_adv_param(hdev, skb); + break; + case HCI_OP_WRITE_REMOTE_AMP_ASSOC: hci_cc_write_remote_amp_assoc(hdev, skb); break; @@ -2351,6 +2595,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cs_accept_phylink(hdev, ev->status); break; + case HCI_OP_LE_CREATE_CONN: + hci_cs_le_create_conn(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; @@ -2630,7 +2878,8 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { - if (key->type == HCI_LK_UNAUTH_COMBINATION && + if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 || + key->type == HCI_LK_UNAUTH_COMBINATION_P256) && conn->auth_type != 0xff && (conn->auth_type & 0x01)) { BT_DBG("%s ignoring unauthenticated key", hdev->name); goto not_found; @@ -2844,6 +3093,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, * features do not indicate SSP support */ clear_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } + + if (ev->features[0] & LMP_HOST_SC) + set_bit(HCI_CONN_SC_ENABLED, &conn->flags); } if (conn->state != BT_CONFIG) @@ -3337,20 +3589,36 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, data = hci_find_remote_oob_data(hdev, &ev->bdaddr); if (data) { - struct hci_cp_remote_oob_data_reply cp; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) { + struct hci_cp_remote_oob_ext_data_reply cp; - bacpy(&cp.bdaddr, &ev->bdaddr); - memcpy(cp.hash, data->hash, sizeof(cp.hash)); - memcpy(cp.randomizer, data->randomizer, sizeof(cp.randomizer)); + bacpy(&cp.bdaddr, &ev->bdaddr); + memcpy(cp.hash192, data->hash192, sizeof(cp.hash192)); + memcpy(cp.randomizer192, data->randomizer192, + sizeof(cp.randomizer192)); + memcpy(cp.hash256, data->hash256, sizeof(cp.hash256)); + memcpy(cp.randomizer256, data->randomizer256, + sizeof(cp.randomizer256)); + + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY, + sizeof(cp), &cp); + } else { + struct hci_cp_remote_oob_data_reply cp; + + bacpy(&cp.bdaddr, &ev->bdaddr); + memcpy(cp.hash, data->hash192, sizeof(cp.hash)); + memcpy(cp.randomizer, data->randomizer192, + sizeof(cp.randomizer)); - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp), - &cp); + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, + sizeof(cp), &cp); + } } else { struct hci_cp_remote_oob_data_neg_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, sizeof(cp), - &cp); + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, + sizeof(cp), &cp); } unlock: @@ -3484,6 +3752,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; + struct smp_irk *irk; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -3514,19 +3783,70 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->out = true; conn->link_mode |= HCI_LM_MASTER; } + + /* If we didn't have a hci_conn object previously + * but we're in master role this must be something + * initiated using a white list. Since white list based + * connections are not "first class citizens" we don't + * have full tracking of them. Therefore, we go ahead + * with a "best effort" approach of determining the + * initiator address based on the HCI_PRIVACY flag. + */ + if (conn->out) { + conn->resp_addr_type = ev->bdaddr_type; + bacpy(&conn->resp_addr, &ev->bdaddr); + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, &hdev->rpa); + } else { + hci_copy_identity_address(hdev, + &conn->init_addr, + &conn->init_addr_type); + } + } else { + /* Set the responder (our side) address type based on + * the advertising address type. + */ + conn->resp_addr_type = hdev->adv_addr_type; + if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) + bacpy(&conn->resp_addr, &hdev->random_addr); + else + bacpy(&conn->resp_addr, &hdev->bdaddr); + + conn->init_addr_type = ev->bdaddr_type; + bacpy(&conn->init_addr, &ev->bdaddr); + } + } else { + cancel_delayed_work(&conn->le_conn_timeout); + } + + /* Ensure that the hci_conn contains the identity address type + * regardless of which address the connection was made with. + */ + hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + + /* Lookup the identity address from the stored connection + * address and address type. + * + * When establishing connections to an identity address, the + * connection procedure will store the resolvable random + * address first. Now if it can be converted back into the + * identity address, start using the identity address from + * now on. + */ + irk = hci_get_irk(hdev, &conn->dst, conn->dst_type); + if (irk) { + bacpy(&conn->dst, &irk->bdaddr); + conn->dst_type = irk->addr_type; } if (ev->status) { - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); - hci_proto_connect_cfm(conn, ev->status); - conn->state = BT_CLOSED; - hci_conn_del(conn); + hci_le_conn_failed(conn, ev->status); goto unlock; } if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, &ev->bdaddr, conn->type, + mgmt_device_connected(hdev, &conn->dst, conn->type, conn->dst_type, 0, NULL, 0, NULL); conn->sec_level = BT_SECURITY_LOW; @@ -3540,25 +3860,73 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_proto_connect_cfm(conn, ev->status); + hci_pend_le_conn_del(hdev, &conn->dst, conn->dst_type); + unlock: hci_dev_unlock(hdev); } +/* This function requires the caller holds hdev->lock */ +static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, + u8 addr_type) +{ + struct hci_conn *conn; + struct smp_irk *irk; + + /* If this is a resolvable address, we should resolve it and then + * update address and address type variables. + */ + irk = hci_get_irk(hdev, addr, addr_type); + if (irk) { + addr = &irk->bdaddr; + addr_type = irk->addr_type; + } + + if (!hci_pend_le_conn_lookup(hdev, addr, addr_type)) + return; + + conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, + HCI_AT_NO_BONDING); + if (!IS_ERR(conn)) + return; + + switch (PTR_ERR(conn)) { + case -EBUSY: + /* If hci_connect() returns -EBUSY it means there is already + * an LE connection attempt going on. Since controllers don't + * support more than one connection attempt at the time, we + * don't consider this an error case. + */ + break; + default: + BT_DBG("Failed to connect: err %ld", PTR_ERR(conn)); + } +} + static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) { u8 num_reports = skb->data[0]; void *ptr = &skb->data[1]; s8 rssi; + hci_dev_lock(hdev); + while (num_reports--) { struct hci_ev_le_advertising_info *ev = ptr; + if (ev->evt_type == LE_ADV_IND || + ev->evt_type == LE_ADV_DIRECT_IND) + check_pending_le_conn(hdev, &ev->bdaddr, + ev->bdaddr_type); + rssi = ev->data[ev->length]; mgmt_device_found(hdev, &ev->bdaddr, LE_LINK, ev->bdaddr_type, NULL, rssi, 0, 1, ev->data, ev->length); ptr += sizeof(*ev) + ev->length + 1; } + + hci_dev_unlock(hdev); } static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -3577,7 +3945,7 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) if (conn == NULL) goto not_found; - ltk = hci_find_ltk(hdev, ev->ediv, ev->random); + ltk = hci_find_ltk(hdev, ev->ediv, ev->rand, conn->out); if (ltk == NULL) goto not_found; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 7552f9e3089c..68e51a84e72d 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -716,6 +716,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, err = hci_dev_open(hdev->id); if (err) { clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags); + mgmt_index_added(hdev); hci_dev_put(hdev); goto done; } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 0b61250cfdf9..555982a78a58 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -49,14 +49,7 @@ static struct attribute *bt_link_attrs[] = { NULL }; -static struct attribute_group bt_link_group = { - .attrs = bt_link_attrs, -}; - -static const struct attribute_group *bt_link_groups[] = { - &bt_link_group, - NULL -}; +ATTRIBUTE_GROUPS(bt_link); static void bt_link_release(struct device *dev) { @@ -182,14 +175,7 @@ static struct attribute *bt_host_attrs[] = { NULL }; -static struct attribute_group bt_host_group = { - .attrs = bt_host_attrs, -}; - -static const struct attribute_group *bt_host_groups[] = { - &bt_host_group, - NULL -}; +ATTRIBUTE_GROUPS(bt_host); static void bt_host_release(struct device *dev) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b0ad2c752d73..9ed2168fa59f 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -42,6 +42,8 @@ #include "amp.h" #include "6lowpan.h" +#define LE_FLOWCTL_MAX_CREDITS 65535 + bool disable_ertm; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN | L2CAP_FEAT_UCD; @@ -330,44 +332,20 @@ static inline bool l2cap_seq_list_contains(struct l2cap_seq_list *seq_list, return seq_list->list[seq & seq_list->mask] != L2CAP_SEQ_LIST_CLEAR; } -static u16 l2cap_seq_list_remove(struct l2cap_seq_list *seq_list, u16 seq) +static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list) { + u16 seq = seq_list->head; u16 mask = seq_list->mask; - if (seq_list->head == L2CAP_SEQ_LIST_CLEAR) { - /* In case someone tries to pop the head of an empty list */ - return L2CAP_SEQ_LIST_CLEAR; - } else if (seq_list->head == seq) { - /* Head can be removed in constant time */ - seq_list->head = seq_list->list[seq & mask]; - seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - - if (seq_list->head == L2CAP_SEQ_LIST_TAIL) { - seq_list->head = L2CAP_SEQ_LIST_CLEAR; - seq_list->tail = L2CAP_SEQ_LIST_CLEAR; - } - } else { - /* Walk the list to find the sequence number */ - u16 prev = seq_list->head; - while (seq_list->list[prev & mask] != seq) { - prev = seq_list->list[prev & mask]; - if (prev == L2CAP_SEQ_LIST_TAIL) - return L2CAP_SEQ_LIST_CLEAR; - } + seq_list->head = seq_list->list[seq & mask]; + seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - /* Unlink the number from the list and clear it */ - seq_list->list[prev & mask] = seq_list->list[seq & mask]; - seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - if (seq_list->tail == seq) - seq_list->tail = prev; + if (seq_list->head == L2CAP_SEQ_LIST_TAIL) { + seq_list->head = L2CAP_SEQ_LIST_CLEAR; + seq_list->tail = L2CAP_SEQ_LIST_CLEAR; } - return seq; -} -static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list) -{ - /* Remove the head in constant time */ - return l2cap_seq_list_remove(seq_list, seq_list->head); + return seq; } static void l2cap_seq_list_clear(struct l2cap_seq_list *seq_list) @@ -506,7 +484,7 @@ static void l2cap_le_flowctl_init(struct l2cap_chan *chan) chan->sdu_len = 0; chan->tx_credits = 0; chan->rx_credits = le_max_credits; - chan->mps = min_t(u16, chan->imtu, L2CAP_LE_DEFAULT_MPS); + chan->mps = min_t(u16, chan->imtu, le_default_mps); skb_queue_head_init(&chan->tx_q); } @@ -522,18 +500,10 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) switch (chan->chan_type) { case L2CAP_CHAN_CONN_ORIENTED: - if (conn->hcon->type == LE_LINK) { - if (chan->dcid == L2CAP_CID_ATT) { - chan->omtu = L2CAP_DEFAULT_MTU; - chan->scid = L2CAP_CID_ATT; - } else { - chan->scid = l2cap_alloc_cid(conn); - } - } else { - /* Alloc CID for connection-oriented socket */ - chan->scid = l2cap_alloc_cid(conn); + /* Alloc CID for connection-oriented socket */ + chan->scid = l2cap_alloc_cid(conn); + if (conn->hcon->type == ACL_LINK) chan->omtu = L2CAP_DEFAULT_MTU; - } break; case L2CAP_CHAN_CONN_LESS: @@ -543,11 +513,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->omtu = L2CAP_DEFAULT_MTU; break; - case L2CAP_CHAN_CONN_FIX_A2MP: - chan->scid = L2CAP_CID_A2MP; - chan->dcid = L2CAP_CID_A2MP; - chan->omtu = L2CAP_A2MP_DEFAULT_MTU; - chan->imtu = L2CAP_A2MP_DEFAULT_MTU; + case L2CAP_CHAN_FIXED: + /* Caller will set CID and CID specific MTU values */ break; default: @@ -595,7 +562,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) chan->conn = NULL; - if (chan->chan_type != L2CAP_CHAN_CONN_FIX_A2MP) + if (chan->scid != L2CAP_CID_A2MP) hci_conn_drop(conn->hcon); if (mgr && mgr->bredr_chan == chan) @@ -642,6 +609,23 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) return; } +void l2cap_conn_update_id_addr(struct hci_conn *hcon) +{ + struct l2cap_conn *conn = hcon->l2cap_data; + struct l2cap_chan *chan; + + mutex_lock(&conn->chan_lock); + + list_for_each_entry(chan, &conn->chan_l, list) { + l2cap_chan_lock(chan); + bacpy(&chan->dst, &hcon->dst); + chan->dst_type = bdaddr_type(hcon, hcon->dst_type); + l2cap_chan_unlock(chan); + } + + mutex_unlock(&conn->chan_lock); +} + static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -699,10 +683,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) case BT_CONNECTED: case BT_CONFIG: - /* ATT uses L2CAP_CHAN_CONN_ORIENTED so we must also - * check for chan->psm. - */ - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && chan->psm) { + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) { __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); l2cap_send_disconn_req(chan, reason); } else @@ -737,6 +718,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) case L2CAP_CHAN_RAW: switch (chan->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: return HCI_AT_DEDICATED_BONDING_MITM; case BT_SECURITY_MEDIUM: return HCI_AT_DEDICATED_BONDING; @@ -749,7 +731,8 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) if (chan->sec_level == BT_SECURITY_LOW) chan->sec_level = BT_SECURITY_SDP; } - if (chan->sec_level == BT_SECURITY_HIGH) + if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) return HCI_AT_NO_BONDING_MITM; else return HCI_AT_NO_BONDING; @@ -759,7 +742,8 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) if (chan->sec_level == BT_SECURITY_LOW) chan->sec_level = BT_SECURITY_SDP; - if (chan->sec_level == BT_SECURITY_HIGH) + if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) return HCI_AT_NO_BONDING_MITM; else return HCI_AT_NO_BONDING; @@ -768,6 +752,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) default: switch (chan->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: return HCI_AT_GENERAL_BONDING_MITM; case BT_SECURITY_MEDIUM: return HCI_AT_GENERAL_BONDING; @@ -1330,7 +1315,7 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) __clear_ack_timer(chan); } - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_state_change(chan, BT_DISCONN); return; } @@ -1493,8 +1478,6 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) if (!chan) goto clean; - chan->dcid = L2CAP_CID_ATT; - bacpy(&chan->src, &hcon->src); bacpy(&chan->dst, &hcon->dst); chan->src_type = bdaddr_type(hcon, hcon->src_type); @@ -1528,7 +1511,7 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_chan_unlock(chan); continue; } @@ -1546,6 +1529,8 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) } mutex_unlock(&conn->chan_lock); + + queue_work(hcon->hdev->workqueue, &conn->pending_rx_work); } /* Notify sockets that we cannot guaranty reliability anymore */ @@ -1671,6 +1656,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) kfree_skb(conn->rx_skb); + skb_queue_purge(&conn->pending_rx); + flush_work(&conn->pending_rx_work); + l2cap_unregister_all_users(conn); mutex_lock(&conn->chan_lock); @@ -1718,66 +1706,6 @@ static void security_timeout(struct work_struct *work) } } -static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) -{ - struct l2cap_conn *conn = hcon->l2cap_data; - struct hci_chan *hchan; - - if (conn) - return conn; - - hchan = hci_chan_create(hcon); - if (!hchan) - return NULL; - - conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); - if (!conn) { - hci_chan_del(hchan); - return NULL; - } - - kref_init(&conn->ref); - hcon->l2cap_data = conn; - conn->hcon = hcon; - hci_conn_get(conn->hcon); - conn->hchan = hchan; - - BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); - - switch (hcon->type) { - case LE_LINK: - if (hcon->hdev->le_mtu) { - conn->mtu = hcon->hdev->le_mtu; - break; - } - /* fall through */ - default: - conn->mtu = hcon->hdev->acl_mtu; - break; - } - - conn->feat_mask = 0; - - if (hcon->type == ACL_LINK) - conn->hs_enabled = test_bit(HCI_HS_ENABLED, - &hcon->hdev->dev_flags); - - spin_lock_init(&conn->lock); - mutex_init(&conn->chan_lock); - - INIT_LIST_HEAD(&conn->chan_l); - INIT_LIST_HEAD(&conn->users); - - if (hcon->type == LE_LINK) - INIT_DELAYED_WORK(&conn->security_timer, security_timeout); - else - INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout); - - conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM; - - return conn; -} - static void l2cap_conn_free(struct kref *ref) { struct l2cap_conn *conn = container_of(ref, struct l2cap_conn, ref); @@ -1848,154 +1776,6 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, return c1; } -static bool is_valid_psm(u16 psm, u8 dst_type) -{ - if (!psm) - return false; - - if (bdaddr_type_is_le(dst_type)) - return (psm <= 0x00ff); - - /* PSM must be odd and lsb of upper byte must be 0 */ - return ((psm & 0x0101) == 0x0001); -} - -int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type) -{ - struct l2cap_conn *conn; - struct hci_conn *hcon; - struct hci_dev *hdev; - __u8 auth_type; - int err; - - BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, - dst_type, __le16_to_cpu(psm)); - - hdev = hci_get_route(dst, &chan->src); - if (!hdev) - return -EHOSTUNREACH; - - hci_dev_lock(hdev); - - l2cap_chan_lock(chan); - - if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid && - chan->chan_type != L2CAP_CHAN_RAW) { - err = -EINVAL; - goto done; - } - - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !(psm || cid)) { - err = -EINVAL; - goto done; - } - - switch (chan->mode) { - case L2CAP_MODE_BASIC: - break; - case L2CAP_MODE_LE_FLOWCTL: - l2cap_le_flowctl_init(chan); - break; - case L2CAP_MODE_ERTM: - case L2CAP_MODE_STREAMING: - if (!disable_ertm) - break; - /* fall through */ - default: - err = -ENOTSUPP; - goto done; - } - - switch (chan->state) { - case BT_CONNECT: - case BT_CONNECT2: - case BT_CONFIG: - /* Already connecting */ - err = 0; - goto done; - - case BT_CONNECTED: - /* Already connected */ - err = -EISCONN; - goto done; - - case BT_OPEN: - case BT_BOUND: - /* Can connect */ - break; - - default: - err = -EBADFD; - goto done; - } - - /* Set destination address and psm */ - bacpy(&chan->dst, dst); - chan->dst_type = dst_type; - - chan->psm = psm; - chan->dcid = cid; - - auth_type = l2cap_get_auth_type(chan); - - if (bdaddr_type_is_le(dst_type)) - hcon = hci_connect(hdev, LE_LINK, dst, dst_type, - chan->sec_level, auth_type); - else - hcon = hci_connect(hdev, ACL_LINK, dst, dst_type, - chan->sec_level, auth_type); - - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto done; - } - - conn = l2cap_conn_add(hcon); - if (!conn) { - hci_conn_drop(hcon); - err = -ENOMEM; - goto done; - } - - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { - hci_conn_drop(hcon); - err = -EBUSY; - goto done; - } - - /* Update source addr of the socket */ - bacpy(&chan->src, &hcon->src); - chan->src_type = bdaddr_type(hcon, hcon->src_type); - - l2cap_chan_unlock(chan); - l2cap_chan_add(conn, chan); - l2cap_chan_lock(chan); - - /* l2cap_chan_add takes its own ref so we can drop this one */ - hci_conn_drop(hcon); - - l2cap_state_change(chan, BT_CONNECT); - __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); - - if (hcon->state == BT_CONNECTED) { - if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { - __clear_chan_timer(chan); - if (l2cap_chan_check_security(chan)) - l2cap_state_change(chan, BT_CONNECTED); - } else - l2cap_do_start(chan); - } - - err = 0; - -done: - l2cap_chan_unlock(chan); - hci_dev_unlock(hdev); - hci_dev_put(hdev); - return err; -} - static void l2cap_monitor_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, @@ -2654,6 +2434,14 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, if (IS_ERR(skb)) return PTR_ERR(skb); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return -ENOTCONN; + } + l2cap_do_send(chan, skb); return len; } @@ -2703,6 +2491,14 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, if (IS_ERR(skb)) return PTR_ERR(skb); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return -ENOTCONN; + } + l2cap_do_send(chan, skb); err = len; break; @@ -5709,7 +5505,7 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, { struct l2cap_le_credits *pkt; struct l2cap_chan *chan; - u16 cid, credits; + u16 cid, credits, max_credits; if (cmd_len != sizeof(*pkt)) return -EPROTO; @@ -5724,6 +5520,17 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (!chan) return -EBADSLT; + max_credits = LE_FLOWCTL_MAX_CREDITS - chan->tx_credits; + if (credits > max_credits) { + BT_ERR("LE credits overflow"); + l2cap_send_disconn_req(chan, ECONNRESET); + + /* Return 0 so that we don't trigger an unnecessary + * command reject packet. + */ + return 0; + } + chan->tx_credits += credits; while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) { @@ -5770,17 +5577,6 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn, { int err = 0; - if (!enable_lecoc) { - switch (cmd->code) { - case L2CAP_LE_CONN_REQ: - case L2CAP_LE_CONN_RSP: - case L2CAP_LE_CREDITS: - case L2CAP_DISCONN_REQ: - case L2CAP_DISCONN_RSP: - return -EINVAL; - } - } - switch (cmd->code) { case L2CAP_COMMAND_REJ: l2cap_le_command_rej(conn, cmd, cmd_len, data); @@ -6871,6 +6667,7 @@ static int l2cap_le_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) if (!chan->rx_credits) { BT_ERR("No credits to receive LE L2CAP data"); + l2cap_send_disconn_req(chan, ECONNRESET); return -ENOBUFS; } @@ -6995,8 +6792,10 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, * But we don't have any other choice. L2CAP doesn't * provide flow control mechanism. */ - if (chan->imtu < skb->len) + if (chan->imtu < skb->len) { + BT_ERR("Dropping L2CAP data: receive buffer overflow"); goto drop; + } if (!chan->ops->recv(chan, skb)) goto done; @@ -7084,9 +6883,16 @@ drop: static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) { struct l2cap_hdr *lh = (void *) skb->data; + struct hci_conn *hcon = conn->hcon; u16 cid, len; __le16 psm; + if (hcon->state != BT_CONNECTED) { + BT_DBG("queueing pending rx skb"); + skb_queue_tail(&conn->pending_rx, skb); + return; + } + skb_pull(skb, L2CAP_HDR_SIZE); cid = __le16_to_cpu(lh->cid); len = __le16_to_cpu(lh->len); @@ -7132,6 +6938,247 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) } } +static void process_pending_rx(struct work_struct *work) +{ + struct l2cap_conn *conn = container_of(work, struct l2cap_conn, + pending_rx_work); + struct sk_buff *skb; + + BT_DBG(""); + + while ((skb = skb_dequeue(&conn->pending_rx))) + l2cap_recv_frame(conn, skb); +} + +static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) +{ + struct l2cap_conn *conn = hcon->l2cap_data; + struct hci_chan *hchan; + + if (conn) + return conn; + + hchan = hci_chan_create(hcon); + if (!hchan) + return NULL; + + conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); + if (!conn) { + hci_chan_del(hchan); + return NULL; + } + + kref_init(&conn->ref); + hcon->l2cap_data = conn; + conn->hcon = hcon; + hci_conn_get(conn->hcon); + conn->hchan = hchan; + + BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); + + switch (hcon->type) { + case LE_LINK: + if (hcon->hdev->le_mtu) { + conn->mtu = hcon->hdev->le_mtu; + break; + } + /* fall through */ + default: + conn->mtu = hcon->hdev->acl_mtu; + break; + } + + conn->feat_mask = 0; + + if (hcon->type == ACL_LINK) + conn->hs_enabled = test_bit(HCI_HS_ENABLED, + &hcon->hdev->dev_flags); + + spin_lock_init(&conn->lock); + mutex_init(&conn->chan_lock); + + INIT_LIST_HEAD(&conn->chan_l); + INIT_LIST_HEAD(&conn->users); + + if (hcon->type == LE_LINK) + INIT_DELAYED_WORK(&conn->security_timer, security_timeout); + else + INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout); + + skb_queue_head_init(&conn->pending_rx); + INIT_WORK(&conn->pending_rx_work, process_pending_rx); + + conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM; + + return conn; +} + +static bool is_valid_psm(u16 psm, u8 dst_type) { + if (!psm) + return false; + + if (bdaddr_type_is_le(dst_type)) + return (psm <= 0x00ff); + + /* PSM must be odd and lsb of upper byte must be 0 */ + return ((psm & 0x0101) == 0x0001); +} + +int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, + bdaddr_t *dst, u8 dst_type) +{ + struct l2cap_conn *conn; + struct hci_conn *hcon; + struct hci_dev *hdev; + __u8 auth_type; + int err; + + BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, + dst_type, __le16_to_cpu(psm)); + + hdev = hci_get_route(dst, &chan->src); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + + l2cap_chan_lock(chan); + + if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid && + chan->chan_type != L2CAP_CHAN_RAW) { + err = -EINVAL; + goto done; + } + + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !psm) { + err = -EINVAL; + goto done; + } + + if (chan->chan_type == L2CAP_CHAN_FIXED && !cid) { + err = -EINVAL; + goto done; + } + + switch (chan->mode) { + case L2CAP_MODE_BASIC: + break; + case L2CAP_MODE_LE_FLOWCTL: + l2cap_le_flowctl_init(chan); + break; + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + if (!disable_ertm) + break; + /* fall through */ + default: + err = -ENOTSUPP; + goto done; + } + + switch (chan->state) { + case BT_CONNECT: + case BT_CONNECT2: + case BT_CONFIG: + /* Already connecting */ + err = 0; + goto done; + + case BT_CONNECTED: + /* Already connected */ + err = -EISCONN; + goto done; + + case BT_OPEN: + case BT_BOUND: + /* Can connect */ + break; + + default: + err = -EBADFD; + goto done; + } + + /* Set destination address and psm */ + bacpy(&chan->dst, dst); + chan->dst_type = dst_type; + + chan->psm = psm; + chan->dcid = cid; + + auth_type = l2cap_get_auth_type(chan); + + if (bdaddr_type_is_le(dst_type)) { + /* Convert from L2CAP channel address type to HCI address type + */ + if (dst_type == BDADDR_LE_PUBLIC) + dst_type = ADDR_LE_DEV_PUBLIC; + else + dst_type = ADDR_LE_DEV_RANDOM; + + hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level, + auth_type); + } else { + hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type); + } + + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto done; + } + + conn = l2cap_conn_add(hcon); + if (!conn) { + hci_conn_drop(hcon); + err = -ENOMEM; + goto done; + } + + if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { + hci_conn_drop(hcon); + err = -EBUSY; + goto done; + } + + /* Update source addr of the socket */ + bacpy(&chan->src, &hcon->src); + chan->src_type = bdaddr_type(hcon, hcon->src_type); + + l2cap_chan_unlock(chan); + l2cap_chan_add(conn, chan); + l2cap_chan_lock(chan); + + /* l2cap_chan_add takes its own ref so we can drop this one */ + hci_conn_drop(hcon); + + l2cap_state_change(chan, BT_CONNECT); + __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); + + /* Release chan->sport so that it can be reused by other + * sockets (as it's only used for listening sockets). + */ + write_lock(&chan_list_lock); + chan->sport = 0; + write_unlock(&chan_list_lock); + + if (hcon->state == BT_CONNECTED) { + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + __clear_chan_timer(chan); + if (l2cap_chan_check_security(chan)) + l2cap_state_change(chan, BT_CONNECTED); + } else + l2cap_do_start(chan); + } + + err = 0; + +done: + l2cap_chan_unlock(chan); + hci_dev_unlock(hdev); + hci_dev_put(hdev); + return err; +} + /* ---- L2CAP interface with lower layer (HCI) ---- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -7206,7 +7253,8 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { __set_chan_timer(chan, L2CAP_ENC_TIMEOUT); - } else if (chan->sec_level == BT_SECURITY_HIGH) + } else if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) l2cap_chan_close(chan, ECONNREFUSED); } else { if (chan->sec_level == BT_SECURITY_MEDIUM) @@ -7226,7 +7274,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (hcon->type == LE_LINK) { if (!status && encrypt) - smp_distribute_keys(conn, 0); + smp_distribute_keys(conn); cancel_delayed_work(&conn->security_timer); } @@ -7238,7 +7286,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, state_to_string(chan->state)); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_chan_unlock(chan); continue; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d58f76bcebd1..b247f9d27fed 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -36,8 +36,6 @@ #include "smp.h" -bool enable_lecoc; - static struct bt_sock_list l2cap_sk_list = { .lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock) }; @@ -101,9 +99,16 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) if (!bdaddr_type_is_valid(la.l2_bdaddr_type)) return -EINVAL; + if (la.l2_cid) { + /* When the socket gets created it defaults to + * CHAN_CONN_ORIENTED, so we need to overwrite the + * default here. + */ + chan->chan_type = L2CAP_CHAN_FIXED; + chan->omtu = L2CAP_DEFAULT_MTU; + } + if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - if (!enable_lecoc && la.l2_psm) - return -EINVAL; /* We only allow ATT user space socket */ if (la.l2_cid && la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) @@ -220,8 +225,6 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - if (!enable_lecoc && la.l2_psm) - return -EINVAL; /* We only allow ATT user space socket */ if (la.l2_cid && la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) @@ -357,17 +360,20 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); + if (peer && sk->sk_state != BT_CONNECTED) + return -ENOTCONN; + memset(la, 0, sizeof(struct sockaddr_l2)); addr->sa_family = AF_BLUETOOTH; *len = sizeof(struct sockaddr_l2); + la->l2_psm = chan->psm; + if (peer) { - la->l2_psm = chan->psm; bacpy(&la->l2_bdaddr, &chan->dst); la->l2_cid = cpu_to_le16(chan->dcid); la->l2_bdaddr_type = chan->dst_type; } else { - la->l2_psm = chan->sport; bacpy(&la->l2_bdaddr, &chan->src); la->l2_cid = cpu_to_le16(chan->scid); la->l2_bdaddr_type = chan->src_type; @@ -432,6 +438,10 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT | L2CAP_LM_SECURE; break; + case BT_SECURITY_FIPS: + opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT | + L2CAP_LM_SECURE | L2CAP_LM_FIPS; + break; default: opt = 0; break; @@ -445,6 +455,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, if (put_user(opt, (u32 __user *) optval)) err = -EFAULT; + break; case L2CAP_CONNINFO: @@ -499,6 +510,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_FIXED && chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; @@ -560,11 +572,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_SNDMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -580,11 +587,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_RCVMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -699,6 +701,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; } + if (opt & L2CAP_LM_FIPS) { + err = -EINVAL; + break; + } + if (opt & L2CAP_LM_AUTH) chan->sec_level = BT_SECURITY_LOW; if (opt & L2CAP_LM_ENCRYPT) @@ -750,6 +757,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_FIXED && chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; @@ -895,11 +903,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_SNDMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -912,11 +915,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_RCVMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -1449,6 +1447,11 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->tx_credits = pchan->tx_credits; chan->rx_credits = pchan->rx_credits; + if (chan->chan_type == L2CAP_CHAN_FIXED) { + chan->scid = pchan->scid; + chan->dcid = pchan->scid; + } + security_sk_clone(parent, sk); } else { switch (sk->sk_type) { @@ -1614,6 +1617,3 @@ void l2cap_cleanup_sockets(void) bt_sock_unregister(BTPROTO_L2CAP); proto_unregister(&l2cap_proto); } - -module_param(enable_lecoc, bool, 0644); -MODULE_PARM_DESC(enable_lecoc, "Enable support for LE CoC"); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index a03ca3ca91bf..98e9df3556e7 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -34,7 +34,7 @@ #include "smp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 4 +#define MGMT_REVISION 5 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -79,6 +79,10 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_BREDR, MGMT_OP_SET_STATIC_ADDRESS, MGMT_OP_SET_SCAN_PARAMS, + MGMT_OP_SET_SECURE_CONN, + MGMT_OP_SET_DEBUG_KEYS, + MGMT_OP_SET_PRIVACY, + MGMT_OP_LOAD_IRKS, }; static const u16 mgmt_events[] = { @@ -103,6 +107,7 @@ static const u16 mgmt_events[] = { MGMT_EV_DEVICE_UNBLOCKED, MGMT_EV_DEVICE_UNPAIRED, MGMT_EV_PASSKEY_NOTIFY, + MGMT_EV_NEW_IRK, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -127,7 +132,7 @@ static u8 mgmt_status_table[] = { MGMT_STATUS_FAILED, /* Hardware Failure */ MGMT_STATUS_CONNECT_FAILED, /* Page Timeout */ MGMT_STATUS_AUTH_FAILED, /* Authentication Failed */ - MGMT_STATUS_NOT_PAIRED, /* PIN or Key Missing */ + MGMT_STATUS_AUTH_FAILED, /* PIN or Key Missing */ MGMT_STATUS_NO_RESOURCES, /* Memory Full */ MGMT_STATUS_TIMEOUT, /* Connection Timeout */ MGMT_STATUS_NO_RESOURCES, /* Max Number of Connections */ @@ -363,6 +368,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_POWERED; settings |= MGMT_SETTING_PAIRABLE; + settings |= MGMT_SETTING_DEBUG_KEYS; if (lmp_bredr_capable(hdev)) { settings |= MGMT_SETTING_CONNECTABLE; @@ -376,11 +382,16 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_SSP; settings |= MGMT_SETTING_HS; } + + if (lmp_sc_capable(hdev) || + test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + settings |= MGMT_SETTING_SECURE_CONN; } if (lmp_le_capable(hdev)) { settings |= MGMT_SETTING_LE; settings |= MGMT_SETTING_ADVERTISING; + settings |= MGMT_SETTING_PRIVACY; } return settings; @@ -423,6 +434,15 @@ static u32 get_current_settings(struct hci_dev *hdev) if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) settings |= MGMT_SETTING_ADVERTISING; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + settings |= MGMT_SETTING_SECURE_CONN; + + if (test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags)) + settings |= MGMT_SETTING_DEBUG_KEYS; + + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + settings |= MGMT_SETTING_PRIVACY; + return settings; } @@ -629,14 +649,8 @@ static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr) flags |= get_adv_discov_flags(hdev); - if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { - if (lmp_le_br_capable(hdev)) - flags |= LE_AD_SIM_LE_BREDR_CTRL; - if (lmp_host_le_br_capable(hdev)) - flags |= LE_AD_SIM_LE_BREDR_HOST; - } else { + if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) flags |= LE_AD_NO_BREDR; - } if (flags) { BT_DBG("adv flags 0x%02x", flags); @@ -803,6 +817,64 @@ static void update_class(struct hci_request *req) hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod); } +static bool get_connectable(struct hci_dev *hdev) +{ + struct pending_cmd *cmd; + + /* If there's a pending mgmt command the flag will not yet have + * it's final value, so check for this first. + */ + cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); + if (cmd) { + struct mgmt_mode *cp = cmd->param; + return cp->val; + } + + return test_bit(HCI_CONNECTABLE, &hdev->dev_flags); +} + +static void enable_advertising(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_adv_param cp; + u8 own_addr_type, enable = 0x01; + bool connectable; + + /* Clear the HCI_ADVERTISING bit temporarily so that the + * hci_update_random_address knows that it's safe to go ahead + * and write a new random address. The flag will be set back on + * as soon as the SET_ADV_ENABLE HCI command completes. + */ + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + + connectable = get_connectable(hdev); + + /* Set require_privacy to true only when non-connectable + * advertising is used. In that case it is fine to use a + * non-resolvable private address. + */ + if (hci_update_random_address(req, !connectable, &own_addr_type) < 0) + return; + + memset(&cp, 0, sizeof(cp)); + cp.min_interval = __constant_cpu_to_le16(0x0800); + cp.max_interval = __constant_cpu_to_le16(0x0800); + cp.type = connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND; + cp.own_address_type = own_addr_type; + cp.channel_map = hdev->le_adv_channel_map; + + hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + +static void disable_advertising(struct hci_request *req) +{ + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + static void service_cache_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -824,12 +896,39 @@ static void service_cache_off(struct work_struct *work) hci_req_run(&req, NULL); } +static void rpa_expired(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + rpa_expired.work); + struct hci_request req; + + BT_DBG(""); + + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + + if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags) || + hci_conn_num(hdev, LE_LINK) > 0) + return; + + /* The generation of a new RPA and programming it into the + * controller happens in the enable_advertising() function. + */ + + hci_req_init(&req, hdev); + + disable_advertising(&req); + enable_advertising(&req); + + hci_req_run(&req, NULL); +} + static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev) { if (test_and_set_bit(HCI_MGMT, &hdev->dev_flags)) return; INIT_DELAYED_WORK(&hdev->service_cache, service_cache_off); + INIT_DELAYED_WORK(&hdev->rpa_expired, rpa_expired); /* Non-mgmt controlled devices get this bit set * implicitly so that pairing works for them, however @@ -935,6 +1034,71 @@ static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) sizeof(settings)); } +static void clean_up_hci_complete(struct hci_dev *hdev, u8 status) +{ + BT_DBG("%s status 0x%02x", hdev->name, status); + + if (hci_conn_count(hdev) == 0) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } +} + +static int clean_up_hci_state(struct hci_dev *hdev) +{ + struct hci_request req; + struct hci_conn *conn; + + hci_req_init(&req, hdev); + + if (test_bit(HCI_ISCAN, &hdev->flags) || + test_bit(HCI_PSCAN, &hdev->flags)) { + u8 scan = 0x00; + hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); + } + + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + disable_advertising(&req); + + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + hci_req_add_le_scan_disable(&req); + } + + list_for_each_entry(conn, &hdev->conn_hash.list, list) { + struct hci_cp_disconnect dc; + struct hci_cp_reject_conn_req rej; + + switch (conn->state) { + case BT_CONNECTED: + case BT_CONFIG: + dc.handle = cpu_to_le16(conn->handle); + dc.reason = 0x15; /* Terminated due to Power Off */ + hci_req_add(&req, HCI_OP_DISCONNECT, sizeof(dc), &dc); + break; + case BT_CONNECT: + if (conn->type == LE_LINK) + hci_req_add(&req, HCI_OP_LE_CREATE_CONN_CANCEL, + 0, NULL); + else if (conn->type == ACL_LINK) + hci_req_add(&req, HCI_OP_CREATE_CONN_CANCEL, + 6, &conn->dst); + break; + case BT_CONNECT2: + bacpy(&rej.bdaddr, &conn->dst); + rej.reason = 0x15; /* Terminated due to Power Off */ + if (conn->type == ACL_LINK) + hci_req_add(&req, HCI_OP_REJECT_CONN_REQ, + sizeof(rej), &rej); + else if (conn->type == SCO_LINK) + hci_req_add(&req, HCI_OP_REJECT_SYNC_CONN_REQ, + sizeof(rej), &rej); + break; + } + } + + return hci_req_run(&req, clean_up_hci_complete); +} + static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -978,12 +1142,23 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (cp->val) + if (cp->val) { queue_work(hdev->req_workqueue, &hdev->power_on); - else - queue_work(hdev->req_workqueue, &hdev->power_off.work); - - err = 0; + err = 0; + } else { + /* Disconnect connections, stop scans, etc */ + err = clean_up_hci_state(hdev); + if (!err) + queue_delayed_work(hdev->req_workqueue, &hdev->power_off, + HCI_POWER_OFF_TIMEOUT); + + /* ENODATA means there were no HCI commands queued */ + if (err == -ENODATA) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + err = 0; + } + } failed: hci_dev_unlock(hdev); @@ -1336,50 +1511,6 @@ static void write_fast_connectable(struct hci_request *req, bool enable) hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type); } -static u8 get_adv_type(struct hci_dev *hdev) -{ - struct pending_cmd *cmd; - bool connectable; - - /* If there's a pending mgmt command the flag will not yet have - * it's final value, so check for this first. - */ - cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); - if (cmd) { - struct mgmt_mode *cp = cmd->param; - connectable = !!cp->val; - } else { - connectable = test_bit(HCI_CONNECTABLE, &hdev->dev_flags); - } - - return connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND; -} - -static void enable_advertising(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_param cp; - u8 enable = 0x01; - - memset(&cp, 0, sizeof(cp)); - cp.min_interval = __constant_cpu_to_le16(0x0800); - cp.max_interval = __constant_cpu_to_le16(0x0800); - cp.type = get_adv_type(hdev); - cp.own_address_type = hdev->own_addr_type; - cp.channel_map = 0x07; - - hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - -static void disable_advertising(struct hci_request *req) -{ - u8 enable = 0x00; - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - static void set_connectable_complete(struct hci_dev *hdev, u8 status) { struct pending_cmd *cmd; @@ -2065,7 +2196,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, } if (memcmp(cp->uuid, bt_uuid_any, 16) == 0) { - err = hci_uuids_clear(hdev); + hci_uuids_clear(hdev); if (enable_service_cache(hdev)) { err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, @@ -2205,6 +2336,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_cp_load_link_keys *cp = data; u16 key_count, expected_len; + bool changed; int i; BT_DBG("request for %s", hdev->name); @@ -2234,7 +2366,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - if (key->addr.type != BDADDR_BREDR) + if (key->addr.type != BDADDR_BREDR || key->type > 0x08) return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -2244,9 +2376,12 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, hci_link_keys_clear(hdev); if (cp->debug_keys) - set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); else - clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + + if (changed) + new_settings(hdev, NULL); for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; @@ -2306,10 +2441,22 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - if (cp->addr.type == BDADDR_BREDR) + if (cp->addr.type == BDADDR_BREDR) { err = hci_remove_link_key(hdev, &cp->addr.bdaddr); - else - err = hci_remove_ltk(hdev, &cp->addr.bdaddr); + } else { + u8 addr_type; + + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type); + + hci_conn_params_del(hdev, &cp->addr.bdaddr, addr_type); + + err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type); + } if (err < 0) { err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, @@ -2633,6 +2780,16 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status) mgmt_pending_remove(cmd); } +void mgmt_smp_complete(struct hci_conn *conn, bool complete) +{ + u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED; + struct pending_cmd *cmd; + + cmd = find_pairing(conn); + if (cmd) + pairing_complete(cmd, status); +} + static void pairing_complete_cb(struct hci_conn *conn, u8 status) { struct pending_cmd *cmd; @@ -2646,7 +2803,7 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status) pairing_complete(cmd, mgmt_status(status)); } -static void le_connect_complete_cb(struct hci_conn *conn, u8 status) +static void le_pairing_complete_cb(struct hci_conn *conn, u8 status) { struct pending_cmd *cmd; @@ -2697,12 +2854,22 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, else auth_type = HCI_AT_DEDICATED_BONDING_MITM; - if (cp->addr.type == BDADDR_BREDR) - conn = hci_connect(hdev, ACL_LINK, &cp->addr.bdaddr, - cp->addr.type, sec_level, auth_type); - else - conn = hci_connect(hdev, LE_LINK, &cp->addr.bdaddr, - cp->addr.type, sec_level, auth_type); + if (cp->addr.type == BDADDR_BREDR) { + conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, + auth_type); + } else { + u8 addr_type; + + /* Convert from L2CAP channel address type to HCI address type + */ + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + conn = hci_connect_le(hdev, &cp->addr.bdaddr, addr_type, + sec_level, auth_type); + } if (IS_ERR(conn)) { int status; @@ -2733,13 +2900,16 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, } /* For LE, just connecting isn't a proof that the pairing finished */ - if (cp->addr.type == BDADDR_BREDR) + if (cp->addr.type == BDADDR_BREDR) { conn->connect_cfm_cb = pairing_complete_cb; - else - conn->connect_cfm_cb = le_connect_complete_cb; + conn->security_cfm_cb = pairing_complete_cb; + conn->disconn_cfm_cb = pairing_complete_cb; + } else { + conn->connect_cfm_cb = le_pairing_complete_cb; + conn->security_cfm_cb = le_pairing_complete_cb; + conn->disconn_cfm_cb = le_pairing_complete_cb; + } - conn->security_cfm_cb = pairing_complete_cb; - conn->disconn_cfm_cb = pairing_complete_cb; conn->io_capability = cp->io_cap; cmd->user_data = conn; @@ -3071,7 +3241,12 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA, + 0, NULL); + else + err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + if (err < 0) mgmt_pending_remove(cmd); @@ -3083,23 +3258,46 @@ unlock: static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { - struct mgmt_cp_add_remote_oob_data *cp = data; - u8 status; int err; BT_DBG("%s ", hdev->name); hci_dev_lock(hdev); - err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, cp->hash, - cp->randomizer); - if (err < 0) - status = MGMT_STATUS_FAILED; - else - status = MGMT_STATUS_SUCCESS; + if (len == MGMT_ADD_REMOTE_OOB_DATA_SIZE) { + struct mgmt_cp_add_remote_oob_data *cp = data; + u8 status; - err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, status, - &cp->addr, sizeof(cp->addr)); + err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, + cp->hash, cp->randomizer); + if (err < 0) + status = MGMT_STATUS_FAILED; + else + status = MGMT_STATUS_SUCCESS; + + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); + } else if (len == MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE) { + struct mgmt_cp_add_remote_oob_ext_data *cp = data; + u8 status; + + err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr, + cp->hash192, + cp->randomizer192, + cp->hash256, + cp->randomizer256); + if (err < 0) + status = MGMT_STATUS_FAILED; + else + status = MGMT_STATUS_SUCCESS; + + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); + } else { + BT_ERR("add_remote_oob_data: invalid length of %u bytes", len); + err = cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS); + } hci_dev_unlock(hdev); return err; @@ -3195,7 +3393,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, struct hci_request req; /* General inquiry access code (GIAC) */ u8 lap[3] = { 0x33, 0x8b, 0x9e }; - u8 status; + u8 status, own_addr_type; int err; BT_DBG("%s", hdev->name); @@ -3280,18 +3478,31 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, goto failed; } - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + /* If controller is scanning, it means the background scanning + * is running. Thus, we should temporarily stop it in order to + * set the discovery scanning parameters. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + hci_req_add_le_scan_disable(&req); + + memset(¶m_cp, 0, sizeof(param_cp)); + + /* All active scans will be done with either a resolvable + * private address (when privacy feature has been enabled) + * or unresolvable private address. + */ + err = hci_update_random_address(&req, true, &own_addr_type); + if (err < 0) { err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY, - MGMT_STATUS_BUSY); + MGMT_STATUS_FAILED); mgmt_pending_remove(cmd); goto failed; } - memset(¶m_cp, 0, sizeof(param_cp)); param_cp.type = LE_SCAN_ACTIVE; param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT); param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN); - param_cp.own_address_type = hdev->own_addr_type; + param_cp.own_address_type = own_addr_type; hci_req_add(&req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), ¶m_cp); @@ -3361,7 +3572,6 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_cp_remote_name_req_cancel cp; struct inquiry_entry *e; struct hci_request req; - struct hci_cp_le_set_scan_enable enable_cp; int err; BT_DBG("%s", hdev->name); @@ -3397,10 +3607,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, } else { cancel_delayed_work(&hdev->le_scan_disable); - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_DISABLE; - hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, - sizeof(enable_cp), &enable_cp); + hci_req_add_le_scan_disable(&req); } break; @@ -3457,15 +3664,17 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hci_discovery_active(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_FAILED); + err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); goto failed; } e = hci_inquiry_cache_lookup_unknown(hdev, &cp->addr.bdaddr); if (!e) { - err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_INVALID_PARAMS); + err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_INVALID_PARAMS, &cp->addr, + sizeof(cp->addr)); goto failed; } @@ -3754,6 +3963,21 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0); + /* If background scan is running, restart it so new parameters are + * loaded. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + hdev->discovery.state == DISCOVERY_STOPPED) { + struct hci_request req; + + hci_req_init(&req, hdev); + + hci_req_add_le_scan_disable(&req); + hci_req_add_le_passive_scan(&req); + + hci_req_run(&req, NULL); + } + hci_dev_unlock(hdev); return err; @@ -3999,15 +4223,269 @@ unlock: return err; } +static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_mode *cp = data; + struct pending_cmd *cmd; + u8 val, status; + int err; + + BT_DBG("request for %s", hdev->name); + + status = mgmt_bredr_support(hdev); + if (status) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + status); + + if (!lmp_sc_capable(hdev) && + !test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_NOT_SUPPORTED); + + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + bool changed; + + if (cp->val) { + changed = !test_and_set_bit(HCI_SC_ENABLED, + &hdev->dev_flags); + if (cp->val == 0x02) + set_bit(HCI_SC_ONLY, &hdev->dev_flags); + else + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_SC_ENABLED, + &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); + if (err < 0) + goto failed; + + if (changed) + err = new_settings(hdev, sk); + + goto failed; + } + + if (mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) { + err = cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_BUSY); + goto failed; + } + + val = !!cp->val; + + if (val == test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + (cp->val == 0x02) == test_bit(HCI_SC_ONLY, &hdev->dev_flags)) { + err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); + goto failed; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_SET_SECURE_CONN, hdev, data, len); + if (!cmd) { + err = -ENOMEM; + goto failed; + } + + err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val); + if (err < 0) { + mgmt_pending_remove(cmd); + goto failed; + } + + if (cp->val == 0x02) + set_bit(HCI_SC_ONLY, &hdev->dev_flags); + else + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + +failed: + hci_dev_unlock(hdev); + return err; +} + +static int set_debug_keys(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_mode *cp = data; + bool changed; + int err; + + BT_DBG("request for %s", hdev->name); + + if (cp->val != 0x00 && cp->val != 0x01) + return cmd_status(sk, hdev->id, MGMT_OP_SET_DEBUG_KEYS, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (cp->val) + changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + else + changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + + err = send_settings_rsp(sk, MGMT_OP_SET_DEBUG_KEYS, hdev); + if (err < 0) + goto unlock; + + if (changed) + err = new_settings(hdev, sk); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, + u16 len) +{ + struct mgmt_cp_set_privacy *cp = cp_data; + bool changed; + int err; + + BT_DBG("request for %s", hdev->name); + + if (!lmp_le_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_NOT_SUPPORTED); + + if (cp->privacy != 0x00 && cp->privacy != 0x01) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_INVALID_PARAMS); + + if (hdev_is_powered(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_REJECTED); + + hci_dev_lock(hdev); + + /* If user space supports this command it is also expected to + * handle IRKs. Therefore, set the HCI_RPA_RESOLVING flag. + */ + set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + + if (cp->privacy) { + changed = !test_and_set_bit(HCI_PRIVACY, &hdev->dev_flags); + memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_PRIVACY, &hdev->dev_flags); + memset(hdev->irk, 0, sizeof(hdev->irk)); + clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + } + + err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev); + if (err < 0) + goto unlock; + + if (changed) + err = new_settings(hdev, sk); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static bool irk_is_valid(struct mgmt_irk_info *irk) +{ + switch (irk->addr.type) { + case BDADDR_LE_PUBLIC: + return true; + + case BDADDR_LE_RANDOM: + /* Two most significant bits shall be set */ + if ((irk->addr.bdaddr.b[5] & 0xc0) != 0xc0) + return false; + return true; + } + + return false; +} + +static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, + u16 len) +{ + struct mgmt_cp_load_irks *cp = cp_data; + u16 irk_count, expected_len; + int i, err; + + BT_DBG("request for %s", hdev->name); + + if (!lmp_le_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_NOT_SUPPORTED); + + irk_count = __le16_to_cpu(cp->irk_count); + + expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info); + if (expected_len != len) { + BT_ERR("load_irks: expected %u bytes, got %u bytes", + len, expected_len); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); + } + + BT_DBG("%s irk_count %u", hdev->name, irk_count); + + for (i = 0; i < irk_count; i++) { + struct mgmt_irk_info *key = &cp->irks[i]; + + if (!irk_is_valid(key)) + return cmd_status(sk, hdev->id, + MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); + } + + hci_dev_lock(hdev); + + hci_smp_irks_clear(hdev); + + for (i = 0; i < irk_count; i++) { + struct mgmt_irk_info *irk = &cp->irks[i]; + u8 addr_type; + + if (irk->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + hci_add_irk(hdev, &irk->addr.bdaddr, addr_type, irk->val, + BDADDR_ANY); + } + + set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + + err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0); + + hci_dev_unlock(hdev); + + return err; +} + static bool ltk_is_valid(struct mgmt_ltk_info *key) { - if (key->authenticated != 0x00 && key->authenticated != 0x01) - return false; if (key->master != 0x00 && key->master != 0x01) return false; - if (!bdaddr_type_is_le(key->addr.type)) - return false; - return true; + + switch (key->addr.type) { + case BDADDR_LE_PUBLIC: + return true; + + case BDADDR_LE_RANDOM: + /* Two most significant bits shall be set */ + if ((key->addr.bdaddr.b[5] & 0xc0) != 0xc0) + return false; + return true; + } + + return false; } static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, @@ -4063,9 +4541,9 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, else type = HCI_SMP_LTK_SLAVE; - hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, - type, 0, key->authenticated, key->val, - key->enc_size, key->ediv, key->rand); + hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, type, + key->type, key->val, key->enc_size, key->ediv, + key->rand); } err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0, @@ -4115,7 +4593,7 @@ static const struct mgmt_handler { { user_passkey_reply, false, MGMT_USER_PASSKEY_REPLY_SIZE }, { user_passkey_neg_reply, false, MGMT_USER_PASSKEY_NEG_REPLY_SIZE }, { read_local_oob_data, false, MGMT_READ_LOCAL_OOB_DATA_SIZE }, - { add_remote_oob_data, false, MGMT_ADD_REMOTE_OOB_DATA_SIZE }, + { add_remote_oob_data, true, MGMT_ADD_REMOTE_OOB_DATA_SIZE }, { remove_remote_oob_data, false, MGMT_REMOVE_REMOTE_OOB_DATA_SIZE }, { start_discovery, false, MGMT_START_DISCOVERY_SIZE }, { stop_discovery, false, MGMT_STOP_DISCOVERY_SIZE }, @@ -4127,6 +4605,10 @@ static const struct mgmt_handler { { set_bredr, false, MGMT_SETTING_SIZE }, { set_static_address, false, MGMT_SET_STATIC_ADDRESS_SIZE }, { set_scan_params, false, MGMT_SET_SCAN_PARAMS_SIZE }, + { set_secure_conn, false, MGMT_SETTING_SIZE }, + { set_debug_keys, false, MGMT_SETTING_SIZE }, + { set_privacy, false, MGMT_SET_PRIVACY_SIZE }, + { load_irks, true, MGMT_LOAD_IRKS_SIZE }, }; @@ -4243,6 +4725,17 @@ void mgmt_index_removed(struct hci_dev *hdev) mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL); } +/* This function requires the caller holds hdev->lock */ +static void restart_le_auto_conns(struct hci_dev *hdev) +{ + struct hci_conn_params *p; + + list_for_each_entry(p, &hdev->le_conn_params, list) { + if (p->auto_connect == HCI_AUTO_CONN_ALWAYS) + hci_pend_le_conn_add(hdev, &p->addr, p->addr_type); + } +} + static void powered_complete(struct hci_dev *hdev, u8 status) { struct cmd_lookup match = { NULL, hdev }; @@ -4251,6 +4744,8 @@ static void powered_complete(struct hci_dev *hdev, u8 status) hci_dev_lock(hdev); + restart_le_auto_conns(hdev); + mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); new_settings(hdev, match.sk); @@ -4292,11 +4787,6 @@ static int powered_update_hci(struct hci_dev *hdev) } if (lmp_le_capable(hdev)) { - /* Set random address to static address if configured */ - if (bacmp(&hdev->static_addr, BDADDR_ANY)) - hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6, - &hdev->static_addr); - /* Make sure the controller has a good default for * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. @@ -4422,6 +4912,10 @@ void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable) if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) return; + /* Powering off may clear the scan mode - don't let that interfere */ + if (!discoverable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + if (discoverable) { changed = !test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags); } else { @@ -4455,6 +4949,10 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable) if (mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) return; + /* Powering off may clear the scan mode - don't let that interfere */ + if (!connectable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + if (connectable) changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags); else @@ -4464,6 +4962,18 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable) new_settings(hdev, NULL); } +void mgmt_advertising(struct hci_dev *hdev, u8 advertising) +{ + /* Powering off may stop advertising - don't let that interfere */ + if (!advertising && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + + if (advertising) + set_bit(HCI_ADVERTISING, &hdev->dev_flags); + else + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); +} + void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status) { u8 mgmt_err = mgmt_status(status); @@ -4494,28 +5004,74 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL); } -void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent) +void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key) { struct mgmt_ev_new_long_term_key ev; memset(&ev, 0, sizeof(ev)); - ev.store_hint = persistent; + /* Devices using resolvable or non-resolvable random addresses + * without providing an indentity resolving key don't require + * to store long term keys. Their addresses will change the + * next time around. + * + * Only when a remote device provides an identity address + * make sure the long term key is stored. If the remote + * identity is known, the long term keys are internally + * mapped to the identity address. So allow static random + * and public addresses here. + */ + if (key->bdaddr_type == ADDR_LE_DEV_RANDOM && + (key->bdaddr.b[5] & 0xc0) != 0xc0) + ev.store_hint = 0x00; + else + ev.store_hint = 0x01; + bacpy(&ev.key.addr.bdaddr, &key->bdaddr); ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); - ev.key.authenticated = key->authenticated; + ev.key.type = key->authenticated; ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; + ev.key.rand = key->rand; if (key->type == HCI_SMP_LTK) ev.key.master = 1; - memcpy(ev.key.rand, key->rand, sizeof(key->rand)); memcpy(ev.key.val, key->val, sizeof(key->val)); mgmt_event(MGMT_EV_NEW_LONG_TERM_KEY, hdev, &ev, sizeof(ev), NULL); } +void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk) +{ + struct mgmt_ev_new_irk ev; + + memset(&ev, 0, sizeof(ev)); + + /* For identity resolving keys from devices that are already + * using a public address or static random address, do not + * ask for storing this key. The identity resolving key really + * is only mandatory for devices using resovlable random + * addresses. + * + * Storing all identity resolving keys has the downside that + * they will be also loaded on next boot of they system. More + * identity resolving keys, means more time during scanning is + * needed to actually resolve these addresses. + */ + if (bacmp(&irk->rpa, BDADDR_ANY)) + ev.store_hint = 0x01; + else + ev.store_hint = 0x00; + + bacpy(&ev.rpa, &irk->rpa); + bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); + ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); + memcpy(ev.irk.val, irk->val, sizeof(irk->val)); + + mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); +} + static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) { @@ -4590,11 +5146,29 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data) } void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 link_type, u8 addr_type, u8 reason) + u8 link_type, u8 addr_type, u8 reason, + bool mgmt_connected) { struct mgmt_ev_device_disconnected ev; + struct pending_cmd *power_off; struct sock *sk = NULL; + power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + if (power_off) { + struct mgmt_mode *cp = power_off->param; + + /* The connection is still in hci_conn_hash so test for 1 + * instead of 0 to know if this is the last one. + */ + if (!cp->val && hci_conn_count(hdev) == 1) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } + } + + if (!mgmt_connected) + return; + if (link_type != ACL_LINK && link_type != LE_LINK) return; @@ -4649,6 +5223,20 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status) { struct mgmt_ev_connect_failed ev; + struct pending_cmd *power_off; + + power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + if (power_off) { + struct mgmt_mode *cp = power_off->param; + + /* The connection is still in hci_conn_hash so test for 1 + * instead of 0 to know if this is the last one. + */ + if (!cp->val && hci_conn_count(hdev) == 1) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } + } bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); @@ -4910,6 +5498,43 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) hci_req_run(&req, NULL); } +void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) +{ + struct cmd_lookup match = { NULL, hdev }; + bool changed = false; + + if (status) { + u8 mgmt_err = mgmt_status(status); + + if (enable) { + if (test_and_clear_bit(HCI_SC_ENABLED, + &hdev->dev_flags)) + new_settings(hdev, NULL); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, + cmd_status_rsp, &mgmt_err); + return; + } + + if (enable) { + changed = !test_and_set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, + settings_rsp, &match); + + if (changed) + new_settings(hdev, match.sk); + + if (match.sk) + sock_put(match.sk); +} + static void sk_lookup(struct pending_cmd *cmd, void *data) { struct cmd_lookup *match = data; @@ -4964,8 +5589,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) cmd ? cmd->sk : NULL); } -void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash, - u8 *randomizer, u8 status) +void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, + u8 *randomizer192, u8 *hash256, + u8 *randomizer256, u8 status) { struct pending_cmd *cmd; @@ -4979,13 +5605,32 @@ void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash, cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, mgmt_status(status)); } else { - struct mgmt_rp_read_local_oob_data rp; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + hash256 && randomizer256) { + struct mgmt_rp_read_local_oob_ext_data rp; + + memcpy(rp.hash192, hash192, sizeof(rp.hash192)); + memcpy(rp.randomizer192, randomizer192, + sizeof(rp.randomizer192)); + + memcpy(rp.hash256, hash256, sizeof(rp.hash256)); + memcpy(rp.randomizer256, randomizer256, + sizeof(rp.randomizer256)); + + cmd_complete(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, 0, + &rp, sizeof(rp)); + } else { + struct mgmt_rp_read_local_oob_data rp; - memcpy(rp.hash, hash, sizeof(rp.hash)); - memcpy(rp.randomizer, randomizer, sizeof(rp.randomizer)); + memcpy(rp.hash, hash192, sizeof(rp.hash)); + memcpy(rp.randomizer, randomizer192, + sizeof(rp.randomizer)); - cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - 0, &rp, sizeof(rp)); + cmd_complete(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, 0, + &rp, sizeof(rp)); + } } mgmt_pending_remove(cmd); @@ -4997,6 +5642,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { char buf[512]; struct mgmt_ev_device_found *ev = (void *) buf; + struct smp_irk *irk; size_t ev_size; if (!hci_discovery_active(hdev)) @@ -5008,8 +5654,15 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, memset(buf, 0, sizeof(buf)); - bacpy(&ev->addr.bdaddr, bdaddr); - ev->addr.type = link_to_bdaddr(link_type, addr_type); + irk = hci_get_irk(hdev, bdaddr, addr_type); + if (irk) { + bacpy(&ev->addr.bdaddr, &irk->bdaddr); + ev->addr.type = link_to_bdaddr(link_type, irk->addr_type); + } else { + bacpy(&ev->addr.bdaddr, bdaddr); + ev->addr.type = link_to_bdaddr(link_type, addr_type); + } + ev->rssi = rssi; if (cfm_name) ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index facd8a79c038..21e15318937c 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -216,6 +216,7 @@ static int rfcomm_check_security(struct rfcomm_dlc *d) switch (d->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: auth_type = HCI_AT_GENERAL_BONDING_MITM; break; case BT_SECURITY_MEDIUM: @@ -359,6 +360,11 @@ static struct rfcomm_dlc *rfcomm_dlc_get(struct rfcomm_session *s, u8 dlci) return NULL; } +static int rfcomm_check_channel(u8 channel) +{ + return channel < 1 || channel > 30; +} + static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel) { struct rfcomm_session *s; @@ -368,7 +374,7 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d", d, d->state, src, dst, channel); - if (channel < 1 || channel > 30) + if (rfcomm_check_channel(channel)) return -EINVAL; if (d->state != BT_OPEN && d->state != BT_CLOSED) @@ -425,6 +431,20 @@ int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 chann return r; } +static void __rfcomm_dlc_disconn(struct rfcomm_dlc *d) +{ + struct rfcomm_session *s = d->session; + + d->state = BT_DISCONN; + if (skb_queue_empty(&d->tx_queue)) { + rfcomm_send_disc(s, d->dlci); + rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT); + } else { + rfcomm_queue_disc(d); + rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2); + } +} + static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) { struct rfcomm_session *s = d->session; @@ -437,32 +457,29 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) switch (d->state) { case BT_CONNECT: case BT_CONFIG: + case BT_OPEN: + case BT_CONNECT2: if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { set_bit(RFCOMM_AUTH_REJECT, &d->flags); rfcomm_schedule(); - break; + return 0; } - /* Fall through */ + } + switch (d->state) { + case BT_CONNECT: case BT_CONNECTED: - d->state = BT_DISCONN; - if (skb_queue_empty(&d->tx_queue)) { - rfcomm_send_disc(s, d->dlci); - rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT); - } else { - rfcomm_queue_disc(d); - rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2); - } + __rfcomm_dlc_disconn(d); break; - case BT_OPEN: - case BT_CONNECT2: - if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { - set_bit(RFCOMM_AUTH_REJECT, &d->flags); - rfcomm_schedule(); + case BT_CONFIG: + if (s->state != BT_BOUND) { + __rfcomm_dlc_disconn(d); break; } - /* Fall through */ + /* if closing a dlc in a session that hasn't been started, + * just close and unlink the dlc + */ default: rfcomm_dlc_clear_timer(d); @@ -513,6 +530,25 @@ no_session: return r; } +struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel) +{ + struct rfcomm_session *s; + struct rfcomm_dlc *dlc = NULL; + u8 dlci; + + if (rfcomm_check_channel(channel)) + return ERR_PTR(-EINVAL); + + rfcomm_lock(); + s = rfcomm_session_get(src, dst); + if (s) { + dlci = __dlci(!s->initiator, channel); + dlc = rfcomm_dlc_get(s, dlci); + } + rfcomm_unlock(); + return dlc; +} + int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) { int len = skb->len; @@ -533,6 +569,20 @@ int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) return len; } +void rfcomm_dlc_send_noerror(struct rfcomm_dlc *d, struct sk_buff *skb) +{ + int len = skb->len; + + BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + + rfcomm_make_uih(skb, d->addr); + skb_queue_tail(&d->tx_queue, skb); + + if (d->state == BT_CONNECTED && + !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) + rfcomm_schedule(); +} + void __rfcomm_dlc_throttle(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); @@ -1943,12 +1993,11 @@ static void rfcomm_process_sessions(void) continue; } - if (s->state == BT_LISTEN) { + switch (s->state) { + case BT_LISTEN: rfcomm_accept_connection(s); continue; - } - switch (s->state) { case BT_BOUND: s = rfcomm_check_connection(s); break; @@ -2085,7 +2134,8 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) set_bit(RFCOMM_SEC_PENDING, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); continue; - } else if (d->sec_level == BT_SECURITY_HIGH) { + } else if (d->sec_level == BT_SECURITY_HIGH || + d->sec_level == BT_SECURITY_FIPS) { set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 3c2d3e4aa2f5..c024e715512f 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -105,13 +105,18 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) } /* ---- Socket functions ---- */ -static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) +static struct sock *__rfcomm_get_listen_sock_by_addr(u8 channel, bdaddr_t *src) { struct sock *sk = NULL; sk_for_each(sk, &rfcomm_sk_list.head) { - if (rfcomm_pi(sk)->channel == channel && - !bacmp(&rfcomm_pi(sk)->src, src)) + if (rfcomm_pi(sk)->channel != channel) + continue; + + if (bacmp(&rfcomm_pi(sk)->src, src)) + continue; + + if (sk->sk_state == BT_BOUND || sk->sk_state == BT_LISTEN) break; } @@ -331,6 +336,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr { struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; struct sock *sk = sock->sk; + int chan = sa->rc_channel; int err = 0; BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr); @@ -352,12 +358,12 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr write_lock(&rfcomm_sk_list.lock); - if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) { + if (chan && __rfcomm_get_listen_sock_by_addr(chan, &sa->rc_bdaddr)) { err = -EADDRINUSE; } else { /* Save source address */ bacpy(&rfcomm_pi(sk)->src, &sa->rc_bdaddr); - rfcomm_pi(sk)->channel = sa->rc_channel; + rfcomm_pi(sk)->channel = chan; sk->sk_state = BT_BOUND; } @@ -439,7 +445,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog) write_lock(&rfcomm_sk_list.lock); for (channel = 1; channel < 31; channel++) - if (!__rfcomm_get_sock_by_addr(channel, src)) { + if (!__rfcomm_get_listen_sock_by_addr(channel, src)) { rfcomm_pi(sk)->channel = channel; err = 0; break; @@ -528,6 +534,9 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * BT_DBG("sock %p, sk %p", sock, sk); + if (peer && sk->sk_state != BT_CONNECTED) + return -ENOTCONN; + memset(sa, 0, sizeof(*sa)); sa->rc_family = AF_BLUETOOTH; sa->rc_channel = rfcomm_pi(sk)->channel; @@ -648,6 +657,11 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u break; } + if (opt & RFCOMM_LM_FIPS) { + err = -EINVAL; + break; + } + if (opt & RFCOMM_LM_AUTH) rfcomm_pi(sk)->sec_level = BT_SECURITY_LOW; if (opt & RFCOMM_LM_ENCRYPT) @@ -762,7 +776,11 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u break; case BT_SECURITY_HIGH: opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT | - RFCOMM_LM_SECURE; + RFCOMM_LM_SECURE; + break; + case BT_SECURITY_FIPS: + opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT | + RFCOMM_LM_SECURE | RFCOMM_LM_FIPS; break; default: opt = 0; @@ -774,6 +792,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u if (put_user(opt, (u32 __user *) optval)) err = -EFAULT; + break; case RFCOMM_CONNINFO: diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index f9c0980abeea..403ec09f480a 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -40,6 +40,7 @@ #define RFCOMM_TTY_MAJOR 216 /* device node major id of the usb/bluetooth.c driver */ #define RFCOMM_TTY_MINOR 0 +static DEFINE_MUTEX(rfcomm_ioctl_mutex); static struct tty_driver *rfcomm_tty_driver; struct rfcomm_dev { @@ -51,6 +52,8 @@ struct rfcomm_dev { unsigned long flags; int err; + unsigned long status; /* don't export to userspace */ + bdaddr_t src; bdaddr_t dst; u8 channel; @@ -58,7 +61,6 @@ struct rfcomm_dev { uint modem_status; struct rfcomm_dlc *dlc; - wait_queue_head_t conn_wait; struct device *tty_dev; @@ -83,10 +85,6 @@ static void rfcomm_dev_destruct(struct tty_port *port) BT_DBG("dev %p dlc %p", dev, dlc); - spin_lock(&rfcomm_dev_lock); - list_del(&dev->list); - spin_unlock(&rfcomm_dev_lock); - rfcomm_dlc_lock(dlc); /* Detach DLC if it's owned by this dev */ if (dlc->owner == dev) @@ -95,7 +93,12 @@ static void rfcomm_dev_destruct(struct tty_port *port) rfcomm_dlc_put(dlc); - tty_unregister_device(rfcomm_tty_driver, dev->id); + if (dev->tty_dev) + tty_unregister_device(rfcomm_tty_driver, dev->id); + + spin_lock(&rfcomm_dev_lock); + list_del(&dev->list); + spin_unlock(&rfcomm_dev_lock); kfree(dev); @@ -104,60 +107,24 @@ static void rfcomm_dev_destruct(struct tty_port *port) module_put(THIS_MODULE); } -static struct device *rfcomm_get_device(struct rfcomm_dev *dev) -{ - struct hci_dev *hdev; - struct hci_conn *conn; - - hdev = hci_get_route(&dev->dst, &dev->src); - if (!hdev) - return NULL; - - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); - - hci_dev_put(hdev); - - return conn ? &conn->dev : NULL; -} - /* device-specific initialization: open the dlc */ static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty) { struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); - DEFINE_WAIT(wait); int err; err = rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel); if (err) - return err; - - while (1) { - prepare_to_wait(&dev->conn_wait, &wait, TASK_INTERRUPTIBLE); - - if (dev->dlc->state == BT_CLOSED) { - err = -dev->err; - break; - } - - if (dev->dlc->state == BT_CONNECTED) - break; - - if (signal_pending(current)) { - err = -ERESTARTSYS; - break; - } - - tty_unlock(tty); - schedule(); - tty_lock(tty); - } - finish_wait(&dev->conn_wait, &wait); + set_bit(TTY_IO_ERROR, &tty->flags); + return err; +} - if (!err) - device_move(dev->tty_dev, rfcomm_get_device(dev), - DPM_ORDER_DEV_AFTER_PARENT); +/* we block the open until the dlc->state becomes BT_CONNECTED */ +static int rfcomm_dev_carrier_raised(struct tty_port *port) +{ + struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); - return err; + return (dev->dlc->state == BT_CONNECTED); } /* device-specific cleanup: close the dlc */ @@ -176,9 +143,10 @@ static const struct tty_port_operations rfcomm_port_ops = { .destruct = rfcomm_dev_destruct, .activate = rfcomm_dev_activate, .shutdown = rfcomm_dev_shutdown, + .carrier_raised = rfcomm_dev_carrier_raised, }; -static struct rfcomm_dev *__rfcomm_dev_get(int id) +static struct rfcomm_dev *__rfcomm_dev_lookup(int id) { struct rfcomm_dev *dev; @@ -195,20 +163,41 @@ static struct rfcomm_dev *rfcomm_dev_get(int id) spin_lock(&rfcomm_dev_lock); - dev = __rfcomm_dev_get(id); + dev = __rfcomm_dev_lookup(id); - if (dev) { - if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) - dev = NULL; - else - tty_port_get(&dev->port); - } + if (dev && !tty_port_get(&dev->port)) + dev = NULL; spin_unlock(&rfcomm_dev_lock); return dev; } +static void rfcomm_reparent_device(struct rfcomm_dev *dev) +{ + struct hci_dev *hdev; + struct hci_conn *conn; + + hdev = hci_get_route(&dev->dst, &dev->src); + if (!hdev) + return; + + /* The lookup results are unsafe to access without the + * hci device lock (FIXME: why is this not documented?) + */ + hci_dev_lock(hdev); + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); + + /* Just because the acl link is in the hash table is no + * guarantee the sysfs device has been added ... + */ + if (conn && device_is_registered(&conn->dev)) + device_move(dev->tty_dev, &conn->dev, DPM_ORDER_DEV_AFTER_PARENT); + + hci_dev_unlock(hdev); + hci_dev_put(hdev); +} + static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); @@ -224,17 +213,16 @@ static ssize_t show_channel(struct device *tty_dev, struct device_attribute *att static DEVICE_ATTR(address, S_IRUGO, show_address, NULL); static DEVICE_ATTR(channel, S_IRUGO, show_channel, NULL); -static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) +static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, + struct rfcomm_dlc *dlc) { struct rfcomm_dev *dev, *entry; struct list_head *head = &rfcomm_dev_list; int err = 0; - BT_DBG("id %d channel %d", req->dev_id, req->channel); - dev = kzalloc(sizeof(struct rfcomm_dev), GFP_KERNEL); if (!dev) - return -ENOMEM; + return ERR_PTR(-ENOMEM); spin_lock(&rfcomm_dev_lock); @@ -282,7 +270,6 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) tty_port_init(&dev->port); dev->port.ops = &rfcomm_port_ops; - init_waitqueue_head(&dev->conn_wait); skb_queue_head_init(&dev->pending); @@ -318,22 +305,37 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) holds reference to this module. */ __module_get(THIS_MODULE); + spin_unlock(&rfcomm_dev_lock); + return dev; + out: spin_unlock(&rfcomm_dev_lock); + kfree(dev); + return ERR_PTR(err); +} + +static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) +{ + struct rfcomm_dev *dev; + struct device *tty; + + BT_DBG("id %d channel %d", req->dev_id, req->channel); - if (err < 0) - goto free; + dev = __rfcomm_dev_add(req, dlc); + if (IS_ERR(dev)) { + rfcomm_dlc_put(dlc); + return PTR_ERR(dev); + } - dev->tty_dev = tty_port_register_device(&dev->port, rfcomm_tty_driver, + tty = tty_port_register_device(&dev->port, rfcomm_tty_driver, dev->id, NULL); - if (IS_ERR(dev->tty_dev)) { - err = PTR_ERR(dev->tty_dev); - spin_lock(&rfcomm_dev_lock); - list_del(&dev->list); - spin_unlock(&rfcomm_dev_lock); - goto free; + if (IS_ERR(tty)) { + tty_port_put(&dev->port); + return PTR_ERR(tty); } + dev->tty_dev = tty; + rfcomm_reparent_device(dev); dev_set_drvdata(dev->tty_dev, dev); if (device_create_file(dev->tty_dev, &dev_attr_address) < 0) @@ -343,24 +345,23 @@ out: BT_ERR("Failed to create channel attribute"); return dev->id; - -free: - kfree(dev); - return err; } /* ---- Send buffer ---- */ -static inline unsigned int rfcomm_room(struct rfcomm_dlc *dlc) +static inline unsigned int rfcomm_room(struct rfcomm_dev *dev) { - /* We can't let it be zero, because we don't get a callback - when tx_credits becomes nonzero, hence we'd never wake up */ - return dlc->mtu * (dlc->tx_credits?:1); + struct rfcomm_dlc *dlc = dev->dlc; + + /* Limit the outstanding number of packets not yet sent to 40 */ + int pending = 40 - atomic_read(&dev->wmem_alloc); + + return max(0, pending) * dlc->mtu; } static void rfcomm_wfree(struct sk_buff *skb) { struct rfcomm_dev *dev = (void *) skb->sk; - atomic_sub(skb->truesize, &dev->wmem_alloc); + atomic_dec(&dev->wmem_alloc); if (test_bit(RFCOMM_TTY_ATTACHED, &dev->flags)) tty_port_tty_wakeup(&dev->port); tty_port_put(&dev->port); @@ -369,28 +370,24 @@ static void rfcomm_wfree(struct sk_buff *skb) static void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev) { tty_port_get(&dev->port); - atomic_add(skb->truesize, &dev->wmem_alloc); + atomic_inc(&dev->wmem_alloc); skb->sk = (void *) dev; skb->destructor = rfcomm_wfree; } static struct sk_buff *rfcomm_wmalloc(struct rfcomm_dev *dev, unsigned long size, gfp_t priority) { - if (atomic_read(&dev->wmem_alloc) < rfcomm_room(dev->dlc)) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - rfcomm_set_owner_w(skb, dev); - return skb; - } - } - return NULL; + struct sk_buff *skb = alloc_skb(size, priority); + if (skb) + rfcomm_set_owner_w(skb, dev); + return skb; } /* ---- Device IOCTLs ---- */ #define NOCAP_FLAGS ((1 << RFCOMM_REUSE_DLC) | (1 << RFCOMM_RELEASE_ONHUP)) -static int rfcomm_create_dev(struct sock *sk, void __user *arg) +static int __rfcomm_create_dev(struct sock *sk, void __user *arg) { struct rfcomm_dev_req req; struct rfcomm_dlc *dlc; @@ -412,16 +409,22 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg) dlc = rfcomm_pi(sk)->dlc; rfcomm_dlc_hold(dlc); } else { + /* Validate the channel is unused */ + dlc = rfcomm_dlc_exists(&req.src, &req.dst, req.channel); + if (IS_ERR(dlc)) + return PTR_ERR(dlc); + else if (dlc) { + rfcomm_dlc_put(dlc); + return -EBUSY; + } dlc = rfcomm_dlc_alloc(GFP_KERNEL); if (!dlc) return -ENOMEM; } id = rfcomm_dev_add(&req, dlc); - if (id < 0) { - rfcomm_dlc_put(dlc); + if (id < 0) return id; - } if (req.flags & (1 << RFCOMM_REUSE_DLC)) { /* DLC is now used by device. @@ -432,7 +435,7 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg) return id; } -static int rfcomm_release_dev(void __user *arg) +static int __rfcomm_release_dev(void __user *arg) { struct rfcomm_dev_req req; struct rfcomm_dev *dev; @@ -452,6 +455,12 @@ static int rfcomm_release_dev(void __user *arg) return -EPERM; } + /* only release once */ + if (test_and_set_bit(RFCOMM_DEV_RELEASED, &dev->status)) { + tty_port_put(&dev->port); + return -EALREADY; + } + if (req.flags & (1 << RFCOMM_HANGUP_NOW)) rfcomm_dlc_close(dev->dlc, 0); @@ -462,14 +471,35 @@ static int rfcomm_release_dev(void __user *arg) tty_kref_put(tty); } - if (!test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags) && - !test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)) + if (!test_bit(RFCOMM_TTY_OWNED, &dev->status)) tty_port_put(&dev->port); tty_port_put(&dev->port); return 0; } +static int rfcomm_create_dev(struct sock *sk, void __user *arg) +{ + int ret; + + mutex_lock(&rfcomm_ioctl_mutex); + ret = __rfcomm_create_dev(sk, arg); + mutex_unlock(&rfcomm_ioctl_mutex); + + return ret; +} + +static int rfcomm_release_dev(void __user *arg) +{ + int ret; + + mutex_lock(&rfcomm_ioctl_mutex); + ret = __rfcomm_release_dev(arg); + mutex_unlock(&rfcomm_ioctl_mutex); + + return ret; +} + static int rfcomm_get_dev_list(void __user *arg) { struct rfcomm_dev *dev; @@ -497,7 +527,7 @@ static int rfcomm_get_dev_list(void __user *arg) spin_lock(&rfcomm_dev_lock); list_for_each_entry(dev, &rfcomm_dev_list, list) { - if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) + if (!tty_port_get(&dev->port)) continue; (di + n)->id = dev->id; (di + n)->flags = dev->flags; @@ -505,6 +535,7 @@ static int rfcomm_get_dev_list(void __user *arg) (di + n)->channel = dev->channel; bacpy(&(di + n)->src, &dev->src); bacpy(&(di + n)->dst, &dev->dst); + tty_port_put(&dev->port); if (++n >= dev_num) break; } @@ -601,9 +632,11 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) BT_DBG("dlc %p dev %p err %d", dlc, dev, err); dev->err = err; - wake_up_interruptible(&dev->conn_wait); + if (dlc->state == BT_CONNECTED) { + rfcomm_reparent_device(dev); - if (dlc->state == BT_CLOSED) + wake_up_interruptible(&dev->port.open_wait); + } else if (dlc->state == BT_CLOSED) tty_port_tty_hangup(&dev->port, false); } @@ -703,8 +736,10 @@ static int rfcomm_tty_install(struct tty_driver *driver, struct tty_struct *tty) * when the last process closes the tty. The behaviour is expected by * userspace. */ - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) + if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { + set_bit(RFCOMM_TTY_OWNED, &dev->status); tty_port_put(&dev->port); + } return 0; } @@ -750,7 +785,7 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; struct rfcomm_dlc *dlc = dev->dlc; struct sk_buff *skb; - int err = 0, sent = 0, size; + int sent = 0, size; BT_DBG("tty %p count %d", tty, count); @@ -758,7 +793,6 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in size = min_t(uint, count, dlc->mtu); skb = rfcomm_wmalloc(dev, size + RFCOMM_SKB_RESERVE, GFP_ATOMIC); - if (!skb) break; @@ -766,32 +800,24 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in memcpy(skb_put(skb, size), buf + sent, size); - err = rfcomm_dlc_send(dlc, skb); - if (err < 0) { - kfree_skb(skb); - break; - } + rfcomm_dlc_send_noerror(dlc, skb); sent += size; count -= size; } - return sent ? sent : err; + return sent; } static int rfcomm_tty_write_room(struct tty_struct *tty) { struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; - int room; + int room = 0; - BT_DBG("tty %p", tty); - - if (!dev || !dev->dlc) - return 0; + if (dev && dev->dlc) + room = rfcomm_room(dev); - room = rfcomm_room(dev->dlc) - atomic_read(&dev->wmem_alloc); - if (room < 0) - room = 0; + BT_DBG("tty %p room %d", tty, room); return room; } @@ -1125,7 +1151,7 @@ int __init rfcomm_init_ttys(void) rfcomm_tty_driver->subtype = SERIAL_TYPE_NORMAL; rfcomm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV; rfcomm_tty_driver->init_termios = tty_std_termios; - rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; + rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL; rfcomm_tty_driver->init_termios.c_lflag &= ~ICANON; tty_set_operations(rfcomm_tty_driver, &rfcomm_ops); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 45007362683b..f886bcae1b7e 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -78,6 +78,70 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) return err; } +static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3]) +{ + u8 _res[16], k[16]; + int err; + + /* r' = padding || r */ + memset(_res, 0, 13); + _res[13] = r[2]; + _res[14] = r[1]; + _res[15] = r[0]; + + swap128(irk, k); + err = smp_e(tfm, k, _res); + if (err) { + BT_ERR("Encrypt error"); + return err; + } + + /* The output of the random address function ah is: + * ah(h, r) = e(k, r') mod 2^24 + * The output of the security function e is then truncated to 24 bits + * by taking the least significant 24 bits of the output of e as the + * result of ah. + */ + res[0] = _res[15]; + res[1] = _res[14]; + res[2] = _res[13]; + + return 0; +} + +bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16], + bdaddr_t *bdaddr) +{ + u8 hash[3]; + int err; + + BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk); + + err = smp_ah(tfm, irk, &bdaddr->b[3], hash); + if (err) + return false; + + return !memcmp(bdaddr->b, hash, 3); +} + +int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa) +{ + int err; + + get_random_bytes(&rpa->b[3], 3); + + rpa->b[5] &= 0x3f; /* Clear two most significant bits */ + rpa->b[5] |= 0x40; /* Set second most significant bit */ + + err = smp_ah(tfm, irk, &rpa->b[3], rpa->b); + if (err < 0) + return err; + + BT_DBG("RPA %pMR", rpa); + + return 0; +} + static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], u8 preq[7], u8 pres[7], u8 _iat, bdaddr_t *ia, u8 _rat, bdaddr_t *ra, u8 res[16]) @@ -203,31 +267,45 @@ static void build_pairing_cmd(struct l2cap_conn *conn, struct smp_cmd_pairing *req, struct smp_cmd_pairing *rsp, __u8 authreq) { - u8 dist_keys = 0; + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + u8 local_dist = 0, remote_dist = 0; if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->dev_flags)) { - dist_keys = SMP_DIST_ENC_KEY; + local_dist = SMP_DIST_ENC_KEY; + remote_dist = SMP_DIST_ENC_KEY; authreq |= SMP_AUTH_BONDING; } else { authreq &= ~SMP_AUTH_BONDING; } + if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags)) + remote_dist |= SMP_DIST_ID_KEY; + + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + local_dist |= SMP_DIST_ID_KEY; + if (rsp == NULL) { req->io_capability = conn->hcon->io_capability; req->oob_flag = SMP_OOB_NOT_PRESENT; req->max_key_size = SMP_MAX_ENC_KEY_SIZE; - req->init_key_dist = 0; - req->resp_key_dist = dist_keys; + req->init_key_dist = local_dist; + req->resp_key_dist = remote_dist; req->auth_req = (authreq & AUTH_REQ_MASK); + + smp->remote_key_dist = remote_dist; return; } rsp->io_capability = conn->hcon->io_capability; rsp->oob_flag = SMP_OOB_NOT_PRESENT; rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE; - rsp->init_key_dist = 0; - rsp->resp_key_dist = req->resp_key_dist & dist_keys; + rsp->init_key_dist = req->init_key_dist & remote_dist; + rsp->resp_key_dist = req->resp_key_dist & local_dist; rsp->auth_req = (authreq & AUTH_REQ_MASK); + + smp->remote_key_dist = rsp->init_key_dist; } static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) @@ -356,29 +434,23 @@ static void confirm_work(struct work_struct *work) { struct smp_chan *smp = container_of(work, struct smp_chan, confirm); struct l2cap_conn *conn = smp->conn; - struct crypto_blkcipher *tfm; + struct hci_dev *hdev = conn->hcon->hdev; + struct crypto_blkcipher *tfm = hdev->tfm_aes; struct smp_cmd_pairing_confirm cp; int ret; u8 res[16], reason; BT_DBG("conn %p", conn); - tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) { - reason = SMP_UNSPECIFIED; - goto error; - } + /* Prevent mutual access to hdev->tfm_aes */ + hci_dev_lock(hdev); - smp->tfm = tfm; + ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, + conn->hcon->init_addr_type, &conn->hcon->init_addr, + conn->hcon->resp_addr_type, &conn->hcon->resp_addr, res); + + hci_dev_unlock(hdev); - if (conn->hcon->out) - ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, - conn->hcon->src_type, &conn->hcon->src, - conn->hcon->dst_type, &conn->hcon->dst, res); - else - ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, - conn->hcon->dst_type, &conn->hcon->dst, - conn->hcon->src_type, &conn->hcon->src, res); if (ret) { reason = SMP_UNSPECIFIED; goto error; @@ -400,7 +472,8 @@ static void random_work(struct work_struct *work) struct smp_chan *smp = container_of(work, struct smp_chan, random); struct l2cap_conn *conn = smp->conn; struct hci_conn *hcon = conn->hcon; - struct crypto_blkcipher *tfm = smp->tfm; + struct hci_dev *hdev = hcon->hdev; + struct crypto_blkcipher *tfm = hdev->tfm_aes; u8 reason, confirm[16], res[16], key[16]; int ret; @@ -411,14 +484,15 @@ static void random_work(struct work_struct *work) BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); - if (hcon->out) - ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, - hcon->src_type, &hcon->src, - hcon->dst_type, &hcon->dst, res); - else - ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, - hcon->dst_type, &hcon->dst, - hcon->src_type, &hcon->src, res); + /* Prevent mutual access to hdev->tfm_aes */ + hci_dev_lock(hdev); + + ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, + hcon->init_addr_type, &hcon->init_addr, + hcon->resp_addr_type, &hcon->resp_addr, res); + + hci_dev_unlock(hdev); + if (ret) { reason = SMP_UNSPECIFIED; goto error; @@ -433,11 +507,9 @@ static void random_work(struct work_struct *work) } if (hcon->out) { - u8 stk[16], rand[8]; - __le16 ediv; - - memset(rand, 0, sizeof(rand)); - ediv = 0; + u8 stk[16]; + __le64 rand = 0; + __le16 ediv = 0; smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, key); swap128(key, stk); @@ -453,11 +525,9 @@ static void random_work(struct work_struct *work) hci_le_start_enc(hcon, ediv, rand, stk); hcon->enc_key_size = smp->enc_key_size; } else { - u8 stk[16], r[16], rand[8]; - __le16 ediv; - - memset(rand, 0, sizeof(rand)); - ediv = 0; + u8 stk[16], r[16]; + __le64 rand = 0; + __le16 ediv = 0; swap128(smp->prnd, r); smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r); @@ -469,7 +539,7 @@ static void random_work(struct work_struct *work) SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_STK_SLAVE, 0, 0, stk, smp->enc_key_size, + HCI_SMP_STK_SLAVE, 0, stk, smp->enc_key_size, ediv, rand); } @@ -479,6 +549,20 @@ error: smp_failure(conn, reason); } +static void smp_reencrypt(struct work_struct *work) +{ + struct smp_chan *smp = container_of(work, struct smp_chan, + reencrypt.work); + struct l2cap_conn *conn = smp->conn; + struct hci_conn *hcon = conn->hcon; + struct smp_ltk *ltk = smp->ltk; + + BT_DBG(""); + + hci_le_start_enc(hcon, ltk->ediv, ltk->rand, ltk->val); + hcon->enc_key_size = ltk->enc_size; +} + static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) { struct smp_chan *smp; @@ -489,6 +573,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) INIT_WORK(&smp->confirm, confirm_work); INIT_WORK(&smp->random, random_work); + INIT_DELAYED_WORK(&smp->reencrypt, smp_reencrypt); smp->conn = conn; conn->smp_chan = smp; @@ -502,11 +587,32 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) void smp_chan_destroy(struct l2cap_conn *conn) { struct smp_chan *smp = conn->smp_chan; + bool complete; BUG_ON(!smp); - if (smp->tfm) - crypto_free_blkcipher(smp->tfm); + cancel_delayed_work_sync(&smp->reencrypt); + + complete = test_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + mgmt_smp_complete(conn->hcon, complete); + + /* If pairing failed clean up any keys we might have */ + if (!complete) { + if (smp->ltk) { + list_del(&smp->ltk->list); + kfree(smp->ltk); + } + + if (smp->slave_ltk) { + list_del(&smp->slave_ltk->list); + kfree(smp->slave_ltk); + } + + if (smp->remote_irk) { + list_del(&smp->remote_irk->list); + kfree(smp->remote_irk); + } + } kfree(smp); conn->smp_chan = NULL; @@ -565,6 +671,9 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*req)) + return SMP_UNSPECIFIED; + if (conn->hcon->link_mode & HCI_LM_MASTER) return SMP_CMD_NOTSUPP; @@ -617,6 +726,9 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*rsp)) + return SMP_UNSPECIFIED; + if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -661,6 +773,9 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); + if (skb->len < sizeof(smp->pcnf)) + return SMP_UNSPECIFIED; + memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf)); skb_pull(skb, sizeof(smp->pcnf)); @@ -686,6 +801,9 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(smp->rrnd)) + return SMP_UNSPECIFIED; + swap128(skb->data, smp->rrnd); skb_pull(skb, sizeof(smp->rrnd)); @@ -699,7 +817,8 @@ static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) struct smp_ltk *key; struct hci_conn *hcon = conn->hcon; - key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type); + key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type, + hcon->out); if (!key) return 0; @@ -724,6 +843,9 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -813,6 +935,15 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_encrypt_info *rp = (void *) skb->data; struct smp_chan *smp = conn->smp_chan; + BT_DBG("conn %p", conn); + + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) + return 0; + skb_pull(skb, sizeof(*rp)); memcpy(smp->tk, rp->ltk, sizeof(smp->tk)); @@ -826,21 +957,114 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_chan *smp = conn->smp_chan; struct hci_dev *hdev = conn->hcon->hdev; struct hci_conn *hcon = conn->hcon; + struct smp_ltk *ltk; u8 authenticated; + BT_DBG("conn %p", conn); + + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) + return 0; + + /* Mark the information as received */ + smp->remote_key_dist &= ~SMP_DIST_ENC_KEY; + skb_pull(skb, sizeof(*rp)); hci_dev_lock(hdev); authenticated = (hcon->sec_level == BT_SECURITY_HIGH); - hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, 1, - authenticated, smp->tk, smp->enc_key_size, - rp->ediv, rp->rand); - smp_distribute_keys(conn, 1); + ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, + authenticated, smp->tk, smp->enc_key_size, + rp->ediv, rp->rand); + smp->ltk = ltk; + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + smp_distribute_keys(conn); hci_dev_unlock(hdev); return 0; } +static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_ident_info *info = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; + + BT_DBG(""); + + if (skb->len < sizeof(*info)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + return 0; + + skb_pull(skb, sizeof(*info)); + + memcpy(smp->irk, info->irk, 16); + + return 0; +} + +static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, + struct sk_buff *skb) +{ + struct smp_cmd_ident_addr_info *info = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + bdaddr_t rpa; + + BT_DBG(""); + + if (skb->len < sizeof(*info)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + return 0; + + /* Mark the information as received */ + smp->remote_key_dist &= ~SMP_DIST_ID_KEY; + + skb_pull(skb, sizeof(*info)); + + /* Strictly speaking the Core Specification (4.1) allows sending + * an empty address which would force us to rely on just the IRK + * as "identity information". However, since such + * implementations are not known of and in order to not over + * complicate our implementation, simply pretend that we never + * received an IRK for such a device. + */ + if (!bacmp(&info->bdaddr, BDADDR_ANY)) { + BT_ERR("Ignoring IRK with no identity address"); + smp_distribute_keys(conn); + return 0; + } + + bacpy(&smp->id_addr, &info->bdaddr); + smp->id_addr_type = info->addr_type; + + if (hci_bdaddr_is_rpa(&hcon->dst, hcon->dst_type)) + bacpy(&rpa, &hcon->dst); + else + bacpy(&rpa, BDADDR_ANY); + + smp->remote_irk = hci_add_irk(conn->hcon->hdev, &smp->id_addr, + smp->id_addr_type, smp->irk, &rpa); + + /* Track the connection based on the Identity Address from now on */ + bacpy(&hcon->dst, &smp->id_addr); + hcon->dst_type = smp->id_addr_type; + + l2cap_conn_update_id_addr(hcon); + + smp_distribute_keys(conn); + + return 0; +} + int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) { struct hci_conn *hcon = conn->hcon; @@ -915,7 +1139,13 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) break; case SMP_CMD_IDENT_INFO: + reason = smp_cmd_ident_info(conn, skb); + break; + case SMP_CMD_IDENT_ADDR_INFO: + reason = smp_cmd_ident_addr_info(conn, skb); + break; + case SMP_CMD_SIGN_INFO: /* Just ignored */ reason = 0; @@ -937,26 +1167,51 @@ done: return err; } -int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) +static void smp_notify_keys(struct l2cap_conn *conn) +{ + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + + if (smp->remote_irk) + mgmt_new_irk(hdev, smp->remote_irk); + + if (smp->ltk) { + smp->ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->ltk); + } + + if (smp->slave_ltk) { + smp->slave_ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->slave_ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->slave_ltk); + } +} + +int smp_distribute_keys(struct l2cap_conn *conn) { struct smp_cmd_pairing *req, *rsp; struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + bool ltk_encrypt; __u8 *keydist; - BT_DBG("conn %p force %d", conn, force); + BT_DBG("conn %p", conn); - if (!test_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) + if (!test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) return 0; rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (!force && conn->hcon->out && (rsp->resp_key_dist & 0x07)) + if (hcon->out && (smp->remote_key_dist & 0x07)) return 0; req = (void *) &smp->preq[1]; - if (conn->hcon->out) { + if (hcon->out) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -964,28 +1219,30 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) *keydist &= req->resp_key_dist; } - BT_DBG("keydist 0x%x", *keydist); if (*keydist & SMP_DIST_ENC_KEY) { struct smp_cmd_encrypt_info enc; struct smp_cmd_master_ident ident; - struct hci_conn *hcon = conn->hcon; + struct smp_ltk *ltk; u8 authenticated; __le16 ediv; + __le64 rand; get_random_bytes(enc.ltk, sizeof(enc.ltk)); get_random_bytes(&ediv, sizeof(ediv)); - get_random_bytes(ident.rand, sizeof(ident.rand)); + get_random_bytes(&rand, sizeof(rand)); smp_send_cmd(conn, SMP_CMD_ENCRYPT_INFO, sizeof(enc), &enc); authenticated = hcon->sec_level == BT_SECURITY_HIGH; - hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_LTK_SLAVE, 1, authenticated, - enc.ltk, smp->enc_key_size, ediv, ident.rand); + ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, + HCI_SMP_LTK_SLAVE, authenticated, enc.ltk, + smp->enc_key_size, ediv, rand); + smp->slave_ltk = ltk; ident.ediv = ediv; + ident.rand = rand; smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident); @@ -996,14 +1253,18 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) struct smp_cmd_ident_addr_info addrinfo; struct smp_cmd_ident_info idinfo; - /* Send a dummy key */ - get_random_bytes(idinfo.irk, sizeof(idinfo.irk)); + memcpy(idinfo.irk, hdev->irk, sizeof(idinfo.irk)); smp_send_cmd(conn, SMP_CMD_IDENT_INFO, sizeof(idinfo), &idinfo); - /* Just public address */ - memset(&addrinfo, 0, sizeof(addrinfo)); - bacpy(&addrinfo.bdaddr, &conn->hcon->src); + /* The hci_conn contains the local identity address + * after the connection has been established. + * + * This is true even when the connection has been + * established using a resolvable random address. + */ + bacpy(&addrinfo.bdaddr, &hcon->src); + addrinfo.addr_type = hcon->src_type; smp_send_cmd(conn, SMP_CMD_IDENT_ADDR_INFO, sizeof(addrinfo), &addrinfo); @@ -1022,9 +1283,34 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) *keydist &= ~SMP_DIST_SIGN; } - if (conn->hcon->out || force) { - clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags); + /* If there are still keys to be received wait for them */ + if ((smp->remote_key_dist & 0x07)) + return 0; + + /* Check if we should try to re-encrypt the link with the LTK. + * SMP_FLAG_LTK_ENCRYPT flag is used to track whether we've + * already tried this (in which case we shouldn't try again). + * + * The request will trigger an encryption key refresh event + * which will cause a call to auth_cfm and eventually lead to + * l2cap_core.c calling this smp_distribute_keys function again + * and thereby completing the process. + */ + if (smp->ltk) + ltk_encrypt = !test_and_set_bit(SMP_FLAG_LTK_ENCRYPT, + &smp->smp_flags); + else + ltk_encrypt = false; + + /* Re-encrypt the link with LTK if possible */ + if (ltk_encrypt && hcon->out) { + queue_delayed_work(hdev->req_workqueue, &smp->reencrypt, + SMP_REENCRYPT_TIMEOUT); + } else { + clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags); cancel_delayed_work_sync(&conn->security_timer); + set_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + smp_notify_keys(conn); smp_chan_destroy(conn); } diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index a700bcb490d7..f55d83617218 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -78,7 +78,7 @@ struct smp_cmd_encrypt_info { #define SMP_CMD_MASTER_IDENT 0x07 struct smp_cmd_master_ident { __le16 ediv; - __u8 rand[8]; + __le64 rand; } __packed; #define SMP_CMD_IDENT_INFO 0x08 @@ -118,6 +118,10 @@ struct smp_cmd_security_req { #define SMP_FLAG_TK_VALID 1 #define SMP_FLAG_CFM_PENDING 2 #define SMP_FLAG_MITM_AUTH 3 +#define SMP_FLAG_LTK_ENCRYPT 4 +#define SMP_FLAG_COMPLETE 5 + +#define SMP_REENCRYPT_TIMEOUT msecs_to_jiffies(250) struct smp_chan { struct l2cap_conn *conn; @@ -128,20 +132,30 @@ struct smp_chan { u8 pcnf[16]; /* SMP Pairing Confirm */ u8 tk[16]; /* SMP Temporary Key */ u8 enc_key_size; + u8 remote_key_dist; + bdaddr_t id_addr; + u8 id_addr_type; + u8 irk[16]; + struct smp_ltk *ltk; + struct smp_ltk *slave_ltk; + struct smp_irk *remote_irk; unsigned long smp_flags; - struct crypto_blkcipher *tfm; struct work_struct confirm; struct work_struct random; - + struct delayed_work reencrypt; }; /* SMP Commands */ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb); -int smp_distribute_keys(struct l2cap_conn *conn, __u8 force); +int smp_distribute_keys(struct l2cap_conn *conn); int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey); void smp_chan_destroy(struct l2cap_conn *conn); +bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16], + bdaddr_t *bdaddr); +int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa); + #endif /* __SMP_H */ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index b063050b63e2..f2a08477e0f5 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -136,9 +136,9 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, const struct pcpu_sw_netstats *bstats = per_cpu_ptr(br->stats, cpu); do { - start = u64_stats_fetch_begin_bh(&bstats->syncp); + start = u64_stats_fetch_begin_irq(&bstats->syncp); memcpy(&tmp, bstats, sizeof(tmp)); - } while (u64_stats_fetch_retry_bh(&bstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&bstats->syncp, start)); sum.tx_bytes += tmp.tx_bytes; sum.tx_packets += tmp.tx_packets; sum.rx_bytes += tmp.rx_bytes; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index c97c3c8ccdfb..7b757b5dc773 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1127,9 +1127,10 @@ static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_querier *querier, int saddr, + bool is_general_query, unsigned long max_delay) { - if (saddr) + if (saddr && is_general_query) br_multicast_update_querier_timer(br, querier, max_delay); else if (timer_pending(&querier->timer)) return; @@ -1181,8 +1182,16 @@ static int br_ip4_multicast_query(struct net_bridge *br, IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr, - max_delay); + !group, max_delay); if (!group) goto out; @@ -1228,6 +1237,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long max_delay; unsigned long now = jiffies; const struct in6_addr *group = NULL; + bool is_general_query; int err = 0; spin_lock(&br->multicast_lock); @@ -1235,6 +1245,12 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { + err = -EINVAL; + goto out; + } + if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1256,8 +1272,19 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } + is_general_query = group && ipv6_addr_any(group); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip6_querier, - !ipv6_addr_any(&ip6h->saddr), max_delay); + !ipv6_addr_any(&ip6h->saddr), + is_general_query, max_delay); if (!group) goto out; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index df0f114fb8cb..80e1b0f60a30 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -167,7 +167,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE; + rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } diff --git a/net/can/raw.c b/net/can/raw.c index 8be757cca2ec..081e81fd017f 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -121,13 +121,9 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->recv_own_msgs && oskb->sk == sk) return; - /* do not pass frames with DLC > 8 to a legacy socket */ - if (!ro->fd_frames) { - struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; - - if (unlikely(cfd->len > CAN_MAX_DLEN)) - return; - } + /* do not pass non-CAN2.0 frames to a legacy socket */ + if (!ro->fd_frames && oskb->len != CAN_MTU) + return; /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); @@ -738,9 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct raw_sock *ro = raw_sk(sk); struct sk_buff *skb; - int rxmtu; int err = 0; int noblock; @@ -751,20 +745,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - /* - * when serving a legacy socket the DLC <= 8 is already checked inside - * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy - * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU - */ - if (!ro->fd_frames) - rxmtu = CAN_MTU; - else - rxmtu = skb->len; - - if (size < rxmtu) + if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else - size = rxmtu; + size = skb->len; err = memcpy_toiovec(msg->msg_iov, skb->data, size); if (err < 0) { diff --git a/net/core/dev.c b/net/core/dev.c index b1b0c8d4d7df..55f8e64c03a2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3231,10 +3231,6 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - /* if netpoll wants it, pretend we never saw it */ - if (netpoll_rx(skb)) - return NET_RX_DROP; - net_timestamp_check(netdev_tstamp_prequeue, skb); trace_netif_rx(skb); @@ -3495,11 +3491,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { - case __constant_htons(ETH_P_ARP): - case __constant_htons(ETH_P_IP): - case __constant_htons(ETH_P_IPV6): - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_ARP): + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): return true; default: return false; @@ -3520,10 +3516,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) trace_netif_receive_skb(skb); - /* if we've gotten here through NAPI, check netpoll */ - if (netpoll_receive_skb(skb)) - goto out; - orig_dev = skb->dev; skb_reset_network_header(skb); @@ -3650,7 +3642,6 @@ drop: unlock: rcu_read_unlock(); -out: return ret; } @@ -3875,7 +3866,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff int same_flow; enum gro_result ret; - if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) + if (!(skb->dev->features & NETIF_F_GRO)) goto normal; if (skb_is_gso(skb) || skb_has_frag_list(skb)) diff --git a/net/core/flow.c b/net/core/flow.c index 344a184011fd..31cfb365e0c6 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -45,6 +45,8 @@ struct flow_flush_info { struct completion completion; }; +static struct kmem_cache *flow_cachep __read_mostly; + #define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) @@ -75,7 +77,7 @@ static void flow_entry_kill(struct flow_cache_entry *fle, { if (fle->object) fle->object->ops->delete(fle->object); - kmem_cache_free(xfrm->flow_cachep, fle); + kmem_cache_free(flow_cachep, fle); } static void flow_cache_gc_task(struct work_struct *work) @@ -230,7 +232,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); - fle = kmem_cache_alloc(net->xfrm.flow_cachep, GFP_ATOMIC); + fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { fle->net = net; fle->family = family; @@ -435,10 +437,10 @@ int flow_cache_init(struct net *net) int i; struct flow_cache *fc = &net->xfrm.flow_cache_global; - /* Initialize per-net flow cache global variables here */ - net->xfrm.flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, NULL); + if (!flow_cachep) + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); spin_lock_init(&net->xfrm.flow_cache_gc_lock); INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list); INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); @@ -482,3 +484,22 @@ err: return -ENOMEM; } EXPORT_SYMBOL(flow_cache_init); + +void flow_cache_fini(struct net *net) +{ + int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; + + del_timer_sync(&fc->rnd_timer); + unregister_hotcpu_notifier(&fc->hotcpu_notifier); + + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + free_percpu(fc->percpu); + fc->percpu = NULL; +} +EXPORT_SYMBOL(flow_cache_fini); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index e29e810663d7..80201bf69d59 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) again: switch (proto) { - case __constant_htons(ETH_P_IP): { + case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; ip: @@ -77,7 +77,7 @@ ip: iph_to_flow_copy_addrs(flow, iph); break; } - case __constant_htons(ETH_P_IPV6): { + case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; ipv6: @@ -91,8 +91,8 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } - case __constant_htons(ETH_P_8021AD): - case __constant_htons(ETH_P_8021Q): { + case htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; @@ -104,7 +104,7 @@ ipv6: nhoff += sizeof(*vlan); goto again; } - case __constant_htons(ETH_P_PPP_SES): { + case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; @@ -115,9 +115,9 @@ ipv6: proto = hdr->proto; nhoff += PPPOE_SES_HLEN; switch (proto) { - case __constant_htons(PPP_IP): + case htons(PPP_IP): goto ip; - case __constant_htons(PPP_IPV6): + case htons(PPP_IPV6): goto ipv6; default: return false; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index fbde4e3ce802..8f8a96ef9f3f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -766,9 +766,6 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) - goto out; - /* * periodically recompute ReachableTime from random function */ @@ -781,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; @@ -3047,7 +3047,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (!t) goto err; - for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; t->neigh_vars[i].extra2 = p; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a664f7829a6d..7291dde93469 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -46,13 +46,9 @@ static struct sk_buff_head skb_pool; -static atomic_t trapped; - DEFINE_STATIC_SRCU(netpoll_srcu); #define USEC_PER_POLL 50 -#define NETPOLL_RX_ENABLED 1 -#define NETPOLL_RX_DROP 2 #define MAX_SKB_SIZE \ (sizeof(struct ethhdr) + \ @@ -61,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu); MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; @@ -109,25 +104,6 @@ static void queue_process(struct work_struct *work) } } -static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, - unsigned short ulen, __be32 saddr, __be32 daddr) -{ - __wsum psum; - - if (uh->check == 0 || skb_csum_unnecessary(skb)) - return 0; - - psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_fold(csum_add(psum, skb->csum))) - return 0; - - skb->csum = psum; - - return __skb_checksum_complete(skb); -} - /* * Check whether delayed processing was scheduled for our NIC. If so, * we attempt to grab the poll lock and use ->poll() to pump the card. @@ -138,14 +114,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, * trylock here and interrupts are already disabled in the softirq * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. - * - * In cases where there is bi-directional communications, reading only - * one message at a time can lead to packets being dropped by the - * network adapter, forcing superfluous retries and possibly timeouts. - * Thus, we set our budget to greater than 1. */ -static int poll_one_napi(struct netpoll_info *npinfo, - struct napi_struct *napi, int budget) +static int poll_one_napi(struct napi_struct *napi, int budget) { int work; @@ -156,52 +126,35 @@ static int poll_one_napi(struct netpoll_info *npinfo, if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - npinfo->rx_flags |= NETPOLL_RX_DROP; - atomic_inc(&trapped); set_bit(NAPI_STATE_NPSVC, &napi->state); work = napi->poll(napi, budget); + WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); - atomic_dec(&trapped); - npinfo->rx_flags &= ~NETPOLL_RX_DROP; return budget - work; } -static void poll_napi(struct net_device *dev) +static void poll_napi(struct net_device *dev, int budget) { struct napi_struct *napi; - int budget = 16; list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(rcu_dereference_bh(dev->npinfo), - napi, budget); + budget = poll_one_napi(napi, budget); spin_unlock(&napi->poll_lock); - - if (!budget) - break; } } } -static void service_neigh_queue(struct netpoll_info *npi) -{ - if (npi) { - struct sk_buff *skb; - - while ((skb = skb_dequeue(&npi->neigh_tx))) - netpoll_neigh_reply(skb, npi); - } -} - static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + int budget = 0; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity @@ -224,27 +177,10 @@ static void netpoll_poll_dev(struct net_device *dev) /* Process pending work on NIC */ ops->ndo_poll_controller(dev); - poll_napi(dev); + poll_napi(dev, budget); up(&ni->dev_lock); - if (dev->flags & IFF_SLAVE) { - if (ni) { - struct net_device *bond_dev; - struct sk_buff *skb; - struct netpoll_info *bond_ni; - - bond_dev = netdev_master_upper_dev_get_rcu(dev); - bond_ni = rcu_dereference_bh(bond_dev->npinfo); - while ((skb = skb_dequeue(&ni->neigh_tx))) { - skb->dev = bond_dev; - skb_queue_tail(&bond_ni->neigh_tx, skb); - } - } - } - - service_neigh_queue(ni); - zap_completion_queue(); } @@ -529,384 +465,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) -{ - int size, type = ARPOP_REPLY; - __be32 sip, tip; - unsigned char *sha; - struct sk_buff *send_skb; - struct netpoll *np, *tmp; - unsigned long flags; - int hlen, tlen; - int hits = 0, proto; - - if (list_empty(&npinfo->rx_np)) - return; - - /* Before checking the packet, we do some early - inspection whether this is interesting at all */ - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->dev == skb->dev) - hits++; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - - /* No netpoll struct is using this dev */ - if (!hits) - return; - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto == ETH_P_ARP) { - struct arphdr *arp; - unsigned char *arp_ptr; - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); - - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; - - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; - - size = arp_hdr_len(skb->dev); - - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip.ip) - continue; - - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; - - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); - - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; - } - - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ - - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); - - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_skb_hooks for the same - * address we're fine by sending a single reply - */ - break; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } else if( proto == ETH_P_IPV6) { -#if IS_ENABLED(CONFIG_IPV6) - struct nd_msg *msg; - u8 *lladdr = NULL; - struct ipv6hdr *hdr; - struct icmp6hdr *icmp6h; - const struct in6_addr *saddr; - const struct in6_addr *daddr; - struct inet6_dev *in6_dev = NULL; - struct in6_addr *target; - - in6_dev = in6_dev_get(skb->dev); - if (!in6_dev || !in6_dev->cnf.accept_ra) - return; - - if (!pskb_may_pull(skb, skb->len)) - return; - - msg = (struct nd_msg *)skb_transport_header(skb); - - __skb_push(skb, skb->data - skb_transport_header(skb)); - - if (ipv6_hdr(skb)->hop_limit != 255) - return; - if (msg->icmph.icmp6_code != 0) - return; - if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) - return; - - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; - - size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); - - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (!ipv6_addr_equal(daddr, &np->local_ip.in6)) - continue; - - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; - - send_skb->protocol = htons(ETH_P_IPV6); - send_skb->dev = skb->dev; - - skb_reset_network_header(send_skb); - hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr)); - *(__be32*)hdr = htonl(0x60000000); - hdr->payload_len = htons(size); - hdr->nexthdr = IPPROTO_ICMPV6; - hdr->hop_limit = 255; - hdr->saddr = *saddr; - hdr->daddr = *daddr; - - icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr)); - icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; - icmp6h->icmp6_router = 0; - icmp6h->icmp6_solicited = 1; - - target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr)); - *target = msg->target; - icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, - IPPROTO_ICMPV6, - csum_partial(icmp6h, - size, 0)); - - if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6, - lladdr, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; - } - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_skb_hooks for the same - * address, we're fine by sending a single reply - */ - break; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); -#endif - } -} - -static bool pkt_is_ns(struct sk_buff *skb) -{ - struct nd_msg *msg; - struct ipv6hdr *hdr; - - if (skb->protocol != htons(ETH_P_ARP)) - return false; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) - return false; - - msg = (struct nd_msg *)skb_transport_header(skb); - __skb_push(skb, skb->data - skb_transport_header(skb)); - hdr = ipv6_hdr(skb); - - if (hdr->nexthdr != IPPROTO_ICMPV6) - return false; - if (hdr->hop_limit != 255) - return false; - if (msg->icmph.icmp6_code != 0) - return false; - if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) - return false; - - return true; -} - -int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) -{ - int proto, len, ulen, data_len; - int hits = 0, offset; - const struct iphdr *iph; - struct udphdr *uh; - struct netpoll *np, *tmp; - uint16_t source; - - if (list_empty(&npinfo->rx_np)) - goto out; - - if (skb->dev->type != ARPHRD_ETHER) - goto out; - - /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { - skb_queue_tail(&npinfo->neigh_tx, skb); - return 1; - } else if (pkt_is_ns(skb) && atomic_read(&trapped)) { - skb_queue_tail(&npinfo->neigh_tx, skb); - return 1; - } - - if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); - if (unlikely(!skb)) - goto out; - } - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP && proto != ETH_P_IPV6) - goto out; - if (skb->pkt_type == PACKET_OTHERHOST) - goto out; - if (skb_shared(skb)) - goto out; - - if (proto == ETH_P_IP) { - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = (struct iphdr *)skb->data; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - iph = (struct iphdr *)skb->data; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; - - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; - - iph = (struct iphdr *)skb->data; - if (iph->protocol != IPPROTO_UDP) - goto out; - - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - offset = (unsigned char *)(uh + 1) - skb->data; - ulen = ntohs(uh->len); - data_len = skb->len - offset; - source = ntohs(uh->source); - - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip.ip && np->local_ip.ip != iph->daddr) - continue; - if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; - - np->rx_skb_hook(np, source, skb, offset, data_len); - hits++; - } - } else { -#if IS_ENABLED(CONFIG_IPV6) - const struct ipv6hdr *ip6h; - - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto out; - ip6h = (struct ipv6hdr *)skb->data; - if (ip6h->version != 6) - goto out; - len = ntohs(ip6h->payload_len); - if (!len) - goto out; - if (len + sizeof(struct ipv6hdr) > skb->len) - goto out; - if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr))) - goto out; - ip6h = ipv6_hdr(skb); - if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto out; - uh = udp_hdr(skb); - offset = (unsigned char *)(uh + 1) - skb->data; - ulen = ntohs(uh->len); - data_len = skb->len - offset; - source = ntohs(uh->source); - if (ulen != skb->len) - goto out; - if (udp6_csum_init(skb, uh, IPPROTO_UDP)) - goto out; - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr)) - continue; - if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr)) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; - - np->rx_skb_hook(np, source, skb, offset, data_len); - hits++; - } -#endif - } - - if (!hits) - goto out; - - kfree_skb(skb); - return 1; - -out: - if (atomic_read(&trapped)) { - kfree_skb(skb); - return 1; - } - - return 0; -} - void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); @@ -1030,7 +588,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) { struct netpoll_info *npinfo; const struct net_device_ops *ops; - unsigned long flags; int err; np->dev = ndev; @@ -1052,12 +609,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) goto out; } - npinfo->rx_flags = 0; - INIT_LIST_HEAD(&npinfo->rx_np); - - spin_lock_init(&npinfo->rx_lock); sema_init(&npinfo->dev_lock, 1); - skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -1076,13 +628,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) npinfo->netpoll = np; - if (np->rx_skb_hook) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_flags |= NETPOLL_RX_ENABLED; - list_add_tail(&np->rx, &npinfo->rx_np); - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -1231,7 +776,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); - skb_queue_purge(&npinfo->neigh_tx); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ @@ -1247,7 +791,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; - unsigned long flags; /* rtnl_dereference would be preferable here but * rcu_cleanup_netpoll path can put us in here safely without @@ -1257,14 +800,6 @@ void __netpoll_cleanup(struct netpoll *np) if (!npinfo) return; - if (!list_empty(&npinfo->rx_np)) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_del(&np->rx); - if (list_empty(&npinfo->rx_np)) - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - synchronize_srcu(&netpoll_srcu); if (atomic_dec_and_test(&npinfo->refcnt)) { @@ -1308,18 +843,3 @@ out: rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); - -int netpoll_trap(void) -{ - return atomic_read(&trapped); -} -EXPORT_SYMBOL(netpoll_trap); - -void netpoll_set_trap(int trap) -{ - if (trap) - atomic_inc(&trapped); - else - atomic_dec(&trapped); -} -EXPORT_SYMBOL(netpoll_set_trap); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f28c37996aad..3f14c638c2b1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT @@ -2841,81 +2838,84 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); /** * skb_segment - Perform protocol segmentation on skb. - * @skb: buffer to segment + * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) +struct sk_buff *skb_segment(struct sk_buff *head_skb, + netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; - struct sk_buff *fskb = skb_shinfo(skb)->frag_list; - skb_frag_t *skb_frag = skb_shinfo(skb)->frags; - unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int doffset = skb->data - skb_mac_header(skb); + struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; + skb_frag_t *frag = skb_shinfo(head_skb)->frags; + unsigned int mss = skb_shinfo(head_skb)->gso_size; + unsigned int doffset = head_skb->data - skb_mac_header(head_skb); + struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; - unsigned int tnl_hlen = skb_tnl_header_len(skb); + unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int headroom; unsigned int len; __be16 proto; bool csum; int sg = !!(features & NETIF_F_SG); - int nfrags = skb_shinfo(skb)->nr_frags; + int nfrags = skb_shinfo(head_skb)->nr_frags; int err = -ENOMEM; int i = 0; int pos; - proto = skb_network_protocol(skb); + proto = skb_network_protocol(head_skb); if (unlikely(!proto)) return ERR_PTR(-EINVAL); csum = !!can_checksum_protocol(features, proto); - __skb_push(skb, doffset); - headroom = skb_headroom(skb); - pos = skb_headlen(skb); + __skb_push(head_skb, doffset); + headroom = skb_headroom(head_skb); + pos = skb_headlen(head_skb); do { struct sk_buff *nskb; - skb_frag_t *frag; + skb_frag_t *nskb_frag; int hsize; int size; - len = skb->len - offset; + len = head_skb->len - offset; if (len > mss) len = mss; - hsize = skb_headlen(skb) - offset; + hsize = skb_headlen(head_skb) - offset; if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; - if (!hsize && i >= nfrags && skb_headlen(fskb) && - (skb_headlen(fskb) == len || sg)) { - BUG_ON(skb_headlen(fskb) > len); + if (!hsize && i >= nfrags && skb_headlen(list_skb) && + (skb_headlen(list_skb) == len || sg)) { + BUG_ON(skb_headlen(list_skb) > len); i = 0; - nfrags = skb_shinfo(fskb)->nr_frags; - skb_frag = skb_shinfo(fskb)->frags; - pos += skb_headlen(fskb); + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); - size = skb_frag_size(skb_frag); + size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; - skb_frag++; + frag++; } - nskb = skb_clone(fskb, GFP_ATOMIC); - fskb = fskb->next; + nskb = skb_clone(list_skb, GFP_ATOMIC); + list_skb = list_skb->next; if (unlikely(!nskb)) goto err; @@ -2936,7 +2936,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) __skb_push(nskb, doffset); } else { nskb = __alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC, skb_alloc_rx_flag(skb), + GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) @@ -2952,12 +2952,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) segs = nskb; tail = nskb; - __copy_skb_header(nskb, skb); - nskb->mac_len = skb->mac_len; + __copy_skb_header(nskb, head_skb); + nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); - skb_copy_from_linear_data_offset(skb, -tnl_hlen, + skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); @@ -2966,30 +2966,32 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (!sg) { nskb->ip_summed = CHECKSUM_NONE; - nskb->csum = skb_copy_and_csum_bits(skb, offset, + nskb->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len, 0); continue; } - frag = skb_shinfo(nskb)->frags; + nskb_frag = skb_shinfo(nskb)->frags; - skb_copy_from_linear_data_offset(skb, offset, + skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags & + SKBTX_SHARED_FRAG; while (pos < offset + len) { if (i >= nfrags) { - BUG_ON(skb_headlen(fskb)); + BUG_ON(skb_headlen(list_skb)); i = 0; - nfrags = skb_shinfo(fskb)->nr_frags; - skb_frag = skb_shinfo(fskb)->frags; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; BUG_ON(!nfrags); - fskb = fskb->next; + list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= @@ -3000,27 +3002,30 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) goto err; } - *frag = *skb_frag; - __skb_frag_ref(frag); - size = skb_frag_size(frag); + if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) + goto err; + + *nskb_frag = *frag; + __skb_frag_ref(nskb_frag); + size = skb_frag_size(nskb_frag); if (pos < offset) { - frag->page_offset += offset - pos; - skb_frag_size_sub(frag, offset - pos); + nskb_frag->page_offset += offset - pos; + skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; - skb_frag++; + frag++; pos += size; } else { - skb_frag_size_sub(frag, pos + size - (offset + len)); + skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } - frag++; + nskb_frag++; } skip_fraglist: @@ -3034,7 +3039,7 @@ perform_csum_check: nskb->len - doffset, 0); nskb->ip_summed = CHECKSUM_NONE; } - } while ((offset += len) < skb->len); + } while ((offset += len) < head_skb->len); return segs; @@ -3569,15 +3574,47 @@ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, return 0; } +#define MAX_TCP_HDR_LEN (15 * 4) + +static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, + typeof(IPPROTO_IP) proto, + unsigned int off) +{ + switch (proto) { + int err; + + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), + off + MAX_TCP_HDR_LEN); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; + + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), + off + sizeof(struct udphdr)); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct udphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &udp_hdr(skb)->check; + } + + return ERR_PTR(-EPROTO); +} + /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 -static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; + __sum16 *csum; int err; fragment = false; @@ -3598,51 +3635,15 @@ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) if (fragment) goto out; - switch (ip_hdr(skb)->protocol) { - case IPPROTO_TCP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - tcp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - udp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } + csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + if (recalculate) + *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + ip_hdr(skb)->protocol, 0); err = 0; out: @@ -3665,6 +3666,7 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) unsigned int len; bool fragment; bool done; + __sum16 *csum; fragment = false; done = false; @@ -3742,51 +3744,14 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) if (!done || fragment) goto out; - switch (nexthdr) { - case IPPROTO_TCP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - udp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } + csum = skb_checksum_setup_ip(skb, nexthdr, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + if (recalculate) + *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, nexthdr, 0); err = 0; out: @@ -3804,7 +3769,7 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) switch (skb->protocol) { case htons(ETH_P_IP): - err = skb_checksum_setup_ip(skb, recalculate); + err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): diff --git a/net/core/sock.c b/net/core/sock.c index 5b6a9431b017..c0fc6bdad1e3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2357,10 +2357,13 @@ void release_sock(struct sock *sk) if (sk->sk_backlog.tail) __release_sock(sk); + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); - sk->sk_lock.owned = 0; + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 3d0100f0bae3..83e58449366a 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -297,7 +297,7 @@ static bool seq_nr_after(u16 a, u16 b) void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx) { - if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) { + if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) { WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx); return; } diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h deleted file mode 100644 index 0dccf62434d5..000000000000 --- a/net/ieee802154/6lowpan.h +++ /dev/null @@ -1,432 +0,0 @@ -/* - * Copyright 2011, Siemens AG - * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> - */ - -/* - * Based on patches from Jon Smirl <jonsmirl@gmail.com> - * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> - * - * 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 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. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -/* Jon's code is based on 6lowpan implementation for Contiki which is: - * Copyright (c) 2008, Swedish Institute of Computer Science. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Institute nor the names of its contributors - * may be used to endorse or promote products derived from this software - * without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - */ - -#ifndef __6LOWPAN_H__ -#define __6LOWPAN_H__ - -#define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ -#define UIP_IPH_LEN 40 /* ipv6 fixed header size */ -#define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ -#define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ - -/* - * ipv6 address based on mac - * second bit-flip (Universe/Local) is done according RFC2464 - */ -#define is_addr_mac_addr_based(a, m) \ - ((((a)->s6_addr[8]) == (((m)[0]) ^ 0x02)) && \ - (((a)->s6_addr[9]) == (m)[1]) && \ - (((a)->s6_addr[10]) == (m)[2]) && \ - (((a)->s6_addr[11]) == (m)[3]) && \ - (((a)->s6_addr[12]) == (m)[4]) && \ - (((a)->s6_addr[13]) == (m)[5]) && \ - (((a)->s6_addr[14]) == (m)[6]) && \ - (((a)->s6_addr[15]) == (m)[7])) - -/* ipv6 address is unspecified */ -#define is_addr_unspecified(a) \ - ((((a)->s6_addr32[0]) == 0) && \ - (((a)->s6_addr32[1]) == 0) && \ - (((a)->s6_addr32[2]) == 0) && \ - (((a)->s6_addr32[3]) == 0)) - -/* compare ipv6 addresses prefixes */ -#define ipaddr_prefixcmp(addr1, addr2, length) \ - (memcmp(addr1, addr2, length >> 3) == 0) - -/* local link, i.e. FE80::/10 */ -#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80)) - -/* - * check whether we can compress the IID to 16 bits, - * it's possible for unicast adresses with first 49 bits are zero only. - */ -#define lowpan_is_iid_16_bit_compressable(a) \ - ((((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0) && \ - (((a)->s6_addr[11]) == 0xff) && \ - (((a)->s6_addr[12]) == 0xfe) && \ - (((a)->s6_addr[13]) == 0)) - -/* multicast address */ -#define is_addr_mcast(a) (((a)->s6_addr[0]) == 0xFF) - -/* check whether the 112-bit gid of the multicast address is mappable to: */ - -/* 9 bits, for FF02::1 (all nodes) and FF02::2 (all routers) addresses only. */ -#define lowpan_is_mcast_addr_compressable(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr16[6]) == 0) && \ - (((a)->s6_addr[14]) == 0) && \ - ((((a)->s6_addr[15]) == 1) || (((a)->s6_addr[15]) == 2))) - -/* 48 bits, FFXX::00XX:XXXX:XXXX */ -#define lowpan_is_mcast_addr_compressable48(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0)) - -/* 32 bits, FFXX::00XX:XXXX */ -#define lowpan_is_mcast_addr_compressable32(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr[12]) == 0)) - -/* 8 bits, FF02::00XX */ -#define lowpan_is_mcast_addr_compressable8(a) \ - ((((a)->s6_addr[1]) == 2) && \ - (((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr16[6]) == 0) && \ - (((a)->s6_addr[14]) == 0)) - -#define lowpan_is_addr_broadcast(a) \ - ((((a)[0]) == 0xFF) && \ - (((a)[1]) == 0xFF) && \ - (((a)[2]) == 0xFF) && \ - (((a)[3]) == 0xFF) && \ - (((a)[4]) == 0xFF) && \ - (((a)[5]) == 0xFF) && \ - (((a)[6]) == 0xFF) && \ - (((a)[7]) == 0xFF)) - -#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ -#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ -#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ -#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ -#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ - -#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ - -#define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ - -#define LOWPAN_FRAG1_HEAD_SIZE 0x4 -#define LOWPAN_FRAGN_HEAD_SIZE 0x5 - -/* - * According IEEE802.15.4 standard: - * - MTU is 127 octets - * - maximum MHR size is 37 octets - * - MFR size is 2 octets - * - * so minimal payload size that we may guarantee is: - * MTU - MHR - MFR = 88 octets - */ -#define LOWPAN_FRAG_SIZE 88 - -/* - * Values of fields within the IPHC encoding first byte - * (C stands for compressed and I for inline) - */ -#define LOWPAN_IPHC_TF 0x18 - -#define LOWPAN_IPHC_FL_C 0x10 -#define LOWPAN_IPHC_TC_C 0x08 -#define LOWPAN_IPHC_NH_C 0x04 -#define LOWPAN_IPHC_TTL_1 0x01 -#define LOWPAN_IPHC_TTL_64 0x02 -#define LOWPAN_IPHC_TTL_255 0x03 -#define LOWPAN_IPHC_TTL_I 0x00 - - -/* Values of fields within the IPHC encoding second byte */ -#define LOWPAN_IPHC_CID 0x80 - -#define LOWPAN_IPHC_ADDR_00 0x00 -#define LOWPAN_IPHC_ADDR_01 0x01 -#define LOWPAN_IPHC_ADDR_02 0x02 -#define LOWPAN_IPHC_ADDR_03 0x03 - -#define LOWPAN_IPHC_SAC 0x40 -#define LOWPAN_IPHC_SAM 0x30 - -#define LOWPAN_IPHC_SAM_BIT 4 - -#define LOWPAN_IPHC_M 0x08 -#define LOWPAN_IPHC_DAC 0x04 -#define LOWPAN_IPHC_DAM_00 0x00 -#define LOWPAN_IPHC_DAM_01 0x01 -#define LOWPAN_IPHC_DAM_10 0x02 -#define LOWPAN_IPHC_DAM_11 0x03 - -#define LOWPAN_IPHC_DAM_BIT 0 -/* - * LOWPAN_UDP encoding (works together with IPHC) - */ -#define LOWPAN_NHC_UDP_MASK 0xF8 -#define LOWPAN_NHC_UDP_ID 0xF0 -#define LOWPAN_NHC_UDP_CHECKSUMC 0x04 -#define LOWPAN_NHC_UDP_CHECKSUMI 0x00 - -#define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0 -#define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0 -#define LOWPAN_NHC_UDP_8BIT_PORT 0xF000 -#define LOWPAN_NHC_UDP_8BIT_MASK 0xFF00 - -/* values for port compression, _with checksum_ ie bit 5 set to 0 */ -#define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */ -#define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline, - dest = 0xF0 + 8 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_10 0xF2 /* source = 0xF0 + 8bit inline, - dest = 16 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ -#define LOWPAN_NHC_UDP_CS_C 0x04 /* checksum elided */ - -#ifdef DEBUG -/* print data in line */ -static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) -{ - if (msg) - pr_debug("%s():%s: ", caller, msg); - - print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, buf, len, false); -} - -/* print data in a table format: - * - * addr: xx xx xx xx xx xx - * addr: xx xx xx xx xx xx - * ... - */ -static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) -{ - if (msg) - pr_debug("%s():%s:\n", caller, msg); - - print_hex_dump_debug("\t", DUMP_PREFIX_OFFSET, 16, 1, buf, len, false); -} -#else -static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) { } -static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) { } -#endif - -static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val) -{ - if (unlikely(!pskb_may_pull(skb, 2))) - return -EINVAL; - - *val = (skb->data[0] << 8) | skb->data[1]; - skb_pull(skb, 2); - - return 0; -} - -static inline bool lowpan_fetch_skb(struct sk_buff *skb, - void *data, const unsigned int len) -{ - if (unlikely(!pskb_may_pull(skb, len))) - return true; - - skb_copy_from_linear_data(skb, data, len); - skb_pull(skb, len); - - return false; -} - -static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, - const size_t len) -{ - memcpy(*hc_ptr, data, len); - *hc_ptr += len; -} - -static inline u8 lowpan_addr_mode_size(const u8 addr_mode) -{ - static const u8 addr_sizes[] = { - [LOWPAN_IPHC_ADDR_00] = 16, - [LOWPAN_IPHC_ADDR_01] = 8, - [LOWPAN_IPHC_ADDR_02] = 2, - [LOWPAN_IPHC_ADDR_03] = 0, - }; - return addr_sizes[addr_mode]; -} - -static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header) -{ - u8 ret = 1; - - if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - *uncomp_header += sizeof(struct udphdr); - - switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) { - case LOWPAN_NHC_UDP_CS_P_00: - ret += 4; - break; - case LOWPAN_NHC_UDP_CS_P_01: - case LOWPAN_NHC_UDP_CS_P_10: - ret += 3; - break; - case LOWPAN_NHC_UDP_CS_P_11: - ret++; - break; - default: - break; - } - - if (!(h_enc & LOWPAN_NHC_UDP_CS_C)) - ret += 2; - } - - return ret; -} - -/** - * lowpan_uncompress_size - returns skb->len size with uncompressed header - * @skb: sk_buff with 6lowpan header inside - * @datagram_offset: optional to get the datagram_offset value - * - * Returns the skb->len with uncompressed header - */ -static inline u16 -lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset) -{ - u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr); - u8 iphc0, iphc1, h_enc; - - iphc0 = skb_network_header(skb)[0]; - iphc1 = skb_network_header(skb)[1]; - - switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - case 0: - ret += 4; - break; - case 1: - ret += 3; - break; - case 2: - ret++; - break; - default: - break; - } - - if (!(iphc0 & LOWPAN_IPHC_NH_C)) - ret++; - - if (!(iphc0 & 0x03)) - ret++; - - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >> - LOWPAN_IPHC_SAM_BIT); - - if (iphc1 & LOWPAN_IPHC_M) { - switch ((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT) { - case LOWPAN_IPHC_DAM_00: - ret += 16; - break; - case LOWPAN_IPHC_DAM_01: - ret += 6; - break; - case LOWPAN_IPHC_DAM_10: - ret += 4; - break; - case LOWPAN_IPHC_DAM_11: - ret++; - break; - default: - break; - } - } else { - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT); - } - - if (iphc0 & LOWPAN_IPHC_NH_C) { - h_enc = skb_network_header(skb)[ret]; - ret += lowpan_next_hdr_size(h_enc, &uncomp_header); - } - - if (dgram_offset) - *dgram_offset = uncomp_header; - - return skb->len + uncomp_header - ret; -} - -typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev); - -int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, - const u8 *saddr, const u8 saddr_type, const u8 saddr_len, - const u8 *daddr, const u8 daddr_type, const u8 daddr_len, - u8 iphc0, u8 iphc1, skb_delivery_cb skb_deliver); -int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *_daddr, - const void *_saddr, unsigned int len); - -#endif /* __6LOWPAN_H__ */ diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c index 860aa2d445ba..211b5686d719 100644 --- a/net/ieee802154/6lowpan_iphc.c +++ b/net/ieee802154/6lowpan_iphc.c @@ -54,11 +54,10 @@ #include <linux/if_arp.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <net/6lowpan.h> #include <net/ipv6.h> #include <net/af_ieee802154.h> -#include "6lowpan.h" - /* * Uncompress address function for source and * destination address(non-multicast). diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c index e4726180fc36..606039442a59 100644 --- a/net/ieee802154/6lowpan_rtnl.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -52,10 +52,10 @@ #include <net/af_ieee802154.h> #include <net/ieee802154.h> #include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> #include <net/ipv6.h> #include "reassembly.h" -#include "6lowpan.h" static LIST_HEAD(lowpan_devices); @@ -119,29 +119,29 @@ static int lowpan_header_create(struct sk_buff *skb, mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); /* prepare wpan address data */ - sa.addr_type = IEEE802154_ADDR_LONG; + sa.mode = IEEE802154_ADDR_LONG; sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + sa.extended_addr = ieee802154_devaddr_from_raw(saddr); - memcpy(&(sa.hwaddr), saddr, 8); /* intra-PAN communications */ - da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + da.pan_id = sa.pan_id; /* if the destination address is the broadcast address, use the * corresponding short address */ if (lowpan_is_addr_broadcast(daddr)) { - da.addr_type = IEEE802154_ADDR_SHORT; - da.short_addr = IEEE802154_ADDR_BROADCAST; + da.mode = IEEE802154_ADDR_SHORT; + da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); } else { - da.addr_type = IEEE802154_ADDR_LONG; - memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN); + da.mode = IEEE802154_ADDR_LONG; + da.extended_addr = ieee802154_devaddr_from_raw(daddr); /* request acknowledgment */ mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; } return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, - type, (void *)&da, (void *)&sa, skb->len); + type, (void *)&da, (void *)&sa, 0); } static int lowpan_give_skb_to_devices(struct sk_buff *skb, @@ -168,10 +168,11 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb, return stat; } -static int process_data(struct sk_buff *skb) +static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr) { u8 iphc0, iphc1; - const struct ieee802154_addr *_saddr, *_daddr; + struct ieee802154_addr_sa sa, da; + void *sap, *dap; raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); /* at least two bytes will be used for the encoding */ @@ -184,14 +185,23 @@ static int process_data(struct sk_buff *skb) if (lowpan_fetch_skb_u8(skb, &iphc1)) goto drop; - _saddr = &mac_cb(skb)->sa; - _daddr = &mac_cb(skb)->da; + ieee802154_addr_to_sa(&sa, &hdr->source); + ieee802154_addr_to_sa(&da, &hdr->dest); - return lowpan_process_data(skb, skb->dev, (u8 *)_saddr->hwaddr, - _saddr->addr_type, IEEE802154_ADDR_LEN, - (u8 *)_daddr->hwaddr, _daddr->addr_type, - IEEE802154_ADDR_LEN, iphc0, iphc1, - lowpan_give_skb_to_devices); + if (sa.addr_type == IEEE802154_ADDR_SHORT) + sap = &sa.short_addr; + else + sap = &sa.hwaddr; + + if (da.addr_type == IEEE802154_ADDR_SHORT) + dap = &da.short_addr; + else + dap = &da.hwaddr; + + return lowpan_process_data(skb, skb->dev, sap, sa.addr_type, + IEEE802154_ADDR_LEN, dap, da.addr_type, + IEEE802154_ADDR_LEN, iphc0, iphc1, + lowpan_give_skb_to_devices); drop: kfree_skb(skb); @@ -352,13 +362,13 @@ static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) return ieee802154_mlme_ops(real_dev)->get_phy(real_dev); } -static u16 lowpan_get_pan_id(const struct net_device *dev) +static __le16 lowpan_get_pan_id(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); } -static u16 lowpan_get_short_addr(const struct net_device *dev) +static __le16 lowpan_get_short_addr(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); @@ -438,6 +448,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sk_buff *local_skb; + struct ieee802154_hdr hdr; int ret; if (!netif_running(dev)) @@ -446,6 +457,9 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (dev->type != ARPHRD_IEEE802154) goto drop_skb; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + goto drop_skb; + local_skb = skb_clone(skb, GFP_ATOMIC); if (!local_skb) goto drop_skb; @@ -466,14 +480,14 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, } else { switch (skb->data[0] & 0xe0) { case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ - ret = process_data(local_skb); + ret = process_data(local_skb, &hdr); if (ret == NET_RX_DROP) goto drop; break; case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ ret = lowpan_frag_rcv(local_skb, LOWPAN_DISPATCH_FRAG1); if (ret == 1) { - ret = process_data(local_skb); + ret = process_data(local_skb, &hdr); if (ret == NET_RX_DROP) goto drop; } @@ -481,7 +495,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ ret = lowpan_frag_rcv(local_skb, LOWPAN_DISPATCH_FRAGN); if (ret == 1) { - ret = process_data(local_skb); + ret = process_data(local_skb, &hdr); if (ret == NET_RX_DROP) goto drop; } @@ -613,7 +627,7 @@ static struct notifier_block lowpan_dev_notifier = { }; static struct packet_type lowpan_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = lowpan_rcv, }; diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 9c9879d5ea64..8af1330b3137 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -15,7 +15,7 @@ config IEEE802154_6LOWPAN depends on IEEE802154 && IPV6 select 6LOWPAN_IPHC ---help--- - IPv6 compression over IEEE 802.15.4. + IPv6 compression over IEEE 802.15.4. config 6LOWPAN_IPHC tristate diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index b113fc4be3e0..bf1b51497a41 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -3,5 +3,8 @@ obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o 6lowpan-y := 6lowpan_rtnl.o reassembly.o -ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o +ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o \ + header_ops.o af_802154-y := af_ieee802154.o raw.o dgram.o + +ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h index b1ec52537522..8330a09bfc95 100644 --- a/net/ieee802154/af802154.h +++ b/net/ieee802154/af802154.h @@ -25,12 +25,13 @@ #define AF802154_H struct sk_buff; -struct net_devce; +struct net_device; +struct ieee802154_addr; extern struct proto ieee802154_raw_prot; extern struct proto ieee802154_dgram_prot; void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb); int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb); struct net_device *ieee802154_get_dev(struct net *net, - struct ieee802154_addr *addr); + const struct ieee802154_addr *addr); #endif diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 40e606f3788f..be44a86751aa 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -43,25 +43,27 @@ /* * Utility function for families */ -struct net_device *ieee802154_get_dev(struct net *net, - struct ieee802154_addr *addr) +struct net_device* +ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) { struct net_device *dev = NULL; struct net_device *tmp; - u16 pan_id, short_addr; + __le16 pan_id, short_addr; + u8 hwaddr[IEEE802154_ADDR_LEN]; - switch (addr->addr_type) { + switch (addr->mode) { case IEEE802154_ADDR_LONG: + ieee802154_devaddr_to_raw(hwaddr, addr->extended_addr); rcu_read_lock(); - dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr); + dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, hwaddr); if (dev) dev_hold(dev); rcu_read_unlock(); break; case IEEE802154_ADDR_SHORT: - if (addr->pan_id == 0xffff || - addr->short_addr == IEEE802154_ADDR_UNDEF || - addr->short_addr == 0xffff) + if (addr->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST) || + addr->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || + addr->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF)) break; rtnl_lock(); @@ -86,7 +88,7 @@ struct net_device *ieee802154_get_dev(struct net *net, break; default: pr_warning("Unsupported ieee802154 address type: %d\n", - addr->addr_type); + addr->mode); break; } @@ -326,7 +328,7 @@ drop: static struct packet_type ieee802154_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = ieee802154_rcv, }; diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 1846c1fe0d06..4c47154041b0 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -73,10 +73,10 @@ static int dgram_init(struct sock *sk) { struct dgram_sock *ro = dgram_sk(sk); - ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; - ro->dst_addr.pan_id = 0xffff; + ro->dst_addr.mode = IEEE802154_ADDR_LONG; + ro->dst_addr.pan_id = cpu_to_le16(IEEE802154_ADDR_BROADCAST); ro->want_ack = 1; - memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); return 0; } @@ -88,6 +88,7 @@ static void dgram_close(struct sock *sk, long timeout) static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; + struct ieee802154_addr haddr; struct dgram_sock *ro = dgram_sk(sk); int err = -EINVAL; struct net_device *dev; @@ -102,7 +103,8 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) if (addr->family != AF_IEEE802154) goto out; - dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + ieee802154_addr_from_sa(&haddr, &addr->addr); + dev = ieee802154_get_dev(sock_net(sk), &haddr); if (!dev) { err = -ENODEV; goto out; @@ -113,7 +115,7 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) goto out_put; } - memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr)); + ro->src_addr = haddr; ro->bound = 1; err = 0; @@ -149,8 +151,7 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) * of this packet since that is all * that will be read. */ - /* FIXME: parse the header for more correct value */ - amount = skb->len - (3+8+8); + amount = skb->len - ieee802154_hdr_length(skb); } spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); @@ -181,7 +182,7 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } - memcpy(&ro->dst_addr, &addr->addr, sizeof(struct ieee802154_addr)); + ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr); out: release_sock(sk); @@ -194,8 +195,8 @@ static int dgram_disconnect(struct sock *sk, int flags) lock_sock(sk); - ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; - memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + ro->dst_addr.mode = IEEE802154_ADDR_LONG; + memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); release_sock(sk); @@ -232,7 +233,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, if (size > mtu) { pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; + err = -EMSGSIZE; goto out_dev; } @@ -312,7 +313,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (saddr) { saddr->family = AF_IEEE802154; - saddr->addr = mac_cb(skb)->sa; + ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source); *addr_len = sizeof(*saddr); } @@ -336,40 +337,43 @@ static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb) return NET_RX_SUCCESS; } -static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id, - u16 short_addr, struct dgram_sock *ro) +static inline bool +ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr, + struct dgram_sock *ro) { if (!ro->bound) - return 1; + return true; - if (ro->src_addr.addr_type == IEEE802154_ADDR_LONG && - !memcmp(ro->src_addr.hwaddr, hw_addr, IEEE802154_ADDR_LEN)) - return 1; + if (ro->src_addr.mode == IEEE802154_ADDR_LONG && + hw_addr == ro->src_addr.extended_addr) + return true; - if (ro->src_addr.addr_type == IEEE802154_ADDR_SHORT && - pan_id == ro->src_addr.pan_id && - short_addr == ro->src_addr.short_addr) - return 1; + if (ro->src_addr.mode == IEEE802154_ADDR_SHORT && + pan_id == ro->src_addr.pan_id && + short_addr == ro->src_addr.short_addr) + return true; - return 0; + return false; } int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk, *prev = NULL; int ret = NET_RX_SUCCESS; - u16 pan_id, short_addr; + __le16 pan_id, short_addr; + __le64 hw_addr; /* Data frame processing */ BUG_ON(dev->type != ARPHRD_IEEE802154); pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); + hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr); read_lock(&dgram_lock); sk_for_each(sk, &dgram_head) { - if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr, - dgram_sk(sk))) { + if (ieee802154_match_sock(hw_addr, pan_id, short_addr, + dgram_sk(sk))) { if (prev) { struct sk_buff *clone; clone = skb_clone(skb, GFP_ATOMIC); diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c new file mode 100644 index 000000000000..bed42a48408c --- /dev/null +++ b/net/ieee802154/header_ops.c @@ -0,0 +1,287 @@ +/* + * Copyright (C) 2014 Fraunhofer ITWM + * + * 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 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. + * + * Written by: + * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> + */ + +#include <net/mac802154.h> +#include <net/ieee802154.h> +#include <net/ieee802154_netdev.h> + +static int +ieee802154_hdr_push_addr(u8 *buf, const struct ieee802154_addr *addr, + bool omit_pan) +{ + int pos = 0; + + if (addr->mode == IEEE802154_ADDR_NONE) + return 0; + + if (!omit_pan) { + memcpy(buf + pos, &addr->pan_id, 2); + pos += 2; + } + + switch (addr->mode) { + case IEEE802154_ADDR_SHORT: + memcpy(buf + pos, &addr->short_addr, 2); + pos += 2; + break; + + case IEEE802154_ADDR_LONG: + memcpy(buf + pos, &addr->extended_addr, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + + default: + return -EINVAL; + } + + return pos; +} + +static int +ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr) +{ + int pos = 5; + + memcpy(buf, hdr, 1); + memcpy(buf + 1, &hdr->frame_counter, 4); + + switch (hdr->key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + return pos; + + case IEEE802154_SCF_KEY_INDEX: + break; + + case IEEE802154_SCF_KEY_SHORT_INDEX: + memcpy(buf + pos, &hdr->short_src, 4); + pos += 4; + break; + + case IEEE802154_SCF_KEY_HW_INDEX: + memcpy(buf + pos, &hdr->extended_src, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + } + + buf[pos++] = hdr->key_id; + + return pos; +} + +int +ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr) +{ + u8 buf[MAC802154_FRAME_HARD_HEADER_LEN]; + int pos = 2; + int rc; + struct ieee802154_hdr_fc fc = hdr->fc; + + buf[pos++] = hdr->seq; + + fc.dest_addr_mode = hdr->dest.mode; + + rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false); + if (rc < 0) + return -EINVAL; + pos += rc; + + fc.source_addr_mode = hdr->source.mode; + + if (hdr->source.pan_id == hdr->dest.pan_id && + hdr->dest.mode != IEEE802154_ADDR_NONE) + fc.intra_pan = true; + + rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan); + if (rc < 0) + return -EINVAL; + pos += rc; + + if (fc.security_enabled) { + fc.version = 1; + + rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec); + if (rc < 0) + return -EINVAL; + + pos += rc; + } + + memcpy(buf, &fc, 2); + + memcpy(skb_push(skb, pos), buf, pos); + + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_push); + +static int +ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan, + struct ieee802154_addr *addr) +{ + int pos = 0; + + addr->mode = mode; + + if (mode == IEEE802154_ADDR_NONE) + return 0; + + if (!omit_pan) { + memcpy(&addr->pan_id, buf + pos, 2); + pos += 2; + } + + if (mode == IEEE802154_ADDR_SHORT) { + memcpy(&addr->short_addr, buf + pos, 2); + return pos + 2; + } else { + memcpy(&addr->extended_addr, buf + pos, IEEE802154_ADDR_LEN); + return pos + IEEE802154_ADDR_LEN; + } +} + +static int ieee802154_hdr_addr_len(int mode, bool omit_pan) +{ + int pan_len = omit_pan ? 0 : 2; + + switch (mode) { + case IEEE802154_ADDR_NONE: return 0; + case IEEE802154_ADDR_SHORT: return 2 + pan_len; + case IEEE802154_ADDR_LONG: return IEEE802154_ADDR_LEN + pan_len; + default: return -EINVAL; + } +} + +static int +ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr) +{ + int pos = 5; + + memcpy(hdr, buf, 1); + memcpy(&hdr->frame_counter, buf + 1, 4); + + switch (hdr->key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + return pos; + + case IEEE802154_SCF_KEY_INDEX: + break; + + case IEEE802154_SCF_KEY_SHORT_INDEX: + memcpy(&hdr->short_src, buf + pos, 4); + pos += 4; + break; + + case IEEE802154_SCF_KEY_HW_INDEX: + memcpy(&hdr->extended_src, buf + pos, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + } + + hdr->key_id = buf[pos++]; + + return pos; +} + +static int ieee802154_hdr_sechdr_len(u8 sc) +{ + switch (IEEE802154_SCF_KEY_ID_MODE(sc)) { + case IEEE802154_SCF_KEY_IMPLICIT: return 5; + case IEEE802154_SCF_KEY_INDEX: return 6; + case IEEE802154_SCF_KEY_SHORT_INDEX: return 10; + case IEEE802154_SCF_KEY_HW_INDEX: return 14; + default: return -EINVAL; + } +} + +static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr) +{ + int dlen, slen; + + dlen = ieee802154_hdr_addr_len(hdr->fc.dest_addr_mode, false); + slen = ieee802154_hdr_addr_len(hdr->fc.source_addr_mode, + hdr->fc.intra_pan); + + if (slen < 0 || dlen < 0) + return -EINVAL; + + return 3 + dlen + slen + hdr->fc.security_enabled; +} + +static int +ieee802154_hdr_get_addrs(const u8 *buf, struct ieee802154_hdr *hdr) +{ + int pos = 0; + + pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.dest_addr_mode, + false, &hdr->dest); + pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.source_addr_mode, + hdr->fc.intra_pan, &hdr->source); + + if (hdr->fc.intra_pan) + hdr->source.pan_id = hdr->dest.pan_id; + + return pos; +} + +int +ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr) +{ + int pos = 3, rc; + + if (!pskb_may_pull(skb, 3)) + return -EINVAL; + + memcpy(hdr, skb->data, 3); + + rc = ieee802154_hdr_minlen(hdr); + if (rc < 0 || !pskb_may_pull(skb, rc)) + return -EINVAL; + + pos += ieee802154_hdr_get_addrs(skb->data + pos, hdr); + + if (hdr->fc.security_enabled) { + int want = pos + ieee802154_hdr_sechdr_len(skb->data[pos]); + + if (!pskb_may_pull(skb, want)) + return -EINVAL; + + pos += ieee802154_hdr_get_sechdr(skb->data + pos, &hdr->sec); + } + + skb_pull(skb, pos); + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_pull); + +int +ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr) +{ + const u8 *buf = skb_mac_header(skb); + int pos = 3, rc; + + if (buf + 3 > skb_tail_pointer(skb)) + return -EINVAL; + + memcpy(hdr, buf, 3); + + rc = ieee802154_hdr_minlen(hdr); + if (rc < 0 || buf + rc > skb_tail_pointer(skb)) + return -EINVAL; + + pos += ieee802154_hdr_get_addrs(buf + pos, hdr); + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index ba5c1e002f37..bda8dba4f993 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -39,6 +39,26 @@ #include "ieee802154.h" +static int nla_put_hwaddr(struct sk_buff *msg, int type, __le64 hwaddr) +{ + return nla_put_u64(msg, type, swab64((__force u64)hwaddr)); +} + +static __le64 nla_get_hwaddr(const struct nlattr *nla) +{ + return ieee802154_devaddr_from_raw(nla_data(nla)); +} + +static int nla_put_shortaddr(struct sk_buff *msg, int type, __le16 addr) +{ + return nla_put_u16(msg, type, le16_to_cpu(addr)); +} + +static __le16 nla_get_shortaddr(const struct nlattr *nla) +{ + return cpu_to_le16(nla_get_u16(nla)); +} + int ieee802154_nl_assoc_indic(struct net_device *dev, struct ieee802154_addr *addr, u8 cap) { @@ -46,7 +66,7 @@ int ieee802154_nl_assoc_indic(struct net_device *dev, pr_debug("%s\n", __func__); - if (addr->addr_type != IEEE802154_ADDR_LONG) { + if (addr->mode != IEEE802154_ADDR_LONG) { pr_err("%s: received non-long source address!\n", __func__); return -EINVAL; } @@ -59,8 +79,8 @@ int ieee802154_nl_assoc_indic(struct net_device *dev, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr) || + nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR, + addr->extended_addr) || nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap)) goto nla_put_failure; @@ -72,7 +92,7 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_assoc_indic); -int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, +int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr, u8 status) { struct sk_buff *msg; @@ -87,7 +107,7 @@ int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) goto nla_put_failure; return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP); @@ -114,13 +134,13 @@ int ieee802154_nl_disassoc_indic(struct net_device *dev, nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr)) goto nla_put_failure; - if (addr->addr_type == IEEE802154_ADDR_LONG) { - if (nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr)) + if (addr->mode == IEEE802154_ADDR_LONG) { + if (nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR, + addr->extended_addr)) goto nla_put_failure; } else { - if (nla_put_u16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, - addr->short_addr)) + if (nla_put_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, + addr->short_addr)) goto nla_put_failure; } if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason)) @@ -157,8 +177,8 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm); -int ieee802154_nl_beacon_indic(struct net_device *dev, - u16 panid, u16 coord_addr) +int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid, + __le16 coord_addr) { struct sk_buff *msg; @@ -172,8 +192,9 @@ int ieee802154_nl_beacon_indic(struct net_device *dev, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) || - nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid)) + nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, + coord_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_PAN_ID, panid)) goto nla_put_failure; return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP); @@ -243,6 +264,7 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, { void *hdr; struct wpan_phy *phy; + __le16 short_addr, pan_id; pr_debug("%s\n", __func__); @@ -254,15 +276,16 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, phy = ieee802154_mlme_ops(dev)->get_phy(dev); BUG_ON(!phy); + short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); + pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, - ieee802154_mlme_ops(dev)->get_short_addr(dev)) || - nla_put_u16(msg, IEEE802154_ATTR_PAN_ID, - ieee802154_mlme_ops(dev)->get_pan_id(dev))) + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id)) goto nla_put_failure; wpan_phy_put(phy); return genlmsg_end(msg, hdr); @@ -322,16 +345,16 @@ int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info) goto out; if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_COORD_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]); } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); } - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + addr.pan_id = nla_get_shortaddr( + info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); if (info->attrs[IEEE802154_ATTR_PAGE]) page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); @@ -365,14 +388,13 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info) if (!ieee802154_mlme_ops(dev)->assoc_resp) goto out; - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, - nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), + nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); out: @@ -398,13 +420,12 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) goto out; if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); } addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); @@ -449,10 +470,11 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) if (!ieee802154_mlme_ops(dev)->start_req) goto out; - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + addr.pan_id = nla_get_shortaddr( + info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); @@ -467,7 +489,7 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) page = 0; - if (addr.short_addr == IEEE802154_ADDR_BROADCAST) { + if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); dev_put(dev); return -EINVAL; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 41f538b8e59c..e5258cf6773b 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -28,6 +28,7 @@ #include <linux/slab.h> #include <net/sock.h> #include <net/af_ieee802154.h> +#include <net/ieee802154_netdev.h> #include "af802154.h" @@ -55,21 +56,24 @@ static void raw_close(struct sock *sk, long timeout) sk_common_release(sk); } -static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len) +static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) { - struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; + struct ieee802154_addr addr; + struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr; int err = 0; struct net_device *dev = NULL; - if (len < sizeof(*addr)) + if (len < sizeof(*uaddr)) return -EINVAL; - if (addr->family != AF_IEEE802154) + uaddr = (struct sockaddr_ieee802154 *)_uaddr; + if (uaddr->family != AF_IEEE802154) return -EINVAL; lock_sock(sk); - dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + ieee802154_addr_from_sa(&addr, &uaddr->addr); + dev = ieee802154_get_dev(sock_net(sk), &addr); if (!dev) { err = -ENODEV; goto out; diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c index 4511fc22ef16..ef2d54372b13 100644 --- a/net/ieee802154/reassembly.c +++ b/net/ieee802154/reassembly.c @@ -24,12 +24,23 @@ #include <linux/export.h> #include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> #include <net/ipv6.h> #include <net/inet_frag.h> -#include "6lowpan.h" #include "reassembly.h" +struct lowpan_frag_info { + __be16 d_tag; + u16 d_size; + u8 d_offset; +}; + +struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb) +{ + return (struct lowpan_frag_info *)skb->cb; +} + static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, @@ -58,19 +69,18 @@ static unsigned int lowpan_hashfn(struct inet_frag_queue *q) return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr); } -bool lowpan_frag_match(struct inet_frag_queue *q, void *a) +static bool lowpan_frag_match(struct inet_frag_queue *q, void *a) { struct lowpan_frag_queue *fq; struct lowpan_create_arg *arg = a; fq = container_of(q, struct lowpan_frag_queue, q); return fq->tag == arg->tag && fq->d_size == arg->d_size && - ieee802154_addr_addr_equal(&fq->saddr, arg->src) && - ieee802154_addr_addr_equal(&fq->daddr, arg->dst); + ieee802154_addr_equal(&fq->saddr, arg->src) && + ieee802154_addr_equal(&fq->daddr, arg->dst); } -EXPORT_SYMBOL(lowpan_frag_match); -void lowpan_frag_init(struct inet_frag_queue *q, void *a) +static void lowpan_frag_init(struct inet_frag_queue *q, void *a) { struct lowpan_frag_queue *fq; struct lowpan_create_arg *arg = a; @@ -82,21 +92,6 @@ void lowpan_frag_init(struct inet_frag_queue *q, void *a) fq->saddr = *arg->src; fq->daddr = *arg->dst; } -EXPORT_SYMBOL(lowpan_frag_init); - -void lowpan_expire_frag_queue(struct frag_queue *fq, struct inet_frags *frags) -{ - spin_lock(&fq->q.lock); - - if (fq->q.last_in & INET_FRAG_COMPLETE) - goto out; - - inet_frag_kill(&fq->q, frags); -out: - spin_unlock(&fq->q.lock); - inet_frag_put(&fq->q, frags); -} -EXPORT_SYMBOL(lowpan_expire_frag_queue); static void lowpan_frag_expire(unsigned long data) { @@ -106,12 +101,21 @@ static void lowpan_frag_expire(unsigned long data) fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); - lowpan_expire_frag_queue(fq, &lowpan_frags); + spin_lock(&fq->q.lock); + + if (fq->q.last_in & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q, &lowpan_frags); +out: + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q, &lowpan_frags); } static inline struct lowpan_frag_queue * -fq_find(struct net *net, const struct ieee802154_frag_info *frag_info, - const struct ieee802154_addr *src, const struct ieee802154_addr *dst) +fq_find(struct net *net, const struct lowpan_frag_info *frag_info, + const struct ieee802154_addr *src, + const struct ieee802154_addr *dst) { struct inet_frag_queue *q; struct lowpan_create_arg arg; @@ -144,8 +148,8 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; - offset = mac_cb(skb)->frag_info.d_offset << 3; - end = mac_cb(skb)->frag_info.d_size; + offset = lowpan_cb(skb)->d_offset << 3; + end = lowpan_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { @@ -171,15 +175,13 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, * this fragment, right? */ prev = fq->q.fragments_tail; - if (!prev || mac_cb(prev)->frag_info.d_offset < - mac_cb(skb)->frag_info.d_offset) { + if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) { next = NULL; goto found; } prev = NULL; for (next = fq->q.fragments; next != NULL; next = next->next) { - if (mac_cb(next)->frag_info.d_offset >= - mac_cb(skb)->frag_info.d_offset) + if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset) break; /* bingo! */ prev = next; } @@ -326,7 +328,7 @@ out_oom: } static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, - struct ieee802154_frag_info *frag_info) + struct lowpan_frag_info *frag_info) { bool fail; u8 pattern = 0, low = 0; @@ -353,9 +355,13 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); - struct ieee802154_frag_info *frag_info = &mac_cb(skb)->frag_info; + struct lowpan_frag_info *frag_info = lowpan_cb(skb); + struct ieee802154_addr source, dest; int err; + source = mac_cb(skb)->source; + dest = mac_cb(skb)->dest; + err = lowpan_get_frag_info(skb, frag_type, frag_info); if (err < 0) goto err; @@ -365,7 +371,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) inet_frag_evictor(&net->ieee802154_lowpan.frags, &lowpan_frags, false); - fq = fq_find(net, frag_info, &mac_cb(skb)->sa, &mac_cb(skb)->da); + fq = fq_find(net, frag_info, &source, &dest); if (fq != NULL) { int ret; spin_lock(&fq->q.lock); @@ -441,7 +447,7 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) table[0].data = &net->ieee802154_lowpan.frags.high_thresh; table[1].data = &net->ieee802154_lowpan.frags.low_thresh; table[2].data = &net->ieee802154_lowpan.frags.timeout; - table[2].data = &net->ieee802154_lowpan.max_dsize; + table[3].data = &net->ieee802154_lowpan.max_dsize; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) @@ -535,7 +541,7 @@ int __init lowpan_net_frag_init(void) ret = lowpan_frags_sysctl_register(); if (ret) - goto out; + return ret; ret = register_pernet_subsys(&lowpan_frags_ops); if (ret) @@ -550,9 +556,10 @@ int __init lowpan_net_frag_init(void) lowpan_frags.frag_expire = lowpan_frag_expire; lowpan_frags.secret_interval = 10 * 60 * HZ; inet_frags_init(&lowpan_frags); + + return ret; err_pernet: lowpan_frags_sysctl_unregister(); -out: return ret; } diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h index 055518b9da2d..74e4a7c98191 100644 --- a/net/ieee802154/reassembly.h +++ b/net/ieee802154/reassembly.h @@ -23,10 +23,10 @@ struct lowpan_frag_queue { static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) { - switch (a->addr_type) { + switch (a->mode) { case IEEE802154_ADDR_LONG: - return (__force u32)((((u32 *)a->hwaddr))[0] ^ - ((u32 *)(a->hwaddr))[1]); + return (((__force u64)a->extended_addr) >> 32) ^ + (((__force u64)a->extended_addr) & 0xffffffff); case IEEE802154_ADDR_SHORT: return (__force u32)(a->short_addr); default: @@ -34,31 +34,6 @@ static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) } } -static inline bool ieee802154_addr_addr_equal(const struct ieee802154_addr *a1, - const struct ieee802154_addr *a2) -{ - if (a1->pan_id != a2->pan_id) - return false; - - if (a1->addr_type != a2->addr_type) - return false; - - switch (a1->addr_type) { - case IEEE802154_ADDR_LONG: - if (memcmp(a1->hwaddr, a2->hwaddr, IEEE802154_ADDR_LEN)) - return false; - break; - case IEEE802154_ADDR_SHORT: - if (a1->short_addr != a2->short_addr) - return false; - break; - default: - return false; - } - - return true; -} - int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type); void lowpan_net_frag_exit(void); int lowpan_net_frag_init(void); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ecd2c3f245ce..8c54870db792 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - /* Note : following gso_segment() might change skb->encapsulation */ - udpfrag = !skb->encapsulation && proto == IPPROTO_UDP; + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) @@ -1502,9 +1505,9 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) bhptr = per_cpu_ptr(mib[0], cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_bh(syncp); + start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_bh(syncp, start)); + } while (u64_stats_fetch_retry_irq(syncp, start)); res += v; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bb075fc9a14f..3b01959bf4bb 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e85445b2b102..1a0755fea491 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ 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 IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 4fff64418fb2..66aaf506fbef 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { @@ -119,52 +120,6 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) return (struct rtable *)dst; } -/* Often modified stats are per cpu, other are shared (netdev->stats) */ -struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; - } - - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - - return tot; -} -EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); - static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) { @@ -763,7 +718,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -1091,7 +1046,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6156f4ef5e91..b86f0a37fa7c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -108,7 +108,6 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) nf_reset(skb); secpath_reset(skb); skb_clear_hash_if_not_l4(skb); - skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; @@ -148,3 +147,49 @@ error: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); + +/* Often modified stats are per cpu, other are shared (netdev->stats) */ +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_errors; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + tot->collisions = dev->stats.collisions; + + return tot; +} +EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3e0adea9c27..7ebd6e37875c 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -61,7 +61,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) skb_dst_set(skb, NULL); dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0); if (IS_ERR(dst)) - return PTR_ERR(dst);; + return PTR_ERR(dst); skb_dst_set(skb, dst); } #endif diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31b416e..7c676671329d 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7374905b3701..4bd6d52eeffb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index f49351edf97d..2b9464c93b88 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size && - left < sk->sk_gso_max_segs) + left < tp->xmit_size_goal_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6e4809389cbf..e1661f46fd19 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1944,8 +1944,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; @@ -3066,6 +3067,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; } else { last_ackt = skb->skb_mstamp; + WARN_ON_ONCE(last_ackt.v64 == 0); if (!first_ackt.v64) first_ackt = last_ackt; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index aaa68f5b1055..e0a7b33fe953 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -87,8 +87,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) tcp_rearm_rto(sk); } - NET_ADD_STATS_BH(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, - tcp_skb_pcount(skb)); + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -780,6 +780,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); @@ -873,8 +884,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (unlikely(skb->fclone == SKB_FCLONE_ORIG && fclone->fclone == SKB_FCLONE_CLONE)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -882,6 +893,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); @@ -2358,6 +2371,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2421,11 +2435,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + + if (likely(!err)) + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -2930,7 +2948,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; @@ -2960,6 +2983,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) tcp_connect_queue_skb(sk, data); fo->copied = data->len; + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index d92e5586783e..438a73aa777c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION config IPV6_VTI tristate "Virtual (secure) IPv6: tunneling" select IPV6_TUNNEL + select NET_IP_TUNNEL depends on INET6_XFRM_MODE_TUNNEL ---help--- Tunneling means encapsulating data of one protocol type within diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index fdbfeca36d63..344e972426df 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1103,8 +1103,11 @@ retry: * Lifetime is greater than REGEN_ADVANCE time units. In particular, * an implementation must not create a temporary address with a zero * Preferred Lifetime. + * Use age calculation as in addrconf_verify to avoid unnecessary + * temporary addresses being generated. */ - if (tmp_prefered_lft <= regen_advance) { + age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if (tmp_prefered_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 140748debc4a..8af3eb57f438 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, found = (nexthdr == target); if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) + if (target < 0 || found) break; return -ENOENT; } diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index cf77f3abfd06..447a7fbd1bb6 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void) int ret; ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); - if (!ret) + if (ret) goto out; ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); - if (!ret) + if (ret) goto out_rt; out: diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1e8683b135bb..59f95affceb0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, unsigned int unfrag_ip6hlen; u8 *prevhdr; int offset = 0; - bool tunnel; + bool encap, udpfrag; int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & @@ -110,8 +110,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; - tunnel = SKB_GSO_CB(skb)->encap_level > 0; - if (tunnel) + encap = SKB_GSO_CB(skb)->encap_level > 0; + if (encap) features = skb->dev->hw_enc_features & netif_skb_features(skb); SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); @@ -121,6 +121,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); @@ -133,13 +139,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); - if (tunnel) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } skb->network_header = (u8 *)ipv6h - skb->head; - if (!tunnel && proto == IPPROTO_UDP) { + if (udpfrag) { unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); @@ -148,6 +150,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); } + if (encap) + skb_reset_inner_headers(skb); } out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index be1b7f5a3a54..90dd551fdd3c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -367,6 +367,9 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->forwarding == 0) goto error; + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -376,9 +379,6 @@ int ip6_forward(struct sk_buff *skb) goto drop; } - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -530,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif skb_copy_secmark(to, from); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8ad59f4811df..e1df691d78be 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -108,12 +108,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) per_cpu_ptr(dev->tstats, i); do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); + start = u64_stats_fetch_begin_irq(&tstats->syncp); tmp.rx_packets = tstats->rx_packets; tmp.rx_bytes = tstats->rx_bytes; tmp.tx_packets = tstats->tx_packets; tmp.tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); sum.rx_packets += tmp.rx_packets; sum.rx_bytes += tmp.rx_bytes; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 827f795209cf..d1b35d377e62 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -13,7 +13,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) int old, new; #if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { + if (rt) { struct inet_peer *peer; struct net *net; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fb9beb78f00b..587bbdcb22b4 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -135,6 +135,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 11dac21e6586..fba54a407bb2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1513,7 +1513,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 958027be0e94..1693c8d885f0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } + ip_tunnel_dst_reset_all(tunnel); dev_put(dev); } @@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) t->parms.link = p->link; ipip6_tunnel_bind_dev(t->dev); } + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); } @@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); return 0; } @@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); break; @@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = { static void ipip6_dev_free(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1368,6 +1375,12 @@ static int ipip6_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + return 0; } @@ -1391,6 +1404,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + dev_hold(dev); rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index e7359f9eaa8d..b261ee8b83fc 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -113,7 +113,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index e5dc42f0e527..ab48d4192edd 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -112,7 +112,6 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; -static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) @@ -1131,7 +1130,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1151,23 +1150,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, return 0; } -/* Automatically called when the skb is freed. - */ -static void l2tp_sock_wfree(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - -/* For data skbs that we transmit, we associate with the tunnel socket - * but don't do accounting. - */ -static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - sock_hold(sk); - skb->sk = sk; - skb->destructor = l2tp_sock_wfree; -} - #if IS_ENABLED(CONFIG_IPV6) static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, int udp_len) @@ -1221,7 +1203,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len return NET_XMIT_DROP; } - skb_orphan(skb); /* Setup L2TP header */ session->build_header(session, __skb_push(skb, hdr_len)); @@ -1287,8 +1268,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len break; } - l2tp_skb_set_owner_w(skb, sk); - l2tp_xmit_core(session, skb, fl, data_len); out_unlock: bh_unlock_sock(sk); @@ -1861,7 +1840,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_len parameters are set. */ -static void l2tp_session_set_header_len(struct l2tp_session *session, int version) +void l2tp_session_set_header_len(struct l2tp_session *session, int version) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; @@ -1874,6 +1853,7 @@ static void l2tp_session_set_header_len(struct l2tp_session *session, int versio } } +EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 1f01ba3435bc..3f93ccd6ba97 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -263,6 +263,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int length, int (*payload_hook)(struct sk_buff *skb)); int l2tp_session_queue_purge(struct l2tp_session *session); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); +void l2tp_session_set_header_len(struct l2tp_session *session, int version); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 4cfd722e9153..bd7387adea9e 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -578,8 +578,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); - if (info->attrs[L2TP_ATTR_SEND_SEQ]) + if (info->attrs[L2TP_ATTR_SEND_SEQ]) { session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]); + l2tp_session_set_header_len(session, session->tunnel->version); + } if (info->attrs[L2TP_ATTR_LNS_MODE]) session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ec40bc344be6..d276e2d4a589 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -254,12 +254,14 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n", - session->name); + l2tp_dbg(session, PPPOL2TP_MSG_DATA, + "%s: recv %d byte data frame, passing to L2TP socket\n", + session->name, data_len); - /* Not bound. Nothing we can do, so discard. */ - atomic_long_inc(&session->stats.rx_errors); - kfree_skb(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { + atomic_long_inc(&session->stats.rx_errors); + kfree_skb(skb); + } } return; @@ -1309,6 +1311,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } + l2tp_session_set_header_len(session, session->tunnel->version); l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set send_seq=%d\n", session->name, session->send_seq); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 363d19b5d5c8..1acb29109b45 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1347,9 +1347,6 @@ static int sta_apply_parameters(struct ieee80211_local *local, params->vht_capa, sta); if (params->opmode_notif_used) { - enum ieee80211_band band = - ieee80211_get_sdata_band(sdata); - /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it */ @@ -3647,8 +3644,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *extra_ies, - size_t extra_ies_len) + u16 status_code, u32 peer_capability, + const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 42c659229a09..bd1fd8ea5105 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -100,6 +100,12 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, } max_bw = max(max_bw, width); } + + /* use the configured bandwidth in case of monitor interface */ + sdata = rcu_dereference(local->monitor_sdata); + if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf) + max_bw = max(max_bw, conf->def.width); + rcu_read_unlock(); return max_bw; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index ebf80f3abd83..40a648938985 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -358,6 +358,18 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( } IEEE80211_IF_FILE_W(tkip_mic_test); +static ssize_t ieee80211_if_parse_beacon_loss( + struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) +{ + if (!ieee80211_sdata_running(sdata) || !sdata->vif.bss_conf.assoc) + return -ENOTCONN; + + ieee80211_beacon_loss(&sdata->vif); + + return buflen; +} +IEEE80211_IF_FILE_W(beacon_loss); + static ssize_t ieee80211_if_fmt_uapsd_queues( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { @@ -569,6 +581,7 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(beacon_timeout); DEBUGFS_ADD_MODE(smps, 0600); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); + DEBUGFS_ADD_MODE(beacon_loss, 0200); DEBUGFS_ADD_MODE(uapsd_queues, 0600); DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index ef8b385eff04..fc689f5d971e 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -354,16 +354,20 @@ drv_sched_scan_start(struct ieee80211_local *local, return ret; } -static inline void drv_sched_scan_stop(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +static inline int drv_sched_scan_stop(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { + int ret; + might_sleep(); check_sdata_in_driver(sdata); trace_drv_sched_scan_stop(local, sdata); - local->ops->sched_scan_stop(&local->hw, &sdata->vif); - trace_drv_return_void(local); + ret = local->ops->sched_scan_stop(&local->hw, &sdata->vif); + trace_drv_return_int(local, ret); + + return ret; } static inline void drv_sw_scan_start(struct ieee80211_local *local) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index afbe2b203c3e..c150b68436d7 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -482,8 +482,6 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, return; if (vif->type == NL80211_IFTYPE_STATION) { - if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF)) - smps_mode = IEEE80211_SMPS_AUTOMATIC; if (sdata->u.mgd.driver_smps_mode == smps_mode) return; sdata->u.mgd.driver_smps_mode = smps_mode; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 4453e2725e40..e458ca0dffec 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -283,6 +283,11 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy, &chandef); + if (err < 0) { + sdata_info(sdata, + "Failed to join IBSS, invalid chandef\n"); + return; + } if (err > 0) { if (!ifibss->userspace_handles_dfs) { sdata_info(sdata, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0014b5396ce5..0d1a0f801b94 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1242,6 +1242,8 @@ struct ieee80211_local { struct ieee80211_sub_if_data __rcu *p2p_sdata; + struct napi_struct *napi; + /* virtual monitor interface */ struct ieee80211_sub_if_data __rcu *monitor_sdata; struct cfg80211_chan_def monitor_chandef; @@ -1698,14 +1700,8 @@ void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); -void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data); -static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local, - struct sk_buff_head *skbs) -{ - ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL); -} +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs); void ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 088111af6c7c..b8d331e7d883 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -101,9 +101,8 @@ static u32 __ieee80211_idle_on(struct ieee80211_local *local) static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, bool force_active) { - bool working = false, scanning, active; + bool working, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; - struct ieee80211_roc_work *roc; lockdep_assert_held(&local->mtx); @@ -111,12 +110,8 @@ static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, !list_empty(&local->chanctx_list) || local->monitors; - if (!local->ops->remain_on_channel) { - list_for_each_entry(roc, &local->roc_list, list) { - working = true; - break; - } - } + working = !local->ops->remain_on_channel && + !list_empty(&local->roc_list); scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) || test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 1f7d8422d62d..b055f6a55c68 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1076,6 +1076,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_register_hw); +void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi, + struct net_device *napi_dev, + int (*poll)(struct napi_struct *, int), + int weight) +{ + struct ieee80211_local *local = hw_to_local(hw); + + netif_napi_add(napi_dev, napi, poll, weight); + local->napi = napi; +} +EXPORT_SYMBOL_GPL(ieee80211_napi_add); + void ieee80211_unregister_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 2802f9d9279d..ad8b377b4b9f 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) sdata->vif.addr); nullfunc->frame_control = fc; nullfunc->duration_id = 0; + nullfunc->seq_ctrl = 0; /* no address resolution for this frame -> set addr 1 immediately */ memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memset(skb_put(skb, 2), 0, 2); /* append QoS control field */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 61604834b914..94f0af29b742 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -131,13 +131,13 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata) if (unlikely(!sdata->u.mgd.associated)) return; + ifmgd->probe_send_count = 0; + if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) return; mod_timer(&sdata->u.mgd.conn_mon_timer, round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); - - ifmgd->probe_send_count = 0; } static int ecw2cw(int ecw) @@ -222,6 +222,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, switch (vht_oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: vht_chandef.width = chandef->width; + vht_chandef.center_freq1 = chandef->center_freq1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: vht_chandef.width = NL80211_CHAN_WIDTH_80; @@ -271,6 +272,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; out: + /* + * When tracking the current AP, don't do any further checks if the + * new chandef is identical to the one we're currently using for the + * connection. This keeps us from playing ping-pong with regulatory, + * without it the following can happen (for example): + * - connect to an AP with 80 MHz, world regdom allows 80 MHz + * - AP advertises regdom US + * - CRDA loads regdom US with 80 MHz prohibited (old database) + * - the code below detects an unsupported channel, downgrades, and + * we disconnect from the AP in the caller + * - disconnect causes CRDA to reload world regdomain and the game + * starts anew. + * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * + * It seems possible that there are still scenarios with CSA or real + * bandwidth changes where a this could happen, but those cases are + * less common and wouldn't completely prevent using the AP. + */ + if (tracking && + cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef)) + return ret; + /* don't print the message below for VHT mismatch if VHT is disabled */ if (ret & IEEE80211_STA_DISABLE_VHT) vht_chandef = *chandef; @@ -2249,6 +2272,62 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, /* ignore frame -- wait for timeout */ } +#define case_WLAN(type) \ + case WLAN_REASON_##type: return #type + +static const char *ieee80211_get_reason_code_string(u16 reason_code) +{ + switch (reason_code) { + case_WLAN(UNSPECIFIED); + case_WLAN(PREV_AUTH_NOT_VALID); + case_WLAN(DEAUTH_LEAVING); + case_WLAN(DISASSOC_DUE_TO_INACTIVITY); + case_WLAN(DISASSOC_AP_BUSY); + case_WLAN(CLASS2_FRAME_FROM_NONAUTH_STA); + case_WLAN(CLASS3_FRAME_FROM_NONASSOC_STA); + case_WLAN(DISASSOC_STA_HAS_LEFT); + case_WLAN(STA_REQ_ASSOC_WITHOUT_AUTH); + case_WLAN(DISASSOC_BAD_POWER); + case_WLAN(DISASSOC_BAD_SUPP_CHAN); + case_WLAN(INVALID_IE); + case_WLAN(MIC_FAILURE); + case_WLAN(4WAY_HANDSHAKE_TIMEOUT); + case_WLAN(GROUP_KEY_HANDSHAKE_TIMEOUT); + case_WLAN(IE_DIFFERENT); + case_WLAN(INVALID_GROUP_CIPHER); + case_WLAN(INVALID_PAIRWISE_CIPHER); + case_WLAN(INVALID_AKMP); + case_WLAN(UNSUPP_RSN_VERSION); + case_WLAN(INVALID_RSN_IE_CAP); + case_WLAN(IEEE8021X_FAILED); + case_WLAN(CIPHER_SUITE_REJECTED); + case_WLAN(DISASSOC_UNSPECIFIED_QOS); + case_WLAN(DISASSOC_QAP_NO_BANDWIDTH); + case_WLAN(DISASSOC_LOW_ACK); + case_WLAN(DISASSOC_QAP_EXCEED_TXOP); + case_WLAN(QSTA_LEAVE_QBSS); + case_WLAN(QSTA_NOT_USE); + case_WLAN(QSTA_REQUIRE_SETUP); + case_WLAN(QSTA_TIMEOUT); + case_WLAN(QSTA_CIPHER_NOT_SUPP); + case_WLAN(MESH_PEER_CANCELED); + case_WLAN(MESH_MAX_PEERS); + case_WLAN(MESH_CONFIG); + case_WLAN(MESH_CLOSE); + case_WLAN(MESH_MAX_RETRIES); + case_WLAN(MESH_CONFIRM_TIMEOUT); + case_WLAN(MESH_INVALID_GTK); + case_WLAN(MESH_INCONSISTENT_PARAM); + case_WLAN(MESH_INVALID_SECURITY); + case_WLAN(MESH_PATH_ERROR); + case_WLAN(MESH_PATH_NOFORWARD); + case_WLAN(MESH_PATH_DEST_UNREACHABLE); + case_WLAN(MAC_EXISTS_IN_MBSS); + case_WLAN(MESH_CHAN_REGULATORY); + case_WLAN(MESH_CHAN); + default: return "<unknown>"; + } +} static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) @@ -2270,8 +2349,8 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - sdata_info(sdata, "deauthenticated from %pM (Reason: %u)\n", - bssid, reason_code); + sdata_info(sdata, "deauthenticated from %pM (Reason: %u=%s)\n", + bssid, reason_code, ieee80211_get_reason_code_string(reason_code)); ieee80211_set_disassoc(sdata, 0, 0, false, NULL); @@ -3792,6 +3871,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (WARN_ON(!chanctx_conf)) { rcu_read_unlock(); + sta_info_free(local, new_sta); return -EINVAL; } rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def); @@ -4340,8 +4420,8 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, bool report_frame = false; sdata_info(sdata, - "deauthenticating from %pM by local choice (reason=%d)\n", - req->bssid, req->reason_code); + "deauthenticating from %pM by local choice (Reason: %u=%s)\n", + req->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); if (ifmgd->auth_data) { drv_mgd_prepare_tx(sdata->local, sdata); @@ -4387,8 +4467,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, return -ENOLINK; sdata_info(sdata, - "disassociating from %pM by local choice (reason=%d)\n", - req->bss->bssid, req->reason_code); + "disassociating from %pM by local choice (Reason: %u=%s)\n", + req->bss->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); memcpy(bssid, req->bss->bssid, ETH_ALEN); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DISASSOC, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 593062109c50..5b617660b0ba 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1092,6 +1092,13 @@ static void sta_ps_end(struct sta_info *sta) sta->sta.addr, sta->sta.aid); if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + /* + * Clear the flag only if the other one is still set + * so that the TX path won't start TX'ing new frames + * directly ... In the case that the driver flag isn't + * set ieee80211_sta_ps_deliver_wakeup() will clear it. + */ + clear_sta_flag(sta, WLAN_STA_PS_STA); ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n", sta->sta.addr, sta->sta.aid); return; @@ -1954,7 +1961,10 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - netif_receive_skb(skb); + if (rx->local->napi) + napi_gro_receive(rx->local->napi, skb); + else + netif_receive_skb(skb); } if (xmit_skb) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 88c81616f8f7..836f500dfbf3 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -472,9 +472,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->ops->hw_scan) { u8 *ies; - local->hw_scan_ies_bufsize = 2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len + - req->ie_len; + local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; local->hw_scan_req = kmalloc( sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]) + @@ -979,8 +977,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def chandef; int ret, i, iebufsz; - iebufsz = 2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len + req->ie_len; + iebufsz = local->scan_ies_len + req->ie_len; lockdep_assert_held(&local->mtx); @@ -1059,7 +1056,7 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata) local->sched_scan_req = NULL; if (rcu_access_pointer(local->sched_scan_sdata)) - drv_sched_scan_stop(local, sdata); + ret = drv_sched_scan_stop(local, sdata); out: mutex_unlock(&local->mtx); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index decd30c1e290..137a192e64bc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -91,7 +91,7 @@ static int sta_info_hash_del(struct ieee80211_local *local, return -ENOENT; } -static void cleanup_single_sta(struct sta_info *sta) +static void __cleanup_single_sta(struct sta_info *sta) { int ac, i; struct tid_ampdu_tx *tid_tx; @@ -99,7 +99,8 @@ static void cleanup_single_sta(struct sta_info *sta) struct ieee80211_local *local = sdata->local; struct ps_data *ps; - if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + if (test_sta_flag(sta, WLAN_STA_PS_STA) || + test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ps = &sdata->bss->ps; @@ -109,6 +110,7 @@ static void cleanup_single_sta(struct sta_info *sta) return; clear_sta_flag(sta, WLAN_STA_PS_STA); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); atomic_dec(&ps->num_sta_ps); sta_info_recalc_tim(sta); @@ -139,7 +141,14 @@ static void cleanup_single_sta(struct sta_info *sta) ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending); kfree(tid_tx); } +} +static void cleanup_single_sta(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + + __cleanup_single_sta(sta); sta_info_free(local, sta); } @@ -330,6 +339,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); spin_lock_init(&sta->lock); + spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -487,21 +497,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) goto out_err; } - /* notify driver */ - err = sta_info_insert_drv_state(local, sdata, sta); - if (err) - goto out_err; - local->num_sta++; local->sta_generation++; smp_mb(); + /* simplify things and don't accept BA sessions yet */ + set_sta_flag(sta, WLAN_STA_BLOCK_BA); + /* make the station visible */ sta_info_hash_add(local, sta); list_add_rcu(&sta->list, &local->sta_list); + /* notify driver */ + err = sta_info_insert_drv_state(local, sdata, sta); + if (err) + goto out_remove; + set_sta_flag(sta, WLAN_STA_INSERTED); + /* accept BA sessions now */ + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_recalc_min_chandef(sdata); ieee80211_sta_debugfs_add(sta); @@ -522,6 +537,12 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) mesh_accept_plinks_update(sdata); return 0; + out_remove: + sta_info_hash_del(local, sta); + list_del_rcu(&sta->list); + local->num_sta--; + synchronize_net(); + __cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); rcu_read_lock(); @@ -1071,10 +1092,14 @@ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, } EXPORT_SYMBOL(ieee80211_find_sta); -static void clear_sta_ps_flags(void *_sta) +/* powersave support code */ +void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) { - struct sta_info *sta = _sta; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + struct sk_buff_head pending; + int filtered = 0, buffered = 0, ac; + unsigned long flags; struct ps_data *ps; if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -1085,20 +1110,6 @@ static void clear_sta_ps_flags(void *_sta) else return; - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); - if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA)) - atomic_dec(&ps->num_sta_ps); -} - -/* powersave support code */ -void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) -{ - struct ieee80211_sub_if_data *sdata = sta->sdata; - struct ieee80211_local *local = sdata->local; - struct sk_buff_head pending; - int filtered = 0, buffered = 0, ac; - unsigned long flags; - clear_sta_flag(sta, WLAN_STA_SP); BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1); @@ -1109,6 +1120,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) skb_queue_head_init(&pending); + /* sync with ieee80211_tx_h_unicast_ps_buf */ + spin_lock(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; @@ -1127,7 +1140,12 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) buffered += tmp - count; } - ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta); + ieee80211_add_pending_skbs(local, &pending); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + clear_sta_flag(sta, WLAN_STA_PS_STA); + spin_unlock(&sta->ps_lock); + + atomic_dec(&ps->num_sta_ps); /* This station just woke up and isn't aware of our SMPS state */ if (!ieee80211_smps_is_restrictive(sta->known_smps_mode, @@ -1188,6 +1206,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); + nullfunc->seq_ctrl = 0; skb->priority = tid; skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index d4d85de0d75d..4acc5fc402fa 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -268,6 +268,7 @@ struct ieee80211_tx_latency_stat { * @drv_unblock_wk: used for driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly + * @ps_lock: used for powersave (when mac80211 is the AP) related locking * @ps_tx_buf: buffers (per AC) of frames to transmit to this station * when it leaves power saving state or polls * @tx_filtered: buffers (per AC) of frames we already tried to @@ -357,10 +358,8 @@ struct sta_info { /* use the accessors defined below */ unsigned long _flags; - /* - * STA powersave frame queues, no more than the internal - * locking required. - */ + /* STA powersave lock and frame queues */ + spinlock_t ps_lock; struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 722151fa5dce..cd9f80498c48 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -477,6 +477,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); + + /* sync with ieee80211_sta_ps_deliver_wakeup */ + spin_lock(&sta->ps_lock); + /* + * STA woke up the meantime and all the frames on ps_tx_buf have + * been queued to pending queue. No reordering can happen, go + * ahead and Tx the packet. + */ + if (!test_sta_flag(sta, WLAN_STA_PS_STA) && + !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + spin_unlock(&sta->ps_lock); + return TX_CONTINUE; + } + if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); ps_dbg(tx->sdata, @@ -491,6 +505,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); + spin_unlock(&sta->ps_lock); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d842af5c8a95..275c94f995f7 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -435,9 +435,8 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } -void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, - struct sk_buff_head *skbs, - void (*fn)(void *data), void *data) +void ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) { struct ieee80211_hw *hw = &local->hw; struct sk_buff *skb; @@ -461,9 +460,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, __skb_queue_tail(&local->pending[queue], skb); } - if (fn) - fn(data); - for (i = 0; i < hw->queues; i++) __ieee80211_wake_queue(hw, i, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); @@ -1767,6 +1763,26 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_QUEUE_STOP_REASON_SUSPEND); /* + * Reconfigure sched scan if it was interrupted by FW restart or + * suspend. + */ + mutex_lock(&local->mtx); + sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, + lockdep_is_held(&local->mtx)); + if (sched_scan_sdata && local->sched_scan_req) + /* + * Sched scan stopped, but we don't want to report it. Instead, + * we're trying to reschedule. + */ + if (__ieee80211_request_sched_scan_start(sched_scan_sdata, + local->sched_scan_req)) + sched_scan_stopped = true; + mutex_unlock(&local->mtx); + + if (sched_scan_stopped) + cfg80211_sched_scan_stopped(local->hw.wiphy); + + /* * If this is for hw restart things are still running. * We may want to change that later, however. */ @@ -1794,26 +1810,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(1); #endif - /* - * Reconfigure sched scan if it was interrupted by FW restart or - * suspend. - */ - mutex_lock(&local->mtx); - sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, - lockdep_is_held(&local->mtx)); - if (sched_scan_sdata && local->sched_scan_req) - /* - * Sched scan stopped, but we don't want to report it. Instead, - * we're trying to reschedule. - */ - if (__ieee80211_request_sched_scan_start(sched_scan_sdata, - local->sched_scan_req)) - sched_scan_stopped = true; - mutex_unlock(&local->mtx); - - if (sched_scan_stopped) - cfg80211_sched_scan_stopped(local->hw.wiphy); - return 0; } diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 21211c60ca98..d51422c778de 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -154,6 +154,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return IEEE80211_AC_BE; } + if (skb->protocol == sdata->control_port_protocol) { + skb->priority = 7; + return ieee80211_downgrade_queue(sdata, skb); + } + /* use the data classifier to determine what 802.1d tag the * data frame has */ rcu_read_lock(); diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile index 57cf5d1a2e4a..15d62df52182 100644 --- a/net/mac802154/Makefile +++ b/net/mac802154/Makefile @@ -1,2 +1,4 @@ obj-$(CONFIG_MAC802154) += mac802154.o mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o + +ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index b75bb01e5c6b..10cdb091b775 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -27,6 +27,7 @@ #include <net/netlink.h> #include <linux/nl802154.h> #include <net/mac802154.h> +#include <net/ieee802154_netdev.h> #include <net/route.h> #include <net/wpan-phy.h> @@ -46,7 +47,9 @@ int mac802154_slave_open(struct net_device *dev) } if (ipriv->ops->ieee_addr) { - res = ipriv->ops->ieee_addr(&ipriv->hw, dev->dev_addr); + __le64 addr = ieee802154_devaddr_from_raw(dev->dev_addr); + + res = ipriv->ops->ieee_addr(&ipriv->hw, addr); WARN_ON(res); if (res) goto err; diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h index d48422e27110..4619486f1da2 100644 --- a/net/mac802154/mac802154.h +++ b/net/mac802154/mac802154.h @@ -76,6 +76,7 @@ struct mac802154_sub_if_data { __le16 pan_id; __le16 short_addr; + __le64 extended_addr; u8 chan; u8 page; @@ -106,11 +107,11 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, u8 page, u8 chan); /* MIB callbacks */ -void mac802154_dev_set_short_addr(struct net_device *dev, u16 val); -u16 mac802154_dev_get_short_addr(const struct net_device *dev); +void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val); +__le16 mac802154_dev_get_short_addr(const struct net_device *dev); void mac802154_dev_set_ieee_addr(struct net_device *dev); -u16 mac802154_dev_get_pan_id(const struct net_device *dev); -void mac802154_dev_set_pan_id(struct net_device *dev, u16 val); +__le16 mac802154_dev_get_pan_id(const struct net_device *dev); +void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val); void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); u8 mac802154_dev_get_dsn(const struct net_device *dev); diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index a99910d4d52f..15bac3358889 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -40,7 +40,7 @@ static int mac802154_mlme_start_req(struct net_device *dev, u8 pan_coord, u8 blx, u8 coord_realign) { - BUG_ON(addr->addr_type != IEEE802154_ADDR_SHORT); + BUG_ON(addr->mode != IEEE802154_ADDR_SHORT); mac802154_dev_set_pan_id(dev, addr->pan_id); mac802154_dev_set_short_addr(dev, addr->short_addr); diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index f48f40c1da1a..153bd1ddbfbb 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -24,7 +24,9 @@ #include <linux/if_arp.h> #include <net/mac802154.h> +#include <net/ieee802154_netdev.h> #include <net/wpan-phy.h> +#include <net/ieee802154_netdev.h> #include "mac802154.h" @@ -79,7 +81,7 @@ static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) queue_work(priv->hw->dev_workqueue, &work->work); } -void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) +void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val) { struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -96,10 +98,10 @@ void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) } } -u16 mac802154_dev_get_short_addr(const struct net_device *dev) +__le16 mac802154_dev_get_short_addr(const struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); - u16 ret; + __le16 ret; BUG_ON(dev->type != ARPHRD_IEEE802154); @@ -115,19 +117,19 @@ void mac802154_dev_set_ieee_addr(struct net_device *dev) struct mac802154_sub_if_data *priv = netdev_priv(dev); struct mac802154_priv *mac = priv->hw; + priv->extended_addr = ieee802154_devaddr_from_raw(dev->dev_addr); + if (mac->ops->set_hw_addr_filt && - memcmp(mac->hw.hw_filt.ieee_addr, - dev->dev_addr, IEEE802154_ADDR_LEN)) { - memcpy(mac->hw.hw_filt.ieee_addr, - dev->dev_addr, IEEE802154_ADDR_LEN); + mac->hw.hw_filt.ieee_addr != priv->extended_addr) { + mac->hw.hw_filt.ieee_addr = priv->extended_addr; set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED); } } -u16 mac802154_dev_get_pan_id(const struct net_device *dev) +__le16 mac802154_dev_get_pan_id(const struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); - u16 ret; + __le16 ret; BUG_ON(dev->type != ARPHRD_IEEE802154); @@ -138,7 +140,7 @@ u16 mac802154_dev_get_pan_id(const struct net_device *dev) return ret; } -void mac802154_dev_set_pan_id(struct net_device *dev, u16 val) +void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val) { struct mac802154_sub_if_data *priv = netdev_priv(dev); diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 372d8a222b91..80cbee1a2f56 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -35,35 +35,6 @@ #include "mac802154.h" -static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val) -{ - if (unlikely(!pskb_may_pull(skb, 2))) - return -EINVAL; - - *val = skb->data[0] | (skb->data[1] << 8); - skb_pull(skb, 2); - - return 0; -} - -static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src) -{ - int i; - for (i = 0; i < IEEE802154_ADDR_LEN; i++) - dest[IEEE802154_ADDR_LEN - i - 1] = src[i]; -} - static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -76,19 +47,25 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGIFADDR: - if (priv->pan_id == IEEE802154_PANID_BROADCAST || - priv->short_addr == IEEE802154_ADDR_BROADCAST) { + { + u16 pan_id, short_addr; + + pan_id = le16_to_cpu(priv->pan_id); + short_addr = le16_to_cpu(priv->short_addr); + if (pan_id == IEEE802154_PANID_BROADCAST || + short_addr == IEEE802154_ADDR_BROADCAST) { err = -EADDRNOTAVAIL; break; } sa->family = AF_IEEE802154; sa->addr.addr_type = IEEE802154_ADDR_SHORT; - sa->addr.pan_id = priv->pan_id; - sa->addr.short_addr = priv->short_addr; + sa->addr.pan_id = pan_id; + sa->addr.short_addr = short_addr; err = 0; break; + } case SIOCSIFADDR: dev_warn(&dev->dev, "Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n"); @@ -101,8 +78,8 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - priv->pan_id = sa->addr.pan_id; - priv->short_addr = sa->addr.short_addr; + priv->pan_id = cpu_to_le16(sa->addr.pan_id); + priv->short_addr = cpu_to_le16(sa->addr.short_addr); err = 0; break; @@ -128,187 +105,70 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) static int mac802154_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *_daddr, - const void *_saddr, + const void *daddr, + const void *saddr, unsigned len) { - const struct ieee802154_addr *saddr = _saddr; - const struct ieee802154_addr *daddr = _daddr; - struct ieee802154_addr dev_addr; + struct ieee802154_hdr hdr; struct mac802154_sub_if_data *priv = netdev_priv(dev); - int pos = 2; - u8 head[MAC802154_FRAME_HARD_HEADER_LEN]; - u16 fc; + int hlen; if (!daddr) return -EINVAL; - head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */ - fc = mac_cb_type(skb); - if (mac_cb_is_ackreq(skb)) - fc |= IEEE802154_FC_ACK_REQ; + memset(&hdr.fc, 0, sizeof(hdr.fc)); + hdr.fc.type = mac_cb_type(skb); + hdr.fc.security_enabled = mac_cb_is_secen(skb); + hdr.fc.ack_request = mac_cb_is_ackreq(skb); if (!saddr) { spin_lock_bh(&priv->mib_lock); - if (priv->short_addr == IEEE802154_ADDR_BROADCAST || - priv->short_addr == IEEE802154_ADDR_UNDEF || - priv->pan_id == IEEE802154_PANID_BROADCAST) { - dev_addr.addr_type = IEEE802154_ADDR_LONG; - memcpy(dev_addr.hwaddr, dev->dev_addr, - IEEE802154_ADDR_LEN); + if (priv->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || + priv->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || + priv->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { + hdr.source.mode = IEEE802154_ADDR_LONG; + hdr.source.extended_addr = priv->extended_addr; } else { - dev_addr.addr_type = IEEE802154_ADDR_SHORT; - dev_addr.short_addr = priv->short_addr; + hdr.source.mode = IEEE802154_ADDR_SHORT; + hdr.source.short_addr = priv->short_addr; } - dev_addr.pan_id = priv->pan_id; - saddr = &dev_addr; + hdr.source.pan_id = priv->pan_id; spin_unlock_bh(&priv->mib_lock); + } else { + hdr.source = *(const struct ieee802154_addr *)saddr; } - if (daddr->addr_type != IEEE802154_ADDR_NONE) { - fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT); - - head[pos++] = daddr->pan_id & 0xff; - head[pos++] = daddr->pan_id >> 8; - - if (daddr->addr_type == IEEE802154_ADDR_SHORT) { - head[pos++] = daddr->short_addr & 0xff; - head[pos++] = daddr->short_addr >> 8; - } else { - mac802154_haddr_copy_swap(head + pos, daddr->hwaddr); - pos += IEEE802154_ADDR_LEN; - } - } - - if (saddr->addr_type != IEEE802154_ADDR_NONE) { - fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT); - - if ((saddr->pan_id == daddr->pan_id) && - (saddr->pan_id != IEEE802154_PANID_BROADCAST)) { - /* PANID compression/intra PAN */ - fc |= IEEE802154_FC_INTRA_PAN; - } else { - head[pos++] = saddr->pan_id & 0xff; - head[pos++] = saddr->pan_id >> 8; - } - - if (saddr->addr_type == IEEE802154_ADDR_SHORT) { - head[pos++] = saddr->short_addr & 0xff; - head[pos++] = saddr->short_addr >> 8; - } else { - mac802154_haddr_copy_swap(head + pos, saddr->hwaddr); - pos += IEEE802154_ADDR_LEN; - } - } + hdr.dest = *(const struct ieee802154_addr *)daddr; - head[0] = fc; - head[1] = fc >> 8; + hlen = ieee802154_hdr_push(skb, &hdr); + if (hlen < 0) + return -EINVAL; - memcpy(skb_push(skb, pos), head, pos); skb_reset_mac_header(skb); - skb->mac_len = pos; + skb->mac_len = hlen; + + if (hlen + len + 2 > dev->mtu) + return -EMSGSIZE; - return pos; + return hlen; } static int mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) { - const u8 *hdr = skb_mac_header(skb); - const u8 *tail = skb_tail_pointer(skb); + struct ieee802154_hdr hdr; struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; - u16 fc; - int da_type; - - if (hdr + 3 > tail) - goto malformed; - - fc = hdr[0] | (hdr[1] << 8); - - hdr += 3; - - da_type = IEEE802154_FC_DAMODE(fc); - addr->addr_type = IEEE802154_FC_SAMODE(fc); - - switch (da_type) { - case IEEE802154_ADDR_NONE: - if (fc & IEEE802154_FC_INTRA_PAN) - goto malformed; - break; - case IEEE802154_ADDR_LONG: - if (fc & IEEE802154_FC_INTRA_PAN) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } - - if (hdr + IEEE802154_ADDR_LEN > tail) - goto malformed; - - hdr += IEEE802154_ADDR_LEN; - break; - case IEEE802154_ADDR_SHORT: - if (fc & IEEE802154_FC_INTRA_PAN) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } - - if (hdr + 2 > tail) - goto malformed; - - hdr += 2; - break; - default: - goto malformed; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { + pr_debug("malformed packet\n"); + return 0; } - switch (addr->addr_type) { - case IEEE802154_ADDR_NONE: - break; - case IEEE802154_ADDR_LONG: - if (!(fc & IEEE802154_FC_INTRA_PAN)) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } - - if (hdr + IEEE802154_ADDR_LEN > tail) - goto malformed; - - mac802154_haddr_copy_swap(addr->hwaddr, hdr); - hdr += IEEE802154_ADDR_LEN; - break; - case IEEE802154_ADDR_SHORT: - if (!(fc & IEEE802154_FC_INTRA_PAN)) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } - - if (hdr + 2 > tail) - goto malformed; - - addr->short_addr = hdr[0] | (hdr[1] << 8); - hdr += 2; - break; - default: - goto malformed; - } - - return sizeof(struct ieee802154_addr); - -malformed: - pr_debug("malformed packet\n"); - return 0; + *addr = hdr.source; + return sizeof(*addr); } static netdev_tx_t @@ -382,8 +242,8 @@ void mac802154_wpan_setup(struct net_device *dev) get_random_bytes(&priv->bsn, 1); get_random_bytes(&priv->dsn, 1); - priv->pan_id = IEEE802154_PANID_BROADCAST; - priv->short_addr = IEEE802154_ADDR_BROADCAST; + priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); + priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); } static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) @@ -394,13 +254,18 @@ static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) static int mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) { + __le16 span, sshort; + pr_debug("getting packet via slave interface %s\n", sdata->dev->name); spin_lock_bh(&sdata->mib_lock); - switch (mac_cb(skb)->da.addr_type) { + span = sdata->pan_id; + sshort = sdata->short_addr; + + switch (mac_cb(skb)->dest.mode) { case IEEE802154_ADDR_NONE: - if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) + if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE) /* FIXME: check if we are PAN coordinator */ skb->pkt_type = PACKET_OTHERHOST; else @@ -408,23 +273,22 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; break; case IEEE802154_ADDR_LONG: - if (mac_cb(skb)->da.pan_id != sdata->pan_id && - mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + if (mac_cb(skb)->dest.pan_id != span && + mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; - else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr, - IEEE802154_ADDR_LEN)) + else if (mac_cb(skb)->dest.extended_addr == sdata->extended_addr) skb->pkt_type = PACKET_HOST; else skb->pkt_type = PACKET_OTHERHOST; break; case IEEE802154_ADDR_SHORT: - if (mac_cb(skb)->da.pan_id != sdata->pan_id && - mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + if (mac_cb(skb)->dest.pan_id != span && + mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; - else if (mac_cb(skb)->da.short_addr == sdata->short_addr) + else if (mac_cb(skb)->dest.short_addr == sshort) skb->pkt_type = PACKET_HOST; - else if (mac_cb(skb)->da.short_addr == - IEEE802154_ADDR_BROADCAST) + else if (mac_cb(skb)->dest.short_addr == + cpu_to_le16(IEEE802154_ADDR_BROADCAST)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_OTHERHOST; @@ -451,88 +315,82 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) } } -static int mac802154_parse_frame_start(struct sk_buff *skb) +static void mac802154_print_addr(const char *name, + const struct ieee802154_addr *addr) { - u8 *head = skb->data; - u16 fc; + if (addr->mode == IEEE802154_ADDR_NONE) + pr_debug("%s not present\n", name); - if (mac802154_fetch_skb_u16(skb, &fc) || - mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq))) - goto err; + pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id)); + if (addr->mode == IEEE802154_ADDR_SHORT) { + pr_debug("%s is short: %04x\n", name, + le16_to_cpu(addr->short_addr)); + } else { + u64 hw = swab64((__force u64) addr->extended_addr); - pr_debug("fc: %04x dsn: %02x\n", fc, head[2]); - - mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc); - mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc); - mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc); + pr_debug("%s is hardware: %8phC\n", name, &hw); + } +} - if (fc & IEEE802154_FC_INTRA_PAN) - mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN; +static int mac802154_parse_frame_start(struct sk_buff *skb) +{ + int hlen; + struct ieee802154_hdr hdr; - if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) { - if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id))) - goto err; + hlen = ieee802154_hdr_pull(skb, &hdr); + if (hlen < 0) + return -EINVAL; - /* source PAN id compression */ - if (mac_cb_is_intrapan(skb)) - mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id; + skb->mac_len = hlen; - pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr.fc), + hdr.seq); - if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) { - u16 *da = &(mac_cb(skb)->da.short_addr); + mac_cb(skb)->flags = hdr.fc.type; - if (mac802154_fetch_skb_u16(skb, da)) - goto err; + if (hdr.fc.ack_request) + mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; + if (hdr.fc.security_enabled) + mac_cb(skb)->flags |= MAC_CB_FLAG_SECEN; - pr_debug("destination address is short: %04x\n", - mac_cb(skb)->da.short_addr); - } else { - if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) - goto err; + mac802154_print_addr("destination", &hdr.dest); + mac802154_print_addr("source", &hdr.source); - mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr, - skb->data); - skb_pull(skb, IEEE802154_ADDR_LEN); + mac_cb(skb)->source = hdr.source; + mac_cb(skb)->dest = hdr.dest; - pr_debug("destination address is hardware\n"); - } - } + if (hdr.fc.security_enabled) { + u64 key; - if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) { - /* non PAN-compression, fetch source address id */ - if (!(mac_cb_is_intrapan(skb))) { - u16 *sa_pan = &(mac_cb(skb)->sa.pan_id); + pr_debug("seclevel %i\n", hdr.sec.level); - if (mac802154_fetch_skb_u16(skb, sa_pan)) - goto err; - } - - pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id); - - if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) { - u16 *sa = &(mac_cb(skb)->sa.short_addr); - - if (mac802154_fetch_skb_u16(skb, sa)) - goto err; + switch (hdr.sec.key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + pr_debug("implicit key\n"); + break; - pr_debug("source address is short: %04x\n", - mac_cb(skb)->sa.short_addr); - } else { - if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) - goto err; + case IEEE802154_SCF_KEY_INDEX: + pr_debug("key %02x\n", hdr.sec.key_id); + break; - mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr, - skb->data); - skb_pull(skb, IEEE802154_ADDR_LEN); + case IEEE802154_SCF_KEY_SHORT_INDEX: + pr_debug("key %04x:%04x %02x\n", + le32_to_cpu(hdr.sec.short_src) >> 16, + le32_to_cpu(hdr.sec.short_src) & 0xffff, + hdr.sec.key_id); + break; - pr_debug("source address is hardware\n"); + case IEEE802154_SCF_KEY_HW_INDEX: + key = swab64((__force u64) hdr.sec.extended_src); + pr_debug("key source %8phC %02x\n", &key, + hdr.sec.key_id); + break; } + + return -EINVAL; } return 0; -err: - return -EINVAL; } void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig index 44cd4f58adf0..2f7f5c32c6f9 100644 --- a/net/netfilter/ipset/Kconfig +++ b/net/netfilter/ipset/Kconfig @@ -61,6 +61,15 @@ config IP_SET_HASH_IP To compile it as a module, choose M here. If unsure, say N. +config IP_SET_HASH_IPMARK + tristate "hash:ip,mark set support" + depends on IP_SET + help + This option adds the hash:ip,mark set type support, by which one + can store IPv4/IPv6 address and mark pairs. + + To compile it as a module, choose M here. If unsure, say N. + config IP_SET_HASH_IPPORT tristate "hash:ip,port set support" depends on IP_SET diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile index 44b2d38476fa..231f10196cb9 100644 --- a/net/netfilter/ipset/Makefile +++ b/net/netfilter/ipset/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o # hash types obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o +obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de770ec39e51..117208321f16 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -54,10 +54,10 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex is held: */ -#define nfnl_dereference(p) \ +#define ip_set_dereference(p) \ rcu_dereference_protected(p, 1) -#define nfnl_set(inst, id) \ - nfnl_dereference((inst)->ip_set_list)[id] +#define ip_set(inst, id) \ + ip_set_dereference((inst)->ip_set_list)[id] /* * The set types are implemented in modules and registered set types @@ -368,6 +368,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) if (tb[IPSET_ATTR_CADT_FLAGS]) cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_WITH_FORCEADD) + set->flags |= IPSET_CREATE_FLAG_FORCEADD; for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; @@ -510,7 +512,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) - return 0; + return -IPSET_ERR_TYPE_MISMATCH; write_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); @@ -533,7 +535,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) - return 0; + return -IPSET_ERR_TYPE_MISMATCH; write_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); @@ -640,7 +642,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) return IPSET_INVALID_ID; nfnl_lock(NFNL_SUBSYS_IPSET); - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set) __ip_set_get(set); else @@ -666,7 +668,7 @@ ip_set_nfnl_put(struct net *net, ip_set_id_t index) nfnl_lock(NFNL_SUBSYS_IPSET); if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */ - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set != NULL) __ip_set_put(set); } @@ -734,7 +736,7 @@ find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id) *id = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { - set = nfnl_set(inst, i); + set = ip_set(inst, i); if (set != NULL && STREQ(set->name, name)) { *id = i; break; @@ -760,7 +762,7 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, *index = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s == NULL) { if (*index == IPSET_INVALID_ID) *index = i; @@ -883,7 +885,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = nfnl_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst->ip_set_list); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ @@ -900,7 +902,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, * Finally! Add our shiny new set to the list, and be done. */ pr_debug("create: '%s' created with index %u!\n", set->name, index); - nfnl_set(inst, index) = set; + ip_set(inst, index) = set; return ret; @@ -925,10 +927,10 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { static void ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index) { - struct ip_set *set = nfnl_set(inst, index); + struct ip_set *set = ip_set(inst, index); pr_debug("set: %s\n", set->name); - nfnl_set(inst, index) = NULL; + ip_set(inst, index) = NULL; /* Must call it without holding any lock */ set->variant->destroy(set); @@ -962,7 +964,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL && s->ref) { ret = -IPSET_ERR_BUSY; goto out; @@ -970,7 +972,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, } read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL) ip_set_destroy_set(inst, i); } @@ -1020,7 +1022,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL) ip_set_flush_set(s); } @@ -1074,7 +1076,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL && STREQ(s->name, name2)) { ret = -IPSET_ERR_EXIST_SETNAME2; goto out; @@ -1134,8 +1136,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); - nfnl_set(inst, from_id) = to; - nfnl_set(inst, to_id) = from; + ip_set(inst, from_id) = to; + ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); return 0; @@ -1157,7 +1159,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; if (cb->args[IPSET_CB_ARG0]) { pr_debug("release set %s\n", - nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name); + ip_set(inst, cb->args[IPSET_CB_INDEX])->name); __ip_set_put_byindex(inst, (ip_set_id_t) cb->args[IPSET_CB_INDEX]); } @@ -1254,7 +1256,7 @@ dump_last: dump_type, dump_flags, cb->args[IPSET_CB_INDEX]); for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) { index = (ip_set_id_t) cb->args[IPSET_CB_INDEX]; - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set == NULL) { if (dump_type == DUMP_ONE) { ret = -ENOENT; @@ -1332,7 +1334,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - pr_debug("release set %s\n", nfnl_set(inst, index)->name); + pr_debug("release set %s\n", ip_set(inst, index)->name); __ip_set_put_byindex(inst, index); cb->args[IPSET_CB_ARG0] = 0; } @@ -1887,7 +1889,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) find_set_and_id(inst, req_get->set.name, &id); req_get->set.index = id; if (id != IPSET_INVALID_ID) - req_get->family = nfnl_set(inst, id)->family; + req_get->family = ip_set(inst, id)->family; nfnl_unlock(NFNL_SUBSYS_IPSET); goto copy; } @@ -1901,7 +1903,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) goto done; } nfnl_lock(NFNL_SUBSYS_IPSET); - set = nfnl_set(inst, req_get->set.index); + set = ip_set(inst, req_get->set.index); strncpy(req_get->set.name, set ? set->name : "", IPSET_MAXNAMELEN); nfnl_unlock(NFNL_SUBSYS_IPSET); @@ -1945,7 +1947,6 @@ ip_set_net_init(struct net *net) return -ENOMEM; inst->is_deleted = 0; rcu_assign_pointer(inst->ip_set_list, list); - pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } @@ -1960,7 +1961,7 @@ ip_set_net_exit(struct net *net) inst->is_deleted = 1; /* flag for ip_set_nfnl_put */ for (i = 0; i < inst->ip_set_max; i++) { - set = nfnl_set(inst, i); + set = ip_set(inst, i); if (set != NULL) ip_set_destroy_set(inst, i); } @@ -1996,6 +1997,7 @@ ip_set_init(void) nfnetlink_subsys_unregister(&ip_set_netlink_subsys); return ret; } + pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index be6932ad3a86..61c7fb052802 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -263,6 +263,9 @@ struct htype { u32 maxelem; /* max elements in the hash */ u32 elements; /* current element (vs timeout) */ u32 initval; /* random jhash init value */ +#ifdef IP_SET_HASH_WITH_MARKMASK + u32 markmask; /* markmask value for mark mask to store */ +#endif struct timer_list gc; /* garbage collection when timeout enabled */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_MULTI @@ -454,6 +457,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) #ifdef IP_SET_HASH_WITH_NETMASK x->netmask == y->netmask && #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + x->markmask == y->markmask && +#endif a->extensions == b->extensions; } @@ -627,6 +633,18 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, bool flag_exist = flags & IPSET_FLAG_EXIST; u32 key, multi = 0; + if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) { + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t,key); + if (n->pos) { + /* Choosing the first entry in the array to replace */ + j = 0; + goto reuse_slot; + } + rcu_read_unlock_bh(); + } if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem) /* FIXME: when set is full, we slow down here */ mtype_expire(set, h, NLEN(set->family), set->dsize); @@ -908,6 +926,10 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) goto nla_put_failure; #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) + goto nla_put_failure; +#endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; @@ -1016,6 +1038,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; +#ifdef IP_SET_HASH_WITH_MARKMASK + u32 markmask; +#endif u8 hbits; #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; @@ -1026,6 +1051,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; + +#ifdef IP_SET_HASH_WITH_MARKMASK + markmask = 0xffffffff; +#endif #ifdef IP_SET_HASH_WITH_NETMASK netmask = set->family == NFPROTO_IPV4 ? 32 : 128; pr_debug("Create set %s with family %s\n", @@ -1034,6 +1063,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || +#ifdef IP_SET_HASH_WITH_MARKMASK + !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) || +#endif !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; @@ -1057,6 +1089,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return -IPSET_ERR_INVALID_NETMASK; } #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + if (tb[IPSET_ATTR_MARKMASK]) { + markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK])); + + if ((markmask > 4294967295u) || markmask == 0) + return -IPSET_ERR_INVALID_MARKMASK; + } +#endif hsize = sizeof(*h); #ifdef IP_SET_HASH_WITH_NETS @@ -1071,6 +1111,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + h->markmask = markmask; +#endif get_random_bytes(&h->initval, sizeof(h->initval)); set->timeout = IPSET_NO_TIMEOUT; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index e65fc2423d56..dd40607f878e 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -25,7 +25,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Counters support */ -#define IPSET_TYPE_REV_MAX 2 /* Comments support */ +/* 2 Comments support */ +#define IPSET_TYPE_REV_MAX 3 /* Forceadd support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c new file mode 100644 index 000000000000..4eff0a297254 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -0,0 +1,321 @@ +/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net> + * + * 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 + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip,mark type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +#define IPSET_TYPE_REV_MIN 0 +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support */ + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>"); +IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); +MODULE_ALIAS("ip_set_hash:ip,mark"); + +/* Type specific function prefix */ +#define HTYPE hash_ipmark +#define IP_SET_HASH_WITH_MARKMASK + +/* IPv4 variant */ + +/* Member elements */ +struct hash_ipmark4_elem { + __be32 ip; + __u32 mark; +}; + +/* Common functions */ + +static inline bool +hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1, + const struct hash_ipmark4_elem *ip2, + u32 *multi) +{ + return ip1->ip == ip2->ip && + ip1->mark == ip2->mark; +} + +static bool +hash_ipmark4_data_list(struct sk_buff *skb, + const struct hash_ipmark4_elem *data) +{ + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return 1; +} + +static inline void +hash_ipmark4_data_next(struct hash_ipmark4_elem *next, + const struct hash_ipmark4_elem *d) +{ + next->ip = d->ip; +} + +#define MTYPE hash_ipmark4 +#define PF 4 +#define HOST_MASK 32 +#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem) +#include "ip_set_hash_gen.h" + +static int +hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark4_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + + e.mark = skb->mark; + e.mark &= h->markmask; + + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); +} + +static int +hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark4_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + u32 ip, ip_to = 0; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || + ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark &= h->markmask; + + if (adt == IPSET_TEST || + !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { + ret = adtfn(set, &e, &ext, &ext, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ip_to = ip = ntohl(e.ip); + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (!cidr || cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip_set_mask_from_to(ip, ip_to, cidr); + } + + if (retried) + ip = ntohl(h->next.ip); + for (; !before(ip_to, ip); ip++) { + e.ip = htonl(ip); + ret = adtfn(set, &e, &ext, &ext, flags); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* IPv6 variant */ + +struct hash_ipmark6_elem { + union nf_inet_addr ip; + __u32 mark; +}; + +/* Common functions */ + +static inline bool +hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1, + const struct hash_ipmark6_elem *ip2, + u32 *multi) +{ + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ip1->mark == ip2->mark; +} + +static bool +hash_ipmark6_data_list(struct sk_buff *skb, + const struct hash_ipmark6_elem *data) +{ + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return 1; +} + +static inline void +hash_ipmark6_data_next(struct hash_ipmark4_elem *next, + const struct hash_ipmark6_elem *d) +{ +} + +#undef MTYPE +#undef PF +#undef HOST_MASK +#undef HKEY_DATALEN + +#define MTYPE hash_ipmark6 +#define PF 6 +#define HOST_MASK 128 +#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem) +#define IP_SET_EMIT_CREATE +#include "ip_set_hash_gen.h" + + +static int +hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark6_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + + e.mark = skb->mark; + e.mark &= h->markmask; + + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); +} + +static int +hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark6_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || + ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark &= h->markmask; + + if (adt == IPSET_TEST) { + ret = adtfn(set, &e, &ext, &ext, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ret = adtfn(set, &e, &ext, &ext, flags); + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + + return ret; +} + +static struct ip_set_type hash_ipmark_type __read_mostly = { + .name = "hash:ip,mark", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_MARK, + .dimension = IPSET_DIM_TWO, + .family = NFPROTO_UNSPEC, + .revision_min = IPSET_TYPE_REV_MIN, + .revision_max = IPSET_TYPE_REV_MAX, + .create = hash_ipmark_create, + .create_policy = { + [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 }, + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_MARK] = { .type = NLA_U32 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, + [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ipmark_init(void) +{ + return ip_set_type_register(&hash_ipmark_type); +} + +static void __exit +hash_ipmark_fini(void) +{ + ip_set_type_unregister(&hash_ipmark_type); +} + +module_init(hash_ipmark_init); +module_exit(hash_ipmark_fini); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 525a595dd1fe..7597b82a8b03 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -27,7 +27,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ -#define IPSET_TYPE_REV_MAX 3 /* Comments support added */ +/* 3 Comments support added */ +#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index f5636631466e..672655ffd573 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -27,7 +27,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ -#define IPSET_TYPE_REV_MAX 3 /* Comments support added */ +/* 3 Comments support added */ +#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5d87fe8a41ff..7308d84f9277 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -29,7 +29,8 @@ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ -#define IPSET_TYPE_REV_MAX 5 /* Comments support added */ +/* 5 Comments support added */ +#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 8295cf4f9fdc..4c7d495783a3 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -26,7 +26,8 @@ /* 1 Range as input support for IPv4 added */ /* 2 nomatch flag support added */ /* 3 Counters support added */ -#define IPSET_TYPE_REV_MAX 4 /* Comments support added */ +/* 4 Comments support added */ +#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index b827a0f1f351..db2606805b35 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -27,7 +27,8 @@ /* 1 nomatch flag support added */ /* 2 /0 support added */ /* 3 Counters support added */ -#define IPSET_TYPE_REV_MAX 4 /* Comments support added */ +/* 4 Comments support added */ +#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6226803fc490..3e99987e4bf2 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -24,7 +24,7 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); @@ -112,10 +112,10 @@ hash_netnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -334,10 +334,10 @@ hash_netnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 7097fb0141bf..1c645fbd09c7 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -28,7 +28,8 @@ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ -#define IPSET_TYPE_REV_MAX 5 /* Comments support added */ +/* 5 Comments support added */ +#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 703d1192a6a2..c0d2ba73f8b2 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -25,7 +25,8 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 /* Comments support added */ +/* 0 Comments support added */ +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c index 4f29fa97044b..04d15fdc99ee 100644 --- a/net/netfilter/ipset/pfxlen.c +++ b/net/netfilter/ipset/pfxlen.c @@ -7,8 +7,8 @@ #define E(a, b, c, d) \ {.ip6 = { \ - __constant_htonl(a), __constant_htonl(b), \ - __constant_htonl(c), __constant_htonl(d), \ + htonl(a), htonl(b), \ + htonl(c), htonl(d), \ } } /* diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 35be035ee0ce..c42e83d2751c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2177,10 +2177,10 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) __u64 inbytes, outbytes; do { - start = u64_stats_fetch_begin_bh(&u->syncp); + start = u64_stats_fetch_begin_irq(&u->syncp); inbytes = u->ustats.inbytes; outbytes = u->ustats.outbytes; - } while (u64_stats_fetch_retry_bh(&u->syncp, start)); + } while (u64_stats_fetch_retry_irq(&u->syncp, start)); seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", i, u->ustats.conns, u->ustats.inpkts, @@ -3580,7 +3580,7 @@ out: } -static const struct genl_ops ip_vs_genl_ops[] __read_mostly = { +static const struct genl_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_NEW_SERVICE, .flags = GENL_ADMIN_PERM, diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index ca056a331e60..547ff33c1efd 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -238,7 +238,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) spin_lock_bh(&svc->sched_lock); tbl->dead = 1; - for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { ip_vs_lblc_del(en); atomic_dec(&tbl->entries); @@ -265,7 +265,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) unsigned long now = jiffies; int i, j; - for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; spin_lock(&svc->sched_lock); @@ -321,7 +321,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (goal > tbl->max_size/2) goal = tbl->max_size/2; - for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; spin_lock(&svc->sched_lock); @@ -340,7 +340,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) tbl->rover = j; out: - mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL); + mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); } @@ -363,7 +363,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) /* * Initialize the hash buckets */ - for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) { INIT_HLIST_HEAD(&tbl->bucket[i]); } tbl->max_size = IP_VS_LBLC_TAB_SIZE*16; @@ -536,8 +536,7 @@ out: /* * IPVS LBLC Scheduler structure */ -static struct ip_vs_scheduler ip_vs_lblc_scheduler = -{ +static struct ip_vs_scheduler ip_vs_lblc_scheduler = { .name = "lblc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 356bef519fe5..6dba48efe01e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -60,8 +60,59 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); -DEFINE_SPINLOCK(nf_conntrack_lock); -EXPORT_SYMBOL_GPL(nf_conntrack_lock); +__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; +EXPORT_SYMBOL_GPL(nf_conntrack_locks); + +__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); +EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); + +static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) +{ + h1 %= CONNTRACK_LOCKS; + h2 %= CONNTRACK_LOCKS; + spin_unlock(&nf_conntrack_locks[h1]); + if (h1 != h2) + spin_unlock(&nf_conntrack_locks[h2]); +} + +/* return true if we need to recompute hashes (in case hash table was resized) */ +static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, + unsigned int h2, unsigned int sequence) +{ + h1 %= CONNTRACK_LOCKS; + h2 %= CONNTRACK_LOCKS; + if (h1 <= h2) { + spin_lock(&nf_conntrack_locks[h1]); + if (h1 != h2) + spin_lock_nested(&nf_conntrack_locks[h2], + SINGLE_DEPTH_NESTING); + } else { + spin_lock(&nf_conntrack_locks[h2]); + spin_lock_nested(&nf_conntrack_locks[h1], + SINGLE_DEPTH_NESTING); + } + if (read_seqcount_retry(&net->ct.generation, sequence)) { + nf_conntrack_double_unlock(h1, h2); + return true; + } + return false; +} + +static void nf_conntrack_all_lock(void) +{ + int i; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_lock_nested(&nf_conntrack_locks[i], i); +} + +static void nf_conntrack_all_unlock(void) +{ + int i; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_unlock(&nf_conntrack_locks[i]); +} unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); @@ -192,6 +243,50 @@ clean_from_lists(struct nf_conn *ct) nf_ct_remove_expectations(ct); } +/* must be called with local_bh_disable */ +static void nf_ct_add_to_dying_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* add this conntrack to the (per cpu) dying list */ + ct->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &pcpu->dying); + spin_unlock(&pcpu->lock); +} + +/* must be called with local_bh_disable */ +static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* add this conntrack to the (per cpu) unconfirmed list */ + ct->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &pcpu->unconfirmed); + spin_unlock(&pcpu->lock); +} + +/* must be called with local_bh_disable */ +static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* We overload first tuple to link into unconfirmed or dying list.*/ + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + spin_unlock(&pcpu->lock); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -203,9 +298,6 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); - /* To make sure we don't get any weird locking issues here: - * destroy_conntrack() MUST NOT be called with a write lock - * to nf_conntrack_lock!!! -HW */ rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -213,19 +305,18 @@ destroy_conntrack(struct nf_conntrack *nfct) rcu_read_unlock(); - spin_lock_bh(&nf_conntrack_lock); + local_bh_disable(); /* Expectations will have been removed in clean_from_lists, * except TFTP can create an expectation on the first packet, * before connection is in the list, so we need to clean here, - * too. */ + * too. + */ nf_ct_remove_expectations(ct); - /* We overload first tuple to link into unconfirmed or dying list.*/ - BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); - hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + nf_ct_del_from_dying_or_unconfirmed_list(ct); NF_CT_STAT_INC(net, delete); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (ct->master) nf_ct_put(ct->master); @@ -237,17 +328,28 @@ destroy_conntrack(struct nf_conntrack *nfct) static void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + unsigned int hash, reply_hash; + u16 zone = nf_ct_zone(ct); + unsigned int sequence; nf_ct_helper_destroy(ct); - spin_lock_bh(&nf_conntrack_lock); - /* Inside lock so preempt is disabled on module removal path. - * Otherwise we can get spurious warnings. */ - NF_CT_STAT_INC(net, delete_list); + + local_bh_disable(); + do { + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + clean_from_lists(ct); - /* add this conntrack to the dying list */ - hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.dying); - spin_unlock_bh(&nf_conntrack_lock); + nf_conntrack_double_unlock(hash, reply_hash); + + nf_ct_add_to_dying_list(ct); + + NF_CT_STAT_INC(net, delete_list); + local_bh_enable(); } static void death_by_event(unsigned long ul_conntrack) @@ -331,8 +433,6 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, * Warning : * - Caller must take a reference on returned object * and recheck nf_ct_tuple_equal(tuple, &h->tuple) - * OR - * - Caller must lock nf_conntrack_lock before calling this function */ static struct nf_conntrack_tuple_hash * ____nf_conntrack_find(struct net *net, u16 zone, @@ -408,32 +508,36 @@ EXPORT_SYMBOL_GPL(nf_conntrack_find_get); static void __nf_conntrack_hash_insert(struct nf_conn *ct, unsigned int hash, - unsigned int repl_hash) + unsigned int reply_hash) { struct net *net = nf_ct_net(ct); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.hash[hash]); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, - &net->ct.hash[repl_hash]); + &net->ct.hash[reply_hash]); } int nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - unsigned int hash, repl_hash; + unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; u16 zone; + unsigned int sequence; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - spin_lock_bh(&nf_conntrack_lock); + local_bh_disable(); + do { + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) @@ -441,7 +545,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) @@ -451,15 +555,16 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) smp_wmb(); /* The caller holds a reference to this object */ atomic_set(&ct->ct_general.use, 2); - __nf_conntrack_hash_insert(ct, hash, repl_hash); + __nf_conntrack_hash_insert(ct, hash, reply_hash); + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); - spin_unlock_bh(&nf_conntrack_lock); - + local_bh_enable(); return 0; out: + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert_failed); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); return -EEXIST; } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); @@ -467,15 +572,22 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* deletion from this larval template list happens via nf_ct_put() */ void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) { + struct ct_pcpu *pcpu; + __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); nf_conntrack_get(&tmpl->ct_general); - spin_lock_bh(&nf_conntrack_lock); + /* add this conntrack to the (per cpu) tmpl list */ + local_bh_disable(); + tmpl->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); + + spin_lock(&pcpu->lock); /* Overload tuple linked list to put us in template list. */ hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.tmpl); - spin_unlock_bh(&nf_conntrack_lock); + &pcpu->tmpl); + spin_unlock_bh(&pcpu->lock); } EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); @@ -483,7 +595,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); int __nf_conntrack_confirm(struct sk_buff *skb) { - unsigned int hash, repl_hash; + unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; @@ -492,6 +604,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) enum ip_conntrack_info ctinfo; struct net *net; u16 zone; + unsigned int sequence; ct = nf_ct_get(skb, &ctinfo); net = nf_ct_net(ct); @@ -504,31 +617,37 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; zone = nf_ct_zone(ct); - /* reuse the hash saved before */ - hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; - hash = hash_bucket(hash, net); - repl_hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + local_bh_disable(); + + do { + sequence = read_seqcount_begin(&net->ct.generation); + /* reuse the hash saved before */ + hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; + hash = hash_bucket(hash, net); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related - connections for unconfirmed conns. But packet copies and - REJECT will give spurious warnings here. */ + * connections for unconfirmed conns. But packet copies and + * REJECT will give spurious warnings here. + */ /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ /* No external references means no one else could have - confirmed us. */ + * confirmed us. + */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); - - spin_lock_bh(&nf_conntrack_lock); - /* We have to check the DYING flag inside the lock to prevent a race against nf_ct_get_next_corpse() possibly called from user context, else we insert an already 'dead' hash, blocking further use of that particular connection -JM */ if (unlikely(nf_ct_is_dying(ct))) { - spin_unlock_bh(&nf_conntrack_lock); + nf_conntrack_double_unlock(hash, reply_hash); + local_bh_enable(); return NF_ACCEPT; } @@ -540,14 +659,13 @@ __nf_conntrack_confirm(struct sk_buff *skb) &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - /* Remove from unconfirmed list */ - hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + nf_ct_del_from_dying_or_unconfirmed_list(ct); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in @@ -570,9 +688,10 @@ __nf_conntrack_confirm(struct sk_buff *skb) * guarantee that no other CPU can find the conntrack before the above * stores are visible. */ - __nf_conntrack_hash_insert(ct, hash, repl_hash); + __nf_conntrack_hash_insert(ct, hash, reply_hash); + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); help = nfct_help(ct); if (help && help->helper) @@ -583,8 +702,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert_failed); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); return NF_DROP; } EXPORT_SYMBOL_GPL(__nf_conntrack_confirm); @@ -627,39 +747,48 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken); /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static noinline int early_drop(struct net *net, unsigned int hash) +static noinline int early_drop(struct net *net, unsigned int _hash) { /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; struct nf_conn *ct = NULL, *tmp; struct hlist_nulls_node *n; - unsigned int i, cnt = 0; + unsigned int i = 0, cnt = 0; int dropped = 0; + unsigned int hash, sequence; + spinlock_t *lockp; - rcu_read_lock(); - for (i = 0; i < net->ct.htable_size; i++) { + local_bh_disable(); +restart: + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_bucket(_hash, net); + for (; i < net->ct.htable_size; i++) { + lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; + spin_lock(lockp); + if (read_seqcount_retry(&net->ct.generation, sequence)) { + spin_unlock(lockp); + goto restart; + } hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); - if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) + if (!test_bit(IPS_ASSURED_BIT, &tmp->status) && + !nf_ct_is_dying(tmp) && + atomic_inc_not_zero(&tmp->ct_general.use)) { ct = tmp; + break; + } cnt++; } - if (ct != NULL) { - if (likely(!nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use))) - break; - else - ct = NULL; - } + hash = (hash + 1) % net->ct.htable_size; + spin_unlock(lockp); - if (cnt >= NF_CT_EVICTION_RANGE) + if (ct || cnt >= NF_CT_EVICTION_RANGE) break; - hash = (hash + 1) % net->ct.htable_size; } - rcu_read_unlock(); + local_bh_enable(); if (!ct) return dropped; @@ -708,7 +837,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - if (!early_drop(net, hash_bucket(hash, net))) { + if (!early_drop(net, hash)) { atomic_dec(&net->ct.count); net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); return ERR_PTR(-ENOMEM); @@ -805,7 +934,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conn_help *help; struct nf_conntrack_tuple repl_tuple; struct nf_conntrack_ecache *ecache; - struct nf_conntrack_expect *exp; + struct nf_conntrack_expect *exp = NULL; u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; struct nf_conn_timeout *timeout_ext; unsigned int *timeouts; @@ -849,42 +978,44 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, ecache ? ecache->expmask : 0, GFP_ATOMIC); - spin_lock_bh(&nf_conntrack_lock); - exp = nf_ct_find_expectation(net, zone, tuple); - if (exp) { - pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", - ct, exp); - /* Welcome, Mr. Bond. We've been expecting you... */ - __set_bit(IPS_EXPECTED_BIT, &ct->status); - ct->master = exp->master; - if (exp->helper) { - help = nf_ct_helper_ext_add(ct, exp->helper, - GFP_ATOMIC); - if (help) - rcu_assign_pointer(help->helper, exp->helper); - } + local_bh_disable(); + if (net->ct.expect_count) { + spin_lock(&nf_conntrack_expect_lock); + exp = nf_ct_find_expectation(net, zone, tuple); + if (exp) { + pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", + ct, exp); + /* Welcome, Mr. Bond. We've been expecting you... */ + __set_bit(IPS_EXPECTED_BIT, &ct->status); + /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ + ct->master = exp->master; + if (exp->helper) { + help = nf_ct_helper_ext_add(ct, exp->helper, + GFP_ATOMIC); + if (help) + rcu_assign_pointer(help->helper, exp->helper); + } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = exp->master->mark; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK - ct->secmark = exp->master->secmark; + ct->secmark = exp->master->secmark; #endif - nf_conntrack_get(&ct->master->ct_general); - NF_CT_STAT_INC(net, expect_new); - } else { + NF_CT_STAT_INC(net, expect_new); + } + spin_unlock(&nf_conntrack_expect_lock); + } + if (!exp) { __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); NF_CT_STAT_INC(net, new); } /* Now it is inserted into the unconfirmed list, bump refcount */ nf_conntrack_get(&ct->ct_general); + nf_ct_add_to_unconfirmed_list(ct); - /* Overload tuple linked list to put us in unconfirmed list. */ - hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.unconfirmed); - - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (exp) { if (exp->expectfn) @@ -1254,27 +1385,42 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; + int cpu; + spinlock_t *lockp; - spin_lock_bh(&nf_conntrack_lock); for (; *bucket < net->ct.htable_size; (*bucket)++) { - hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) - continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; + local_bh_disable(); + spin_lock(lockp); + if (*bucket < net->ct.htable_size) { + hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; + } + } + spin_unlock(lockp); + local_bh_enable(); + } + + 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, n, &pcpu->unconfirmed, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) - goto found; + set_bit(IPS_DYING_BIT, &ct->status); } + spin_unlock_bh(&pcpu->lock); } - hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - set_bit(IPS_DYING_BIT, &ct->status); - } - spin_unlock_bh(&nf_conntrack_lock); return NULL; found: atomic_inc(&ct->ct_general.use); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock(lockp); + local_bh_enable(); return ct; } @@ -1323,14 +1469,19 @@ static void nf_ct_release_dying_list(struct net *net) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; + int cpu; - spin_lock_bh(&nf_conntrack_lock); - hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - /* never fails to remove them, no listeners at this point */ - nf_ct_kill(ct); + 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, n, &pcpu->dying, hnnode) { + ct = nf_ct_tuplehash_to_ctrack(h); + /* never fails to remove them, no listeners at this point */ + nf_ct_kill(ct); + } + spin_unlock_bh(&pcpu->lock); } - spin_unlock_bh(&nf_conntrack_lock); } static int untrack_refs(void) @@ -1417,6 +1568,7 @@ i_see_dead_people: kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); + free_percpu(net->ct.pcpu_lists); } } @@ -1469,12 +1621,16 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hash) return -ENOMEM; + local_bh_disable(); + nf_conntrack_all_lock(); + write_seqcount_begin(&init_net.ct.generation); + /* Lookups in the old hash might happen in parallel, which means we * might get false negatives during connection lookup. New connections * created because of a false negative won't make it into the hash - * though since that required taking the lock. + * though since that required taking the locks. */ - spin_lock_bh(&nf_conntrack_lock); + for (i = 0; i < init_net.ct.htable_size; i++) { while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, @@ -1491,7 +1647,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; init_net.ct.hash = hash; - spin_unlock_bh(&nf_conntrack_lock); + + write_seqcount_end(&init_net.ct.generation); + nf_conntrack_all_unlock(); + local_bh_enable(); nf_ct_free_hashtable(old_hash, old_size); return 0; @@ -1513,7 +1672,10 @@ EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); int nf_conntrack_init_start(void) { int max_factor = 8; - int ret, cpu; + int i, ret, cpu; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_lock_init(&nf_conntrack_locks[i]); /* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ @@ -1629,37 +1791,43 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { - int ret; + int ret = -ENOMEM; + int cpu; atomic_set(&net->ct.count, 0); - INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL); - net->ct.stat = alloc_percpu(struct ip_conntrack_stat); - if (!net->ct.stat) { - ret = -ENOMEM; + + net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu); + if (!net->ct.pcpu_lists) goto err_stat; + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_init(&pcpu->lock); + INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } + net->ct.stat = alloc_percpu(struct ip_conntrack_stat); + if (!net->ct.stat) + goto err_pcpu_lists; + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); - if (!net->ct.slabname) { - ret = -ENOMEM; + if (!net->ct.slabname) goto err_slabname; - } net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname, sizeof(struct nf_conn), 0, SLAB_DESTROY_BY_RCU, NULL); if (!net->ct.nf_conntrack_cachep) { printk(KERN_ERR "Unable to create nf_conn slab cache\n"); - ret = -ENOMEM; goto err_cache; } net->ct.htable_size = nf_conntrack_htable_size; net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1); if (!net->ct.hash) { - ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } @@ -1701,6 +1869,8 @@ err_cache: kfree(net->ct.slabname); err_slabname: free_percpu(net->ct.stat); +err_pcpu_lists: + free_percpu(net->ct.pcpu_lists); err_stat: return ret; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4fd1ca94fd4a..f87e8f68ad45 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -66,9 +66,9 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect) { struct nf_conntrack_expect *exp = (void *)ul_expect; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); nf_ct_unlink_expect(exp); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_put(exp); } @@ -155,6 +155,18 @@ nf_ct_find_expectation(struct net *net, u16 zone, if (!nf_ct_is_confirmed(exp->master)) return NULL; + /* Avoid race with other CPUs, that for exp->master ct, is + * about to invoke ->destroy(), or nf_ct_delete() via timeout + * or early_drop(). + * + * The atomic_inc_not_zero() check tells: If that fails, we + * know that the ct is being destroyed. If it succeeds, we + * can be sure the ct cannot disappear underneath. + */ + if (unlikely(nf_ct_is_dying(exp->master) || + !atomic_inc_not_zero(&exp->master->ct_general.use))) + return NULL; + if (exp->flags & NF_CT_EXPECT_PERMANENT) { atomic_inc(&exp->use); return exp; @@ -162,6 +174,8 @@ nf_ct_find_expectation(struct net *net, u16 zone, nf_ct_unlink_expect(exp); return exp; } + /* Undo exp->master refcnt increase, if del_timer() failed */ + nf_ct_put(exp->master); return NULL; } @@ -177,12 +191,14 @@ void nf_ct_remove_expectations(struct nf_conn *ct) if (!help) return; + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } } + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_remove_expectations); @@ -217,12 +233,12 @@ static inline int expect_matches(const struct nf_conntrack_expect *a, /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_unexpect_related); @@ -335,7 +351,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp) setup_timer(&exp->timeout, nf_ct_expectation_timed_out, (unsigned long)exp); helper = rcu_dereference_protected(master_help->helper, - lockdep_is_held(&nf_conntrack_lock)); + lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { exp->timeout.expires = jiffies + helper->expect_policy[exp->class].timeout * HZ; @@ -395,7 +411,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } /* Will be over limit? */ helper = rcu_dereference_protected(master_help->helper, - lockdep_is_held(&nf_conntrack_lock)); + lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { p = &helper->expect_policy[expect->class]; if (p->max_expected && @@ -417,12 +433,12 @@ out: return ret; } -int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, +int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, u32 portid, int report) { int ret; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); ret = __nf_ct_expect_check(expect); if (ret <= 0) goto out; @@ -430,11 +446,11 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, ret = nf_ct_expect_insert(expect); if (ret < 0) goto out; - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); return ret; out: - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 70866d192efc..3a3a60b126e0 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1476,7 +1476,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_refresh(ct, skb, info->timeout * HZ); /* Set expect timeout */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3, info->sig_port[!dir]); if (exp) { @@ -1486,7 +1486,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_dump_tuple(&exp->tuple); set_expect_timeout(exp, info->timeout); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 974a2a4adefa..5b3eae7d4c9a 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -250,16 +250,14 @@ out: } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); +/* appropiate ct lock protecting must be taken by caller */ static inline int unhelp(struct nf_conntrack_tuple_hash *i, const struct nf_conntrack_helper *me) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); - if (help && rcu_dereference_protected( - help->helper, - lockdep_is_held(&nf_conntrack_lock) - ) == me) { + if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } @@ -284,17 +282,17 @@ static LIST_HEAD(nf_ct_helper_expectfn_list); void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); list_add_rcu(&n->head, &nf_ct_helper_expectfn_list); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); list_del_rcu(&n->head); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); @@ -396,15 +394,17 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, const struct hlist_node *next; const struct hlist_nulls_node *nn; unsigned int i; + int cpu; /* Get rid of expectations */ + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); if ((rcu_dereference_protected( help->helper, - lockdep_is_held(&nf_conntrack_lock) + lockdep_is_held(&nf_conntrack_expect_lock) ) == me || exp->helper == me) && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); @@ -412,14 +412,27 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } } } + spin_unlock_bh(&nf_conntrack_expect_lock); /* Get rid of expecteds, set helpers to NULL. */ - hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) - unhelp(h, me); - for (i = 0; i < net->ct.htable_size; i++) { - hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) + 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) unhelp(h, me); + spin_unlock_bh(&pcpu->lock); + } + local_bh_disable(); + for (i = 0; i < net->ct.htable_size; i++) { + spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + if (i < net->ct.htable_size) { + hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) + unhelp(h, me); + } + spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } + local_bh_enable(); } void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) @@ -437,10 +450,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) synchronize_rcu(); rtnl_lock(); - spin_lock_bh(&nf_conntrack_lock); for_each_net(net) __nf_conntrack_helper_unregister(me, net); - spin_unlock_bh(&nf_conntrack_lock); rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index bb322d0beb48..ccc46fa5edbc 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -764,14 +764,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; + spinlock_t *lockp; + #ifdef CONFIG_NF_CONNTRACK_MARK const struct ctnetlink_dump_filter *filter = cb->data; #endif - spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; + + local_bh_disable(); for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: + lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; + spin_lock(lockp); + if (cb->args[0] >= net->ct.htable_size) { + spin_unlock(lockp); + goto out; + } hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) @@ -803,16 +812,18 @@ restart: if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; + spin_unlock(lockp); goto out; } } + spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (last) nf_ct_put(last); @@ -966,7 +977,6 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, return 0; } -#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, @@ -984,9 +994,9 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, - .len = __CTA_LABELS_MAX_LENGTH }, + .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, - .len = __CTA_LABELS_MAX_LENGTH }, + .len = NF_CT_LABELS_MAX_SIZE }, }; static int @@ -1138,50 +1148,65 @@ static int ctnetlink_done_list(struct netlink_callback *cb) } static int -ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, - struct hlist_nulls_head *list) +ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { - struct nf_conn *ct, *last; + struct nf_conn *ct, *last = NULL; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; + int cpu; + struct hlist_nulls_head *list; + struct net *net = sock_net(skb->sk); if (cb->args[2]) return 0; - spin_lock_bh(&nf_conntrack_lock); - last = (struct nf_conn *)cb->args[1]; -restart: - hlist_nulls_for_each_entry(h, n, list, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - if (l3proto && nf_ct_l3num(ct) != l3proto) + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + struct ct_pcpu *pcpu; + + if (!cpu_possible(cpu)) continue; - if (cb->args[1]) { - if (ct != last) + + pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + spin_lock_bh(&pcpu->lock); + last = (struct nf_conn *)cb->args[1]; + list = dying ? &pcpu->dying : &pcpu->unconfirmed; +restart: + hlist_nulls_for_each_entry(h, n, list, hnnode) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (l3proto && nf_ct_l3num(ct) != l3proto) continue; - cb->args[1] = 0; - } - rcu_read_lock(); - res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct); - rcu_read_unlock(); - if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; - goto out; + if (cb->args[1]) { + if (ct != last) + continue; + cb->args[1] = 0; + } + rcu_read_lock(); + res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + ct); + rcu_read_unlock(); + if (res < 0) { + nf_conntrack_get(&ct->ct_general); + cb->args[1] = (unsigned long)ct; + spin_unlock_bh(&pcpu->lock); + goto out; + } } + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } else + cb->args[2] = 1; + spin_unlock_bh(&pcpu->lock); } - if (cb->args[1]) { - cb->args[1] = 0; - goto restart; - } else - cb->args[2] = 1; out: - spin_unlock_bh(&nf_conntrack_lock); if (last) nf_ct_put(last); @@ -1191,9 +1216,7 @@ out: static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - - return ctnetlink_dump_list(skb, cb, &net->ct.dying); + return ctnetlink_dump_list(skb, cb, true); } static int @@ -1215,9 +1238,7 @@ ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb, static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - - return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed); + return ctnetlink_dump_list(skb, cb, false); } static int @@ -1310,27 +1331,22 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) } static int -ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[]) +ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_NAT_NEEDED int ret; - if (cda[CTA_NAT_DST]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_DST, - cda[CTA_NAT_DST]); - if (ret < 0) - return ret; - } - if (cda[CTA_NAT_SRC]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_SRC, - cda[CTA_NAT_SRC]); - if (ret < 0) - return ret; - } - return 0; + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, + cda[CTA_NAT_DST]); + if (ret < 0) + return ret; + + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, + cda[CTA_NAT_SRC]); + return ret; #else + if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) + return 0; return -EOPNOTSUPP; #endif } @@ -1366,14 +1382,14 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) nf_ct_protonum(ct)); if (helper == NULL) { #ifdef CONFIG_MODULES - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); return -EOPNOTSUPP; } - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) @@ -1659,11 +1675,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } - if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) { - err = ctnetlink_change_nat(ct, cda); - if (err < 0) - goto err2; - } + err = ctnetlink_setup_nat(ct, cda); + if (err < 0) + goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); @@ -1811,9 +1825,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); err = ctnetlink_change_conntrack(ct, cda); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | @@ -2142,9 +2156,9 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) if (ret < 0) return ret; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } @@ -2699,13 +2713,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } /* after list removal, usage count == 1 */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); @@ -2714,7 +2728,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conn_help *m_help; /* delete all expectations for this helper */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], @@ -2729,10 +2743,10 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } } } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } else { /* This basically means we have to flush everything*/ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], @@ -2745,7 +2759,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } } } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } return 0; @@ -2971,11 +2985,11 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(net, zone, &tuple); if (!exp) { - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(net, zone, cda, @@ -2989,7 +3003,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, err = -EEXIST; if (!(nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return err; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 466410eaa482..4c3ba1c8d682 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -800,7 +800,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct, struct hlist_node *next; int found = 0; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (exp->class != SIP_EXPECT_SIGNALLING || !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) || @@ -815,7 +815,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct, found = 1; break; } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return found; } @@ -825,7 +825,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) struct nf_conntrack_expect *exp; struct hlist_node *next; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media) continue; @@ -836,7 +836,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) if (!media) break; } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d3f5cd6dd962..52ca952b802c 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -432,15 +432,15 @@ nf_nat_setup_info(struct nf_conn *ct, } EXPORT_SYMBOL(nf_nat_setup_info); -unsigned int -nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +static unsigned int +__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) { /* Force range to this IP; let proto decide mapping for * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). * Use reply in case it's already been mangled (eg local packet). */ union nf_inet_addr ip = - (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); struct nf_nat_range range = { @@ -448,7 +448,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) .min_addr = ip, .max_addr = ip, }; - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); + return nf_nat_setup_info(ct, &range, manip); +} + +unsigned int +nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum)); } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); @@ -702,9 +708,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range) + const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_nat_l3proto *l3proto) { - const struct nf_nat_l3proto *l3proto; struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -714,38 +720,46 @@ nfnetlink_parse_nat(const struct nlattr *nat, if (err < 0) return err; - rcu_read_lock(); - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - if (l3proto == NULL) { - err = -EAGAIN; - goto out; - } err = l3proto->nlattr_to_range(tb, range); if (err < 0) - goto out; + return err; if (!tb[CTA_NAT_PROTO]) - goto out; + return 0; - err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); -out: - rcu_read_unlock(); - return err; + return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); } +/* This function is called under rcu_read_lock() */ static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { struct nf_nat_range range; + const struct nf_nat_l3proto *l3proto; int err; - err = nfnetlink_parse_nat(attr, ct, &range); + /* Should not happen, restricted to creating new conntracks + * via ctnetlink. + */ + if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) + return -EEXIST; + + /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to + * attach the null binding, otherwise this may oops. + */ + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) + return -EAGAIN; + + /* No NAT information has been passed, allocate the null-binding */ + if (attr == NULL) + return __nf_nat_alloc_null_binding(ct, manip); + + err = nfnetlink_parse_nat(attr, ct, &range, l3proto); if (err < 0) return err; - if (nf_nat_initialized(ct, manip)) - return -EEXIST; return nf_nat_setup_info(ct, &range, manip); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index adce01e8bb57..33045a562297 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -794,9 +794,8 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); if (chain->stats) { - /* nfnl_lock is held, add some nfnl function for this, later */ struct nft_stats __percpu *oldstats = - rcu_dereference_protected(chain->stats, 1); + nft_dereference(chain->stats); rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); @@ -1254,10 +1253,11 @@ err1: return err; } -static void nf_tables_expr_destroy(struct nft_expr *expr) +static void nf_tables_expr_destroy(const struct nft_ctx *ctx, + struct nft_expr *expr) { if (expr->ops->destroy) - expr->ops->destroy(expr); + expr->ops->destroy(ctx, expr); module_put(expr->ops->type->owner); } @@ -1296,6 +1296,8 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { [NFTA_RULE_EXPRESSIONS] = { .type = NLA_NESTED }, [NFTA_RULE_COMPAT] = { .type = NLA_NESTED }, [NFTA_RULE_POSITION] = { .type = NLA_U64 }, + [NFTA_RULE_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq, @@ -1348,6 +1350,10 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq, } nla_nest_end(skb, list); + if (rule->ulen && + nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule))) + goto nla_put_failure; + return nlmsg_end(skb, nlh); nla_put_failure: @@ -1531,7 +1537,8 @@ err: return err; } -static void nf_tables_rule_destroy(struct nft_rule *rule) +static void nf_tables_rule_destroy(const struct nft_ctx *ctx, + struct nft_rule *rule) { struct nft_expr *expr; @@ -1541,7 +1548,7 @@ static void nf_tables_rule_destroy(struct nft_rule *rule) */ expr = nft_expr_first(rule); while (expr->ops && expr != nft_expr_last(rule)) { - nf_tables_expr_destroy(expr); + nf_tables_expr_destroy(ctx, expr); expr = nft_expr_next(expr); } kfree(rule); @@ -1552,7 +1559,7 @@ static void nf_tables_rule_destroy(struct nft_rule *rule) static struct nft_expr_info *info; static struct nft_rule_trans * -nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx) +nf_tables_trans_add(struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_rule_trans *rupd; @@ -1560,11 +1567,8 @@ nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx) if (rupd == NULL) return NULL; - rupd->chain = ctx->chain; - rupd->table = ctx->table; + rupd->ctx = *ctx; rupd->rule = rule; - rupd->family = ctx->afi->family; - rupd->nlh = ctx->nlh; list_add_tail(&rupd->list, &ctx->net->nft.commit_list); return rupd; @@ -1584,7 +1588,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; - unsigned int size, i, n; + unsigned int size, i, n, ulen = 0; int err, rem; bool create; u64 handle, pos_handle; @@ -1650,8 +1654,11 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, } } + if (nla[NFTA_RULE_USERDATA]) + ulen = nla_len(nla[NFTA_RULE_USERDATA]); + err = -ENOMEM; - rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL); + rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL); if (rule == NULL) goto err1; @@ -1659,6 +1666,10 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, rule->handle = handle; rule->dlen = size; + rule->ulen = ulen; + + if (ulen) + nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen); expr = nft_expr_first(rule); for (i = 0; i < n; i++) { @@ -1671,7 +1682,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_REPLACE) { if (nft_rule_is_active_next(net, old_rule)) { - repl = nf_tables_trans_add(old_rule, &ctx); + repl = nf_tables_trans_add(&ctx, old_rule); if (repl == NULL) { err = -ENOMEM; goto err2; @@ -1694,7 +1705,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, list_add_rcu(&rule->list, &chain->rules); } - if (nf_tables_trans_add(rule, &ctx) == NULL) { + if (nf_tables_trans_add(&ctx, rule) == NULL) { err = -ENOMEM; goto err3; } @@ -1709,7 +1720,7 @@ err3: kfree(repl); } err2: - nf_tables_rule_destroy(rule); + nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops != NULL) @@ -1723,7 +1734,7 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ if (nft_rule_is_active_next(ctx->net, rule)) { - if (nf_tables_trans_add(rule, ctx) == NULL) + if (nf_tables_trans_add(ctx, rule) == NULL) return -ENOMEM; nft_rule_disactivate_next(ctx->net, rule); return 0; @@ -1819,10 +1830,10 @@ static int nf_tables_commit(struct sk_buff *skb) */ if (nft_rule_is_active(net, rupd->rule)) { nft_rule_clear(net, rupd->rule); - nf_tables_rule_notify(skb, rupd->nlh, rupd->table, - rupd->chain, rupd->rule, - NFT_MSG_NEWRULE, 0, - rupd->family); + nf_tables_rule_notify(skb, rupd->ctx.nlh, + rupd->ctx.table, rupd->ctx.chain, + rupd->rule, NFT_MSG_NEWRULE, 0, + rupd->ctx.afi->family); list_del(&rupd->list); kfree(rupd); continue; @@ -1830,9 +1841,10 @@ static int nf_tables_commit(struct sk_buff *skb) /* This rule is in the past, get rid of it */ list_del_rcu(&rupd->rule->list); - nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain, + nf_tables_rule_notify(skb, rupd->ctx.nlh, + rupd->ctx.table, rupd->ctx.chain, rupd->rule, NFT_MSG_DELRULE, 0, - rupd->family); + rupd->ctx.afi->family); } /* Make sure we don't see any packet traversing old rules */ @@ -1840,7 +1852,7 @@ static int nf_tables_commit(struct sk_buff *skb) /* Now we can safely release unused old rules */ list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(rupd->rule); + nf_tables_rule_destroy(&rupd->ctx, rupd->rule); list_del(&rupd->list); kfree(rupd); } @@ -1869,7 +1881,7 @@ static int nf_tables_abort(struct sk_buff *skb) synchronize_rcu(); list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(rupd->rule); + nf_tables_rule_destroy(&rupd->ctx, rupd->rule); list_del(&rupd->list); kfree(rupd); } @@ -2430,8 +2442,7 @@ err1: static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { list_del(&set->list); - if (!(set->flags & NFT_SET_ANONYMOUS)) - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); set->ops->destroy(set); module_put(set->ops->owner); @@ -3175,9 +3186,16 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: + default: + switch (data->verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; + default: + return -EINVAL; + } + /* fall through */ case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -3198,8 +3216,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->chain = chain; desc->len = sizeof(data); break; - default: - return -EINVAL; } desc->type = NFT_DATA_VERDICT; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 046aa13b4fea..e8138da4c14f 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -61,6 +61,14 @@ void nfnl_unlock(__u8 subsys_id) } EXPORT_SYMBOL_GPL(nfnl_unlock); +#ifdef CONFIG_PROVE_LOCKING +int lockdep_nfnl_is_held(u8 subsys_id) +{ + return lockdep_is_held(&table[subsys_id].mutex); +} +EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); +#endif + int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index a155d19a225e..d292c8d286eb 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -28,8 +28,6 @@ #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/list.h> -#include <linux/jhash.h> -#include <linux/random.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netfilter/nf_log.h> @@ -75,7 +73,6 @@ struct nfulnl_instance { }; #define INSTANCE_BUCKETS 16 -static unsigned int hash_init; static int nfnl_log_net_id __read_mostly; @@ -1067,11 +1064,6 @@ static int __init nfnetlink_log_init(void) { int status = -ENOMEM; - /* it's not really all that important to have a random value, so - * we can do this from the init function, even if there hasn't - * been that much entropy yet */ - get_random_bytes(&hash_init, sizeof(hash_init)); - netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); if (status < 0) { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 82cb8236f8a1..8a779be832fb 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -192,7 +192,7 @@ err: } static void -nft_target_destroy(const struct nft_expr *expr) +nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; @@ -379,7 +379,7 @@ err: } static void -nft_match_destroy(const struct nft_expr *expr) +nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_match *match = expr->ops->data; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46e275403838..bd0d41e69341 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -19,15 +19,15 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_labels.h> struct nft_ct { enum nft_ct_keys key:8; enum ip_conntrack_dir dir:8; - union{ + union { enum nft_registers dreg:8; enum nft_registers sreg:8; }; - uint8_t family; }; static void nft_ct_get_eval(const struct nft_expr *expr, @@ -97,6 +97,26 @@ static void nft_ct_get_eval(const struct nft_expr *expr, goto err; strncpy((char *)dest->data, helper->name, sizeof(dest->data)); return; +#ifdef CONFIG_NF_CONNTRACK_LABELS + case NFT_CT_LABELS: { + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + unsigned int size; + + if (!labels) { + memset(dest->data, 0, sizeof(dest->data)); + return; + } + + BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > sizeof(dest->data)); + size = labels->words * sizeof(long); + + memcpy(dest->data, labels->bits, size); + if (size < sizeof(dest->data)) + memset(((char *) dest->data) + size, 0, + sizeof(dest->data) - size); + return; + } +#endif } tuple = &ct->tuplehash[priv->dir].tuple; @@ -221,6 +241,9 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr, #ifdef CONFIG_NF_CONNTRACK_SECMARK case NFT_CT_SECMARK: #endif +#ifdef CONFIG_NF_CONNTRACK_LABELS + case NFT_CT_LABELS: +#endif case NFT_CT_EXPIRATION: case NFT_CT_HELPER: if (tb[NFTA_CT_DIRECTION] != NULL) @@ -292,16 +315,13 @@ static int nft_ct_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->family = ctx->afi->family; - return 0; } -static void nft_ct_destroy(const struct nft_expr *expr) +static void nft_ct_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { - struct nft_ct *priv = nft_expr_priv(expr); - - nft_ct_l3proto_module_put(priv->family); + nft_ct_l3proto_module_put(ctx->afi->family); } static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 3d3f8fce10a5..6a1acde16c60 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * 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 @@ -18,17 +18,29 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#define NFT_HASH_MIN_SIZE 4 + struct nft_hash { - struct hlist_head *hash; - unsigned int hsize; + struct nft_hash_table __rcu *tbl; +}; + +struct nft_hash_table { + unsigned int size; + unsigned int elements; + struct nft_hash_elem __rcu *buckets[]; }; struct nft_hash_elem { - struct hlist_node hnode; - struct nft_data key; - struct nft_data data[]; + struct nft_hash_elem __rcu *next; + struct nft_data key; + struct nft_data data[]; }; +#define nft_hash_for_each_entry(i, head) \ + for (i = nft_dereference(head); i != NULL; i = nft_dereference(i->next)) +#define nft_hash_for_each_entry_rcu(i, head) \ + for (i = rcu_dereference(head); i != NULL; i = rcu_dereference(i->next)) + static u32 nft_hash_rnd __read_mostly; static bool nft_hash_rnd_initted __read_mostly; @@ -38,7 +50,7 @@ static unsigned int nft_hash_data(const struct nft_data *data, unsigned int h; h = jhash(data->data, len, nft_hash_rnd); - return ((u64)h * hsize) >> 32; + return h & (hsize - 1); } static bool nft_hash_lookup(const struct nft_set *set, @@ -46,11 +58,12 @@ static bool nft_hash_lookup(const struct nft_set *set, struct nft_data *data) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = rcu_dereference(priv->tbl); const struct nft_hash_elem *he; unsigned int h; - h = nft_hash_data(key, priv->hsize, set->klen); - hlist_for_each_entry(he, &priv->hash[h], hnode) { + h = nft_hash_data(key, tbl->size, set->klen); + nft_hash_for_each_entry_rcu(he, tbl->buckets[h]) { if (nft_data_cmp(&he->key, key, set->klen)) continue; if (set->flags & NFT_SET_MAP) @@ -60,19 +73,148 @@ static bool nft_hash_lookup(const struct nft_set *set, return false; } -static void nft_hash_elem_destroy(const struct nft_set *set, - struct nft_hash_elem *he) +static void nft_hash_tbl_free(const struct nft_hash_table *tbl) { - nft_data_uninit(&he->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP) - nft_data_uninit(he->data, set->dtype); - kfree(he); + if (is_vmalloc_addr(tbl)) + vfree(tbl); + else + kfree(tbl); +} + +static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets) +{ + struct nft_hash_table *tbl; + size_t size; + + size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); + tbl = kzalloc(size, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN); + if (tbl == NULL) + tbl = vzalloc(size); + if (tbl == NULL) + return NULL; + tbl->size = nbuckets; + + return tbl; +} + +static void nft_hash_chain_unzip(const struct nft_set *set, + const struct nft_hash_table *ntbl, + struct nft_hash_table *tbl, unsigned int n) +{ + struct nft_hash_elem *he, *last, *next; + unsigned int h; + + he = nft_dereference(tbl->buckets[n]); + if (he == NULL) + return; + h = nft_hash_data(&he->key, ntbl->size, set->klen); + + /* Find last element of first chain hashing to bucket h */ + last = he; + nft_hash_for_each_entry(he, he->next) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) + break; + last = he; + } + + /* Unlink first chain from the old table */ + RCU_INIT_POINTER(tbl->buckets[n], last->next); + + /* If end of chain reached, done */ + if (he == NULL) + return; + + /* Find first element of second chain hashing to bucket h */ + next = NULL; + nft_hash_for_each_entry(he, he->next) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) + continue; + next = he; + break; + } + + /* Link the two chains */ + RCU_INIT_POINTER(last->next, next); +} + +static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv) +{ + struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; + struct nft_hash_elem *he; + unsigned int i, h; + bool complete; + + ntbl = nft_hash_tbl_alloc(tbl->size * 2); + if (ntbl == NULL) + return -ENOMEM; + + /* Link new table's buckets to first element in the old table + * hashing to the new bucket. + */ + for (i = 0; i < ntbl->size; i++) { + h = i < tbl->size ? i : i - tbl->size; + nft_hash_for_each_entry(he, tbl->buckets[h]) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != i) + continue; + RCU_INIT_POINTER(ntbl->buckets[i], he); + break; + } + } + ntbl->elements = tbl->elements; + + /* Publish new table */ + rcu_assign_pointer(priv->tbl, ntbl); + + /* Unzip interleaved hash chains */ + do { + /* Wait for readers to use new table/unzipped chains */ + synchronize_rcu(); + + complete = true; + for (i = 0; i < tbl->size; i++) { + nft_hash_chain_unzip(set, ntbl, tbl, i); + if (tbl->buckets[i] != NULL) + complete = false; + } + } while (!complete); + + nft_hash_tbl_free(tbl); + return 0; +} + +static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv) +{ + struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; + struct nft_hash_elem __rcu **pprev; + unsigned int i; + + ntbl = nft_hash_tbl_alloc(tbl->size / 2); + if (ntbl == NULL) + return -ENOMEM; + + for (i = 0; i < ntbl->size; i++) { + ntbl->buckets[i] = tbl->buckets[i]; + + for (pprev = &ntbl->buckets[i]; *pprev != NULL; + pprev = &nft_dereference(*pprev)->next) + ; + RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]); + } + ntbl->elements = tbl->elements; + + /* Publish new table */ + rcu_assign_pointer(priv->tbl, ntbl); + synchronize_rcu(); + + nft_hash_tbl_free(tbl); + return 0; } static int nft_hash_insert(const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_table *tbl = nft_dereference(priv->tbl); struct nft_hash_elem *he; unsigned int size, h; @@ -91,33 +233,66 @@ static int nft_hash_insert(const struct nft_set *set, if (set->flags & NFT_SET_MAP) nft_data_copy(he->data, &elem->data); - h = nft_hash_data(&he->key, priv->hsize, set->klen); - hlist_add_head_rcu(&he->hnode, &priv->hash[h]); + h = nft_hash_data(&he->key, tbl->size, set->klen); + RCU_INIT_POINTER(he->next, tbl->buckets[h]); + rcu_assign_pointer(tbl->buckets[h], he); + tbl->elements++; + + /* Expand table when exceeding 75% load */ + if (tbl->elements > tbl->size / 4 * 3) + nft_hash_tbl_expand(set, priv); + return 0; } +static void nft_hash_elem_destroy(const struct nft_set *set, + struct nft_hash_elem *he) +{ + nft_data_uninit(&he->key, NFT_DATA_VALUE); + if (set->flags & NFT_SET_MAP) + nft_data_uninit(he->data, set->dtype); + kfree(he); +} + static void nft_hash_remove(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_hash_elem *he = elem->cookie; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem *he, __rcu **pprev; - hlist_del_rcu(&he->hnode); + pprev = elem->cookie; + he = nft_dereference((*pprev)); + + RCU_INIT_POINTER(*pprev, he->next); + synchronize_rcu(); kfree(he); + tbl->elements--; + + /* Shrink table beneath 30% load */ + if (tbl->elements < tbl->size * 3 / 10 && + tbl->size > NFT_HASH_MIN_SIZE) + nft_hash_tbl_shrink(set, priv); } static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem __rcu * const *pprev; struct nft_hash_elem *he; unsigned int h; - h = nft_hash_data(&elem->key, priv->hsize, set->klen); - hlist_for_each_entry(he, &priv->hash[h], hnode) { - if (nft_data_cmp(&he->key, &elem->key, set->klen)) + h = nft_hash_data(&elem->key, tbl->size, set->klen); + pprev = &tbl->buckets[h]; + nft_hash_for_each_entry(he, tbl->buckets[h]) { + if (nft_data_cmp(&he->key, &elem->key, set->klen)) { + pprev = &he->next; continue; + } - elem->cookie = he; - elem->flags = 0; + elem->cookie = (void *)pprev; + elem->flags = 0; if (set->flags & NFT_SET_MAP) nft_data_copy(&elem->data, he->data); return 0; @@ -129,12 +304,13 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); const struct nft_hash_elem *he; struct nft_set_elem elem; unsigned int i; - for (i = 0; i < priv->hsize; i++) { - hlist_for_each_entry(he, &priv->hash[i], hnode) { + for (i = 0; i < tbl->size; i++) { + nft_hash_for_each_entry(he, tbl->buckets[i]) { if (iter->count < iter->skip) goto cont; @@ -161,43 +337,35 @@ static int nft_hash_init(const struct nft_set *set, const struct nlattr * const tb[]) { struct nft_hash *priv = nft_set_priv(set); - unsigned int cnt, i; + struct nft_hash_table *tbl; if (unlikely(!nft_hash_rnd_initted)) { get_random_bytes(&nft_hash_rnd, 4); nft_hash_rnd_initted = true; } - /* Aim for a load factor of 0.75 */ - // FIXME: temporarily broken until we have set descriptions - cnt = 100; - cnt = cnt * 4 / 3; - - priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL); - if (priv->hash == NULL) + tbl = nft_hash_tbl_alloc(NFT_HASH_MIN_SIZE); + if (tbl == NULL) return -ENOMEM; - priv->hsize = cnt; - - for (i = 0; i < cnt; i++) - INIT_HLIST_HEAD(&priv->hash[i]); - + RCU_INIT_POINTER(priv->tbl, tbl); return 0; } static void nft_hash_destroy(const struct nft_set *set) { const struct nft_hash *priv = nft_set_priv(set); - const struct hlist_node *next; - struct nft_hash_elem *elem; + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem *he, *next; unsigned int i; - for (i = 0; i < priv->hsize; i++) { - hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) { - hlist_del(&elem->hnode); - nft_hash_elem_destroy(set, elem); + for (i = 0; i < tbl->size; i++) { + for (he = nft_dereference(tbl->buckets[i]); he != NULL; + he = next) { + next = nft_dereference(he->next); + nft_hash_elem_destroy(set, he); } } - kfree(priv->hash); + kfree(tbl); } static struct nft_set_ops nft_hash_ops __read_mostly = { diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index f169501f1ad4..810385eb7249 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -70,7 +70,8 @@ err1: return err; } -static void nft_immediate_destroy(const struct nft_expr *expr) +static void nft_immediate_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg)); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 26c5154e05f3..10cfb156cdf4 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -74,7 +74,8 @@ static int nft_log_init(const struct nft_ctx *ctx, return 0; } -static void nft_log_destroy(const struct nft_expr *expr) +static void nft_log_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_log *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index bb4ef4cccb6e..7fd2bea8aa23 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -89,11 +89,12 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_destroy(const struct nft_expr *expr) +static void nft_lookup_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(NULL, priv->set, &priv->binding); + nf_tables_unbind_set(ctx, priv->set, &priv->binding); } static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e8254ad2e5a9..425cf39af890 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -116,7 +116,7 @@ static void nft_meta_get_eval(const struct nft_expr *expr, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); break; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: { const struct dst_entry *dst = skb_dst(skb); @@ -199,7 +199,7 @@ static int nft_meta_init_validate_get(uint32_t key) case NFT_META_OIFTYPE: case NFT_META_SKUID: case NFT_META_SKGID: -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: #endif #ifdef CONFIG_NETWORK_SECMARK diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index d3b1ffe26181..a0195d28bcfc 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -31,8 +31,8 @@ struct nft_nat { enum nft_registers sreg_addr_max:8; enum nft_registers sreg_proto_min:8; enum nft_registers sreg_proto_max:8; - int family; - enum nf_nat_manip_type type; + enum nf_nat_manip_type type:8; + u8 family; }; static void nft_nat_eval(const struct nft_expr *expr, @@ -88,6 +88,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_nat *priv = nft_expr_priv(expr); + u32 family; int err; if (tb[NFTA_NAT_TYPE] == NULL) @@ -107,9 +108,12 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (tb[NFTA_NAT_FAMILY] == NULL) return -EINVAL; - priv->family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY])); - if (priv->family != AF_INET && priv->family != AF_INET6) - return -EINVAL; + family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY])); + if (family != AF_INET && family != AF_INET6) + return -EAFNOSUPPORT; + if (family != ctx->afi->family) + return -EOPNOTSUPP; + priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { priv->sreg_addr_min = ntohl(nla_get_be32( @@ -202,13 +206,7 @@ static struct nft_expr_type nft_nat_type __read_mostly = { static int __init nft_nat_module_init(void) { - int err; - - err = nft_register_expr(&nft_nat_type); - if (err < 0) - return err; - - return 0; + return nft_register_expr(&nft_nat_type); } static void __exit nft_nat_module_exit(void) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a2aeb318678f..85daa84bfdfe 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data)) return ERR_PTR(-EINVAL); - if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) + if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && + base != NFT_PAYLOAD_LL_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 8a310f239c93..b718a52a4654 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -21,9 +21,9 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, { switch (pkt->ops->pf) { case NFPROTO_IPV4: - nft_reject_ipv4_eval(expr, data, pkt); + return nft_reject_ipv4_eval(expr, data, pkt); case NFPROTO_IPV6: - nft_reject_ipv6_eval(expr, data, pkt); + return nft_reject_ipv6_eval(expr, data, pkt); } } diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index 3228d7f24eb4..4973cbddc446 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -146,11 +146,11 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->family == NFPROTO_BRIDGE) { switch (eth_hdr(skb)->h_proto) { - case __constant_htons(ETH_P_IP): + case htons(ETH_P_IP): audit_ip4(ab, skb); break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): audit_ip6(ab, skb); break; } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index c40b2695633b..458464e7bd7a 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -19,6 +19,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/rbtree.h> #include <linux/module.h> #include <linux/random.h> #include <linux/skbuff.h> @@ -31,6 +32,10 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_zones.h> +#define CONNLIMIT_SLOTS 32 +#define CONNLIMIT_LOCK_SLOTS 32 +#define CONNLIMIT_GC_MAX_NODES 8 + /* we will save the tuples of all connections we care about */ struct xt_connlimit_conn { struct hlist_node node; @@ -38,16 +43,26 @@ struct xt_connlimit_conn { union nf_inet_addr addr; }; +struct xt_connlimit_rb { + struct rb_node node; + struct hlist_head hhead; /* connections/hosts in same subnet */ + union nf_inet_addr addr; /* search key */ +}; + struct xt_connlimit_data { - struct hlist_head iphash[256]; - spinlock_t lock; + struct rb_root climit_root4[CONNLIMIT_SLOTS]; + struct rb_root climit_root6[CONNLIMIT_SLOTS]; + spinlock_t locks[CONNLIMIT_LOCK_SLOTS]; }; static u_int32_t connlimit_rnd __read_mostly; +static struct kmem_cache *connlimit_rb_cachep __read_mostly; +static struct kmem_cache *connlimit_conn_cachep __read_mostly; static inline unsigned int connlimit_iphash(__be32 addr) { - return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF; + return jhash_1word((__force __u32)addr, + connlimit_rnd) % CONNLIMIT_SLOTS; } static inline unsigned int @@ -60,7 +75,8 @@ connlimit_iphash6(const union nf_inet_addr *addr, for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) res.ip6[i] = addr->ip6[i] & mask->ip6[i]; - return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF; + return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), + connlimit_rnd) % CONNLIMIT_SLOTS; } static inline bool already_closed(const struct nf_conn *conn) @@ -72,13 +88,14 @@ static inline bool already_closed(const struct nf_conn *conn) return 0; } -static inline unsigned int +static int same_source_net(const union nf_inet_addr *addr, const union nf_inet_addr *mask, const union nf_inet_addr *u3, u_int8_t family) { if (family == NFPROTO_IPV4) { - return (addr->ip & mask->ip) == (u3->ip & mask->ip); + return ntohl(addr->ip & mask->ip) - + ntohl(u3->ip & mask->ip); } else { union nf_inet_addr lh, rh; unsigned int i; @@ -88,89 +105,205 @@ same_source_net(const union nf_inet_addr *addr, rh.ip6[i] = u3->ip6[i] & mask->ip6[i]; } - return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0; + return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)); } } -static int count_them(struct net *net, - struct xt_connlimit_data *data, +static bool add_hlist(struct hlist_head *head, const struct nf_conntrack_tuple *tuple, - const union nf_inet_addr *addr, - const union nf_inet_addr *mask, - u_int8_t family) + const union nf_inet_addr *addr) +{ + struct xt_connlimit_conn *conn; + + conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC); + if (conn == NULL) + return false; + conn->tuple = *tuple; + conn->addr = *addr; + hlist_add_head(&conn->node, head); + return true; +} + +static unsigned int check_hlist(struct net *net, + struct hlist_head *head, + const struct nf_conntrack_tuple *tuple, + bool *addit) { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; struct hlist_node *n; struct nf_conn *found_ct; - struct hlist_head *hash; - bool addit = true; - int matches = 0; - - if (family == NFPROTO_IPV6) - hash = &data->iphash[connlimit_iphash6(addr, mask)]; - else - hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)]; + unsigned int length = 0; + *addit = true; rcu_read_lock(); /* check the saved connections */ - hlist_for_each_entry_safe(conn, n, hash, node) { + hlist_for_each_entry_safe(conn, n, head, node) { found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, &conn->tuple); - found_ct = NULL; + if (found == NULL) { + hlist_del(&conn->node); + kmem_cache_free(connlimit_conn_cachep, conn); + continue; + } - if (found != NULL) - found_ct = nf_ct_tuplehash_to_ctrack(found); + found_ct = nf_ct_tuplehash_to_ctrack(found); - if (found_ct != NULL && - nf_ct_tuple_equal(&conn->tuple, tuple) && - !already_closed(found_ct)) + if (nf_ct_tuple_equal(&conn->tuple, tuple)) { /* * Just to be sure we have it only once in the list. * We should not see tuples twice unless someone hooks * this into a table without "-p tcp --syn". */ - addit = false; - - if (found == NULL) { - /* this one is gone */ - hlist_del(&conn->node); - kfree(conn); - continue; - } - - if (already_closed(found_ct)) { + *addit = false; + } else if (already_closed(found_ct)) { /* * we do not care about connections which are * closed already -> ditch it */ nf_ct_put(found_ct); hlist_del(&conn->node); - kfree(conn); + kmem_cache_free(connlimit_conn_cachep, conn); continue; } - if (same_source_net(addr, mask, &conn->addr, family)) - /* same source network -> be counted! */ - ++matches; nf_ct_put(found_ct); + length++; } rcu_read_unlock(); - if (addit) { - /* save the new connection in our list */ - conn = kmalloc(sizeof(*conn), GFP_ATOMIC); - if (conn == NULL) - return -ENOMEM; - conn->tuple = *tuple; - conn->addr = *addr; - hlist_add_head(&conn->node, hash); - ++matches; + return length; +} + +static void tree_nodes_free(struct rb_root *root, + struct xt_connlimit_rb *gc_nodes[], + unsigned int gc_count) +{ + struct xt_connlimit_rb *rbconn; + + while (gc_count) { + rbconn = gc_nodes[--gc_count]; + rb_erase(&rbconn->node, root); + kmem_cache_free(connlimit_rb_cachep, rbconn); + } +} + +static unsigned int +count_tree(struct net *net, struct rb_root *root, + const struct nf_conntrack_tuple *tuple, + const union nf_inet_addr *addr, const union nf_inet_addr *mask, + u8 family) +{ + struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES]; + struct rb_node **rbnode, *parent; + struct xt_connlimit_rb *rbconn; + struct xt_connlimit_conn *conn; + unsigned int gc_count; + bool no_gc = false; + + restart: + gc_count = 0; + parent = NULL; + rbnode = &(root->rb_node); + while (*rbnode) { + int diff; + bool addit; + + rbconn = container_of(*rbnode, struct xt_connlimit_rb, node); + + parent = *rbnode; + diff = same_source_net(addr, mask, &rbconn->addr, family); + if (diff < 0) { + rbnode = &((*rbnode)->rb_left); + } else if (diff > 0) { + rbnode = &((*rbnode)->rb_right); + } else { + /* same source network -> be counted! */ + unsigned int count; + count = check_hlist(net, &rbconn->hhead, tuple, &addit); + + tree_nodes_free(root, gc_nodes, gc_count); + if (!addit) + return count; + + if (!add_hlist(&rbconn->hhead, tuple, addr)) + return 0; /* hotdrop */ + + return count + 1; + } + + if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes)) + continue; + + /* only used for GC on hhead, retval and 'addit' ignored */ + check_hlist(net, &rbconn->hhead, tuple, &addit); + if (hlist_empty(&rbconn->hhead)) + gc_nodes[gc_count++] = rbconn; + } + + if (gc_count) { + no_gc = true; + tree_nodes_free(root, gc_nodes, gc_count); + /* tree_node_free before new allocation permits + * allocator to re-use newly free'd object. + * + * This is a rare event; in most cases we will find + * existing node to re-use. (or gc_count is 0). + */ + goto restart; + } + + /* no match, need to insert new node */ + rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC); + if (rbconn == NULL) + return 0; + + conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC); + if (conn == NULL) { + kmem_cache_free(connlimit_rb_cachep, rbconn); + return 0; + } + + conn->tuple = *tuple; + conn->addr = *addr; + rbconn->addr = *addr; + + INIT_HLIST_HEAD(&rbconn->hhead); + hlist_add_head(&conn->node, &rbconn->hhead); + + rb_link_node(&rbconn->node, parent, rbnode); + rb_insert_color(&rbconn->node, root); + return 1; +} + +static int count_them(struct net *net, + struct xt_connlimit_data *data, + const struct nf_conntrack_tuple *tuple, + const union nf_inet_addr *addr, + const union nf_inet_addr *mask, + u_int8_t family) +{ + struct rb_root *root; + int count; + u32 hash; + + if (family == NFPROTO_IPV6) { + hash = connlimit_iphash6(addr, mask); + root = &data->climit_root6[hash]; + } else { + hash = connlimit_iphash(addr->ip & mask->ip); + root = &data->climit_root4[hash]; } - return matches; + spin_lock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]); + + count = count_tree(net, root, tuple, addr, mask, family); + + spin_unlock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]); + + return count; } static bool @@ -183,7 +316,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct nf_conntrack_tuple *tuple_ptr = &tuple; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; - int connections; + unsigned int connections; ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) @@ -202,12 +335,9 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) iph->daddr : iph->saddr; } - spin_lock_bh(&info->data->lock); connections = count_them(net, info->data, tuple_ptr, &addr, &info->mask, par->family); - spin_unlock_bh(&info->data->lock); - - if (connections < 0) + if (connections == 0) /* kmalloc failed, drop it entirely */ goto hotdrop; @@ -247,29 +377,47 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) return -ENOMEM; } - spin_lock_init(&info->data->lock); - for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) - INIT_HLIST_HEAD(&info->data->iphash[i]); + for (i = 0; i < ARRAY_SIZE(info->data->locks); ++i) + spin_lock_init(&info->data->locks[i]); + + for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i) + info->data->climit_root4[i] = RB_ROOT; + for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i) + info->data->climit_root6[i] = RB_ROOT; return 0; } -static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) +static void destroy_tree(struct rb_root *r) { - const struct xt_connlimit_info *info = par->matchinfo; struct xt_connlimit_conn *conn; + struct xt_connlimit_rb *rbconn; struct hlist_node *n; - struct hlist_head *hash = info->data->iphash; + struct rb_node *node; + + while ((node = rb_first(r)) != NULL) { + rbconn = container_of(node, struct xt_connlimit_rb, node); + + rb_erase(node, r); + + hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) + kmem_cache_free(connlimit_conn_cachep, conn); + + kmem_cache_free(connlimit_rb_cachep, rbconn); + } +} + +static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_connlimit_info *info = par->matchinfo; unsigned int i; nf_ct_l3proto_module_put(par->family); - for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { - hlist_for_each_entry_safe(conn, n, &hash[i], node) { - hlist_del(&conn->node); - kfree(conn); - } - } + for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i) + destroy_tree(&info->data->climit_root4[i]); + for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i) + destroy_tree(&info->data->climit_root6[i]); kfree(info->data); } @@ -287,12 +435,37 @@ static struct xt_match connlimit_mt_reg __read_mostly = { static int __init connlimit_mt_init(void) { - return xt_register_match(&connlimit_mt_reg); + int ret; + + BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS); + BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0); + + connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn", + sizeof(struct xt_connlimit_conn), + 0, 0, NULL); + if (!connlimit_conn_cachep) + return -ENOMEM; + + connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb", + sizeof(struct xt_connlimit_rb), + 0, 0, NULL); + if (!connlimit_rb_cachep) { + kmem_cache_destroy(connlimit_conn_cachep); + return -ENOMEM; + } + ret = xt_register_match(&connlimit_mt_reg); + if (ret != 0) { + kmem_cache_destroy(connlimit_conn_cachep); + kmem_cache_destroy(connlimit_rb_cachep); + } + return ret; } static void __exit connlimit_mt_exit(void) { xt_unregister_match(&connlimit_mt_reg); + kmem_cache_destroy(connlimit_conn_cachep); + kmem_cache_destroy(connlimit_rb_cachep); } module_init(connlimit_mt_init); diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c index a4c7561698c5..89d53104c6b3 100644 --- a/net/netfilter/xt_ipcomp.c +++ b/net/netfilter/xt_ipcomp.c @@ -60,7 +60,7 @@ static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par) } return spi_match(compinfo->spis[0], compinfo->spis[1], - ntohl(chdr->cpi << 16), + ntohs(chdr->cpi), !!(compinfo->invflags & XT_IPCOMP_INV_SPI)); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e42214b932c3..c2d585c4f7c5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1489,8 +1489,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family != AF_NETLINK) return -EINVAL; - /* Only superuser is allowed to send multicasts */ - if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + if ((nladdr->nl_groups || nladdr->nl_pid) && + !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -2343,6 +2343,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif + /* Record the max length of recvmsg() calls for future allocations */ + nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); + nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, + 16384); + copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; @@ -2587,7 +2592,27 @@ static int netlink_dump(struct sock *sk) if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; - skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + + /* NLMSG_GOODSIZE is small to avoid high order allocations being + * required, but it makes sense to _attempt_ a 16K bytes allocation + * to reduce number of system calls on dump operations, if user + * ever provided a big enough buffer. + */ + if (alloc_size < nlk->max_recvmsg_len) { + skb = netlink_alloc_skb(sk, + nlk->max_recvmsg_len, + nlk->portid, + GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); + /* available room should be exact amount to avoid MSG_TRUNC */ + if (skb) + skb_reserve(skb, skb_tailroom(skb) - + nlk->max_recvmsg_len); + } + if (!skb) + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, + GFP_KERNEL); if (!skb) goto errout_skb; netlink_skb_set_owner_r(skb, sk); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index acbd774eeb7c..ed13a790b00e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -31,6 +31,7 @@ struct netlink_sock { u32 ngroups; unsigned long *groups; unsigned long state; + size_t max_recvmsg_len; wait_queue_head_t wait; bool cb_running; struct netlink_callback cb; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 46bda010bf11..56db888b1cd5 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -301,7 +301,7 @@ static int nci_open_device(struct nci_dev *ndev) rc = __nci_request(ndev, nci_reset_req, 0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); - if (ndev->ops->setup(ndev)) + if (ndev->ops->setup) ndev->ops->setup(ndev); if (!rc) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 36f8872cb072..c53fe0c9697c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -606,9 +606,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, percpu_stats = per_cpu_ptr(dp->stats_percpu, i); do { - start = u64_stats_fetch_begin_bh(&percpu_stats->syncp); + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); stats->n_hit += local_stats.n_hit; stats->n_missed += local_stats.n_missed; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 3b4db3220456..42c0f4a0b78c 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -277,9 +277,9 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) percpu_stats = per_cpu_ptr(vport->percpu_stats, i); do { - start = u64_stats_fetch_begin_bh(&percpu_stats->syncp); + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); stats->rx_bytes += local_stats.rx_bytes; stats->rx_packets += local_stats.rx_packets; diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index d1c3429b69ed..ec126f91276b 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -20,9 +20,8 @@ af-rxrpc-y := \ ar-skbuff.o \ ar-transport.o -ifeq ($(CONFIG_PROC_FS),y) -af-rxrpc-y += ar-proc.o -endif +af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o +af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e61aa6001c65..7b1670489638 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -838,6 +838,12 @@ static int __init af_rxrpc_init(void) goto error_key_type_s; } + ret = rxrpc_sysctl_init(); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: Cannot register sysctls\n"); + goto error_sysctls; + } + #ifdef CONFIG_PROC_FS proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops); proc_create("rxrpc_conns", 0, init_net.proc_net, @@ -845,6 +851,8 @@ static int __init af_rxrpc_init(void) #endif return 0; +error_sysctls: + unregister_key_type(&key_type_rxrpc_s); error_key_type_s: unregister_key_type(&key_type_rxrpc); error_key_type: @@ -865,6 +873,7 @@ error_call_jar: static void __exit af_rxrpc_exit(void) { _enter(""); + rxrpc_sysctl_exit(); unregister_key_type(&key_type_rxrpc_s); unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index cd97a0ce48d8..c6be17a959a6 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -19,7 +19,49 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -static unsigned int rxrpc_ack_defer = 1; +/* + * How long to wait before scheduling ACK generation after seeing a + * packet with RXRPC_REQUEST_ACK set (in jiffies). + */ +unsigned rxrpc_requested_ack_delay = 1; + +/* + * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * + * We use this when we've received new data packets. If those packets aren't + * all consumed within this time we will send a DELAY ACK if an ACK was not + * requested to let the sender know it doesn't need to resend. + */ +unsigned rxrpc_soft_ack_delay = 1 * HZ; + +/* + * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * + * We use this when we've consumed some previously soft-ACK'd packets when + * further packets aren't immediately received to decide when to send an IDLE + * ACK let the other end know that it can free up its Tx buffer space. + */ +unsigned rxrpc_idle_ack_delay = 0.5 * HZ; + +/* + * Receive window size in packets. This indicates the maximum number of + * unconsumed received packets we're willing to retain in memory. Once this + * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further + * packets. + */ +unsigned rxrpc_rx_window_size = 32; + +/* + * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet + * made by gluing normal packets together that we're willing to handle. + */ +unsigned rxrpc_rx_mtu = 5692; + +/* + * The maximum number of fragments in a received jumbo packet that we tell the + * sender that we're willing to handle. + */ +unsigned rxrpc_rx_jumbo_max = 4; static const char *rxrpc_acks(u8 reason) { @@ -82,24 +124,23 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, switch (ack_reason) { case RXRPC_ACK_DELAY: _debug("run delay timer"); - call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ; - add_timer(&call->ack_timer); - return; + expiry = rxrpc_soft_ack_delay; + goto run_timer; case RXRPC_ACK_IDLE: if (!immediate) { _debug("run defer timer"); - expiry = 1; + expiry = rxrpc_idle_ack_delay; goto run_timer; } goto cancel_timer; case RXRPC_ACK_REQUESTED: - if (!rxrpc_ack_defer) + expiry = rxrpc_requested_ack_delay; + if (!expiry) goto cancel_timer; if (!immediate || serial == cpu_to_be32(1)) { _debug("run defer timer"); - expiry = rxrpc_ack_defer; goto run_timer; } @@ -1174,11 +1215,11 @@ send_ACK: mtu = call->conn->trans->peer->if_mtu; mtu -= call->conn->trans->peer->hdrsize; ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(32); + ackinfo.rwind = htonl(rxrpc_rx_window_size); /* permit the peer to send us jumbo packets if it wants to */ - ackinfo.rxMTU = htonl(5692); - ackinfo.jumbo_max = htonl(4); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max); hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index a3bbb360a3f9..a9e05db0f5d5 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -12,10 +12,22 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/circ_buf.h> +#include <linux/hashtable.h> +#include <linux/spinlock_types.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Maximum lifetime of a call (in jiffies). + */ +unsigned rxrpc_max_call_lifetime = 60 * HZ; + +/* + * Time till dead call expires after last use (in jiffies). + */ +unsigned rxrpc_dead_call_expiry = 2 * HZ; + const char *const rxrpc_call_states[] = { [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", @@ -38,8 +50,6 @@ const char *const rxrpc_call_states[] = { struct kmem_cache *rxrpc_call_jar; LIST_HEAD(rxrpc_calls); DEFINE_RWLOCK(rxrpc_call_lock); -static unsigned int rxrpc_call_max_lifetime = 60; -static unsigned int rxrpc_dead_call_timeout = 2; static void rxrpc_destroy_call(struct work_struct *work); static void rxrpc_call_life_expired(unsigned long _call); @@ -47,6 +57,145 @@ 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 DEFINE_SPINLOCK(rxrpc_call_hash_lock); +static DEFINE_HASHTABLE(rxrpc_call_hash, 10); + +/* + * Hash function for rxrpc_call_hash + */ +static unsigned long rxrpc_call_hashfunc( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + sa_family_t proto, + void *localptr, + unsigned int addr_size, + const u8 *peer_addr) +{ + const u16 *p; + unsigned int i; + unsigned long key; + u32 hcid = ntohl(cid); + + _enter(""); + + key = (unsigned long)localptr; + /* We just want to add up the __be32 values, so forcing the + * cast should be okay. + */ + key += (__force u32)epoch; + key += (__force u16)service_id; + key += (__force u32)call_id; + key += (hcid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT; + key += hcid & RXRPC_CHANNELMASK; + key += clientflag; + key += proto; + /* Step through the peer address in 16-bit portions for speed */ + for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++) + key += *p; + _leave(" key = 0x%lx", key); + return key; +} + +/* + * Add a call to the hashtable + */ +static void rxrpc_call_hash_add(struct rxrpc_call *call) +{ + unsigned long key; + unsigned int addr_size = 0; + + _enter(""); + switch (call->proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + key = rxrpc_call_hashfunc(call->in_clientflag, call->cid, + call->call_id, call->epoch, + call->service_id, call->proto, + call->conn->trans->local, addr_size, + call->peer_ip.ipv6_addr); + /* Store the full key in the call */ + call->hash_key = key; + spin_lock(&rxrpc_call_hash_lock); + hash_add_rcu(rxrpc_call_hash, &call->hash_node, key); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Remove a call from the hashtable + */ +static void rxrpc_call_hash_del(struct rxrpc_call *call) +{ + _enter(""); + spin_lock(&rxrpc_call_hash_lock); + hash_del_rcu(&call->hash_node); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Find a call in the hashtable and return it, or NULL if it + * isn't there. + */ +struct rxrpc_call *rxrpc_find_call_hash( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + void *localptr, + sa_family_t proto, + const u8 *peer_addr) +{ + unsigned long key; + unsigned int addr_size = 0; + struct rxrpc_call *call = NULL; + struct rxrpc_call *ret = NULL; + + _enter(""); + switch (proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + + key = rxrpc_call_hashfunc(clientflag, cid, call_id, epoch, + service_id, proto, localptr, addr_size, + peer_addr); + hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) { + if (call->hash_key == key && + call->call_id == call_id && + call->cid == cid && + call->in_clientflag == clientflag && + call->service_id == service_id && + call->proto == proto && + call->local == localptr && + memcmp(call->peer_ip.ipv6_addr, peer_addr, + addr_size) == 0 && + call->epoch == epoch) { + ret = call; + break; + } + } + _leave(" = %p", ret); + return ret; +} + /* * allocate a new call */ @@ -91,7 +240,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) 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_MAXACKS; + call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size; call->creation_jif = jiffies; return call; } @@ -128,11 +277,31 @@ static struct rxrpc_call *rxrpc_alloc_client_call( return ERR_PTR(ret); } + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + } + call->epoch = call->conn->epoch; + call->service_id = call->conn->service_id; + call->in_clientflag = call->conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + spin_lock(&call->conn->trans->peer->lock); list_add(&call->error_link, &call->conn->trans->peer->error_targets); spin_unlock(&call->conn->trans->peer->lock); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p", call); @@ -320,9 +489,12 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, parent = *p; call = rb_entry(parent, struct rxrpc_call, conn_node); - if (call_id < call->call_id) + /* The tree is sorted in order of the __be32 value without + * turning it into host order. + */ + if ((__force u32)call_id < (__force u32)call->call_id) p = &(*p)->rb_left; - else if (call_id > call->call_id) + else if ((__force u32)call_id > (__force u32)call->call_id) p = &(*p)->rb_right; else goto old_call; @@ -347,9 +519,31 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = conn->trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + conn->trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + default: + break; + } + call->epoch = conn->epoch; + call->service_id = conn->service_id; + call->in_clientflag = conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p {%d} [new]", call, call->debug_id); return call; @@ -533,7 +727,7 @@ void rxrpc_release_call(struct rxrpc_call *call) del_timer_sync(&call->resend_timer); del_timer_sync(&call->ack_timer); del_timer_sync(&call->lifetimer); - call->deadspan.expires = jiffies + rxrpc_dead_call_timeout * HZ; + call->deadspan.expires = jiffies + rxrpc_dead_call_expiry; add_timer(&call->deadspan); _leave(""); @@ -665,6 +859,9 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_connection(call->conn); } + /* Remove the call from the hash */ + rxrpc_call_hash_del(call); + if (call->acks_window) { _debug("kill Tx window %d", CIRC_CNT(call->acks_head, call->acks_tail, diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 7bf5b5b9e8b9..6631f4f1e39b 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -18,11 +18,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time till a connection expires after last use (in seconds). + */ +unsigned rxrpc_connection_expiry = 10 * 60; + static void rxrpc_connection_reaper(struct work_struct *work); LIST_HEAD(rxrpc_connections); DEFINE_RWLOCK(rxrpc_connection_lock); -static unsigned long rxrpc_connection_timeout = 10 * 60; static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); /* @@ -862,7 +866,7 @@ static void rxrpc_connection_reaper(struct work_struct *work) spin_lock(&conn->trans->client_lock); write_lock(&conn->trans->conn_lock); - reap_time = conn->put_time + rxrpc_connection_timeout; + reap_time = conn->put_time + rxrpc_connection_expiry; if (atomic_read(&conn->usage) > 0) { ; @@ -916,7 +920,7 @@ void __exit rxrpc_destroy_all_connections(void) { _enter(""); - rxrpc_connection_timeout = 0; + rxrpc_connection_expiry = 0; cancel_delayed_work(&rxrpc_connection_reap); rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index a9206087b4d7..db57458c824c 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -83,6 +83,7 @@ void rxrpc_UDP_error_report(struct sock *sk) if (mtu == 0) { /* they didn't give us a size, estimate one */ + mtu = peer->if_mtu; if (mtu > 1500) { mtu >>= 1; if (mtu < 1500) diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 529572f18d1f..73742647c135 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -25,8 +25,6 @@ #include <net/net_namespace.h> #include "ar-internal.h" -unsigned long rxrpc_ack_timeout = 1; - const char *rxrpc_pkts[] = { "?00", "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", @@ -349,8 +347,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) * it */ if (sp->hdr.flags & RXRPC_REQUEST_ACK) { _proto("ACK Requested on %%%u", serial); - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, - !(sp->hdr.flags & RXRPC_MORE_PACKETS)); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false); } switch (sp->hdr.type) { @@ -526,36 +523,38 @@ protocol_error: * 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 */ -static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_call(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp; - struct rxrpc_call *call; - struct rb_node *p; - __be32 call_id; - - _enter("%p,%p", conn, skb); - read_lock_bh(&conn->lock); + _enter("%p,%p", call, skb); sp = rxrpc_skb(skb); - /* look at extant calls by channel number first */ - call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK]; - if (!call || call->call_id != sp->hdr.callNumber) - goto call_not_extant; - _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_ABORT, &call->events)) + if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) { rxrpc_queue_call(call); + goto free_unlock; + } case RXRPC_CALL_REMOTELY_ABORTED: case RXRPC_CALL_NETWORK_ERROR: case RXRPC_CALL_DEAD: + goto dead_call; + case RXRPC_CALL_COMPLETE: + case RXRPC_CALL_CLIENT_FINAL_ACK: + /* complete server call */ + if (call->conn->in_clientflag) + goto dead_call; + /* resend last packet of a completed call */ + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_ACK_FINAL, &call->events); + rxrpc_queue_call(call); goto free_unlock; default: break; @@ -563,7 +562,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, read_unlock(&call->state_lock); rxrpc_get_call(call); - read_unlock_bh(&conn->lock); if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.flags & RXRPC_JUMBO_PACKET) @@ -574,78 +572,16 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, rxrpc_put_call(call); goto done; -call_not_extant: - /* search the completed calls in case what we're dealing with is - * there */ - _debug("call not extant"); - - call_id = sp->hdr.callNumber; - p = conn->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, conn_node); - - if (call_id < call->call_id) - p = p->rb_left; - else if (call_id > call->call_id) - p = p->rb_right; - else - goto found_completed_call; - } - dead_call: - /* it's a either a really old call that we no longer remember or its a - * new incoming call */ - read_unlock_bh(&conn->lock); - - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && - sp->hdr.seq == cpu_to_be32(1)) { - _debug("incoming call"); - skb_queue_tail(&conn->trans->local->accept_queue, skb); - rxrpc_queue_work(&conn->trans->local->acceptor); - goto done; - } - - _debug("dead call"); - skb->priority = RX_CALL_DEAD; - rxrpc_reject_packet(conn->trans->local, skb); - goto done; - - /* resend last packet of a completed call - * - client calls may have been aborted or ACK'd - * - server calls may have been aborted - */ -found_completed_call: - _debug("completed call"); - - if (atomic_read(&call->usage) == 0) - goto dead_call; - - /* synchronise any state changes */ - read_lock(&call->state_lock); - ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK, - call->state, >=, RXRPC_CALL_COMPLETE); - - if (call->state == RXRPC_CALL_LOCALLY_ABORTED || - call->state == RXRPC_CALL_REMOTELY_ABORTED || - call->state == RXRPC_CALL_DEAD) { - read_unlock(&call->state_lock); - goto dead_call; - } - - if (call->conn->in_clientflag) { - read_unlock(&call->state_lock); - goto dead_call; /* complete server call */ + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + skb->priority = RX_CALL_DEAD; + rxrpc_reject_packet(call->conn->trans->local, skb); + goto unlock; } - - _debug("final ack again"); - rxrpc_get_call(call); - set_bit(RXRPC_CALL_ACK_FINAL, &call->events); - rxrpc_queue_call(call); - free_unlock: - read_unlock(&call->state_lock); - read_unlock_bh(&conn->lock); rxrpc_free_skb(skb); +unlock: + read_unlock(&call->state_lock); done: _leave(""); } @@ -664,17 +600,42 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, rxrpc_queue_conn(conn); } +static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local, + struct sk_buff *skb, + struct rxrpc_skb_priv *sp) +{ + struct rxrpc_peer *peer; + struct rxrpc_transport *trans; + struct rxrpc_connection *conn; + + peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, + udp_hdr(skb)->source); + if (IS_ERR(peer)) + goto cant_find_conn; + + trans = rxrpc_find_transport(local, peer); + rxrpc_put_peer(peer); + if (!trans) + goto cant_find_conn; + + conn = rxrpc_find_connection(trans, &sp->hdr); + rxrpc_put_transport(trans); + if (!conn) + goto cant_find_conn; + + return conn; +cant_find_conn: + return NULL; +} + /* * handle data received on the local endpoint * - may be called in interrupt context */ void rxrpc_data_ready(struct sock *sk, int count) { - struct rxrpc_connection *conn; - struct rxrpc_transport *trans; struct rxrpc_skb_priv *sp; struct rxrpc_local *local; - struct rxrpc_peer *peer; struct sk_buff *skb; int ret; @@ -749,27 +710,34 @@ void rxrpc_data_ready(struct sock *sk, int count) (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) goto bad_message; - peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source); - if (IS_ERR(peer)) - goto cant_route_call; + if (sp->hdr.callNumber == 0) { + /* This is a connection-level packet. These should be + * fairly rare, so the extra overhead of looking them up the + * old-fashioned way doesn't really hurt */ + struct rxrpc_connection *conn; - trans = rxrpc_find_transport(local, peer); - rxrpc_put_peer(peer); - if (!trans) - goto cant_route_call; + conn = rxrpc_conn_from_local(local, skb, sp); + if (!conn) + goto cant_route_call; - conn = rxrpc_find_connection(trans, &sp->hdr); - rxrpc_put_transport(trans); - if (!conn) - goto cant_route_call; - - _debug("CONN %p {%d}", conn, conn->debug_id); - - if (sp->hdr.callNumber == 0) + _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - else - rxrpc_post_packet_to_call(conn, skb); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn); + } else { + struct rxrpc_call *call; + u8 in_clientflag = 0; + + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + in_clientflag = RXRPC_CLIENT_INITIATED; + call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid, + sp->hdr.callNumber, sp->hdr.epoch, + sp->hdr.serviceId, local, AF_INET, + (u8 *)&ip_hdr(skb)->saddr); + if (call) + rxrpc_post_packet_to_call(call, skb); + else + goto cant_route_call; + } rxrpc_put_local(local); return; @@ -790,8 +758,10 @@ cant_route_call: skb->priority = RX_CALL_DEAD; } - _debug("reject"); - rxrpc_reject_packet(local, skb); + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + _debug("reject type %d",sp->hdr.type); + rxrpc_reject_packet(local, skb); + } rxrpc_put_local(local); _leave(" [no call]"); return; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5f43675ee1df..c831d44b0841 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -396,9 +396,20 @@ struct rxrpc_call { #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; + struct hlist_node hash_node; + unsigned long hash_key; /* Full hash key */ + u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */ + struct rxrpc_local *local; /* Local endpoint. Used for hashing. */ + sa_family_t proto; /* Frame protocol */ /* the following should all be in net order */ __be32 cid; /* connection ID + channel index */ __be32 call_id; /* call ID on connection */ + __be32 epoch; /* epoch of this connection */ + __be16 service_id; /* service ID */ + union { /* Peer IP address for hashing */ + __be32 ipv4_addr; + __u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */ + } peer_ip; }; /* @@ -433,6 +444,13 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * ar-ack.c */ +extern unsigned rxrpc_requested_ack_delay; +extern unsigned rxrpc_soft_ack_delay; +extern unsigned rxrpc_idle_ack_delay; +extern unsigned rxrpc_rx_window_size; +extern unsigned rxrpc_rx_mtu; +extern unsigned rxrpc_rx_jumbo_max; + void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_process_call(struct work_struct *); @@ -440,10 +458,14 @@ void rxrpc_process_call(struct work_struct *); /* * ar-call.c */ +extern unsigned rxrpc_max_call_lifetime; +extern unsigned 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_hash(u8, __be32, __be32, __be32, + __be16, void *, sa_family_t, const u8 *); struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, struct rxrpc_transport *, struct rxrpc_conn_bundle *, @@ -460,6 +482,7 @@ void __exit rxrpc_destroy_all_calls(void); /* * ar-connection.c */ +extern unsigned rxrpc_connection_expiry; extern struct list_head rxrpc_connections; extern rwlock_t rxrpc_connection_lock; @@ -493,7 +516,6 @@ void rxrpc_UDP_error_handler(struct work_struct *); /* * ar-input.c */ -extern unsigned long rxrpc_ack_timeout; extern const char *rxrpc_pkts[]; void rxrpc_data_ready(struct sock *, int); @@ -504,6 +526,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); * ar-local.c */ extern rwlock_t rxrpc_local_lock; + struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *); void rxrpc_put_local(struct rxrpc_local *); void __exit rxrpc_destroy_all_locals(void); @@ -522,7 +545,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, /* * ar-output.c */ -extern int rxrpc_resend_timeout; +extern unsigned rxrpc_resend_timeout; int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *, @@ -572,6 +595,8 @@ void rxrpc_packet_destructor(struct sk_buff *); /* * ar-transport.c */ +extern unsigned rxrpc_transport_expiry; + struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *, struct rxrpc_peer *, gfp_t); void rxrpc_put_transport(struct rxrpc_transport *); @@ -580,6 +605,17 @@ struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, struct rxrpc_peer *); /* + * sysctl.c + */ +#ifdef CONFIG_SYSCTL +extern int __init rxrpc_sysctl_init(void); +extern void rxrpc_sysctl_exit(void); +#else +static inline int __init rxrpc_sysctl_init(void) { return 0; } +static inline void rxrpc_sysctl_exit(void) {} +#endif + +/* * debug tracing */ extern unsigned int rxrpc_debug; diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index d0e8f1c1898a..0b4b9a79f5ab 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -18,7 +18,10 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -int rxrpc_resend_timeout = 4; +/* + * Time till packet resend (in jiffies). + */ +unsigned rxrpc_resend_timeout = 4 * HZ; static int rxrpc_send_data(struct kiocb *iocb, struct rxrpc_sock *rx, @@ -487,7 +490,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); sp->need_resend = false; - sp->resend_at = jiffies + rxrpc_resend_timeout * HZ; + 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; @@ -666,6 +669,7 @@ static int rxrpc_send_data(struct kiocb *iocb, /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || (segment == 0 && !more)) { struct rxrpc_connection *conn = call->conn; + uint32_t seq; size_t pad; /* pad out if we're using security */ @@ -678,11 +682,12 @@ static int rxrpc_send_data(struct kiocb *iocb, memset(skb_put(skb, pad), 0, pad); } + seq = atomic_inc_return(&call->sequence); + sp->hdr.epoch = conn->epoch; sp->hdr.cid = call->cid; sp->hdr.callNumber = call->call_id; - sp->hdr.seq = - htonl(atomic_inc_return(&call->sequence)); + sp->hdr.seq = htonl(seq); sp->hdr.serial = htonl(atomic_inc_return(&conn->serial)); sp->hdr.type = RXRPC_PACKET_TYPE_DATA; @@ -697,6 +702,8 @@ static int rxrpc_send_data(struct kiocb *iocb, else if (CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz) > 1) sp->hdr.flags |= RXRPC_MORE_PACKETS; + if (more && seq & 1) + sp->hdr.flags |= RXRPC_REQUEST_ACK; ret = rxrpc_secure_packet( call, skb, skb->mark, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 34b5490dde65..e9aaa65c0778 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -180,16 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (copy > len - copied) copy = len - copied; - if (skb->ip_summed == CHECKSUM_UNNECESSARY || - skb->ip_summed == CHECKSUM_PARTIAL) { - ret = skb_copy_datagram_iovec(skb, offset, - msg->msg_iov, copy); - } else { - ret = skb_copy_and_csum_datagram_iovec(skb, offset, - msg->msg_iov); - if (ret == -EINVAL) - goto csum_copy_error; - } + ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy); if (ret < 0) goto copy_error; @@ -348,20 +339,6 @@ copy_error: _leave(" = %d", ret); return ret; -csum_copy_error: - _debug("csum error"); - release_sock(&rx->sk); - if (continue_call) - rxrpc_put_call(continue_call); - rxrpc_kill_skb(skb); - if (!(flags & MSG_PEEK)) { - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - } - skb_kill_datagram(&rx->sk, skb, flags); - rxrpc_put_call(call); - return -EAGAIN; - wait_interrupted: ret = sock_intr_errno(timeo); wait_error: diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c index de755e04d29c..4cfab49e329d 100644 --- a/net/rxrpc/ar-skbuff.c +++ b/net/rxrpc/ar-skbuff.c @@ -83,9 +83,14 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, 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, sp->hdr.serial, - true); + false); } spin_unlock_bh(&call->lock); diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 92df566930b9..1976dec84f29 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -17,11 +17,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time after last use at which transport record is cleaned up. + */ +unsigned rxrpc_transport_expiry = 3600 * 24; + static void rxrpc_transport_reaper(struct work_struct *work); static LIST_HEAD(rxrpc_transports); static DEFINE_RWLOCK(rxrpc_transport_lock); -static unsigned long rxrpc_transport_timeout = 3600 * 24; static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper); /* @@ -235,7 +239,7 @@ static void rxrpc_transport_reaper(struct work_struct *work) if (likely(atomic_read(&trans->usage) > 0)) continue; - reap_time = trans->put_time + rxrpc_transport_timeout; + reap_time = trans->put_time + rxrpc_transport_expiry; if (reap_time <= now) list_move_tail(&trans->link, &graveyard); else if (reap_time < earliest) @@ -271,7 +275,7 @@ void __exit rxrpc_destroy_all_transports(void) { _enter(""); - rxrpc_transport_timeout = 0; + rxrpc_transport_expiry = 0; cancel_delayed_work(&rxrpc_transport_reap); rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c new file mode 100644 index 000000000000..50a98a910eb1 --- /dev/null +++ b/net/rxrpc/sysctl.c @@ -0,0 +1,146 @@ +/* sysctls for configuring RxRPC operating parameters + * + * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/sysctl.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static struct ctl_table_header *rxrpc_sysctl_reg_table; +static const unsigned zero = 0; +static const unsigned one = 1; +static const unsigned four = 4; +static const unsigned n_65535 = 65535; +static const unsigned n_max_acks = RXRPC_MAXACKS; + +/* + * RxRPC operating parameters. + * + * See Documentation/networking/rxrpc.txt and the variable definitions for more + * information on the individual parameters. + */ +static struct ctl_table rxrpc_sysctl_table[] = { + /* Values measured in milliseconds */ + { + .procname = "req_ack_delay", + .data = &rxrpc_requested_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&zero, + }, + { + .procname = "soft_ack_delay", + .data = &rxrpc_soft_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "idle_ack_delay", + .data = &rxrpc_idle_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "resend_timeout", + .data = &rxrpc_resend_timeout, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds but used in jiffies */ + { + .procname = "max_call_lifetime", + .data = &rxrpc_max_call_lifetime, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "dead_call_expiry", + .data = &rxrpc_dead_call_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds */ + { + .procname = "connection_expiry", + .data = &rxrpc_connection_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + { + .procname = "transport_expiry", + .data = &rxrpc_transport_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + + /* Non-time values */ + { + .procname = "rx_window_size", + .data = &rxrpc_rx_window_size, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&n_max_acks, + }, + { + .procname = "rx_mtu", + .data = &rxrpc_rx_mtu, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra1 = (void *)&n_65535, + }, + { + .procname = "rx_jumbo_max", + .data = &rxrpc_rx_jumbo_max, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&four, + }, + + { } +}; + +int __init rxrpc_sysctl_init(void) +{ + rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc", + rxrpc_sysctl_table); + if (!rxrpc_sysctl_reg_table) + return -ENOMEM; + return 0; +} + +void rxrpc_sysctl_exit(void) +{ + if (rxrpc_sysctl_reg_table) + unregister_net_sysctl_table(rxrpc_sysctl_reg_table); +} diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1313145e3b86..a0b84e0e22de 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -273,11 +273,12 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) void qdisc_list_add(struct Qdisc *q) { - struct Qdisc *root = qdisc_dev(q)->qdisc; + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + struct Qdisc *root = qdisc_dev(q)->qdisc; - WARN_ON_ONCE(root == &noop_qdisc); - if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) + WARN_ON_ONCE(root == &noop_qdisc); list_add_tail(&q->list, &root->list); + } } EXPORT_SYMBOL(qdisc_list_add); @@ -1303,6 +1304,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct gnet_dump d; struct qdisc_size_table *stab; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; @@ -1434,9 +1436,9 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; - rcu_read_lock(); idx = 0; - for_each_netdev_rcu(net, dev) { + ASSERT_RTNL(); + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) @@ -1459,8 +1461,6 @@ cont: } done: - rcu_read_unlock(); - cb->args[0] = idx; cb->args[1] = q_idx; @@ -1617,6 +1617,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 1f9c31411f19..8449b337f9e3 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -623,8 +623,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) goto nla_put_failure; } - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 2f80d01d42a6..ead526467cca 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1563,8 +1563,7 @@ static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; if (cbq_dump_attr(skb, &q->link) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); @@ -1599,8 +1598,7 @@ cbq_dump_class(struct Qdisc *sch, unsigned long arg, goto nla_put_failure; if (cbq_dump_attr(skb, cl) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 08ef7a42c0e4..23c682b42f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -601,6 +601,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; + void *old_fq_root; u32 idx; if (q->fq_root && log == q->fq_trees_log) @@ -615,13 +616,19 @@ static int fq_resize(struct Qdisc *sch, u32 log) for (idx = 0; idx < (1U << log); idx++) array[idx] = RB_ROOT; - if (q->fq_root) { - fq_rehash(q, q->fq_root, q->fq_trees_log, array, log); - fq_free(q->fq_root); - } + sch_tree_lock(sch); + + old_fq_root = q->fq_root; + if (old_fq_root) + fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); + q->fq_root = array; q->fq_trees_log = log; + sch_tree_unlock(sch); + + fq_free(old_fq_root); + return 0; } @@ -697,9 +704,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } - if (!err) + if (!err) { + sch_tree_unlock(sch); err = fq_resize(sch, fq_log); - + sch_tree_lock(sch); + } while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); @@ -772,8 +781,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index ba5bc929eac7..0bf432c782c1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -450,8 +450,7 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index c4075610502c..ec8aeaac1dd7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1353,8 +1353,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 647680b1c625..edee03d922e2 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -691,8 +691,7 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 722e137df244..9f949abcacef 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1062,12 +1062,13 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) { - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_glob gopt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the qdisc parameters. + */ gopt.direct_pkts = q->direct_pkts; gopt.version = HTB_VER; @@ -1081,13 +1082,10 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } @@ -1096,11 +1094,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct htb_class *cl = (struct htb_class *)arg; - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct nlattr *nest; struct tc_htb_opt opt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the class parameters. + */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; if (!cl->level && cl->un.leaf.q) @@ -1128,12 +1127,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index bce1665239b8..62871c14e1f9 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -100,8 +100,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 0893161b0262..18ff63433709 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -338,18 +338,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB])); - if (q->qdisc != &noop_qdisc) { - err = fifo_set_limit(q->qdisc, qopt->limit); - if (err) - goto done; - } else if (qopt->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); - if (IS_ERR(child)) { - err = PTR_ERR(child); - goto done; - } - } - buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); @@ -396,6 +384,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) goto done; } + if (q->qdisc != &noop_qdisc) { + err = fifo_set_limit(q->qdisc, qopt->limit); + if (err) + goto done; + } else if (qopt->limit > 0) { + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); + if (IS_ERR(child)) { + err = PTR_ERR(child); + goto done; + } + } + sch_tree_lock(sch); if (child) { qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); @@ -475,8 +475,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps)) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index f558433537b8..4f6d6f9d1274 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1239,78 +1239,106 @@ void sctp_assoc_update(struct sctp_association *asoc, } /* Update the retran path for sending a retransmitted packet. - * Round-robin through the active transports, else round-robin - * through the inactive transports as this is the next best thing - * we can try. + * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: + * + * When there is outbound data to send and the primary path + * becomes inactive (e.g., due to failures), or where the + * SCTP user explicitly requests to send data to an + * inactive destination transport address, before reporting + * an error to its ULP, the SCTP endpoint should try to send + * the data to an alternate active destination transport + * address if one exists. + * + * When retransmitting data that timed out, if the endpoint + * is multihomed, it should consider each source-destination + * address pair in its retransmission selection policy. + * When retransmitting timed-out data, the endpoint should + * attempt to pick the most divergent source-destination + * pair from the original source-destination pair to which + * the packet was transmitted. + * + * Note: Rules for picking the most divergent source-destination + * pair are an implementation decision and are not specified + * within this document. + * + * Our basic strategy is to round-robin transports in priorities + * according to sctp_state_prio_map[] e.g., if no such + * transport with state SCTP_ACTIVE exists, round-robin through + * SCTP_UNKNOWN, etc. You get the picture. */ -void sctp_assoc_update_retran_path(struct sctp_association *asoc) +static const u8 sctp_trans_state_to_prio_map[] = { + [SCTP_ACTIVE] = 3, /* best case */ + [SCTP_UNKNOWN] = 2, + [SCTP_PF] = 1, + [SCTP_INACTIVE] = 0, /* worst case */ +}; + +static u8 sctp_trans_score(const struct sctp_transport *trans) { - struct sctp_transport *t, *next; - struct list_head *head = &asoc->peer.transport_addr_list; - struct list_head *pos; + return sctp_trans_state_to_prio_map[trans->state]; +} - if (asoc->peer.transport_count == 1) - return; +static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, + struct sctp_transport *best) +{ + if (best == NULL) + return curr; - /* Find the next transport in a round-robin fashion. */ - t = asoc->peer.retran_path; - pos = &t->transports; - next = NULL; + return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best; +} - while (1) { - /* Skip the head. */ - if (pos->next == head) - pos = head->next; - else - pos = pos->next; +void sctp_assoc_update_retran_path(struct sctp_association *asoc) +{ + struct sctp_transport *trans = asoc->peer.retran_path; + struct sctp_transport *trans_next = NULL; - t = list_entry(pos, struct sctp_transport, transports); + /* We're done as we only have the one and only path. */ + if (asoc->peer.transport_count == 1) + return; + /* If active_path and retran_path are the same and active, + * then this is the only active path. Use it. + */ + if (asoc->peer.active_path == asoc->peer.retran_path && + asoc->peer.active_path->state == SCTP_ACTIVE) + return; - /* We have exhausted the list, but didn't find any - * other active transports. If so, use the next - * transport. - */ - if (t == asoc->peer.retran_path) { - t = next; + /* Iterate from retran_path's successor back to retran_path. */ + for (trans = list_next_entry(trans, transports); 1; + trans = list_next_entry(trans, transports)) { + /* Manually skip the head element. */ + if (&trans->transports == &asoc->peer.transport_addr_list) + continue; + if (trans->state == SCTP_UNCONFIRMED) + continue; + trans_next = sctp_trans_elect_best(trans, trans_next); + /* Active is good enough for immediate return. */ + if (trans_next->state == SCTP_ACTIVE) break; - } - - /* Try to find an active transport. */ - - if ((t->state == SCTP_ACTIVE) || - (t->state == SCTP_UNKNOWN)) { + /* We've reached the end, time to update path. */ + if (trans == asoc->peer.retran_path) break; - } else { - /* Keep track of the next transport in case - * we don't find any active transport. - */ - if (t->state != SCTP_UNCONFIRMED && !next) - next = t; - } } - if (t) - asoc->peer.retran_path = t; - else - t = asoc->peer.retran_path; + asoc->peer.retran_path = trans_next; - pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, - &t->ipaddr.sa); + pr_debug("%s: association:%p updated new path to addr:%pISpc\n", + __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } -/* Choose the transport for sending retransmit packet. */ -struct sctp_transport *sctp_assoc_choose_alter_transport( - struct sctp_association *asoc, struct sctp_transport *last_sent_to) +struct sctp_transport * +sctp_assoc_choose_alter_transport(struct sctp_association *asoc, + struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ - if (!last_sent_to) + if (last_sent_to == NULL) { return asoc->peer.active_path; - else { + } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); + return asoc->peer.retran_path; } } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 632090b961c3..3a1767ef3201 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1421,8 +1421,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk) BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); - /* Free the chunk skb data and the SCTP_chunk stub itself. */ - dev_kfree_skb(chunk->skb); + consume_skb(chunk->skb); + consume_skb(chunk->auth_chunk); SCTP_DBG_OBJCNT_DEC(chunk); kmem_cache_free(sctp_chunk_cachep, chunk); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index bd859154000e..5d6883ff00c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -495,11 +495,12 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, } /* If the transport error count is greater than the pf_retrans - * threshold, and less than pathmaxrtx, then mark this transport - * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1, - * point 1 + * threshold, and less than pathmaxrtx, and if the current state + * is not SCTP_UNCONFIRMED, then mark this transport as Partially + * Failed, see SCTP Quick Failover Draft, section 5.1 */ if ((transport->state != SCTP_PF) && + (transport->state != SCTP_UNCONFIRMED) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 591b44d3b7de..01e002430c85 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -758,6 +758,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, struct sctp_chunk auth; sctp_ierror_t ret; + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; @@ -768,10 +774,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - - /* We can now safely free the auth_chunk clone */ - kfree_skb(chunk->auth_chunk); - if (ret != SCTP_IERROR_NO_ERROR) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); diff --git a/net/socket.c b/net/socket.c index 840cffb7119b..f25eaa30b690 100644 --- a/net/socket.c +++ b/net/socket.c @@ -450,16 +450,17 @@ EXPORT_SYMBOL(sockfd_lookup); static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) { - struct file *file; + struct fd f = fdget(fd); struct socket *sock; *err = -EBADF; - file = fget_light(fd, fput_needed); - if (file) { - sock = sock_from_file(file, err); - if (sock) + if (f.file) { + sock = sock_from_file(f.file, err); + if (likely(sock)) { + *fput_needed = f.flags; return sock; - fput_light(file, *fput_needed); + } + fdput(f); } return NULL; } @@ -1985,6 +1986,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, { if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 6c0513a7f992..36e431ee1c90 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -108,6 +108,7 @@ struct gss_auth { static DEFINE_SPINLOCK(pipe_version_lock); static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); +static void gss_put_auth(struct gss_auth *gss_auth); static void gss_free_ctx(struct gss_cl_ctx *); static const struct rpc_pipe_ops gss_upcall_ops_v0; @@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) if (gss_msg->ctx != NULL) gss_put_ctx(gss_msg->ctx); rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue); + gss_put_auth(gss_msg->auth); kfree(gss_msg); } @@ -498,9 +500,12 @@ gss_alloc_msg(struct gss_auth *gss_auth, default: err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); if (err) - goto err_free_msg; + goto err_put_pipe_version; }; + kref_get(&gss_auth->kref); return gss_msg; +err_put_pipe_version: + put_pipe_version(gss_auth->net); err_free_msg: kfree(gss_msg); err: @@ -991,6 +996,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor); if (gss_auth->service == 0) goto err_put_mech; + if (!gssd_running(gss_auth->net)) + goto err_put_mech; auth = &gss_auth->rpc_auth; auth->au_cslack = GSS_CRED_SLACK >> 2; auth->au_rslack = GSS_VERF_SLACK >> 2; @@ -1062,6 +1069,12 @@ gss_free_callback(struct kref *kref) } static void +gss_put_auth(struct gss_auth *gss_auth) +{ + kref_put(&gss_auth->kref, gss_free_callback); +} + +static void gss_destroy(struct rpc_auth *auth) { struct gss_auth *gss_auth = container_of(auth, @@ -1082,7 +1095,7 @@ gss_destroy(struct rpc_auth *auth) gss_auth->gss_pipe[1] = NULL; rpcauth_destroy_credcache(auth); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } /* @@ -1253,7 +1266,7 @@ gss_destroy_nullcred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, gss_free_cred_callback); if (ctx) gss_put_ctx(ctx); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } static void diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 890a29912d5a..e860d4f7ed2a 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req) free_page((unsigned long)xbufp->head[0].iov_base); xbufp = &req->rq_snd_buf; free_page((unsigned long)xbufp->head[0].iov_base); - list_del(&req->rq_bc_pa_list); kfree(req); } @@ -168,8 +167,10 @@ out_free: /* * Memory allocation failed, free the temporary list */ - list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) + list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) { + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); + } dprintk("RPC: setup backchannel transport failed\n"); return -ENOMEM; @@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) xprt_dec_alloc_count(xprt, max_reqs); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { dprintk("RPC: req=%p\n", req); + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); if (--max_reqs == 0) break; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 817a1e523969..0addefca8e77 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -510,6 +510,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", @@ -527,7 +528,7 @@ static int xs_nospace(struct rpc_task *task) * window size */ set_bit(SOCK_NOSPACE, &transport->sock->flags); - transport->inet->sk_write_pending++; + sk->sk_write_pending++; /* ...and wait for more buffer space */ xprt_wait_for_buffer_space(task, xs_nospace_callback); } @@ -537,6 +538,9 @@ static int xs_nospace(struct rpc_task *task) } spin_unlock_bh(&xprt->transport_lock); + + /* Race breaker in case memory is freed before above code is called */ + sk->sk_write_space(sk); return ret; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 242cddd35a47..7f1f95c57476 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -575,7 +575,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, } static struct packet_type tipc_packet_type __read_mostly = { - .type = __constant_htons(ETH_P_TIPC), + .type = htons(ETH_P_TIPC), .func = tipc_l2_rcv_msg, }; @@ -586,8 +586,13 @@ static struct notifier_block notifier = { int tipc_bearer_setup(void) { + int err; + + err = register_netdevice_notifier(¬ifier); + if (err) + return err; dev_add_pack(&tipc_packet_type); - return register_netdevice_notifier(¬ifier); + return 0; } void tipc_bearer_cleanup(void) diff --git a/net/tipc/config.c b/net/tipc/config.c index c301a9a592d8..e6d721692ae0 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -181,7 +181,7 @@ static struct sk_buff *cfg_set_own_addr(void) if (tipc_own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change node address once assigned)"); - tipc_core_start_net(addr); + tipc_net_start(addr); return tipc_cfg_reply_none(); } @@ -376,7 +376,6 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, struct tipc_cfg_msg_hdr *req_hdr; struct tipc_cfg_msg_hdr *rep_hdr; struct sk_buff *rep_buf; - int ret; /* Validate configuration message header (ignore invalid message) */ req_hdr = (struct tipc_cfg_msg_hdr *)buf; @@ -398,12 +397,8 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr)); rep_hdr->tcm_len = htonl(rep_buf->len); rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST); - - ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, - rep_buf->len); - if (ret < 0) - pr_err("Sending cfg reply message failed, no memory\n"); - + tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, + rep_buf->len); kfree_skb(rep_buf); } } diff --git a/net/tipc/core.c b/net/tipc/core.c index 3f76b98d2fed..e2491b341edb 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -77,37 +77,13 @@ struct sk_buff *tipc_buf_acquire(u32 size) } /** - * tipc_core_stop_net - shut down TIPC networking sub-systems - */ -static void tipc_core_stop_net(void) -{ - tipc_net_stop(); - tipc_bearer_cleanup(); -} - -/** - * start_net - start TIPC networking sub-systems - */ -int tipc_core_start_net(unsigned long addr) -{ - int res; - - tipc_net_start(addr); - res = tipc_bearer_setup(); - if (res < 0) - goto err; - return res; - -err: - tipc_core_stop_net(); - return res; -} - -/** * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode */ static void tipc_core_stop(void) { + tipc_handler_stop(); + tipc_net_stop(); + tipc_bearer_cleanup(); tipc_netlink_stop(); tipc_cfg_stop(); tipc_subscr_stop(); @@ -122,30 +98,65 @@ static void tipc_core_stop(void) */ static int tipc_core_start(void) { - int res; + int err; get_random_bytes(&tipc_random, sizeof(tipc_random)); - res = tipc_handler_start(); - if (!res) - res = tipc_ref_table_init(tipc_max_ports, tipc_random); - if (!res) - res = tipc_nametbl_init(); - if (!res) - res = tipc_netlink_start(); - if (!res) - res = tipc_socket_init(); - if (!res) - res = tipc_register_sysctl(); - if (!res) - res = tipc_subscr_start(); - if (!res) - res = tipc_cfg_init(); - if (res) { - tipc_handler_stop(); - tipc_core_stop(); - } - return res; + err = tipc_handler_start(); + if (err) + goto out_handler; + + err = tipc_ref_table_init(tipc_max_ports, tipc_random); + if (err) + goto out_reftbl; + + err = tipc_nametbl_init(); + if (err) + goto out_nametbl; + + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_socket_init(); + if (err) + goto out_socket; + + err = tipc_register_sysctl(); + if (err) + goto out_sysctl; + + err = tipc_subscr_start(); + if (err) + goto out_subscr; + + err = tipc_cfg_init(); + if (err) + goto out_cfg; + + err = tipc_bearer_setup(); + if (err) + goto out_bearer; + + return 0; +out_bearer: + tipc_cfg_stop(); +out_cfg: + tipc_subscr_stop(); +out_subscr: + tipc_unregister_sysctl(); +out_sysctl: + tipc_socket_stop(); +out_socket: + tipc_netlink_stop(); +out_netlink: + tipc_nametbl_stop(); +out_nametbl: + tipc_ref_table_stop(); +out_reftbl: + tipc_handler_stop(); +out_handler: + return err; } static int __init tipc_init(void) @@ -174,8 +185,6 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { - tipc_handler_stop(); - tipc_core_stop_net(); tipc_core_stop(); pr_info("Deactivated\n"); } diff --git a/net/tipc/core.h b/net/tipc/core.h index 5569d96b4da3..4dfe137587bb 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -90,7 +90,6 @@ extern int tipc_random __read_mostly; /* * Routines available to privileged subsystems */ -int tipc_core_start_net(unsigned long); int tipc_handler_start(void); void tipc_handler_stop(void); int tipc_netlink_start(void); diff --git a/net/tipc/handler.c b/net/tipc/handler.c index e4bc8a296744..1fabf160501f 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -58,7 +58,6 @@ unsigned int tipc_k_signal(Handler routine, unsigned long argument) spin_lock_bh(&qitem_lock); if (!handler_enabled) { - pr_err("Signal request ignored by handler\n"); spin_unlock_bh(&qitem_lock); return -ENOPROTOOPT; } diff --git a/net/tipc/link.c b/net/tipc/link.c index d1a764b9b2d8..a42f4a1d3cd1 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -327,8 +327,6 @@ static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz) spin_lock_bh(&tipc_port_list_lock); p_ptr = tipc_port_lock(origport); if (p_ptr) { - if (!p_ptr->wakeup) - goto exit; if (!list_empty(&p_ptr->wait_list)) goto exit; p_ptr->congested = 1; @@ -363,7 +361,7 @@ void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all) list_del_init(&p_ptr->wait_list); spin_lock_bh(p_ptr->lock); p_ptr->congested = 0; - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); win -= p_ptr->waiting_pkts; spin_unlock_bh(p_ptr->lock); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92a1533af4e0..042e8e3cabc0 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -941,20 +941,48 @@ int tipc_nametbl_init(void) return 0; } -void tipc_nametbl_stop(void) +/** + * tipc_purge_publications - remove all publications for a given type + * + * tipc_nametbl_lock must be held when calling this function + */ +static void tipc_purge_publications(struct name_seq *seq) { - u32 i; + struct publication *publ, *safe; + struct sub_seq *sseq; + struct name_info *info; - if (!table.types) + if (!seq->sseqs) { + nameseq_delete_empty(seq); return; + } + sseq = seq->sseqs; + info = sseq->info; + list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { + tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, + publ->ref, publ->key); + } +} + +void tipc_nametbl_stop(void) +{ + u32 i; + struct name_seq *seq; + struct hlist_head *seq_head; + struct hlist_node *safe; - /* Verify name table is empty, then release it */ + /* Verify name table is empty and purge any lingering + * publications, then release the name table + */ write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { if (hlist_empty(&table.types[i])) continue; - pr_err("nametbl_stop(): orphaned hash chain detected\n"); - break; + seq_head = &table.types[i]; + hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) { + tipc_purge_publications(seq); + } + continue; } kfree(table.types); table.types = NULL; diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 9f72a6376362..3aaf73de9e2d 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -83,8 +83,6 @@ static struct genl_ops tipc_genl_ops[] = { }, }; -static int tipc_genl_family_registered; - int tipc_netlink_start(void) { int res; @@ -94,16 +92,10 @@ int tipc_netlink_start(void) pr_err("Failed to register netlink interface\n"); return res; } - - tipc_genl_family_registered = 1; return 0; } void tipc_netlink_stop(void) { - if (!tipc_genl_family_registered) - return; - genl_unregister_family(&tipc_genl_family); - tipc_genl_family_registered = 0; } diff --git a/net/tipc/port.c b/net/tipc/port.c index c7c2b549a39e..5c14c7801ee6 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -1,7 +1,7 @@ /* * net/tipc/port.c: TIPC port code * - * Copyright (c) 1992-2007, Ericsson AB + * Copyright (c) 1992-2007, 2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,6 +38,7 @@ #include "config.h" #include "port.h" #include "name_table.h" +#include "socket.h" /* Connection management: */ #define PROBING_INTERVAL 3600000 /* [ms] => 1 h */ @@ -54,17 +55,6 @@ static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err); static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err); static void port_timeout(unsigned long ref); - -static u32 port_peernode(struct tipc_port *p_ptr) -{ - return msg_destnode(&p_ptr->phdr); -} - -static u32 port_peerport(struct tipc_port *p_ptr) -{ - return msg_destport(&p_ptr->phdr); -} - /** * tipc_port_peer_msg - verify message was sent by connected port's peer * @@ -76,11 +66,11 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) u32 peernode; u32 orignode; - if (msg_origport(msg) != port_peerport(p_ptr)) + if (msg_origport(msg) != tipc_port_peerport(p_ptr)) return 0; orignode = msg_orignode(msg); - peernode = port_peernode(p_ptr); + peernode = tipc_port_peernode(p_ptr); return (orignode == peernode) || (!orignode && (peernode == tipc_own_addr)) || (!peernode && (orignode == tipc_own_addr)); @@ -90,20 +80,18 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) * tipc_port_mcast_xmit - send a multicast message to local and remote * destinations */ -int tipc_port_mcast_xmit(u32 ref, struct tipc_name_seq const *seq, - struct iovec const *msg_sect, unsigned int len) +int tipc_port_mcast_xmit(struct tipc_port *oport, + struct tipc_name_seq const *seq, + struct iovec const *msg_sect, + unsigned int len) { struct tipc_msg *hdr; struct sk_buff *buf; struct sk_buff *ibuf = NULL; struct tipc_port_list dports = {0, NULL, }; - struct tipc_port *oport = tipc_port_deref(ref); int ext_targets; int res; - if (unlikely(!oport)) - return -EINVAL; - /* Create multicast message */ hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); @@ -200,40 +188,32 @@ exit: tipc_port_list_free(dp); } -/** - * tipc_createport - create a generic TIPC port + +void tipc_port_wakeup(struct tipc_port *port) +{ + tipc_sock_wakeup(tipc_port_to_sock(port)); +} + +/* tipc_port_init - intiate TIPC port and lock it * - * Returns pointer to (locked) TIPC port, or NULL if unable to create it + * Returns obtained reference if initialization is successful, zero otherwise */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance) +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 ref; - p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC); - if (!p_ptr) { - pr_warn("Port creation failed, no memory\n"); - return NULL; - } ref = tipc_ref_acquire(p_ptr, &p_ptr->lock); if (!ref) { - pr_warn("Port creation failed, ref. table exhausted\n"); - kfree(p_ptr); - return NULL; + pr_warn("Port registration failed, ref. table exhausted\n"); + return 0; } - p_ptr->sk = sk; p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->ref = ref; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); - p_ptr->dispatcher = dispatcher; - p_ptr->wakeup = wakeup; k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); INIT_LIST_HEAD(&p_ptr->publications); INIT_LIST_HEAD(&p_ptr->port_list); @@ -249,10 +229,10 @@ struct tipc_port *tipc_createport(struct sock *sk, msg_set_origport(msg, ref); list_add_tail(&p_ptr->port_list, &ports); spin_unlock_bh(&tipc_port_list_lock); - return p_ptr; + return ref; } -int tipc_deleteport(struct tipc_port *p_ptr) +void tipc_port_destroy(struct tipc_port *p_ptr) { struct sk_buff *buf = NULL; @@ -273,67 +253,7 @@ int tipc_deleteport(struct tipc_port *p_ptr) list_del(&p_ptr->wait_list); spin_unlock_bh(&tipc_port_list_lock); k_term_timer(&p_ptr->timer); - kfree(p_ptr); tipc_net_route_msg(buf); - return 0; -} - -static int port_unreliable(struct tipc_port *p_ptr) -{ - return msg_src_droppable(&p_ptr->phdr); -} - -int tipc_portunreliable(u32 ref, unsigned int *isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunreliable = port_unreliable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0)); - tipc_port_unlock(p_ptr); - return 0; -} - -static int port_unreturnable(struct tipc_port *p_ptr) -{ - return msg_dest_droppable(&p_ptr->phdr); -} - -int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunrejectable = port_unreturnable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0)); - tipc_port_unlock(p_ptr); - return 0; } /* @@ -351,8 +271,8 @@ static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr, if (buf) { msg = buf_msg(buf); tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE, - port_peernode(p_ptr)); - msg_set_destport(msg, port_peerport(p_ptr)); + tipc_port_peernode(p_ptr)); + msg_set_destport(msg, tipc_port_peerport(p_ptr)); msg_set_origport(msg, p_ptr->ref); msg_set_msgcnt(msg, ack); } @@ -548,13 +468,12 @@ void tipc_port_proto_rcv(struct sk_buff *buf) /* Process protocol message sent by peer */ switch (msg_type(msg)) { case CONN_ACK: - wakeable = tipc_port_congested(p_ptr) && p_ptr->congested && - p_ptr->wakeup; + wakeable = tipc_port_congested(p_ptr) && p_ptr->congested; p_ptr->acked += msg_msgcnt(msg); if (!tipc_port_congested(p_ptr)) { p_ptr->congested = 0; if (wakeable) - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); } break; case CONN_PROBE: @@ -585,8 +504,8 @@ static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id) ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref); if (p_ptr->connected) { - u32 dport = port_peerport(p_ptr); - u32 destnode = port_peernode(p_ptr); + u32 dport = tipc_port_peerport(p_ptr); + u32 destnode = tipc_port_peernode(p_ptr); ret += tipc_snprintf(buf + ret, len - ret, " connected to <%u.%u.%u:%u>", @@ -674,34 +593,6 @@ void tipc_acknowledge(u32 ref, u32 ack) tipc_net_route_msg(buf); } -int tipc_portimportance(u32 ref, unsigned int *importance) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *importance = (unsigned int)msg_importance(&p_ptr->phdr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portimportance(u32 ref, unsigned int imp) -{ - struct tipc_port *p_ptr; - - if (imp > TIPC_CRITICAL_IMPORTANCE) - return -EINVAL; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)imp); - tipc_port_unlock(p_ptr); - return 0; -} - - int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *seq) { @@ -883,7 +774,7 @@ int tipc_port_rcv(struct sk_buff *buf) /* validate destination & pass to port, otherwise reject message */ p_ptr = tipc_port_lock(destport); if (likely(p_ptr)) { - err = p_ptr->dispatcher(p_ptr, buf); + err = tipc_sk_rcv(&tipc_port_to_sock(p_ptr)->sk, buf); tipc_port_unlock(p_ptr); if (likely(!err)) return dsz; @@ -914,19 +805,19 @@ static int tipc_port_iovec_rcv(struct tipc_port *sender, /** * tipc_send - send message sections on connection */ -int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) +int tipc_send(struct tipc_port *p_ptr, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; u32 destnode; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || !p_ptr->connected) + if (!p_ptr->connected) return -EINVAL; p_ptr->congested = 1; if (!tipc_port_congested(p_ptr)) { - destnode = port_peernode(p_ptr); + destnode = tipc_port_peernode(p_ptr); if (likely(!in_own_node(destnode))) res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, destnode); @@ -940,7 +831,7 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) return res; } } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) { p_ptr->congested = 0; return len; } @@ -950,17 +841,18 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) /** * tipc_send2name - send message sections to port name */ -int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2name(struct tipc_port *p_ptr, + struct tipc_name const *name, + unsigned int domain, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; u32 destport; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -987,9 +879,9 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, @@ -999,15 +891,15 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, /** * tipc_send2port - send message sections to port identity */ -int tipc_send2port(u32 ref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2port(struct tipc_port *p_ptr, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -1030,8 +922,8 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 3ec3e94e4334..a00397393bd1 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -1,7 +1,7 @@ /* * net/tipc/port.h: Include file for TIPC port code * - * Copyright (c) 1994-2007, Ericsson AB + * Copyright (c) 1994-2007, 2014, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -48,7 +48,6 @@ /** * struct tipc_port - TIPC port structure - * @sk: pointer to socket handle * @lock: pointer to spinlock for controlling access to port * @connected: non-zero if port is currently connected to a peer port * @conn_type: TIPC type used when connection was established @@ -60,8 +59,6 @@ * @ref: unique reference to port in TIPC object registry * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports - * @dispatcher: ptr to routine which handles received messages - * @wakeup: ptr to routine to call when port is no longer congested * @wait_list: adjacent ports in list of ports waiting on link congestion * @waiting_pkts: * @sent: # of non-empty messages sent by port @@ -74,7 +71,6 @@ * @subscription: "node down" subscription used to terminate failed connections */ struct tipc_port { - struct sock *sk; spinlock_t *lock; int connected; u32 conn_type; @@ -86,8 +82,6 @@ struct tipc_port { u32 ref; struct tipc_msg phdr; struct list_head port_list; - u32 (*dispatcher)(struct tipc_port *, struct sk_buff *); - void (*wakeup)(struct tipc_port *); struct list_head wait_list; u32 waiting_pkts; u32 sent; @@ -106,29 +100,18 @@ struct tipc_port_list; /* * TIPC port manipulation routines */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance); +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance); int tipc_reject_msg(struct sk_buff *buf, u32 err); void tipc_acknowledge(u32 port_ref, u32 ack); -int tipc_deleteport(struct tipc_port *p_ptr); - -int tipc_portimportance(u32 portref, unsigned int *importance); -int tipc_set_portimportance(u32 portref, unsigned int importance); - -int tipc_portunreliable(u32 portref, unsigned int *isunreliable); -int tipc_set_portunreliable(u32 portref, unsigned int isunreliable); - -int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable); -int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); +void tipc_port_destroy(struct tipc_port *p_ptr); int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); + int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); @@ -138,6 +121,7 @@ int tipc_port_disconnect(u32 portref); int tipc_port_shutdown(u32 ref); +void tipc_port_wakeup(struct tipc_port *port); /* * The following routines require that the port be locked on entry @@ -151,20 +135,33 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); * TIPC messaging routines */ int tipc_port_rcv(struct sk_buff *buf); -int tipc_send(u32 portref, struct iovec const *msg_sect, unsigned int len); - -int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain, - struct iovec const *msg_sect, unsigned int len); -int tipc_send2port(u32 portref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len); - -int tipc_port_mcast_xmit(u32 portref, struct tipc_name_seq const *seq, - struct iovec const *msg, unsigned int len); - -int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, +int tipc_send(struct tipc_port *port, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2name(struct tipc_port *port, + struct tipc_name const *name, + u32 domain, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2port(struct tipc_port *port, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_port_mcast_xmit(struct tipc_port *port, + struct tipc_name_seq const *seq, + struct iovec const *msg, + unsigned int len); + +int tipc_port_iovec_reject(struct tipc_port *p_ptr, + struct tipc_msg *hdr, + struct iovec const *msg_sect, + unsigned int len, int err); + struct sk_buff *tipc_port_get_ports(void); void tipc_port_proto_rcv(struct sk_buff *buf); void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp); @@ -188,14 +185,53 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr) spin_unlock_bh(p_ptr->lock); } -static inline struct tipc_port *tipc_port_deref(u32 ref) +static inline int tipc_port_congested(struct tipc_port *p_ptr) +{ + return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); +} + + +static inline u32 tipc_port_peernode(struct tipc_port *p_ptr) { - return (struct tipc_port *)tipc_ref_deref(ref); + return msg_destnode(&p_ptr->phdr); } -static inline int tipc_port_congested(struct tipc_port *p_ptr) +static inline u32 tipc_port_peerport(struct tipc_port *p_ptr) { - return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); + return msg_destport(&p_ptr->phdr); +} + +static inline bool tipc_port_unreliable(struct tipc_port *port) +{ + return msg_src_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreliable(struct tipc_port *port, + bool unreliable) +{ + msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0); +} + +static inline bool tipc_port_unreturnable(struct tipc_port *port) +{ + return msg_dest_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreturnable(struct tipc_port *port, + bool unreturnable) +{ + msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0); +} + + +static inline int tipc_port_importance(struct tipc_port *port) +{ + return msg_importance(&port->phdr); +} + +static inline void tipc_port_set_importance(struct tipc_port *port, int imp) +{ + msg_set_importance(&port->phdr, (u32)imp); } #endif diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 2a2a938dc22c..3d4ecd754eee 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -89,7 +89,7 @@ struct ref_table { static struct ref_table tipc_ref_table; -static DEFINE_RWLOCK(ref_table_lock); +static DEFINE_SPINLOCK(ref_table_lock); /** * tipc_ref_table_init - create reference table for objects @@ -126,9 +126,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start) */ void tipc_ref_table_stop(void) { - if (!tipc_ref_table.entries) - return; - vfree(tipc_ref_table.entries); tipc_ref_table.entries = NULL; } @@ -162,7 +159,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } /* take a free entry, if available; otherwise initialize a new entry */ - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (tipc_ref_table.first_free) { index = tipc_ref_table.first_free; entry = &(tipc_ref_table.entries[index]); @@ -178,7 +175,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } else { ref = 0; } - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); /* * Grab the lock so no one else can modify this entry @@ -219,7 +216,7 @@ void tipc_ref_discard(u32 ref) index = ref & index_mask; entry = &(tipc_ref_table.entries[index]); - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (!entry->object) { pr_err("Attempt to discard ref. to non-existent obj\n"); @@ -245,7 +242,7 @@ void tipc_ref_discard(u32 ref) tipc_ref_table.last_free = index; exit: - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); } /** @@ -267,20 +264,3 @@ void *tipc_ref_lock(u32 ref) } return NULL; } - - -/** - * tipc_ref_deref - return pointer referenced object (without locking it) - */ -void *tipc_ref_deref(u32 ref) -{ - if (likely(tipc_ref_table.entries)) { - struct reference *entry; - - entry = &tipc_ref_table.entries[ref & - tipc_ref_table.index_mask]; - if (likely(entry->ref == ref)) - return entry->object; - } - return NULL; -} diff --git a/net/tipc/ref.h b/net/tipc/ref.h index 5bc8e7ab84de..d01aa1df63b8 100644 --- a/net/tipc/ref.h +++ b/net/tipc/ref.h @@ -44,6 +44,5 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock); void tipc_ref_discard(u32 ref); void *tipc_ref_lock(u32 ref); -void *tipc_ref_deref(u32 ref); #endif diff --git a/net/tipc/server.c b/net/tipc/server.c index b635ca347a87..646a930eefbf 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -87,7 +87,6 @@ static void tipc_clean_outqueues(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct tipc_server *s = con->server; if (con->sock) { tipc_sock_release_local(con->sock); @@ -95,10 +94,6 @@ static void tipc_conn_kref_release(struct kref *kref) } tipc_clean_outqueues(con); - - if (con->conid) - s->tipc_conn_shutdown(con->conid, con->usr_data); - kfree(con); } @@ -181,6 +176,9 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { + if (con->conid) + s->tipc_conn_shutdown(con->conid, con->usr_data); + spin_lock_bh(&s->idr_lock); idr_remove(&s->conn_idr, con->conid); s->idr_in_use--; @@ -429,10 +427,12 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); - if (test_bit(CF_CONNECTED, &con->flags)) + if (test_bit(CF_CONNECTED, &con->flags)) { if (!queue_work(s->send_wq, &con->swork)) conn_put(con); - + } else { + conn_put(con); + } return 0; } @@ -573,7 +573,6 @@ int tipc_server_start(struct tipc_server *s) kmem_cache_destroy(s->rcvbuf_cache); return ret; } - s->enabled = 1; return ret; } @@ -583,10 +582,6 @@ void tipc_server_stop(struct tipc_server *s) int total = 0; int id; - if (!s->enabled) - return; - - s->enabled = 0; spin_lock_bh(&s->idr_lock); for (id = 0; total < s->idr_in_use; id++) { con = idr_find(&s->conn_idr, id); diff --git a/net/tipc/server.h b/net/tipc/server.h index 98b23f20bc0f..be817b0b547e 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -56,7 +56,6 @@ * @name: server name * @imp: message importance * @type: socket type - * @enabled: identify whether server is launched or not */ struct tipc_server { struct idr conn_idr; @@ -74,7 +73,6 @@ struct tipc_server { const char name[TIPC_SERVER_NAME_LEN]; int imp; int type; - int enabled; }; int tipc_conn_sendmsg(struct tipc_server *s, int conid, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index fb885977bd2a..29b7f26a12cf 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012 Ericsson AB + * Copyright (c) 2001-2007, 2012-2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,26 +38,13 @@ #include "port.h" #include <linux/export.h> -#include <net/sock.h> #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -struct tipc_sock { - struct sock sk; - struct tipc_port *p; - struct tipc_portid peer_name; - unsigned int conn_timeout; -}; - -#define tipc_sk(sk) ((struct tipc_sock *)(sk)) -#define tipc_sk_port(sk) (tipc_sk(sk)->p) - static int backlog_rcv(struct sock *sk, struct sk_buff *skb); -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); -static void wakeupdispatch(struct tipc_port *tport); static void tipc_data_ready(struct sock *sk, int len); static void tipc_write_space(struct sock *sk); static int tipc_release(struct socket *sock); @@ -70,8 +57,6 @@ static const struct proto_ops msg_ops; static struct proto tipc_proto; static struct proto tipc_proto_kern; -static int sockets_enabled; - /* * Revised TIPC socket locking policy: * @@ -117,6 +102,8 @@ static int sockets_enabled; * - port reference */ +#include "socket.h" + /** * advance_rx_queue - discard first buffer in socket receive queue * @@ -152,13 +139,15 @@ static void reject_rx_queue(struct sock *sk) * * Returns 0 on success, errno otherwise */ -static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, - int kern) +static int tipc_sk_create(struct net *net, struct socket *sock, + int protocol, int kern) { const struct proto_ops *ops; socket_state state; struct sock *sk; - struct tipc_port *tp_ptr; + struct tipc_sock *tsk; + struct tipc_port *port; + u32 ref; /* Validate arguments */ if (unlikely(protocol != 0)) @@ -191,10 +180,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) return -ENOMEM; - /* Allocate TIPC port for socket to use */ - tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch, - TIPC_LOW_IMPORTANCE); - if (unlikely(!tp_ptr)) { + tsk = tipc_sk(sk); + port = &tsk->port; + + ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE); + if (!ref) { + pr_warn("Socket registration failed, ref. table exhausted\n"); sk_free(sk); return -ENOMEM; } @@ -208,17 +199,14 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; - tipc_sk(sk)->p = tp_ptr; tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT; - - spin_unlock_bh(tp_ptr->lock); + tipc_port_unlock(port); if (sock->state == SS_READY) { - tipc_set_portunreturnable(tp_ptr->ref, 1); + tipc_port_set_unreturnable(port, true); if (sock->type == SOCK_DGRAM) - tipc_set_portunreliable(tp_ptr->ref, 1); + tipc_port_set_unreliable(port, true); } - return 0; } @@ -310,7 +298,8 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, static int tipc_release(struct socket *sock) { struct sock *sk = sock->sk; - struct tipc_port *tport; + struct tipc_sock *tsk; + struct tipc_port *port; struct sk_buff *buf; int res; @@ -321,7 +310,8 @@ static int tipc_release(struct socket *sock) if (sk == NULL) return 0; - tport = tipc_sk_port(sk); + tsk = tipc_sk(sk); + port = &tsk->port; lock_sock(sk); /* @@ -338,17 +328,16 @@ static int tipc_release(struct socket *sock) if ((sock->state == SS_CONNECTING) || (sock->state == SS_CONNECTED)) { sock->state = SS_DISCONNECTING; - tipc_port_disconnect(tport->ref); + tipc_port_disconnect(port->ref); } tipc_reject_msg(buf, TIPC_ERR_NO_PORT); } } - /* - * Delete TIPC port; this ensures no more messages are queued - * (also disconnects an active connection & sends a 'FIN-' to peer) + /* Destroy TIPC port; also disconnects an active connection and + * sends a 'FIN-' to peer. */ - res = tipc_deleteport(tport); + tipc_port_destroy(port); /* Discard any remaining (connection-based) messages in receive queue */ __skb_queue_purge(&sk->sk_receive_queue); @@ -383,12 +372,12 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, { struct sock *sk = sock->sk; struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_port *tport = tipc_sk_port(sock->sk); + struct tipc_sock *tsk = tipc_sk(sk); int res = -EINVAL; lock_sock(sk); if (unlikely(!uaddr_len)) { - res = tipc_withdraw(tport, 0, NULL); + res = tipc_withdraw(&tsk->port, 0, NULL); goto exit; } @@ -416,8 +405,8 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, } res = (addr->scope > 0) ? - tipc_publish(tport, addr->scope, &addr->addr.nameseq) : - tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq); + tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) : + tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq); exit: release_sock(sk); return res; @@ -440,17 +429,17 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_sock *tsock = tipc_sk(sock->sk); + struct tipc_sock *tsk = tipc_sk(sock->sk); memset(addr, 0, sizeof(*addr)); if (peer) { if ((sock->state != SS_CONNECTED) && ((peer != 2) || (sock->state != SS_DISCONNECTING))) return -ENOTCONN; - addr->addr.id.ref = tsock->peer_name.ref; - addr->addr.id.node = tsock->peer_name.node; + addr->addr.id.ref = tipc_port_peerport(&tsk->port); + addr->addr.id.node = tipc_port_peernode(&tsk->port); } else { - addr->addr.id.ref = tsock->p->ref; + addr->addr.id.ref = tsk->port.ref; addr->addr.id.node = tipc_own_addr; } @@ -507,18 +496,19 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); u32 mask = 0; sock_poll_wait(file, sk_sleep(sk), wait); switch ((int)sock->state) { case SS_UNCONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; break; case SS_READY: case SS_CONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; /* fall thru' */ case SS_CONNECTING: @@ -568,7 +558,7 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DEFINE_WAIT(wait); int done; @@ -584,12 +574,13 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) return sock_intr_errno(*timeo_p); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - done = sk_wait_event(sk, timeo_p, !tport->congested); + done = sk_wait_event(sk, timeo_p, !tsk->port.congested); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } + /** * tipc_sendmsg - send message in connectionless manner * @iocb: if NULL, indicates that socket lock is already held @@ -608,7 +599,8 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int needs_conn; long timeo; @@ -635,13 +627,13 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, res = -EISCONN; goto exit; } - if (tport->published) { + if (tsk->port.published) { res = -EOPNOTSUPP; goto exit; } if (dest->addrtype == TIPC_ADDR_NAME) { - tport->conn_type = dest->addr.name.name.type; - tport->conn_instance = dest->addr.name.name.instance; + tsk->port.conn_type = dest->addr.name.name.type; + tsk->port.conn_instance = dest->addr.name.name.instance; } /* Abort any pending connection attempts (very unlikely) */ @@ -654,13 +646,13 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_send2name(tport->ref, + res = tipc_send2name(port, &dest->addr.name.name, dest->addr.name.domain, m->msg_iov, total_len); } else if (dest->addrtype == TIPC_ADDR_ID) { - res = tipc_send2port(tport->ref, + res = tipc_send2port(port, &dest->addr.id, m->msg_iov, total_len); @@ -672,7 +664,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_port_mcast_xmit(tport->ref, + res = tipc_port_mcast_xmit(port, &dest->addr.nameseq, m->msg_iov, total_len); @@ -696,7 +688,8 @@ exit: static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DEFINE_WAIT(wait); int done; @@ -715,7 +708,7 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, timeo_p, - (!tport->congested || !tport->connected)); + (!port->congested || !port->connected)); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; @@ -736,7 +729,7 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int res = -EINVAL; long timeo; @@ -761,7 +754,7 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); do { - res = tipc_send(tport->ref, m->msg_iov, total_len); + res = tipc_send(&tsk->port, m->msg_iov, total_len); if (likely(res != -ELINKCONG)) break; res = tipc_wait_for_sndpkt(sock, &timeo); @@ -790,7 +783,7 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); struct msghdr my_msg; struct iovec my_iov; struct iovec *curr_iov; @@ -838,14 +831,14 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, my_msg.msg_name = NULL; bytes_sent = 0; - hdr_size = msg_hdr_sz(&tport->phdr); + hdr_size = msg_hdr_sz(&tsk->port.phdr); while (curr_iovlen--) { curr_start = curr_iov->iov_base; curr_left = curr_iov->iov_len; while (curr_left) { - bytes_to_send = tport->max_pkt - hdr_size; + bytes_to_send = tsk->port.max_pkt - hdr_size; if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE) bytes_to_send = TIPC_MAX_USER_MSG_SIZE; if (curr_left < bytes_to_send) @@ -874,27 +867,25 @@ exit: /** * auto_connect - complete connection setup to a remote port - * @sock: socket structure + * @tsk: tipc socket structure * @msg: peer's response message * * Returns 0 on success, errno otherwise */ -static int auto_connect(struct socket *sock, struct tipc_msg *msg) +static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg) { - struct tipc_sock *tsock = tipc_sk(sock->sk); - struct tipc_port *p_ptr; + struct tipc_port *port = &tsk->port; + struct socket *sock = tsk->sk.sk_socket; + struct tipc_portid peer; - tsock->peer_name.ref = msg_origport(msg); - tsock->peer_name.node = msg_orignode(msg); - p_ptr = tipc_port_deref(tsock->p->ref); - if (!p_ptr) - return -EINVAL; + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); - __tipc_port_connect(tsock->p->ref, p_ptr, &tsock->peer_name); + __tipc_port_connect(port->ref, port, &peer); if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE) return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg)); + msg_set_importance(&port->phdr, (u32)msg_importance(msg)); sock->state = SS_CONNECTED; return 0; } @@ -1001,7 +992,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sock->state == SS_DISCONNECTING) { err = -ENOTCONN; break; @@ -1040,7 +1031,8 @@ static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1083,7 +1075,7 @@ restart: set_orig_addr(m, msg); /* Capture ancillary data (optional) */ - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; @@ -1109,8 +1101,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { if ((sock->state != SS_READY) && - (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } exit: @@ -1134,7 +1126,8 @@ static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1179,7 +1172,7 @@ restart: /* Optionally capture sender's address & ancillary data of first msg */ if (sz_copied == 0) { set_orig_addr(m, msg); - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; } @@ -1217,8 +1210,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { - if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } @@ -1270,17 +1263,19 @@ static void tipc_data_ready(struct sock *sk, int len) /** * filter_connect - Handle all incoming messages for a connection-based socket - * @tsock: TIPC socket + * @tsk: TIPC socket * @msg: message * * Returns TIPC error status code and socket error status code * once it encounters some errors */ -static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) +static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) { - struct socket *sock = tsock->sk.sk_socket; + struct sock *sk = &tsk->sk; + struct tipc_port *port = &tsk->port; + struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(*buf); - struct sock *sk = &tsock->sk; + u32 retval = TIPC_ERR_NO_PORT; int res; @@ -1290,10 +1285,10 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) switch ((int)sock->state) { case SS_CONNECTED: /* Accept only connection-based messages sent by peer */ - if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) { + if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) { if (unlikely(msg_errcode(msg))) { sock->state = SS_DISCONNECTING; - __tipc_port_disconnect(tsock->p); + __tipc_port_disconnect(port); } retval = TIPC_OK; } @@ -1310,7 +1305,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) if (unlikely(!msg_connected(msg))) break; - res = auto_connect(sock, msg); + res = auto_connect(tsk, msg); if (res) { sock->state = SS_DISCONNECTING; sk->sk_err = -res; @@ -1389,6 +1384,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; + struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *msg = buf_msg(buf); unsigned int limit = rcvbuf_limit(sk, buf); u32 res = TIPC_OK; @@ -1401,7 +1397,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_connected(msg)) return TIPC_ERR_NO_PORT; } else { - res = filter_connect(tipc_sk(sk), &buf); + res = filter_connect(tsk, &buf); if (res != TIPC_OK || buf == NULL) return res; } @@ -1439,17 +1435,16 @@ static int backlog_rcv(struct sock *sk, struct sk_buff *buf) } /** - * dispatch - handle incoming message - * @tport: TIPC port that received message + * tipc_sk_rcv - handle incoming message + * @sk: socket receiving message * @buf: message * * Called with port lock already taken. * * Returns TIPC error status code (TIPC_OK if message is not to be rejected) */ -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf) { - struct sock *sk = tport->sk; u32 res; /* @@ -1472,19 +1467,6 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) return res; } -/** - * wakeupdispatch - wake up port after congestion - * @tport: port to wakeup - * - * Called with port lock already taken. - */ -static void wakeupdispatch(struct tipc_port *tport) -{ - struct sock *sk = tport->sk; - - sk->sk_write_space(sk); -} - static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; @@ -1627,7 +1609,7 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); @@ -1661,9 +1643,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; - struct tipc_sock *new_tsock; - struct tipc_port *new_tport; + struct tipc_port *new_port; struct tipc_msg *msg; + struct tipc_portid peer; u32 new_ref; long timeo; int res; @@ -1674,7 +1656,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) res = -EINVAL; goto exit; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); res = tipc_wait_for_accept(sock, timeo); if (res) @@ -1687,9 +1668,8 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) goto exit; new_sk = new_sock->sk; - new_tsock = tipc_sk(new_sk); - new_tport = new_tsock->p; - new_ref = new_tport->ref; + new_port = &tipc_sk(new_sk)->port; + new_ref = new_port->ref; msg = buf_msg(buf); /* we lock on new_sk; but lockdep sees the lock on sk */ @@ -1702,15 +1682,15 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) reject_rx_queue(new_sk); /* Connect new socket to it's peer */ - new_tsock->peer_name.ref = msg_origport(msg); - new_tsock->peer_name.node = msg_orignode(msg); - tipc_port_connect(new_ref, &new_tsock->peer_name); + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); + tipc_port_connect(new_ref, &peer); new_sock->state = SS_CONNECTED; - tipc_set_portimportance(new_ref, msg_importance(msg)); + tipc_port_set_importance(new_port, msg_importance(msg)); if (msg_named(msg)) { - new_tport->conn_type = msg_nametype(msg); - new_tport->conn_instance = msg_nameinst(msg); + new_port->conn_type = msg_nametype(msg); + new_port->conn_instance = msg_nameinst(msg); } /* @@ -1728,7 +1708,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) skb_set_owner_r(buf, new_sk); } release_sock(new_sk); - exit: release_sock(sk); return res; @@ -1746,7 +1725,8 @@ exit: static int tipc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; int res; @@ -1767,10 +1747,10 @@ restart: kfree_skb(buf); goto restart; } - tipc_port_disconnect(tport->ref); + tipc_port_disconnect(port->ref); tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN); } else { - tipc_port_shutdown(tport->ref); + tipc_port_shutdown(port->ref); } sock->state = SS_DISCONNECTING; @@ -1812,7 +1792,8 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; u32 value; int res; @@ -1830,16 +1811,16 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_set_portimportance(tport->ref, value); + tipc_port_set_importance(port, value); break; case TIPC_SRC_DROPPABLE: if (sock->type != SOCK_STREAM) - res = tipc_set_portunreliable(tport->ref, value); + tipc_port_set_unreliable(port, value); else res = -ENOPROTOOPT; break; case TIPC_DEST_DROPPABLE: - res = tipc_set_portunreturnable(tport->ref, value); + tipc_port_set_unreturnable(port, value); break; case TIPC_CONN_TIMEOUT: tipc_sk(sk)->conn_timeout = value; @@ -1871,7 +1852,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, int __user *ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; int len; u32 value; int res; @@ -1888,13 +1870,13 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_portimportance(tport->ref, &value); + value = tipc_port_importance(port); break; case TIPC_SRC_DROPPABLE: - res = tipc_portunreliable(tport->ref, &value); + value = tipc_port_unreliable(port); break; case TIPC_DEST_DROPPABLE: - res = tipc_portunreturnable(tport->ref, &value); + value = tipc_port_unreturnable(port); break; case TIPC_CONN_TIMEOUT: value = tipc_sk(sk)->conn_timeout; @@ -2029,8 +2011,6 @@ int tipc_socket_init(void) proto_unregister(&tipc_proto); goto out; } - - sockets_enabled = 1; out: return res; } @@ -2040,10 +2020,6 @@ int tipc_socket_init(void) */ void tipc_socket_stop(void) { - if (!sockets_enabled) - return; - - sockets_enabled = 0; sock_unregister(tipc_family_ops.family); proto_unregister(&tipc_proto); } diff --git a/net/tipc/socket.h b/net/tipc/socket.h new file mode 100644 index 000000000000..74e5c7f195a6 --- /dev/null +++ b/net/tipc/socket.h @@ -0,0 +1,72 @@ +/* net/tipc/socket.h: Include file for TIPC socket code + * + * Copyright (c) 2014, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_SOCK_H +#define _TIPC_SOCK_H + +#include "port.h" +#include <net/sock.h> + +/** + * struct tipc_sock - TIPC socket structure + * @sk: socket - interacts with 'port' and with user via the socket API + * @port: port - interacts with 'sk' and with the rest of the TIPC stack + * @peer_name: the peer of the connection, if any + * @conn_timeout: the time we can wait for an unresponded setup request + */ + +struct tipc_sock { + struct sock sk; + struct tipc_port port; + unsigned int conn_timeout; +}; + +static inline struct tipc_sock *tipc_sk(const struct sock *sk) +{ + return container_of(sk, struct tipc_sock, sk); +} + +static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port) +{ + return container_of(port, struct tipc_sock, port); +} + +static inline void tipc_sock_wakeup(struct tipc_sock *tsk) +{ + tsk->sk.sk_write_space(&tsk->sk); +} + +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf); + +#endif diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 7cb0bd5b1176..11c9ae00837d 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -96,20 +96,16 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, { struct tipc_subscriber *subscriber = sub->subscriber; struct kvec msg_sect; - int ret; msg_sect.iov_base = (void *)&sub->evt; msg_sect.iov_len = sizeof(struct tipc_event); - sub->evt.event = htohl(event, sub->swap); sub->evt.found_lower = htohl(found_lower, sub->swap); sub->evt.found_upper = htohl(found_upper, sub->swap); sub->evt.port.ref = htohl(port_ref, sub->swap); sub->evt.port.node = htohl(node, sub->swap); - ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, - msg_sect.iov_base, msg_sect.iov_len); - if (ret < 0) - pr_err("Sending subscription event failed, no memory\n"); + tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base, + msg_sect.iov_len); } /** @@ -153,14 +149,6 @@ static void subscr_timeout(struct tipc_subscription *sub) /* The spin lock per subscriber is used to protect its members */ spin_lock_bh(&subscriber->lock); - /* Validate if the connection related to the subscriber is - * closed (in case subscriber is terminating) - */ - if (subscriber->conid == 0) { - spin_unlock_bh(&subscriber->lock); - return; - } - /* Validate timeout (in case subscription is being cancelled) */ if (sub->timeout == TIPC_WAIT_FOREVER) { spin_unlock_bh(&subscriber->lock); @@ -215,9 +203,6 @@ static void subscr_release(struct tipc_subscriber *subscriber) spin_lock_bh(&subscriber->lock); - /* Invalidate subscriber reference */ - subscriber->conid = 0; - /* Destroy any existing subscriptions for subscriber */ list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, subscription_list) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 29fc8bee9702..ce6ec6c2f4de 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -163,9 +163,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) static inline unsigned int unix_hash_fold(__wsum n) { - unsigned int hash = (__force unsigned int)n; + unsigned int hash = (__force unsigned int)csum_fold(n); - hash ^= hash>>16; hash ^= hash>>8; return hash&(UNIX_HASH_SIZE-1); } diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 2d4268c5529d..cd10c1985074 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -705,12 +705,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: - /* these interface types don't really have a channel */ - return; case NL80211_IFTYPE_P2P_DEVICE: - if (wdev->wiphy->features & - NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL) - *chanmode = CHAN_MODE_EXCLUSIVE; + /* these interface types don't really have a channel */ return; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: diff --git a/net/wireless/core.c b/net/wireless/core.c index 76ae6a605abb..eb7f40821c09 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -788,8 +788,6 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, default: break; } - - wdev->beacon_interval = 0; } static int cfg80211_netdev_notifier_call(struct notifier_block *nb, diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index 9a8217d2a908..fdfd3f063a9b 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -105,6 +105,8 @@ function parse_reg_rule() flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " } else if (flagarray[arg] == "NO-IR") { flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " + } else if (flagarray[arg] == "AUTO-BW") { + flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | " } } diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 1470b90e438f..349db9ddc0d1 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -128,12 +128,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, #endif check_chan = params->chandef.chan; if (params->userspace_handles_dfs) { - /* use channel NULL to check for radar even if the current - * channel is not a radar channel - it might decide to change - * to DFS channel later. + /* Check for radar even if the current channel is not + * a radar channel - it might decide to change to DFS + * channel later. */ radar_detect_width = BIT(params->chandef.width); - check_chan = NULL; } err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index d42a3fcb2f67..5af5cc6b2c4c 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -236,6 +236,12 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, if (!netif_running(wdev->netdev)) return -ENETDOWN; + /* cfg80211_can_use_chan() calls + * cfg80211_can_use_iftype_chan() with no radar + * detection, so if we're trying to use a radar + * channel here, something is wrong. + */ + WARN_ON_ONCE(chandef->chan->flags & IEEE80211_CHAN_RADAR); err = cfg80211_can_use_chan(rdev, wdev, chandef->chan, CHAN_MODE_SHARED); if (err) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8e6b6a2d35cb..2c38b28a85b9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -384,6 +384,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { .len = IEEE80211_QOS_MAP_LEN_MAX }, [NL80211_ATTR_MAC_HINT] = { .len = ETH_ALEN }, [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, + [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -4627,6 +4628,8 @@ static int parse_reg_rule(struct nlattr *tb[], return -EINVAL; if (!tb[NL80211_ATTR_FREQ_RANGE_END]) return -EINVAL; + if (!tb[NL80211_ATTR_FREQ_RANGE_MAX_BW]) + return -EINVAL; if (!tb[NL80211_ATTR_POWER_RULE_MAX_EIRP]) return -EINVAL; @@ -4636,9 +4639,8 @@ static int parse_reg_rule(struct nlattr *tb[], nla_get_u32(tb[NL80211_ATTR_FREQ_RANGE_START]); freq_range->end_freq_khz = nla_get_u32(tb[NL80211_ATTR_FREQ_RANGE_END]); - if (tb[NL80211_ATTR_FREQ_RANGE_MAX_BW]) - freq_range->max_bandwidth_khz = - nla_get_u32(tb[NL80211_ATTR_FREQ_RANGE_MAX_BW]); + freq_range->max_bandwidth_khz = + nla_get_u32(tb[NL80211_ATTR_FREQ_RANGE_MAX_BW]); power_rule->max_eirp = nla_get_u32(tb[NL80211_ATTR_POWER_RULE_MAX_EIRP]); @@ -5710,8 +5712,8 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request->min_rssi_thold = NL80211_SCAN_RSSI_THOLD_OFF; } - if (info->attrs[NL80211_ATTR_IE]) { - request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + if (ie_len) { + request->ie_len = ie_len; memcpy((void *)request->ie, nla_data(info->attrs[NL80211_ATTR_IE]), request->ie_len); @@ -5911,17 +5913,22 @@ skip_beacons: if (!cfg80211_reg_can_beacon(&rdev->wiphy, ¶ms.chandef)) return -EINVAL; - if (dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || - dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO || - dev->ieee80211_ptr->iftype == NL80211_IFTYPE_ADHOC) { + switch (dev->ieee80211_ptr->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: err = cfg80211_chandef_dfs_required(wdev->wiphy, ¶ms.chandef); - if (err < 0) { + if (err < 0) return err; - } else if (err) { + if (err) { radar_detect_width = BIT(params.chandef.width); params.radar_required = true; } + break; + default: + break; } err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, @@ -7269,6 +7276,7 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; u8 action_code, dialog_token; + u32 peer_capability = 0; u16 status_code; u8 *peer; @@ -7287,9 +7295,12 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) action_code = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_ACTION]); status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]); + if (info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]) + peer_capability = + nla_get_u32(info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]); return rdev_tdls_mgmt(rdev, dev, peer, action_code, - dialog_token, status_code, + dialog_token, status_code, peer_capability, nla_data(info->attrs[NL80211_ATTR_IE]), nla_len(info->attrs[NL80211_ATTR_IE])); } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index c8e225947adb..74d97d33c938 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -769,13 +769,16 @@ static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *buf, size_t len) + u16 status_code, u32 peer_capability, + const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code, - dialog_token, status_code, buf, len); + dialog_token, status_code, peer_capability, + buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, - dialog_token, status_code, buf, len); + dialog_token, status_code, peer_capability, + buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 27c5253e7a61..90b82e08ae69 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -563,9 +563,6 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, if (freq_range_tmp->end_freq_khz < freq_range->start_freq_khz) break; - if (freq_range_tmp->max_bandwidth_khz) - break; - freq_range = freq_range_tmp; } @@ -582,9 +579,6 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, if (freq_range_tmp->start_freq_khz > freq_range->end_freq_khz) break; - if (freq_range_tmp->max_bandwidth_khz) - break; - freq_range = freq_range_tmp; } @@ -729,21 +723,29 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, max_bandwidth1 = freq_range1->max_bandwidth_khz; max_bandwidth2 = freq_range2->max_bandwidth_khz; - /* - * In case max_bandwidth1 == 0 and max_bandwith2 == 0 set - * output bandwidth as 0 (auto calculation). Next we will - * calculate this correctly in handle_channel function. - * In other case calculate output bandwidth here. - */ - if (max_bandwidth1 || max_bandwidth2) { - if (!max_bandwidth1) - max_bandwidth1 = reg_get_max_bandwidth(rd1, rule1); - if (!max_bandwidth2) - max_bandwidth2 = reg_get_max_bandwidth(rd2, rule2); - } + if (rule1->flags & NL80211_RRF_AUTO_BW) + max_bandwidth1 = reg_get_max_bandwidth(rd1, rule1); + if (rule2->flags & NL80211_RRF_AUTO_BW) + max_bandwidth2 = reg_get_max_bandwidth(rd2, rule2); freq_range->max_bandwidth_khz = min(max_bandwidth1, max_bandwidth2); + intersected_rule->flags = rule1->flags | rule2->flags; + + /* + * In case NL80211_RRF_AUTO_BW requested for both rules + * set AUTO_BW in intersected rule also. Next we will + * calculate BW correctly in handle_channel function. + * In other case remove AUTO_BW flag while we calculate + * maximum bandwidth correctly and auto calculation is + * not required. + */ + if ((rule1->flags & NL80211_RRF_AUTO_BW) && + (rule2->flags & NL80211_RRF_AUTO_BW)) + intersected_rule->flags |= NL80211_RRF_AUTO_BW; + else + intersected_rule->flags &= ~NL80211_RRF_AUTO_BW; + freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->max_bandwidth_khz > freq_diff) freq_range->max_bandwidth_khz = freq_diff; @@ -753,8 +755,6 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, power_rule->max_antenna_gain = min(power_rule1->max_antenna_gain, power_rule2->max_antenna_gain); - intersected_rule->flags = rule1->flags | rule2->flags; - if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; @@ -938,31 +938,42 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator) EXPORT_SYMBOL(reg_initiator_name); #ifdef CONFIG_CFG80211_REG_DEBUG -static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, +static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd, + struct ieee80211_channel *chan, const struct ieee80211_reg_rule *reg_rule) { const struct ieee80211_power_rule *power_rule; const struct ieee80211_freq_range *freq_range; - char max_antenna_gain[32]; + char max_antenna_gain[32], bw[32]; power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; if (!power_rule->max_antenna_gain) - snprintf(max_antenna_gain, 32, "N/A"); + snprintf(max_antenna_gain, sizeof(max_antenna_gain), "N/A"); + else + snprintf(max_antenna_gain, sizeof(max_antenna_gain), "%d", + power_rule->max_antenna_gain); + + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + freq_range->max_bandwidth_khz, + reg_get_max_bandwidth(regd, reg_rule)); else - snprintf(max_antenna_gain, 32, "%d", power_rule->max_antenna_gain); + snprintf(bw, sizeof(bw), "%d KHz", + freq_range->max_bandwidth_khz); REG_DBG_PRINT("Updating information on frequency %d MHz with regulatory rule:\n", chan->center_freq); - REG_DBG_PRINT("%d KHz - %d KHz @ %d KHz), (%s mBi, %d mBm)\n", + REG_DBG_PRINT("%d KHz - %d KHz @ %s), (%s mBi, %d mBm)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, - freq_range->max_bandwidth_khz, max_antenna_gain, + bw, max_antenna_gain, power_rule->max_eirp); } #else -static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, +static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd, + struct ieee80211_channel *chan, const struct ieee80211_reg_rule *reg_rule) { return; @@ -1022,17 +1033,16 @@ static void handle_channel(struct wiphy *wiphy, return; } - chan_reg_rule_print_dbg(chan, reg_rule); + regd = reg_get_regdomain(wiphy); + chan_reg_rule_print_dbg(regd, chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; max_bandwidth_khz = freq_range->max_bandwidth_khz; /* Check if auto calculation requested */ - if (!max_bandwidth_khz) { - regd = reg_get_regdomain(wiphy); + if (reg_rule->flags & NL80211_RRF_AUTO_BW) max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); - } if (max_bandwidth_khz < MHZ_TO_KHZ(40)) bw_flags = IEEE80211_CHAN_NO_HT40; @@ -1437,14 +1447,14 @@ static void handle_channel_custom(struct wiphy *wiphy, return; } - chan_reg_rule_print_dbg(chan, reg_rule); + chan_reg_rule_print_dbg(regd, chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; max_bandwidth_khz = freq_range->max_bandwidth_khz; /* Check if auto calculation requested */ - if (!max_bandwidth_khz) + if (reg_rule->flags & NL80211_RRF_AUTO_BW) max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); if (max_bandwidth_khz < MHZ_TO_KHZ(40)) @@ -1788,7 +1798,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) return; case NL80211_REGDOM_SET_BY_USER: treatment = reg_process_hint_user(reg_request); - if (treatment == REG_REQ_OK || + if (treatment == REG_REQ_IGNORE || treatment == REG_REQ_ALREADY_SET) return; queue_delayed_work(system_power_efficient_wq, @@ -2254,11 +2264,12 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) freq_range = ®_rule->freq_range; power_rule = ®_rule->power_rule; - if (!freq_range->max_bandwidth_khz) - snprintf(bw, 32, "%d KHz, AUTO", + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + freq_range->max_bandwidth_khz, reg_get_max_bandwidth(rd, reg_rule)); else - snprintf(bw, 32, "%d KHz", + snprintf(bw, sizeof(bw), "%d KHz", freq_range->max_bandwidth_khz); /* @@ -2481,6 +2492,7 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, int set_regdom(const struct ieee80211_regdomain *rd) { struct regulatory_request *lr; + bool user_reset = false; int r; if (!reg_is_valid_request(rd->alpha2)) { @@ -2497,6 +2509,7 @@ int set_regdom(const struct ieee80211_regdomain *rd) break; case NL80211_REGDOM_SET_BY_USER: r = reg_set_rd_user(rd, lr); + user_reset = true; break; case NL80211_REGDOM_SET_BY_DRIVER: r = reg_set_rd_driver(rd, lr); @@ -2510,8 +2523,14 @@ int set_regdom(const struct ieee80211_regdomain *rd) } if (r) { - if (r == -EALREADY) + switch (r) { + case -EALREADY: reg_set_request_processed(); + break; + default: + /* Back to world regulatory in case of errors */ + restore_regulatory_settings(user_reset); + } kfree(rd); return r; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5eaeed59db07..aabccf13e07b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1468,9 +1468,10 @@ TRACE_EVENT(rdev_sched_scan_start, TRACE_EVENT(rdev_tdls_mgmt, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *buf, size_t len), + u16 status_code, u32 peer_capability, + const u8 *buf, size_t len), TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code, - buf, len), + peer_capability, buf, len), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1478,6 +1479,7 @@ TRACE_EVENT(rdev_tdls_mgmt, __field(u8, action_code) __field(u8, dialog_token) __field(u16, status_code) + __field(u32, peer_capability) __dynamic_array(u8, buf, len) ), TP_fast_assign( @@ -1487,13 +1489,15 @@ TRACE_EVENT(rdev_tdls_mgmt, __entry->action_code = action_code; __entry->dialog_token = dialog_token; __entry->status_code = status_code; + __entry->peer_capability = peer_capability; memcpy(__get_dynamic_array(buf), buf, len); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", action_code: %u, " - "dialog_token: %u, status_code: %u, buf: %#.2x ", + "dialog_token: %u, status_code: %u, peer_capability: %u buf: %#.2x ", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->action_code, __entry->dialog_token, - __entry->status_code, ((u8 *)__get_dynamic_array(buf))[0]) + __entry->status_code, __entry->peer_capability, + ((u8 *)__get_dynamic_array(buf))[0]) ); TRACE_EVENT(rdev_dump_survey, diff --git a/net/wireless/util.c b/net/wireless/util.c index ad03af385556..2bb685f3e8fc 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1285,7 +1285,6 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, enum cfg80211_chan_mode chmode; int num_different_channels = 0; int total = 1; - bool radar_required = false; int i, j; ASSERT_RTNL(); @@ -1293,35 +1292,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, if (WARN_ON(hweight32(radar_detect) > 1)) return -EINVAL; - switch (iftype) { - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_P2P_GO: - case NL80211_IFTYPE_WDS: - /* if the interface could potentially choose a DFS channel, - * then mark DFS as required. - */ - if (!chan) { - if (chanmode != CHAN_MODE_UNDEFINED && radar_detect) - radar_required = true; - break; - } - radar_required = !!(chan->flags & IEEE80211_CHAN_RADAR); - break; - case NL80211_IFTYPE_P2P_CLIENT: - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_DEVICE: - case NL80211_IFTYPE_MONITOR: - break; - case NUM_NL80211_IFTYPES: - case NL80211_IFTYPE_UNSPECIFIED: - default: - return -EINVAL; - } - - if (radar_required && !radar_detect) + if (WARN_ON(iftype >= NUM_NL80211_IFTYPES)) return -EINVAL; /* Always allow software iftypes */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index bb3669d973a7..f02f511b7107 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1156,7 +1156,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, if (hlist_unhashed(&pol->bydst)) return NULL; - hlist_del(&pol->bydst); + hlist_del_init(&pol->bydst); hlist_del(&pol->byidx); list_del(&pol->walk.all); net->xfrm.policy_count[dir]--; @@ -2913,15 +2913,19 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; + rv = flow_cache_init(net); + if (rv < 0) + goto out; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); rwlock_init(&net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); - flow_cache_init(net); return 0; +out: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -2934,6 +2938,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + flow_cache_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index cee850c76165..8e9c781a6bba 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1171,6 +1171,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) } x->props.aalgo = orig->props.aalgo; + if (orig->aead) { + x->aead = xfrm_algo_aead_clone(orig->aead); + if (!x->aead) + goto error; + } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) @@ -1211,6 +1216,9 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->tfcpad = orig->tfcpad; + x->replay_maxdiff = orig->replay_maxdiff; + x->replay_maxage = orig->replay_maxage; x->curlft.add_time = orig->curlft.add_time; x->km.state = orig->km.state; x->km.seq = orig->km.seq; @@ -1223,11 +1231,12 @@ out: return NULL; } -/* net->xfrm.xfrm_state_lock is held */ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) { unsigned int h; - struct xfrm_state *x; + struct xfrm_state *x = NULL; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, @@ -1244,7 +1253,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, @@ -1259,11 +1268,13 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } - return NULL; + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); @@ -1458,7 +1469,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - struct net *net = xs_net(*dst); + struct net *net = xs_net(*src); if (!afinfo) return -EAFNOSUPPORT; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 903725b8cc70..cdd9e9c7ff0e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -32,11 +32,6 @@ #include <linux/in6.h> #endif -static inline int aead_len(struct xfrm_algo_aead *alg) -{ - return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); -} - static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) { struct nlattr *rt = attrs[type]; |