diff options
Diffstat (limited to 'net')
91 files changed, 3629 insertions, 2412 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index acf563fbdfd9..17b946f9ba31 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1061,8 +1061,15 @@ int hci_conn_del(struct hci_conn *conn) if (conn->type == ACL_LINK) { struct hci_conn *sco = conn->link; - if (sco) + if (sco) { sco->link = NULL; + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if (sco->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(sco); + } /* Unacked frames */ hdev->acl_cnt += conn->sent; @@ -1243,6 +1250,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) if (conn != hci_lookup_le_connect(hdev)) goto done; + /* Flush to make sure we send create conn cancel command if needed */ + flush_delayed_work(&conn->le_conn_timeout); hci_conn_failed(conn, bt_status(err)); done: @@ -1981,16 +1990,14 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, qos->latency = conn->le_conn_latency; } -static struct hci_conn *hci_bind_bis(struct hci_conn *conn, - struct bt_iso_qos *qos) +static void hci_bind_bis(struct hci_conn *conn, + struct bt_iso_qos *qos) { /* Update LINK PHYs according to QoS preference */ conn->le_tx_phy = qos->out.phy; conn->le_tx_phy = qos->out.phy; conn->iso_qos = *qos; conn->state = BT_BOUND; - - return conn; } static int create_big_sync(struct hci_dev *hdev, void *data) @@ -2119,11 +2126,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, if (IS_ERR(conn)) return conn; - conn = hci_bind_bis(conn, qos); - if (!conn) { - hci_conn_drop(conn); - return ERR_PTR(-ENOMEM); - } + hci_bind_bis(conn, qos); /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a3e0dc6a6e73..adfc3ea06d08 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2683,14 +2683,6 @@ 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; } @@ -2735,14 +2727,6 @@ 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; @@ -2763,14 +2747,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) */ err = l2cap_segment_sdu(chan, &seg_queue, msg, len); - /* The channel could have been closed while segmenting, - * check that it is still connected. - */ - if (chan->state != BT_CONNECTED) { - __skb_queue_purge(&seg_queue); - err = -ENOTCONN; - } - if (err) break; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index ca8f07f3542b..eebe256104bc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1624,6 +1624,14 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, if (!skb) return ERR_PTR(err); + /* 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 ERR_PTR(-ENOTCONN); + } + skb->priority = sk->sk_priority; bt_cb(skb)->l2cap.chan = chan; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d2ea8e19aa1b..7add66f30e4d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -859,6 +859,12 @@ static u32 get_supported_settings(struct hci_dev *hdev) hdev->set_bdaddr) settings |= MGMT_SETTING_CONFIGURATION; + if (cis_central_capable(hdev)) + settings |= MGMT_SETTING_CIS_CENTRAL; + + if (cis_peripheral_capable(hdev)) + settings |= MGMT_SETTING_CIS_PERIPHERAL; + settings |= MGMT_SETTING_PHY_CONFIGURATION; return settings; @@ -932,6 +938,12 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; + if (cis_central_capable(hdev)) + settings |= MGMT_SETTING_CIS_CENTRAL; + + if (cis_peripheral_capable(hdev)) + settings |= MGMT_SETTING_CIS_PERIPHERAL; + return settings; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8da0d73b368e..b766a84c8536 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -234,7 +234,7 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); @@ -484,7 +484,7 @@ out: __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); -int noinline bpf_fentry_test1(int a) +__bpf_kfunc int bpf_fentry_test1(int a) { return a + 1; } @@ -529,27 +529,35 @@ int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) return (long)arg->a; } -int noinline bpf_modify_return_test(int a, int *b) +__bpf_kfunc int bpf_modify_return_test(int a, int *b) { *b += 1; return a + *b; } -u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) { return a + b + c + d; } -int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) { return a + b; } -struct sock * noinline bpf_kfunc_call_test3(struct sock *sk) +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) { return sk; } +long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + struct prog_test_member1 { int a; }; @@ -574,21 +582,21 @@ static struct prog_test_ref_kfunc prog_test_struct = { .cnt = REFCOUNT_INIT(1), }; -noinline struct prog_test_ref_kfunc * +__bpf_kfunc struct prog_test_ref_kfunc * bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) { refcount_inc(&prog_test_struct.cnt); return &prog_test_struct; } -noinline struct prog_test_member * +__bpf_kfunc struct prog_test_member * bpf_kfunc_call_memb_acquire(void) { WARN_ON_ONCE(1); return NULL; } -noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) +__bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) { if (!p) return; @@ -596,11 +604,11 @@ noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) refcount_dec(&p->cnt); } -noinline void bpf_kfunc_call_memb_release(struct prog_test_member *p) +__bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p) { } -noinline void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) { WARN_ON_ONCE(1); } @@ -613,12 +621,14 @@ static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const i return (int *)p; } -noinline int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); } -noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); } @@ -628,16 +638,17 @@ noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, * Acquire functions must return struct pointers, so these ones are * failing. */ -noinline int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); } -noinline void bpf_kfunc_call_int_mem_release(int *p) +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) { } -noinline struct prog_test_ref_kfunc * +__bpf_kfunc struct prog_test_ref_kfunc * bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **pp, int a, int b) { struct prog_test_ref_kfunc *p = READ_ONCE(*pp); @@ -686,48 +697,53 @@ struct prog_test_fail3 { char arr2[]; }; -noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) { } -noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) { } -noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) { } -noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) { } -noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) { } -noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) { } -noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) { } -noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) { } -noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) { } -noinline void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) { } -noinline void bpf_kfunc_call_test_destructive(void) +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) { + return arg; } __diag_pop(); @@ -746,6 +762,7 @@ BTF_SET8_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) BTF_ID_FLAGS(func, bpf_kfunc_call_test2) BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE) @@ -767,6 +784,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_SET8_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 00e5743647b0..25c48d81a597 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -259,7 +259,7 @@ static int __mdb_fill_info(struct sk_buff *skb, #endif } else { ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); - e.state = MDB_PG_FLAGS_PERMANENT; + e.state = MDB_PERMANENT; } e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, @@ -421,8 +421,6 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); - cb->seq = net->dev_base_seq; - for_each_netdev_rcu(net, dev) { if (netif_is_bridge_master(dev)) { struct net_bridge *br = netdev_priv(dev); @@ -685,51 +683,58 @@ static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; -static bool is_valid_mdb_entry(struct br_mdb_entry *entry, - struct netlink_ext_ack *extack) +static int validate_mdb_entry(const struct nlattr *attr, + struct netlink_ext_ack *extack) { + struct br_mdb_entry *entry = nla_data(attr); + + if (nla_len(attr) != sizeof(struct br_mdb_entry)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length"); + return -EINVAL; + } + if (entry->ifindex == 0) { NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed"); - return false; + return -EINVAL; } if (entry->addr.proto == htons(ETH_P_IP)) { if (!ipv4_is_multicast(entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast"); - return false; + return -EINVAL; } if (ipv4_is_local_multicast(entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast"); - return false; + return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) } else if (entry->addr.proto == htons(ETH_P_IPV6)) { if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes"); - return false; + return -EINVAL; } #endif } else if (entry->addr.proto == 0) { /* L2 mdb */ if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) { NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast"); - return false; + return -EINVAL; } } else { NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol"); - return false; + return -EINVAL; } if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) { NL_SET_ERR_MSG_MOD(extack, "Unknown entry state"); - return false; + return -EINVAL; } if (entry->vid >= VLAN_VID_MASK) { NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id"); - return false; + return -EINVAL; } - return true; + return 0; } static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto, @@ -849,11 +854,10 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - MCAST_INCLUDE, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group"); + MCAST_INCLUDE, cfg->rt_protocol, extack); + if (unlikely(!p)) return -ENOMEM; - } + rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&p->timer, @@ -1075,11 +1079,10 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - cfg->filter_mode, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group"); + cfg->filter_mode, cfg->rt_protocol, + extack); + if (unlikely(!p)) return -ENOMEM; - } err = br_mdb_add_group_srcs(cfg, p, brmctx, extack); if (err) @@ -1101,8 +1104,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, return 0; err_del_port_group: - hlist_del_init(&p->mglist); - kfree(p); + br_multicast_del_port_group(p); return err; } @@ -1297,6 +1299,14 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, return 0; } +static const struct nla_policy mdba_policy[MDBA_SET_ENTRY_MAX + 1] = { + [MDBA_SET_ENTRY_UNSPEC] = { .strict_start_type = MDBA_SET_ENTRY_ATTRS + 1 }, + [MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + validate_mdb_entry, + sizeof(struct br_mdb_entry)), + [MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED }, +}; + static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) @@ -1307,7 +1317,7 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, int err; err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, - MDBA_SET_ENTRY_MAX, NULL, extack); + MDBA_SET_ENTRY_MAX, mdba_policy, extack); if (err) return err; @@ -1349,14 +1359,8 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute"); return -EINVAL; } - if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { - NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length"); - return -EINVAL; - } cfg->entry = nla_data(tb[MDBA_SET_ENTRY]); - if (!is_valid_mdb_entry(cfg->entry, extack)) - return -EINVAL; if (cfg->entry->ifindex != cfg->br->dev->ifindex) { struct net_device *pdev; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index dea1ee1bd095..96d1fc78dd39 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -31,6 +31,7 @@ #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif +#include <trace/events/bridge.h> #include "br_private.h" #include "br_private_mcast_eht.h" @@ -234,6 +235,29 @@ out: return pmctx; } +static struct net_bridge_mcast_port * +br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx = NULL; + struct net_bridge_vlan *vlan; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return NULL; + + /* Take RCU to access the vlan. */ + rcu_read_lock(); + + vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); + if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) + pmctx = &vlan->port_mcast_ctx; + + rcu_read_unlock(); + + return pmctx; +} + /* when snooping we need to check if the contexts should be used * in the following order: * - if pmctx is non-NULL (port), check if it should be used @@ -668,6 +692,101 @@ void br_multicast_del_group_src(struct net_bridge_group_src *src, __br_multicast_del_group_src(src); } +static int +br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, + struct netlink_ext_ack *extack, + const char *what) +{ + u32 max = READ_ONCE(pmctx->mdb_max_entries); + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + if (max && n >= max) { + NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", + what, n, max); + return -E2BIG; + } + + WRITE_ONCE(pmctx->mdb_n_entries, n + 1); + return 0; +} + +static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx) +{ + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + WARN_ON_ONCE(n == 0); + WRITE_ONCE(pmctx->mdb_n_entries, n - 1); +} + +static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, + const struct br_ip *group, + struct netlink_ext_ack *extack) +{ + struct net_bridge_mcast_port *pmctx; + int err; + + lockdep_assert_held_once(&port->br->multicast_lock); + + /* Always count on the port context. */ + err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack, + "Port"); + if (err) { + trace_br_mdb_full(port->dev, group); + return err; + } + + /* Only count on the VLAN context if VID is given, and if snooping on + * that VLAN is enabled. + */ + if (!group->vid) + return 0; + + pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid); + if (!pmctx) + return 0; + + err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN"); + if (err) { + trace_br_mdb_full(port->dev, group); + goto dec_one_out; + } + + return 0; + +dec_one_out: + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); + return err; +} + +static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (vid) { + pmctx = br_multicast_port_vid_to_port_ctx(port, vid); + if (pmctx) + br_multicast_port_ngroups_dec_one(pmctx); + } + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); +} + +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_n_entries); +} + +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) +{ + WRITE_ONCE(pmctx->mdb_max_entries, max); +} + +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_max_entries); +} + static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; @@ -702,6 +821,7 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, } else { br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); } + br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid); hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); @@ -1165,6 +1285,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, return mp; if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { + trace_br_mdb_full(br->dev, group); br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); @@ -1284,14 +1405,22 @@ struct net_bridge_port_group *br_multicast_new_port_group( unsigned char flags, const unsigned char *src, u8 filter_mode, - u8 rt_protocol) + u8 rt_protocol, + struct netlink_ext_ack *extack) { struct net_bridge_port_group *p; + int err; - p = kzalloc(sizeof(*p), GFP_ATOMIC); - if (unlikely(!p)) + err = br_multicast_port_ngroups_inc(port, group, extack); + if (err) return NULL; + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) { + NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); + goto dec_out; + } + p->key.addr = *group; p->key.port = port; p->flags = flags; @@ -1305,8 +1434,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( if (!br_multicast_is_star_g(group) && rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params)) { - kfree(p); - return NULL; + NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group"); + goto free_out; } rcu_assign_pointer(p->next, next); @@ -1320,6 +1449,25 @@ struct net_bridge_port_group *br_multicast_new_port_group( eth_broadcast_addr(p->eth_addr); return p; + +free_out: + kfree(p); +dec_out: + br_multicast_port_ngroups_dec(port, group->vid); + return NULL; +} + +void br_multicast_del_port_group(struct net_bridge_port_group *p) +{ + struct net_bridge_port *port = p->key.port; + __u16 vid = p->key.addr.vid; + + hlist_del_init(&p->mglist); + if (!br_multicast_is_star_g(&p->key.addr)) + rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, + br_sg_port_rht_params); + kfree(p); + br_multicast_port_ngroups_dec(port, vid); } void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1387,7 +1535,7 @@ __br_multicast_add_group(struct net_bridge_mcast *brmctx, } p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, - filter_mode, RTPROT_KERNEL); + filter_mode, RTPROT_KERNEL, NULL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; @@ -1933,6 +2081,25 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } + + if (br_multicast_port_ctx_is_vlan(pmctx)) { + struct net_bridge_port_group *pg; + u32 n = 0; + + /* The mcast_n_groups counter might be wrong. First, + * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries + * are flushed, thus mcast_n_groups after the toggle does not + * reflect the true values. And second, permanent entries added + * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected + * either. Thus we have to refresh the counter. + */ + + hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { + if (pg->key.addr.vid == pmctx->vlan->vid) + n++; + } + WRITE_ONCE(pmctx->mdb_n_entries, n); + } } void br_multicast_enable_port(struct net_bridge_port *port) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4316cc82ae17..9173e52b89e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void) + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ @@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, - p->multicast_eht_hosts_cnt)) + p->multicast_eht_hosts_cnt) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, + br_multicast_ngroups_get(&p->multicast_ctx)) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif @@ -858,6 +864,8 @@ static int br_afspec(struct net_bridge *br, } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_UNSPEC] = { .strict_start_type = + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, @@ -881,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -1015,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { + u32 max_groups; + + max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 8914290c75d4..17abf092f7ca 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -188,6 +188,9 @@ initvars: } static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = { + [IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC] = { + .strict_start_type = IFLA_BRIDGE_VLAN_TUNNEL_FLAGS + 1 + }, [IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 }, [IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 }, [IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 }, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 15ef7fd508ee..cef5f6ea850c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,6 +126,8 @@ struct net_bridge_mcast_port { struct hlist_node ip6_rlist; #endif /* IS_ENABLED(CONFIG_IPV6) */ unsigned char multicast_router; + u32 mdb_n_entries; + u32 mdb_max_entries; #endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ }; @@ -956,7 +958,9 @@ br_multicast_new_port_group(struct net_bridge_port *port, const struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src, - u8 filter_mode, u8 rt_protocol); + u8 filter_mode, u8 rt_protocol, + struct netlink_ext_ack *extack); +void br_multicast_del_port_group(struct net_bridge_port_group *p); int br_mdb_hash_init(struct net_bridge *br); void br_mdb_hash_fini(struct net_bridge *br); void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, @@ -974,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx); +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max); +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx); void br_mdb_init(void); void br_mdb_uninit(void); void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1757,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p); size_t br_vlan_opts_nl_size(void); int br_vlan_process_options(const struct net_bridge *br, const struct net_bridge_port *p, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bc75fa1e4666..8a3dbc09ba38 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1816,6 +1816,7 @@ out_err: /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, + const struct net_bridge_port *p, u16 flags, bool dump_stats) { @@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, goto out_err; if (v_opts) { - if (!br_vlan_opts_fill(skb, v_opts)) + if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) @@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br, goto out_kfree; } - if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) + if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); @@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - vlan_flags, dump_stats)) { + p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } @@ -2056,7 +2057,7 @@ update_end: else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - br_vlan_flags(range_start, pvid), + p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } @@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a2724d03278c..e378c2f3a9e2 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, curr_mc_rtr == range_mc_rtr; } -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p) { if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) || !__vlan_tun_put(skb, v)) @@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, br_vlan_multicast_router(v))) return false; + if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) && + (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + br_multicast_ngroups_get(&v->port_mcast_ctx)) || + nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&v->port_mcast_ctx)))) + return false; #endif return true; @@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void) + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */ #endif + 0; } @@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; *changed = true; } + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) { + u32 val; + + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans"); + return -EINVAL; + } + if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN"); + return -EINVAL; + } + + val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&v->port_mcast_ctx, val); + *changed = true; + } #endif return 0; diff --git a/net/can/gw.c b/net/can/gw.c index 23a3d89cad81..37528826935e 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1139,6 +1139,13 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (gwj->dst.dev->type != ARPHRD_CAN) goto out; + /* is sending the skb back to the incoming interface intended? */ + if (gwj->src.dev == gwj->dst.dev && + !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { + err = -EINVAL; + goto out; + } + ASSERT_RTNL(); err = cgw_register_filter(net, gwj); diff --git a/net/can/isotp.c b/net/can/isotp.c index fc81d77724a1..9bc344851704 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1220,6 +1220,9 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_family != AF_CAN) + return -EINVAL; + /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c47327927..ca4ad6cdd5cb 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); diff --git a/net/can/raw.c b/net/can/raw.c index ba86782ba8bb..f64469b98260 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -523,6 +523,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; + int fd_frames; int count = 0; int err = 0; @@ -664,17 +665,17 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; case CAN_RAW_FD_FRAMES: - if (optlen != sizeof(ro->fd_frames)) + if (optlen != sizeof(fd_frames)) return -EINVAL; - if (copy_from_sockptr(&ro->fd_frames, optval, optlen)) + if (copy_from_sockptr(&fd_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ - if (ro->xl_frames && !ro->fd_frames) { - ro->fd_frames = ro->xl_frames; + if (ro->xl_frames && !fd_frames) return -EINVAL; - } + + ro->fd_frames = fd_frames; break; case CAN_RAW_XL_FRAMES: diff --git a/net/core/Makefile b/net/core/Makefile index 10edd66a8a37..8f367813bc68 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o flow_offload.o gro.o + fib_notifier.o xdp.o flow_offload.o gro.o \ + netdev-genl.o netdev-genl-gen.o obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o diff --git a/net/core/dev.c b/net/core/dev.c index bb42150a38ec..7307a0c15c9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) + N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; diff --git a/net/core/dev.h b/net/core/dev.h index a065b7571441..e075e198092c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -9,6 +9,7 @@ struct net_device; struct netdev_bpf; struct netdev_phys_item_id; struct netlink_ext_ack; +struct cpumask; /* Random bits of netdevice that don't need to be exposed */ #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ @@ -134,4 +135,5 @@ static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_ipv4_max_size, size); } +int rps_cpumask_housekeeping(struct cpumask *mask); #endif diff --git a/net/core/filter.c b/net/core/filter.c index d8f9b53f3db6..2ce06a72a5ba 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4318,16 +4318,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; - /* XDP_REDIRECT is not fully supported yet for xdp frags since - * not all XDP capable drivers can map non-linear xdp_frame in - * ndo_xdp_xmit. - */ - if (unlikely(xdp_buff_has_frags(xdp) && - map_type != BPF_MAP_TYPE_CPUMAP)) - return -EOPNOTSUPP; + if (map_type == BPF_MAP_TYPE_XSKMAP) { + /* XDP_REDIRECT is not supported AF_XDP yet. */ + if (unlikely(xdp_buff_has_frags(xdp))) + return -EOPNOTSUPP; - if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + } return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); @@ -7536,7 +7533,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, @@ -7568,7 +7565,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 57258110bccd..6798f6d2423b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ca55dd747d6c..4b361ac6a252 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -831,42 +831,18 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) return len < PAGE_SIZE ? len : -EINVAL; } -static ssize_t store_rps_map(struct netdev_rx_queue *queue, - const char *buf, size_t len) +static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, + cpumask_var_t mask) { - struct rps_map *old_map, *map; - cpumask_var_t mask; - int err, cpu, i; static DEFINE_MUTEX(rps_map_mutex); - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); - if (err) { - free_cpumask_var(mask); - return err; - } - - if (!cpumask_empty(mask)) { - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); - if (cpumask_empty(mask)) { - free_cpumask_var(mask); - return -EINVAL; - } - } + struct rps_map *old_map, *map; + int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); - if (!map) { - free_cpumask_var(mask); + if (!map) return -ENOMEM; - } i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) @@ -893,9 +869,45 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, if (old_map) kfree_rcu(old_map, rcu); + return 0; +} +int rps_cpumask_housekeeping(struct cpumask *mask) +{ + if (!cpumask_empty(mask)) { + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); + if (cpumask_empty(mask)) + return -EINVAL; + } + return 0; +} + +static ssize_t store_rps_map(struct netdev_rx_queue *queue, + const char *buf, size_t len) +{ + cpumask_var_t mask; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) + goto out; + + err = rps_cpumask_housekeeping(mask); + if (err) + goto out; + + err = netdev_rx_queue_set_rps_mask(queue, mask); + +out: free_cpumask_var(mask); - return len; + return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, @@ -1071,6 +1083,13 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) goto err; } +#if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) + if (!cpumask_empty(&rps_default_mask)) { + error = netdev_rx_queue_set_rps_mask(queue, &rps_default_mask); + if (error) + goto err; + } +#endif kobject_uevent(kobj, KOBJ_ADD); return error; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index ee7006bbe49b..805b7385dd8d 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -41,6 +41,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add); EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); +EXPORT_TRACEPOINT_SYMBOL_GPL(br_mdb_full); #endif #if IS_ENABLED(CONFIG_PAGE_POOL) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c new file mode 100644 index 000000000000..48812ec843f5 --- /dev/null +++ b/net/core/netdev-genl-gen.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "netdev-genl-gen.h" + +#include <linux/netdev.h> + +/* NETDEV_CMD_DEV_GET - do */ +static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { + [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +/* Ops table for netdev */ +static const struct genl_split_ops netdev_nl_ops[2] = { + { + .cmd = NETDEV_CMD_DEV_GET, + .doit = netdev_nl_dev_get_doit, + .policy = netdev_dev_get_nl_policy, + .maxattr = NETDEV_A_DEV_IFINDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_DEV_GET, + .dumpit = netdev_nl_dev_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +static const struct genl_multicast_group netdev_nl_mcgrps[] = { + [NETDEV_NLGRP_MGMT] = { "mgmt", }, +}; + +struct genl_family netdev_nl_family __ro_after_init = { + .name = NETDEV_FAMILY_NAME, + .version = NETDEV_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = netdev_nl_ops, + .n_split_ops = ARRAY_SIZE(netdev_nl_ops), + .mcgrps = netdev_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), +}; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h new file mode 100644 index 000000000000..b16dc7e026bb --- /dev/null +++ b/net/core/netdev-genl-gen.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <linux/netdev.h> + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); + +enum { + NETDEV_NLGRP_MGMT, +}; + +extern struct genl_family netdev_nl_family; + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c new file mode 100644 index 000000000000..a4270fafdf11 --- /dev/null +++ b/net/core/netdev-genl.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/netdevice.h> +#include <linux/notifier.h> +#include <linux/rtnetlink.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#include "netdev-genl-gen.h" + +static int +netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, + u32 portid, u32 seq, int flags, u32 cmd) +{ + void *hdr; + + hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, + netdev->xdp_features, NETDEV_A_DEV_PAD)) { + genlmsg_cancel(rsp, hdr); + return -EINVAL; + } + + genlmsg_end(rsp, hdr); + + return 0; +} + +static void +netdev_genl_dev_notify(struct net_device *netdev, int cmd) +{ + struct sk_buff *ntf; + + if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), + NETDEV_NLGRP_MGMT)) + return; + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf, + 0, NETDEV_NLGRP_MGMT, GFP_KERNEL); +} + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *netdev; + struct sk_buff *rsp; + u32 ifindex; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (netdev) + err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid, + info->snd_seq, 0, info->genlhdr->cmd); + else + err = -ENODEV; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + int idx = 0, s_idx; + int h, s_h; + int err; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rtnl_lock(); + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + struct hlist_head *head; + + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(netdev, head, index_hlist) { + if (idx < s_idx) + goto cont; + err = netdev_nl_dev_fill(netdev, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NETDEV_CMD_DEV_GET); + if (err < 0) + break; +cont: + idx++; + } + } + + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + cb->args[1] = idx; + cb->args[0] = h; + cb->seq = net->dev_base_seq; + + return skb->len; +} + +static int netdev_genl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_REGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF); + break; + case NETDEV_UNREGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF); + break; + case NETDEV_XDP_FEAT_CHANGE: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block netdev_genl_nb = { + .notifier_call = netdev_genl_netdevice_event, +}; + +static int __init netdev_genl_init(void) +{ + int err; + + err = register_netdevice_notifier(&netdev_genl_nb); + if (err) + return err; + + err = genl_register_family(&netdev_nl_family); + if (err) + goto err_unreg_ntf; + + return 0; + +err_unreg_ntf: + unregister_netdevice_notifier(&netdev_genl_nb); + return err; +} + +subsys_initcall(netdev_genl_init); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b203d8660e4..193c18799865 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -511,8 +511,8 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; - /* BH protection not needed if current is serving softirq */ - if (in_serving_softirq()) + /* BH protection not needed if current is softirq */ + if (in_softirq()) ret = ptr_ring_produce(&pool->ring, page); else ret = ptr_ring_produce_bh(&pool->ring, page); @@ -570,7 +570,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_dma_sync_for_device(pool, page, dma_sync_size); - if (allow_direct && in_serving_softirq() && + if (allow_direct && in_softirq() && page_pool_recycle_in_cache(page, pool)) return NULL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b9f584955b77..5d8eb57867a9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,7 +58,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 40 +#define RTNL_SLAVE_MAX_TYPE 42 struct rtnl_link { rtnl_doit_func doit; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 44a19805c355..13ea10cf8544 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -84,11 +84,39 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_head_cache __ro_after_init; +struct kmem_cache *skbuff_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif + +/* skb_small_head_cache and related code is only supported + * for CONFIG_SLAB and CONFIG_SLUB. + * As soon as SLOB is removed from the kernel, we can clean up this. + */ +#if !defined(CONFIG_SLOB) +# define HAVE_SKB_SMALL_HEAD_CACHE 1 +#endif + +#ifdef HAVE_SKB_SMALL_HEAD_CACHE +static struct kmem_cache *skb_small_head_cache __ro_after_init; + +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) + +/* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. + * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique + * size, and we can differentiate heads from skb_small_head_cache + * vs system slabs by looking at their size (skb_end_offset()). + */ +#define SKB_SMALL_HEAD_CACHE_SIZE \ + (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ + (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ + SKB_SMALL_HEAD_SIZE) + +#define SKB_SMALL_HEAD_HEADROOM \ + SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) +#endif /* HAVE_SKB_SMALL_HEAD_CACHE */ + int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); @@ -257,7 +285,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, + nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -266,7 +294,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_unpoison_object_data(skbuff_head_cache, skb); + kasan_unpoison_object_data(skbuff_cache, skb); return skb; } @@ -324,7 +352,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -375,7 +403,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -478,17 +506,37 @@ EXPORT_SYMBOL(napi_build_skb); * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ -static void *kmalloc_reserve(size_t size, gfp_t flags, int node, +static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { - void *obj; bool ret_pfmemalloc = false; + unsigned int obj_size; + void *obj; + + obj_size = SKB_HEAD_ALIGN(*size); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && + !(flags & KMALLOC_NOT_NORMAL_BITS)) { + /* skb_small_head_cache has non power of two size, + * likely forcing SLUB to use order-3 pages. + * We deliberately attempt a NOMEMALLOC allocation only. + */ + obj = kmem_cache_alloc_node(skb_small_head_cache, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj) { + *size = SKB_SMALL_HEAD_CACHE_SIZE; + goto out; + } + } +#endif + *size = obj_size = kmalloc_size_roundup(obj_size); /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ - obj = kmalloc_node_track_caller(size, + obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) @@ -496,7 +544,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node, /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmalloc_node_track_caller(size, flags, node); + obj = kmalloc_node_track_caller(obj_size, flags, node); out: if (pfmemalloc) @@ -533,12 +581,11 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - unsigned int osize; bool pfmemalloc; u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_head_cache; + ? skbuff_fclone_cache : skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -558,18 +605,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - osize = kmalloc_size_roundup(size); - data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); + data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(osize); - prefetchw(data + size); + prefetchw(data + SKB_WITH_OVERHEAD(size)); /* * Only clear those fields we need to clear, not those that we will @@ -577,7 +620,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, osize); + __build_skb_around(skb, data, size); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { @@ -632,8 +675,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, goto skb_success; } - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; @@ -732,8 +774,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, data = page_frag_alloc_1k(&nc->page_small, gfp_mask); pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); } else { - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; @@ -809,6 +850,16 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) return page_pool_return_skb_page(virt_to_page(data)); } +static void skb_kfree_head(void *head, unsigned int end_offset) +{ +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (end_offset == SKB_SMALL_HEAD_HEADROOM) + kmem_cache_free(skb_small_head_cache, head); + else +#endif + kfree(head); +} + static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; @@ -818,7 +869,7 @@ static void skb_free_head(struct sk_buff *skb) return; skb_free_frag(head); } else { - kfree(head); + skb_kfree_head(head, skb_end_offset(skb)); } } @@ -870,7 +921,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -984,7 +1035,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_head_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1000,15 +1051,16 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) while (segs) { struct sk_buff *next = segs->next; - if (__kfree_skb_reason(segs, reason)) + if (__kfree_skb_reason(segs, reason)) { + skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); + } segs = next; } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_head_cache, sa.skb_count, - sa.skb_array); + kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1162,15 +1214,15 @@ static void napi_skb_cache_put(struct sk_buff *skb) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; - kasan_poison_object_data(skbuff_head_cache, skb); + kasan_poison_object_data(skbuff_cache, skb); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) - kasan_unpoison_object_data(skbuff_head_cache, + kasan_unpoison_object_data(skbuff_cache, nc->skb_cache[i]); - kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -1754,7 +1806,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); + n = kmem_cache_alloc(skbuff_cache, gfp_mask); if (!n) return NULL; @@ -1936,10 +1988,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); @@ -2002,7 +2051,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, return 0; nofrags: - kfree(data); + skb_kfree_head(data, size); nodata: return -ENOMEM; } @@ -4627,7 +4676,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", + skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -4639,6 +4688,19 @@ void __init skb_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. + * struct skb_shared_info is located at the end of skb->head, + * and should not be copied to/from user. + */ + skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + SKB_SMALL_HEAD_CACHE_SIZE, + 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, + 0, + SKB_SMALL_HEAD_HEADROOM, + NULL); +#endif skb_extensions_init(); } @@ -5493,7 +5555,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); } else { __kfree_skb(skb); } @@ -6287,10 +6349,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6306,7 +6365,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) @@ -6406,10 +6465,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6417,7 +6473,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); @@ -6453,7 +6509,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } skb_release_data(skb, SKB_CONSUMED); diff --git a/net/core/sock.c b/net/core/sock.c index f08b76acde9b..afbb02984d5f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1531,6 +1531,8 @@ set_sndbuf: ret = -EINVAL; break; } + if ((u8)val == SOCK_TXREHASH_DEFAULT) + val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -3383,7 +3385,7 @@ void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) } EXPORT_SYMBOL(sk_stop_timer_sync); -void sock_init_data(struct socket *sock, struct sock *sk) +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; @@ -3403,11 +3405,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; - sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); - sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } + sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) @@ -3455,7 +3456,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; - sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* @@ -3466,6 +3466,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data_uid); + +void sock_init_data(struct socket *sock, struct sock *sk) +{ + kuid_t uid = sock ? + SOCK_INODE(sock)->i_uid : + make_kuid(sock_net(sk)->user_ns, 0); + + sock_init_data_uid(sock, sk, uid); +} EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index e7b98162c632..7130e6d9e263 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -16,6 +16,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/sched/isolation.h> #include <net/ip.h> #include <net/sock.h> @@ -45,7 +46,59 @@ EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); int sysctl_devconf_inherit_init_net __read_mostly; EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); +#if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS) +static void dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos, + struct cpumask *mask) +{ + char kbuf[128]; + int len; + + if (*ppos || !*lenp) { + *lenp = 0; + return; + } + + len = min(sizeof(kbuf) - 1, *lenp); + len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); + if (!len) { + *lenp = 0; + return; + } + + if (len < *lenp) + kbuf[len++] = '\n'; + memcpy(buffer, kbuf, len); + *lenp = len; + *ppos += len; +} +#endif + #ifdef CONFIG_RPS +struct cpumask rps_default_mask; + +static int rps_default_mask_sysctl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int err = 0; + + rtnl_lock(); + if (write) { + err = cpumask_parse(buffer, &rps_default_mask); + if (err) + goto done; + + err = rps_cpumask_housekeeping(&rps_default_mask); + if (err) + goto done; + } else { + dump_cpumask(buffer, lenp, ppos, &rps_default_mask); + } + +done: + rtnl_unlock(); + return err; +} + static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -155,13 +208,6 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, write_unlock: mutex_unlock(&flow_limit_update_mutex); } else { - char kbuf[128]; - - if (*ppos || !*lenp) { - *lenp = 0; - goto done; - } - cpumask_clear(mask); rcu_read_lock(); for_each_possible_cpu(i) { @@ -171,17 +217,7 @@ write_unlock: } rcu_read_unlock(); - len = min(sizeof(kbuf) - 1, *lenp); - len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); - if (!len) { - *lenp = 0; - goto done; - } - if (len < *lenp) - kbuf[len++] = '\n'; - memcpy(buffer, kbuf, len); - *lenp = len; - *ppos += len; + dump_cpumask(buffer, lenp, ppos, mask); } done: @@ -472,6 +508,11 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = rps_sock_flow_sysctl }, + { + .procname = "rps_default_mask", + .mode = 0644, + .proc_handler = rps_default_mask_sysctl + }, #endif #ifdef CONFIG_NET_FLOW_LIMIT { @@ -675,6 +716,10 @@ static __net_initdata struct pernet_operations sysctl_core_ops = { static __init int sysctl_core_init(void) { +#if IS_ENABLED(CONFIG_RPS) + cpumask_copy(&rps_default_mask, cpu_none_mask); +#endif + register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } diff --git a/net/core/xdp.c b/net/core/xdp.c index a5a7ecf6391c..8c92fc553317 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -4,6 +4,7 @@ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> @@ -603,8 +604,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, - n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -673,7 +673,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -722,7 +722,7 @@ __diag_ignore_all("-Wmissing-prototypes", * * Returns 0 on success or ``-errno`` on error. */ -int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) +__bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } @@ -734,7 +734,7 @@ int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) * * Returns 0 on success or ``-errno`` on error. */ -int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) { return -EOPNOTSUPP; } @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void) return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); + +void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) +{ + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; + if (support_sg) + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG; + + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); +} +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); + +void xdp_features_clear_redirect_target(struct net_device *dev) +{ + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG); + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); +} +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); diff --git a/net/devlink/Makefile b/net/devlink/Makefile index 1b1eeac59cb3..daad4521c61e 100644 --- a/net/devlink/Makefile +++ b/net/devlink/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := leftover.o core.o netlink.o +obj-y := leftover.o core.o netlink.o dev.o diff --git a/net/devlink/core.c b/net/devlink/core.c index aeffd1b8206d..a4f47dafb864 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -205,7 +205,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, goto err_xa_alloc; devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + ret = register_netdevice_notifier(&devlink->netdevice_nb); if (ret) goto err_register_netdevice_notifier; @@ -266,8 +266,7 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); + WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); xa_erase(&devlinks, devlink->index); diff --git a/net/devlink/dev.c b/net/devlink/dev.c new file mode 100644 index 000000000000..78d824eda5ec --- /dev/null +++ b/net/devlink/dev.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <net/genetlink.h> +#include <net/sock.h> +#include "devl_internal.h" + +struct devlink_info_req { + struct sk_buff *msg; + void (*version_cb)(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv); + void *version_cb_priv; +}; + +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int +devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr, *act_info, *act_stats; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) + continue; + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; + } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *dev_stats; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) + goto nla_put_failure; + + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); + genlmsg_end(msg, hdr); + return 0; + +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); +} + +const struct devlink_cmd devl_cmd_get = { + .dump_one = devlink_nl_cmd_get_dump_one, +}; + +static void devlink_reload_failed_set(struct devlink *devlink, + bool reload_failed) +{ + if (devlink->reload_failed == reload_failed) + return; + devlink->reload_failed = reload_failed; + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +bool devlink_is_reload_failed(const struct devlink *devlink) +{ + return devlink->reload_failed; +} +EXPORT_SYMBOL_GPL(devlink_is_reload_failed); + +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *curr_net, + struct net *dest_net) +{ + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + devlink_notify_unregister(devlink); + move_netdevice_notifier_net(curr_net, dest_net, + &devlink->netdevice_nb); + write_pnet(&devlink->_net, dest_net); + devlink_notify_register(devlink); +} + +int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) +{ + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; + int err; + + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + + err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); + if (err) + return err; + + curr_net = devlink_net(devlink); + if (dest_net && !net_eq(dest_net, curr_net)) + devlink_reload_netns_change(devlink, curr_net, dest_net); + + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); + devlink_reload_failed_set(devlink, !!err); + if (err) + return err; + + WARN_ON(!(*actions_performed & BIT(action))); + /* Catch driver on updating the remote action within devlink reload */ + WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; + struct net *dest_net = NULL; + u32 actions_performed; + int err; + + err = devlink_resources_validate(devlink, NULL, info); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); + return err; + } + + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); + + if (dest_net) + put_net(dest_net); + + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); +} + +bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + +static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + void *hdr; + int err = 0; + u16 mode; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + if (ops->eswitch_mode_get) { + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto nla_put_failure; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_inline_mode_get) { + err = ops->eswitch_inline_mode_get(devlink, &inline_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, + inline_mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_encap_mode_get) { + err = ops->eswitch_encap_mode_get(devlink, &encap_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); + if (err) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, + info->snd_portid, info->snd_seq, 0); + + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + int err = 0; + u16 mode; + + if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { + if (!ops->eswitch_mode_set) + return -EOPNOTSUPP; + mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; + err = ops->eswitch_mode_set(devlink, mode, info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { + if (!ops->eswitch_inline_mode_set) + return -EOPNOTSUPP; + inline_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); + err = ops->eswitch_inline_mode_set(devlink, inline_mode, + info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { + if (!ops->eswitch_encap_mode_set) + return -EOPNOTSUPP; + encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); + err = ops->eswitch_encap_mode_set(devlink, encap_mode, + info->extack); + if (err) + return err; + } + + return 0; +} + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +int devlink_info_board_serial_number_put(struct devlink_info_req *req, + const char *bsn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, + bsn); +} +EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + struct nlattr *nest; + int err; + + if (req->version_cb) + req->version_cb(version_name, version_type, + req->version_cb_priv); + + if (!req->msg) + return 0; + + nest = nla_nest_start_noflag(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_stored_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +int devlink_info_version_running_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); + +static int devlink_nl_driver_info_get(struct device_driver *drv, + struct devlink_info_req *req) +{ + if (!drv) + return 0; + + if (drv->name[0]) + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, + drv->name); + + return 0; +} + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct device *dev = devlink_to_dev(devlink); + struct devlink_info_req req = {}; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + if (devlink->ops->info_get) { + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + } + + err = devlink_nl_driver_info_get(dev->driver, &req); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + int err; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} + +const struct devlink_cmd devl_cmd_info_get = { + .dump_one = devlink_nl_cmd_info_get_dump_one, +}; + +static int devlink_nl_flash_update_fill(struct sk_buff *msg, + struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) + goto out; + + if (params->status_msg && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, + params->status_msg)) + goto nla_put_failure; + if (params->component && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, + params->component)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, + params->done, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void __devlink_flash_update_notify(struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && + cmd != DEVLINK_CMD_FLASH_UPDATE_END && + cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); + if (err) + goto out_free_msg; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + return; + +out_free_msg: + nlmsg_free(msg); +} + +static void devlink_flash_update_begin_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE, + ¶ms); +} + +static void devlink_flash_update_end_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_END, + ¶ms); +} + +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); + +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + +struct devlink_flash_component_lookup_ctx { + const char *lookup_name; + bool lookup_name_found; +}; + +static void +devlink_flash_component_lookup_cb(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv) +{ + struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; + + if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || + lookup_ctx->lookup_name_found) + return; + + lookup_ctx->lookup_name_found = + !strcmp(lookup_ctx->lookup_name, version_name); +} + +static int devlink_flash_component_get(struct devlink *devlink, + struct nlattr *nla_component, + const char **p_component, + struct netlink_ext_ack *extack) +{ + struct devlink_flash_component_lookup_ctx lookup_ctx = {}; + struct devlink_info_req req = {}; + const char *component; + int ret; + + if (!nla_component) + return 0; + + component = nla_data(nla_component); + + if (!devlink->ops->info_get) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + + lookup_ctx.lookup_name = component; + req.version_cb = devlink_flash_component_lookup_cb; + req.version_cb_priv = &lookup_ctx; + + ret = devlink->ops->info_get(devlink, &req, NULL); + if (ret) + return ret; + + if (!lookup_ctx.lookup_name_found) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "selected component is not supported by this device"); + return -EINVAL; + } + *p_component = component; + return 0; +} + +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_overwrite_mask, *nla_file_name; + struct devlink_flash_update_params params = {}; + struct devlink *devlink = info->user_ptr[0]; + const char *file_name; + u32 supported_params; + int ret; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) + return -EINVAL; + + ret = devlink_flash_component_get(devlink, + info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], + ¶ms.component, info->extack); + if (ret) + return ret; + + supported_params = devlink->ops->supported_flash_update_params; + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } + + nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; + file_name = nla_data(nla_file_name); + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, + "failed to locate the requested firmware file"); + return ret; + } + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); + + return ret; +} + +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + struct devlink_info_req req = {}; + const struct nlattr *nlattr; + struct sk_buff *msg; + int rem, err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + if (!devlink->ops->info_get) + return; + + devl_lock(devlink); + if (devl_is_registered(devlink)) + __devlink_compat_running_version(devlink, buf, len); + devl_unlock(devlink); +} + +int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) +{ + struct devlink_flash_update_params params = {}; + int ret; + + devl_lock(devlink); + if (!devl_is_registered(devlink)) { + ret = -ENODEV; + goto out_unlock; + } + + if (!devlink->ops->flash_update) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) + goto out_unlock; + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, NULL); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); +out_unlock: + devl_unlock(devlink); + + return ret; +} + +static int +devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct nlattr *selftests; + void *hdr; + int err; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, + DEVLINK_CMD_SELFTESTS_GET); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto err_cancel_msg; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + if (devlink->ops->selftest_check(devlink, i, extack)) { + err = nla_put_flag(msg, i); + if (err) + goto err_cancel_msg; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->selftest_check) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, + info->snd_seq, 0, info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) +{ + if (!devlink->ops->selftest_check) + return 0; + + return devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); +} + +const struct devlink_cmd devl_cmd_selftests_get = { + .dump_one = devlink_nl_cmd_selftests_get_dump_one, +}; + +static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, + enum devlink_selftest_status test_status) +{ + struct nlattr *result_attr; + + result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); + if (!result_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || + nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, + test_status)) + goto nla_put_failure; + + nla_nest_end(skb, result_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, result_attr); + return -EMSGSIZE; +} + +static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, +}; + +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *attrs, *selftests; + struct sk_buff *msg; + void *hdr; + int err; + int i; + + if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) + return -EINVAL; + + attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; + + err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, + devlink_selftest_nl_policy, info->extack); + if (err < 0) + return err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto genlmsg_cancel; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + enum devlink_selftest_status test_status; + + if (nla_get_flag(tb[i])) { + if (!devlink->ops->selftest_check(devlink, i, + info->extack)) { + if (devlink_selftest_result_put(msg, i, + DEVLINK_SELFTEST_STATUS_SKIP)) + goto selftests_nest_cancel; + continue; + } + + test_status = devlink->ops->selftest_run(devlink, i, + info->extack); + if (devlink_selftest_result_put(msg, i, test_status)) + goto selftests_nest_cancel; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +selftests_nest_cancel: + nla_nest_cancel(msg, selftests); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return err; +} diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index bdd7ad25c7e8..941174e157d4 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -139,6 +139,16 @@ devlink_dump_state(struct netlink_callback *cb) return (struct devlink_nl_dump_state *)cb->ctx; } +static inline int +devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + /* Commands */ extern const struct devlink_cmd devl_cmd_get; extern const struct devlink_cmd devl_cmd_port_get; @@ -157,6 +167,9 @@ extern const struct devlink_cmd devl_cmd_rate_get; extern const struct devlink_cmd devl_cmd_linecard_get; extern const struct devlink_cmd devl_cmd_selftests_get; +/* Notify */ +void devlink_notify(struct devlink *devlink, enum devlink_command cmd); + /* Ports */ int devlink_port_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr); @@ -176,6 +189,12 @@ static inline bool devlink_reload_supported(const struct devlink_ops *ops) return ops->reload_down && ops->reload_up; } +/* Resources */ +struct devlink_resource; +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info); + /* Line cards */ struct devlink_linecard; @@ -183,8 +202,19 @@ struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info); /* Rates */ +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); struct devlink_rate * devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info); struct devlink_rate * devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info); +/* Devlink nl cmds */ +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index 056d9ca14a3d..f05ab093d231 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -143,10 +143,6 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), }; -static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { - [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, -}; - #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ @@ -596,15 +592,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) -{ - if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) - return -EMSGSIZE; - if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) - return -EMSGSIZE; - return 0; -} - static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) { struct nlattr *nested_attr; @@ -641,185 +628,6 @@ size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } -struct devlink_reload_combination { - enum devlink_reload_action action; - enum devlink_reload_limit limit; -}; - -static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { - { - /* can't reinitialize driver with no down time */ - .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, - }, -}; - -static bool -devlink_reload_combination_is_invalid(enum devlink_reload_action action, - enum devlink_reload_limit limit) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) - if (devlink_reload_invalid_combinations[i].action == action && - devlink_reload_invalid_combinations[i].limit == limit) - return true; - return false; -} - -static bool -devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) -{ - return test_bit(action, &devlink->ops->reload_actions); -} - -static bool -devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) -{ - return test_bit(limit, &devlink->ops->reload_limits); -} - -static int devlink_reload_stat_put(struct sk_buff *msg, - enum devlink_reload_limit limit, u32 value) -{ - struct nlattr *reload_stats_entry; - - reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); - if (!reload_stats_entry) - return -EMSGSIZE; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || - nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) - goto nla_put_failure; - nla_nest_end(msg, reload_stats_entry); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, reload_stats_entry); - return -EMSGSIZE; -} - -static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) -{ - struct nlattr *reload_stats_attr, *act_info, *act_stats; - int i, j, stat_idx; - u32 value; - - if (!is_remote) - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); - else - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); - - if (!reload_stats_attr) - return -EMSGSIZE; - - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && - !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC) - continue; - act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); - if (!act_info) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) - goto action_info_nest_cancel; - act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); - if (!act_stats) - goto action_info_nest_cancel; - - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. - * Stats of actions with unspecified limit are shown - * though drivers don't need to register unspecified - * limit. - */ - if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) || - devlink_reload_combination_is_invalid(i, j)) - continue; - - stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; - if (!is_remote) - value = devlink->stats.reload_stats[stat_idx]; - else - value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, j, value)) - goto action_stats_nest_cancel; - } - nla_nest_end(msg, act_stats); - nla_nest_end(msg, act_info); - } - nla_nest_end(msg, reload_stats_attr); - return 0; - -action_stats_nest_cancel: - nla_nest_cancel(msg, act_stats); -action_info_nest_cancel: - nla_nest_cancel(msg, act_info); -nla_put_failure: - nla_nest_cancel(msg, reload_stats_attr); - return -EMSGSIZE; -} - -static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct nlattr *dev_stats; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) - goto nla_put_failure; - - dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); - if (!dev_stats) - goto nla_put_failure; - - if (devlink_reload_stats_put(msg, devlink, false)) - goto dev_stats_nest_cancel; - if (devlink_reload_stats_put(msg, devlink, true)) - goto dev_stats_nest_cancel; - - nla_nest_end(msg, dev_stats); - genlmsg_end(msg, hdr); - return 0; - -dev_stats_nest_cancel: - nla_nest_cancel(msg, dev_stats); -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { @@ -1274,39 +1082,6 @@ devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, return false; } -static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); -} - -const struct devlink_cmd devl_cmd_get = { - .dump_one = devlink_nl_cmd_get_dump_one, -}; - static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3064,85 +2839,8 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - void *hdr; - int err = 0; - u16 mode; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto nla_put_failure; - - if (ops->eswitch_mode_get) { - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - goto nla_put_failure; - err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_inline_mode_get) { - err = ops->eswitch_inline_mode_get(devlink, &inline_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, - inline_mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_encap_mode_get) { - err = ops->eswitch_encap_mode_get(devlink, &encap_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); - if (err) - goto nla_put_failure; - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, - info->snd_portid, info->snd_seq, 0); - - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, - struct netlink_ext_ack *extack) +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct devlink_rate *devlink_rate; @@ -3154,52 +2852,6 @@ static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, return 0; } -static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - int err = 0; - u16 mode; - - if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { - if (!ops->eswitch_mode_set) - return -EOPNOTSUPP; - mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); - err = devlink_rate_nodes_check(devlink, mode, info->extack); - if (err) - return err; - err = ops->eswitch_mode_set(devlink, mode, info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { - if (!ops->eswitch_inline_mode_set) - return -EOPNOTSUPP; - inline_mode = nla_get_u8( - info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); - err = ops->eswitch_inline_mode_set(devlink, inline_mode, - info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { - if (!ops->eswitch_encap_mode_set) - return -EOPNOTSUPP; - encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); - err = ops->eswitch_encap_mode_set(devlink, encap_mode, - info->extack); - if (err) - return err; - } - - return 0; -} - int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match) { @@ -4170,10 +3822,9 @@ static int devlink_nl_cmd_resource_dump(struct sk_buff *skb, return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0); } -static int -devlink_resources_validate(struct devlink *devlink, - struct devlink_resource *resource, - struct genl_info *info) +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info) { struct list_head *resource_list; int err = 0; @@ -4193,698 +3844,6 @@ devlink_resources_validate(struct devlink *devlink, return err; } -static struct net *devlink_netns_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; - struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; - struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; - struct net *net; - - if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { - NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); - return ERR_PTR(-EINVAL); - } - - if (netns_pid_attr) { - net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); - } else if (netns_fd_attr) { - net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); - } else if (netns_id_attr) { - net = get_net_ns_by_id(sock_net(skb->sk), - nla_get_u32(netns_id_attr)); - if (!net) - net = ERR_PTR(-EINVAL); - } else { - WARN_ON(1); - net = ERR_PTR(-EINVAL); - } - if (IS_ERR(net)) { - NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); - return ERR_PTR(-EINVAL); - } - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { - put_net(net); - return ERR_PTR(-EPERM); - } - return net; -} - -static void devlink_reload_netns_change(struct devlink *devlink, - struct net *curr_net, - struct net *dest_net) -{ - /* Userspace needs to be notified about devlink objects - * removed from original and entering new network namespace. - * The rest of the devlink objects are re-created during - * reload process so the notifications are generated separatelly. - */ - devlink_notify_unregister(devlink); - move_netdevice_notifier_net(curr_net, dest_net, - &devlink->netdevice_nb); - write_pnet(&devlink->_net, dest_net); - devlink_notify_register(devlink); -} - -static void devlink_reload_failed_set(struct devlink *devlink, - bool reload_failed) -{ - if (devlink->reload_failed == reload_failed) - return; - devlink->reload_failed = reload_failed; - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -bool devlink_is_reload_failed(const struct devlink *devlink) -{ - return devlink->reload_failed; -} -EXPORT_SYMBOL_GPL(devlink_is_reload_failed); - -static void -__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, - enum devlink_reload_limit limit, u32 actions_performed) -{ - unsigned long actions = actions_performed; - int stat_idx; - int action; - - for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { - stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; - reload_stats[stat_idx]++; - } - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -static void -devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, - u32 actions_performed) -{ - __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, - actions_performed); -} - -/** - * devlink_remote_reload_actions_performed - Update devlink on reload actions - * performed which are not a direct result of devlink reload call. - * - * This should be called by a driver after performing reload actions in case it was not - * a result of devlink reload call. For example fw_activate was performed as a result - * of devlink reload triggered fw_activate on another host. - * The motivation for this function is to keep data on reload actions performed on this - * function whether it was done due to direct devlink reload call or not. - * - * @devlink: devlink - * @limit: reload limit - * @actions_performed: bitmask of actions performed - */ -void devlink_remote_reload_actions_performed(struct devlink *devlink, - enum devlink_reload_limit limit, - u32 actions_performed) -{ - if (WARN_ON(!actions_performed || - actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || - limit > DEVLINK_RELOAD_LIMIT_MAX)) - return; - - __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, - actions_performed); -} -EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); - -int devlink_reload(struct devlink *devlink, struct net *dest_net, - enum devlink_reload_action action, - enum devlink_reload_limit limit, - u32 *actions_performed, struct netlink_ext_ack *extack) -{ - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - struct net *curr_net; - int err; - - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats)); - - err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); - if (err) - return err; - - curr_net = devlink_net(devlink); - if (dest_net && !net_eq(dest_net, curr_net)) - devlink_reload_netns_change(devlink, curr_net, dest_net); - - err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); - devlink_reload_failed_set(devlink, !!err); - if (err) - return err; - - WARN_ON(!(*actions_performed & BIT(action))); - /* Catch driver on updating the remote action within devlink reload */ - WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats))); - devlink_reload_stats_update(devlink, limit, *actions_performed); - return 0; -} - -static int -devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, - enum devlink_command cmd, struct genl_info *info) -{ - struct sk_buff *msg; - void *hdr; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, - actions_performed)) - goto nla_put_failure; - genlmsg_end(msg, hdr); - - return genlmsg_reply(msg, info); - -nla_put_failure: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - enum devlink_reload_action action; - enum devlink_reload_limit limit; - struct net *dest_net = NULL; - u32 actions_performed; - int err; - - err = devlink_resources_validate(devlink, NULL, info); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); - return err; - } - - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) - action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); - else - action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; - - if (!devlink_reload_action_is_supported(devlink, action)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested reload action is not supported by the driver"); - return -EOPNOTSUPP; - } - - limit = DEVLINK_RELOAD_LIMIT_UNSPEC; - if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { - struct nla_bitfield32 limits; - u32 limits_selected; - - limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); - limits_selected = limits.value & limits.selector; - if (!limits_selected) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); - return -EINVAL; - } - for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) - if (limits_selected & BIT(limit)) - break; - /* UAPI enables multiselection, but currently it is not used */ - if (limits_selected != BIT(limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Multiselection of limit is not supported"); - return -EOPNOTSUPP; - } - if (!devlink_reload_limit_is_supported(devlink, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is not supported by the driver"); - return -EOPNOTSUPP; - } - if (devlink_reload_combination_is_invalid(action, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is invalid for this action"); - return -EINVAL; - } - } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - - err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); - - if (dest_net) - put_net(dest_net); - - if (err) - return err; - /* For backward compatibility generate reply only if attributes used by user */ - if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) - return 0; - - return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, - DEVLINK_CMD_RELOAD, info); -} - -static int devlink_nl_flash_update_fill(struct sk_buff *msg, - struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - void *hdr; - - hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) - goto out; - - if (params->status_msg && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - params->status_msg)) - goto nla_put_failure; - if (params->component && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - params->component)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - params->done, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - params->total, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, - params->timeout, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - -out: - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void __devlink_flash_update_notify(struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && - cmd != DEVLINK_CMD_FLASH_UPDATE_END && - cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); - if (err) - goto out_free_msg; - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); - return; - -out_free_msg: - nlmsg_free(msg); -} - -static void devlink_flash_update_begin_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE, - ¶ms); -} - -static void devlink_flash_update_end_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_END, - ¶ms); -} - -void devlink_flash_update_status_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .done = done, - .total = total, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); - -void devlink_flash_update_timeout_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long timeout) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .timeout = timeout, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); - -struct devlink_info_req { - struct sk_buff *msg; - void (*version_cb)(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv); - void *version_cb_priv; -}; - -struct devlink_flash_component_lookup_ctx { - const char *lookup_name; - bool lookup_name_found; -}; - -static void -devlink_flash_component_lookup_cb(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv) -{ - struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; - - if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || - lookup_ctx->lookup_name_found) - return; - - lookup_ctx->lookup_name_found = - !strcmp(lookup_ctx->lookup_name, version_name); -} - -static int devlink_flash_component_get(struct devlink *devlink, - struct nlattr *nla_component, - const char **p_component, - struct netlink_ext_ack *extack) -{ - struct devlink_flash_component_lookup_ctx lookup_ctx = {}; - struct devlink_info_req req = {}; - const char *component; - int ret; - - if (!nla_component) - return 0; - - component = nla_data(nla_component); - - if (!devlink->ops->info_get) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "component update is not supported by this device"); - return -EOPNOTSUPP; - } - - lookup_ctx.lookup_name = component; - req.version_cb = devlink_flash_component_lookup_cb; - req.version_cb_priv = &lookup_ctx; - - ret = devlink->ops->info_get(devlink, &req, NULL); - if (ret) - return ret; - - if (!lookup_ctx.lookup_name_found) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "selected component is not supported by this device"); - return -EINVAL; - } - *p_component = component; - return 0; -} - -static int devlink_nl_cmd_flash_update(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *nla_overwrite_mask, *nla_file_name; - struct devlink_flash_update_params params = {}; - struct devlink *devlink = info->user_ptr[0]; - const char *file_name; - u32 supported_params; - int ret; - - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) - return -EINVAL; - - ret = devlink_flash_component_get(devlink, - info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], - ¶ms.component, info->extack); - if (ret) - return ret; - - supported_params = devlink->ops->supported_flash_update_params; - - nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; - if (nla_overwrite_mask) { - struct nla_bitfield32 sections; - - if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, - "overwrite settings are not supported by this device"); - return -EOPNOTSUPP; - } - sections = nla_get_bitfield32(nla_overwrite_mask); - params.overwrite_mask = sections.value & sections.selector; - } - - nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; - file_name = nla_data(nla_file_name); - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); - return ret; - } - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); - - return ret; -} - -static int -devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, - u32 portid, u32 seq, int flags, - struct netlink_ext_ack *extack) -{ - struct nlattr *selftests; - void *hdr; - int err; - int i; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, - DEVLINK_CMD_SELFTESTS_GET); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto err_cancel_msg; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - if (devlink->ops->selftest_check(devlink, i, extack)) { - err = nla_put_flag(msg, i); - if (err) - goto err_cancel_msg; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (!devlink->ops->selftest_check) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, - info->snd_seq, 0, info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) -{ - if (!devlink->ops->selftest_check) - return 0; - - return devlink_nl_selftests_fill(msg, devlink, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); -} - -const struct devlink_cmd devl_cmd_selftests_get = { - .dump_one = devlink_nl_cmd_selftests_get_dump_one, -}; - -static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, - enum devlink_selftest_status test_status) -{ - struct nlattr *result_attr; - - result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); - if (!result_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || - nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, - test_status)) - goto nla_put_failure; - - nla_nest_end(skb, result_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, result_attr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; - struct devlink *devlink = info->user_ptr[0]; - struct nlattr *attrs, *selftests; - struct sk_buff *msg; - void *hdr; - int err; - int i; - - if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) - return -EINVAL; - - attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; - - err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, - devlink_selftest_nl_policy, info->extack); - if (err < 0) - return err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = -EMSGSIZE; - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto genlmsg_cancel; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - enum devlink_selftest_status test_status; - - if (nla_get_flag(tb[i])) { - if (!devlink->ops->selftest_check(devlink, i, - info->extack)) { - if (devlink_selftest_result_put(msg, i, - DEVLINK_SELFTEST_STATUS_SKIP)) - goto selftests_nest_cancel; - continue; - } - - test_status = devlink->ops->selftest_run(devlink, i, - info->extack); - if (devlink_selftest_result_put(msg, i, test_status)) - goto selftests_nest_cancel; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return genlmsg_reply(msg, info); - -selftests_nest_cancel: - nla_nest_cancel(msg, selftests); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return err; -} - static const struct devlink_param devlink_param_generic[] = { { .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, @@ -6430,205 +5389,6 @@ out_unlock: return err; } -int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); -} -EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); - -int devlink_info_board_serial_number_put(struct devlink_info_req *req, - const char *bsn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, - bsn); -} -EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); - -static int devlink_info_version_put(struct devlink_info_req *req, int attr, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - struct nlattr *nest; - int err; - - if (req->version_cb) - req->version_cb(version_name, version_type, - req->version_cb_priv); - - if (!req->msg) - return 0; - - nest = nla_nest_start_noflag(req->msg, attr); - if (!nest) - return -EMSGSIZE; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, - version_name); - if (err) - goto nla_put_failure; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, - version_value); - if (err) - goto nla_put_failure; - - nla_nest_end(req->msg, nest); - - return 0; - -nla_put_failure: - nla_nest_cancel(req->msg, nest); - return err; -} - -int devlink_info_version_fixed_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); - -int devlink_info_version_stored_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); - -int devlink_info_version_stored_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); - -int devlink_info_version_running_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put); - -int devlink_info_version_running_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); - -static int devlink_nl_driver_info_get(struct device_driver *drv, - struct devlink_info_req *req) -{ - if (!drv) - return 0; - - if (drv->name[0]) - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, - drv->name); - - return 0; -} - -static int -devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, struct netlink_ext_ack *extack) -{ - struct device *dev = devlink_to_dev(devlink); - struct devlink_info_req req = {}; - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - req.msg = msg; - if (devlink->ops->info_get) { - err = devlink->ops->info_get(devlink, &req, extack); - if (err) - goto err_cancel_msg; - } - - err = devlink_nl_driver_info_get(dev->driver, &req); - if (err) - goto err_cancel_msg; - - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - int err; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - if (err == -EOPNOTSUPP) - err = 0; - return err; -} - -const struct devlink_cmd devl_cmd_info_get = { - .dump_one = devlink_nl_cmd_info_get_dump_one, -}; - struct devlink_fmsg_item { struct list_head list; int attrtype; @@ -7866,18 +6626,22 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, err = devlink_fmsg_obj_nest_start(fmsg); if (err) - return err; + goto out; err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) - return err; + goto out; err = devlink_fmsg_obj_nest_end(fmsg); if (err) - return err; + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); - return devlink_fmsg_snd(fmsg, info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); +out: + devlink_fmsg_free(fmsg); + return err; } static int @@ -9257,35 +8021,6 @@ const struct genl_small_ops devlink_nl_ops[56] = { /* -- No new ops here! Use split ops going forward! -- */ }; -bool devlink_reload_actions_valid(const struct devlink_ops *ops) -{ - const struct devlink_reload_combination *comb; - int i; - - if (!devlink_reload_supported(ops)) { - if (WARN_ON(ops->reload_actions)) - return false; - return true; - } - - if (WARN_ON(!ops->reload_actions || - ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) - return false; - - if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || - ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) - return false; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { - comb = &devlink_reload_invalid_combinations[i]; - if (ops->reload_actions == BIT(comb->action) && - ops->reload_limits == BIT(comb->limit)) - return false; - } - return true; -} - static void devlink_trap_policer_notify(struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, @@ -9695,6 +8430,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this @@ -9704,6 +8441,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, netdev); break; case NETDEV_UNREGISTER: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. @@ -12068,85 +10807,6 @@ devl_trap_policers_unregister(struct devlink *devlink, } EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); -static void __devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - struct devlink_info_req req = {}; - const struct nlattr *nlattr; - struct sk_buff *msg; - int rem, err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - req.msg = msg; - err = devlink->ops->info_get(devlink, &req, NULL); - if (err) - goto free_msg; - - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { - const struct nlattr *kv; - int rem_kv; - - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - - strlcat(buf, nla_data(kv), len); - strlcat(buf, " ", len); - } - } -free_msg: - nlmsg_free(msg); -} - -void devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - if (!devlink->ops->info_get) - return; - - devl_lock(devlink); - if (devl_is_registered(devlink)) - __devlink_compat_running_version(devlink, buf, len); - devl_unlock(devlink); -} - -int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) -{ - struct devlink_flash_update_params params = {}; - int ret; - - devl_lock(devlink); - if (!devl_is_registered(devlink)) { - ret = -ENODEV; - goto out_unlock; - } - - if (!devlink->ops->flash_update) { - ret = -EOPNOTSUPP; - goto out_unlock; - } - - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) - goto out_unlock; - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, NULL); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); -out_unlock: - devl_unlock(devlink); - - return ret; -} - int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 26c458f50ac6..6957971c2db2 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2692,7 +2692,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2705,8 +2706,8 @@ static int dsa_slave_changeupper(struct net_device *dev, err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2718,8 +2719,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c index 7e51f7633001..e612856eed8c 100644 --- a/net/ethtool/mm.c +++ b/net/ethtool/mm.c @@ -56,7 +56,7 @@ static int mm_prepare_data(const struct ethnl_req_info *req_base, out_complete: ethnl_ops_complete(dev); - return 0; + return ret; } static int mm_reply_size(const struct ethnl_req_info *req_base, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f992a323b95..2c778b013cb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -347,6 +347,7 @@ lookup_protocol: sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6ed7e65de494..7d206a10ad14 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1246,9 +1246,6 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); - if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) - sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 006c1f0ed8b4..94df935ee0c5 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -93,7 +93,7 @@ int raw_hash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_nulls_head *hlist; - hlist = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)]; + hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); __sk_nulls_add_node_rcu(sk, hlist); @@ -160,9 +160,9 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) * RFC 1122: SHOULD pass TOS value up to the transport layer. * -> It does. And not only TOS, but all IP header. */ -static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) +static int raw_v4_input(struct net *net, struct sk_buff *skb, + const struct iphdr *iph, int hash) { - struct net *net = dev_net(skb->dev); struct hlist_nulls_head *hlist; struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); @@ -193,9 +193,10 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) int raw_local_deliver(struct sk_buff *skb, int protocol) { - int hash = protocol & (RAW_HTABLE_SIZE - 1); + struct net *net = dev_net(skb->dev); - return raw_v4_input(skb, ip_hdr(skb), hash); + return raw_v4_input(net, skb, ip_hdr(skb), + raw_hashfunc(net, protocol)); } static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) @@ -271,7 +272,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) struct sock *sk; int hash; - hash = protocol & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, protocol); hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); @@ -287,11 +288,13 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + /* Charge it to the socket. */ ipv4_pktinfo_prepare(sk, skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -302,7 +305,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index d2c470524e58..146792cd26fe 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -295,7 +295,7 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) } /* override sysctl_tcp_min_tso_segs */ -static u32 bbr_min_tso_segs(struct sock *sk) +__bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; } @@ -328,7 +328,7 @@ static void bbr_save_cwnd(struct sock *sk) bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp)); } -static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) +__bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); @@ -1023,7 +1023,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_update_gains(sk); } -static void bbr_main(struct sock *sk, const struct rate_sample *rs) +__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; @@ -1035,7 +1035,7 @@ static void bbr_main(struct sock *sk, const struct rate_sample *rs) bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } -static void bbr_init(struct sock *sk) +__bpf_kfunc static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); @@ -1077,7 +1077,7 @@ static void bbr_init(struct sock *sk) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } -static u32 bbr_sndbuf_expand(struct sock *sk) +__bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk) { /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ return 3; @@ -1086,7 +1086,7 @@ static u32 bbr_sndbuf_expand(struct sock *sk) /* In theory BBR does not need to undo the cwnd since it does not * always reduce cwnd on losses (see bbr_main()). Keep it for now. */ -static u32 bbr_undo_cwnd(struct sock *sk) +__bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); @@ -1097,7 +1097,7 @@ static u32 bbr_undo_cwnd(struct sock *sk) } /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ -static u32 bbr_ssthresh(struct sock *sk) +__bpf_kfunc static u32 bbr_ssthresh(struct sock *sk) { bbr_save_cwnd(sk); return tcp_sk(sk)->snd_ssthresh; @@ -1125,7 +1125,7 @@ static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, return 0; } -static void bbr_set_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state) { struct bbr *bbr = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index d3cae40749e8..db8b4b488c31 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -403,7 +403,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ -u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) +__bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); @@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ -void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) +__bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { /* If credits accumulated at a higher w, apply them gently now. */ if (tp->snd_cwnd_cnt >= w) { @@ -443,7 +443,7 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ -void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) +__bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); @@ -462,7 +462,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); /* Slow start threshold is half the congestion window (min 2) */ -u32 tcp_reno_ssthresh(struct sock *sk) +__bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -470,7 +470,7 @@ u32 tcp_reno_ssthresh(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); -u32 tcp_reno_undo_cwnd(struct sock *sk) +__bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 768c10c1f649..0fd78ecb67e7 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -126,7 +126,7 @@ static inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -static void cubictcp_init(struct sock *sk) +__bpf_kfunc static void cubictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); @@ -139,7 +139,7 @@ static void cubictcp_init(struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +__bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); @@ -321,7 +321,7 @@ tcp_friendliness: ca->cnt = max(ca->cnt, 2U); } -static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) +__bpf_kfunc static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); @@ -338,7 +338,7 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) tcp_cong_avoid_ai(tp, ca->cnt, acked); } -static u32 cubictcp_recalc_ssthresh(struct sock *sk) +__bpf_kfunc static u32 cubictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); @@ -355,7 +355,7 @@ static u32 cubictcp_recalc_ssthresh(struct sock *sk) return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } -static void cubictcp_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void cubictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); @@ -445,7 +445,7 @@ static void hystart_update(struct sock *sk, u32 delay) } } -static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) +__bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index e0a2ca7456ff..bb23bb5b387a 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -75,7 +75,7 @@ static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) ca->old_delivered_ce = tp->delivered_ce; } -static void dctcp_init(struct sock *sk) +__bpf_kfunc static void dctcp_init(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -104,7 +104,7 @@ static void dctcp_init(struct sock *sk) INET_ECN_dontxmit(sk); } -static u32 dctcp_ssthresh(struct sock *sk) +__bpf_kfunc static u32 dctcp_ssthresh(struct sock *sk) { struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -113,7 +113,7 @@ static u32 dctcp_ssthresh(struct sock *sk) return max(tcp_snd_cwnd(tp) - ((tcp_snd_cwnd(tp) * ca->dctcp_alpha) >> 11U), 2U); } -static void dctcp_update_alpha(struct sock *sk, u32 flags) +__bpf_kfunc static void dctcp_update_alpha(struct sock *sk, u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); @@ -169,7 +169,7 @@ static void dctcp_react_to_loss(struct sock *sk) tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U); } -static void dctcp_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Recovery && new_state != inet_csk(sk)->icsk_ca_state) @@ -179,7 +179,7 @@ static void dctcp_state(struct sock *sk, u8 new_state) */ } -static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) +__bpf_kfunc static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { struct dctcp *ca = inet_csk_ca(sk); @@ -229,7 +229,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } -static u32 dctcp_cwnd_undo(struct sock *sk) +__bpf_kfunc static u32 dctcp_cwnd_undo(struct sock *sk) { const struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fee9163382c2..847934763868 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -222,6 +222,7 @@ lookup_protocol: np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ada087b50541..bac9ba747bde 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -152,7 +152,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -338,7 +338,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, struct sock *sk; int hash; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -355,17 +355,19 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -386,7 +388,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } @@ -410,7 +412,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index db07cc5b4fcb..56628b52d100 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1002,8 +1002,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, { int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1012,11 +1012,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1ff2efbab29e..c9817aa0f413 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2902,6 +2902,7 @@ bool __mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; @@ -2928,6 +2929,8 @@ cleanup: struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2943,6 +2946,12 @@ cleanup: } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 9986681aaf40..8a9656248b0f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index beaec843f5ca..4ae1a7304cf0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1400,6 +1400,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1410,7 +1411,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -1682,7 +1690,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f71b41c7ce2f..4d6737160857 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -189,6 +189,9 @@ config NF_CONNTRACK_LABELS to connection tracking entries. It can be used with xtables connlabel match and the nftables ct expression. +config NF_CONNTRACK_OVS + bool + config NF_CT_PROTO_DCCP bool 'DCCP protocol connection tracking support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ba2a6b5e93d9..5ffef1cd6143 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -11,6 +11,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_OVS) += nf_conntrack_ovs.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 24002bc61e07..34913521c385 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -249,7 +249,7 @@ __diag_ignore_all("-Wmissing-prototypes", * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn___init * +__bpf_kfunc struct nf_conn___init * bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -283,7 +283,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn * +__bpf_kfunc struct nf_conn * bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -316,7 +316,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn___init * +__bpf_kfunc struct nf_conn___init * bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -351,7 +351,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn * +__bpf_kfunc struct nf_conn * bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -376,7 +376,7 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @nfct - Pointer to referenced nf_conn___init object, obtained * using bpf_xdp_ct_alloc or bpf_skb_ct_alloc. */ -struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) +__bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) { struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; @@ -400,7 +400,7 @@ struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) * @nf_conn - Pointer to referenced nf_conn object, obtained using * bpf_xdp_ct_lookup or bpf_skb_ct_lookup. */ -void bpf_ct_release(struct nf_conn *nfct) +__bpf_kfunc void bpf_ct_release(struct nf_conn *nfct) { if (!nfct) return; @@ -417,7 +417,7 @@ void bpf_ct_release(struct nf_conn *nfct) * bpf_xdp_ct_alloc or bpf_skb_ct_alloc. * @timeout - Timeout in msecs. */ -void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) +__bpf_kfunc void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) { __nf_ct_set_timeout((struct nf_conn *)nfct, msecs_to_jiffies(timeout)); } @@ -432,7 +432,7 @@ void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) * bpf_ct_insert_entry, bpf_xdp_ct_lookup, or bpf_skb_ct_lookup. * @timeout - New timeout in msecs. */ -int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) +__bpf_kfunc int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) { return __nf_ct_change_timeout(nfct, msecs_to_jiffies(timeout)); } @@ -447,7 +447,7 @@ int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) * bpf_xdp_ct_alloc or bpf_skb_ct_alloc. * @status - New status value. */ -int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) +__bpf_kfunc int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) { return nf_ct_change_status_common((struct nf_conn *)nfct, status); } @@ -462,7 +462,7 @@ int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) * bpf_ct_insert_entry, bpf_xdp_ct_lookup or bpf_skb_ct_lookup. * @status - New status value. */ -int bpf_ct_change_status(struct nf_conn *nfct, u32 status) +__bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status) { return nf_ct_change_status_common(nfct, status); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 48ea6d0264b5..0c4db2f2ac43 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -242,104 +242,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); -/* 'skb' should already be pulled to nh_ofs. */ -int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - unsigned int protoff; - int err; - - if (ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - if (helper->tuple.src.l3num != NFPROTO_UNSPEC && - helper->tuple.src.l3num != proto) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - proto = ip_hdr(skb)->protocol; - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - proto = nexthdr; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - if (helper->tuple.dst.protonum != proto) - return NF_ACCEPT; - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} -EXPORT_SYMBOL_GPL(nf_ct_helper); - -int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, - u8 proto, bool nat, struct nf_conntrack_helper **hp) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, family, proto); - if (!helper) - return -EINVAL; - - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } -#if IS_ENABLED(CONFIG_NF_NAT) - if (nat) { - ret = nf_nat_helper_try_module_get(name, family, proto); - if (ret) { - nf_conntrack_helper_put(helper); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - *hp = helper; - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_add_helper); - /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c new file mode 100644 index 000000000000..52b776bdf526 --- /dev/null +++ b/net/netfilter/nf_conntrack_ovs.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Support ct functions for openvswitch and used by OVS and TC conntrack. */ + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/ipv6_frag.h> +#include <net/ip.h> + +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + +/* Trim the skb to the length specified by the IP/IPv6 header, + * removing any trailing lower-layer padding. This prepares the skb + * for higher-layer processing that assumes skb->len excludes padding + * (such as nf_ip_checksum). The caller needs to pull the skb to the + * network header, and ensure ip_hdr/ipv6_hdr points to valid data. + */ +int nf_ct_skb_network_trim(struct sk_buff *skb, int family) +{ + unsigned int len; + + switch (family) { + case NFPROTO_IPV4: + len = skb_ip_totlen(skb); + break; + case NFPROTO_IPV6: + len = sizeof(struct ipv6hdr) + + ntohs(ipv6_hdr(skb)->payload_len); + break; + default: + len = skb->len; + } + + return pskb_trim_rcsum(skb, len); +} +EXPORT_SYMBOL_GPL(nf_ct_skb_network_trim); + +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ +int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u16 zone, u8 family, u8 *proto, u16 *mru) +{ + int err; + + if (family == NFPROTO_IPV4) { + enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + local_bh_disable(); + err = ip_defrag(net, skb, user); + local_bh_enable(); + if (err) + return err; + + *mru = IPCB(skb)->frag_max_size; +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + } else if (family == NFPROTO_IPV6) { + enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; + + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + err = nf_ct_frag6_gather(net, skb, user); + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); + return err; + } + + *proto = ipv6_hdr(skb)->nexthdr; + *mru = IP6CB(skb)->frag_max_size; +#endif + } else { + kfree_skb(skb); + return -EPFNOSUPPORT; + } + + skb_clear_hash(skb); + skb->ignore_df = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(nf_ct_handle_fragments); diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c index 0fa5a0bbb0ff..141ee7783223 100644 --- a/net/netfilter/nf_nat_bpf.c +++ b/net/netfilter/nf_nat_bpf.c @@ -30,9 +30,9 @@ __diag_ignore_all("-Wmissing-prototypes", * interpreted as select a random port. * @manip - NF_NAT_MANIP_SRC or NF_NAT_MANIP_DST */ -int bpf_ct_set_nat_info(struct nf_conn___init *nfct, - union nf_inet_addr *addr, int port, - enum nf_nat_manip_type manip) +__bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct, + union nf_inet_addr *addr, int port, + enum nf_nat_manip_type manip) { struct nf_conn *ct = (struct nf_conn *)nfct; u16 proto = nf_ct_l3num(ct); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 600993c80050..04c4036bf406 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -13,7 +13,7 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> -#include <linux/string.h> +#include <linux/string_helpers.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> @@ -457,7 +457,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; - if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) + if (WARN_ON(!string_is_terminated(grp->name, GENL_NAMSIZ))) return -EINVAL; } diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 747d537a3f06..29a7081858cd 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -15,6 +15,7 @@ config OPENVSWITCH select NET_MPLS_GSO select DST_CACHE select NET_NSH + select NF_CONNTRACK_OVS if NF_CONNTRACK select NF_NAT_OVS if NF_NAT help Open vSwitch is a multilayer Ethernet switch targeted at virtualized diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 2172930b1f17..331730fd3580 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -9,6 +9,7 @@ #include <linux/udp.h> #include <linux/sctp.h> #include <linux/static_key.h> +#include <linux/string_helpers.h> #include <net/ip.h> #include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> @@ -434,52 +435,21 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero - * value if 'skb' is freed. - */ -static int handle_fragments(struct net *net, struct sw_flow_key *key, - u16 zone, struct sk_buff *skb) +static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, + u16 zone, int family, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; - if (key->eth.type == htons(ETH_P_IP)) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - err = ip_defrag(net, skb, user); - if (err) - return err; - - ovs_cb.mru = IPCB(skb)->frag_max_size; -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - } else if (key->eth.type == htons(ETH_P_IPV6)) { - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err) { - if (err != -EINPROGRESS) - kfree_skb(skb); - return err; - } - - key->ip.proto = ipv6_hdr(skb)->nexthdr; - ovs_cb.mru = IP6CB(skb)->frag_max_size; -#endif - } else { - kfree_skb(skb); - return -EPFNOSUPPORT; - } + err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); + if (err) + return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); - key->ip.frag = OVS_FRAG_TYPE_NONE; - skb_clear_hash(skb); - skb->ignore_df = 1; *OVS_CB(skb) = ovs_cb; return 0; @@ -1090,36 +1060,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int ovs_skb_network_trim(struct sk_buff *skb) -{ - unsigned int len; - int err; - - switch (skb->protocol) { - case htons(ETH_P_IP): - len = skb_ip_totlen(skb); - break; - case htons(ETH_P_IPV6): - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - err = pskb_trim_rcsum(skb, len); - if (err) - kfree_skb(skb); - - return err; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1134,12 +1074,15 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = ovs_skb_network_trim(skb); - if (err) + err = nf_ct_skb_network_trim(skb, info->family); + if (err) { + kfree_skb(skb); return err; + } if (key->ip.frag != OVS_FRAG_TYPE_NONE) { - err = handle_fragments(net, key, info->zone.id, skb); + err = ovs_ct_handle_fragments(net, key, info->zone.id, + info->family, skb); if (err) return err; } @@ -1383,7 +1326,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #endif case OVS_CT_ATTR_HELPER: *helper = nla_data(a); - if (!memchr(*helper, '\0', nla_len(a))) { + if (!string_is_terminated(*helper, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack helper"); return -EINVAL; } @@ -1404,7 +1347,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); - if (!memchr(info->timeout, '\0', nla_len(a))) { + if (!string_is_terminated(info->timeout, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e20d1a973417..416976f70322 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -107,7 +107,8 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, rcu_assign_pointer(flow->stats[cpu], new_stats); - cpumask_set_cpu(cpu, &flow->cpu_used_mask); + cpumask_set_cpu(cpu, + flow->cpu_used_mask); goto unlock; } } @@ -135,7 +136,8 @@ void ovs_flow_stats_get(const struct sw_flow *flow, memset(ovs_stats, 0, sizeof(*ovs_stats)); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { @@ -159,7 +161,8 @@ void ovs_flow_stats_clear(struct sw_flow *flow) int cpu; /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 073ab73ffeaa..b5711aff6e76 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -229,7 +229,7 @@ struct sw_flow { */ struct sw_flow_key key; struct sw_flow_id id; - struct cpumask cpu_used_mask; + struct cpumask *cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 0a0e4c283f02..791504b7f42b 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -79,6 +79,7 @@ struct sw_flow *ovs_flow_alloc(void) return ERR_PTR(-ENOMEM); flow->stats_last_writer = -1; + flow->cpu_used_mask = (struct cpumask *)&flow->stats[nr_cpu_ids]; /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, @@ -91,7 +92,7 @@ struct sw_flow *ovs_flow_alloc(void) RCU_INIT_POINTER(flow->stats[0], stats); - cpumask_set_cpu(0, &flow->cpu_used_mask); + cpumask_set_cpu(0, flow->cpu_used_mask); return flow; err: @@ -115,7 +116,7 @@ static void flow_free(struct sw_flow *flow) flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; - cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); @@ -1196,7 +1197,8 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct sw_flow_stats *)), + * sizeof(struct sw_flow_stats *)) + + cpumask_size(), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; diff --git a/net/rds/message.c b/net/rds/message.c index b47e4f0a1639..c19c93561227 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6eaffb0d8fdc..e9f1f49d18c2 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -54,12 +54,14 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); + if (!busy && !rxrpc_try_get_call(call, rxrpc_call_get_poke)) + busy = true; if (!busy) { - rxrpc_get_call(call, rxrpc_call_get_poke); list_add_tail(&call->attend_link, &local->call_attend_q); } spin_unlock_bh(&local->lock); - rxrpc_wake_up_io_thread(local); + if (!busy) + rxrpc_wake_up_io_thread(local); } } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 44414e724415..95f4bc206b3d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -163,7 +163,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), - pkt.ack.reason, 0); + pkt.ack.reason, 0, rxrpc_rx_window_size); break; default: diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 6b2022240076..5e53429c6922 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -80,7 +80,8 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_txbuf *txb) + struct rxrpc_txbuf *txb, + u16 *_rwind) { struct rxrpc_ackinfo ackinfo; unsigned int qsize, sack, wrap, to; @@ -124,6 +125,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); + *_rwind = rsize; ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(rsize); @@ -190,6 +192,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_serial_t serial; size_t len, n; int ret, rtt_slot = -1; + u16 rwind; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; @@ -205,7 +208,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; - n = rxrpc_fill_out_ack(conn, call, txb); + n = rxrpc_fill_out_ack(conn, call, txb, &rwind); if (n == 0) return 0; @@ -217,7 +220,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, + rwind); if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 50d263a6359d..76eb2b9cd936 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -137,7 +137,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) /* Check to see if there's an ACK that needs sending. */ acked = atomic_add_return(call->rx_consumed - old_consumed, &call->ackr_nr_consumed); - if (acked > 2 && + if (acked > 8 && !test_and_set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) rxrpc_poke_call(call, rxrpc_call_poke_idle); } diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 944320e65ea8..3bcd6ee80396 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -63,7 +63,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); - kfree_skb_reason(skb, SKB_CONSUMED); + consume_skb(skb); } } @@ -78,6 +78,6 @@ void rxrpc_purge_queue(struct sk_buff_head *list) int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); - kfree_skb_reason(skb, SKB_CONSUMED); + consume_skb(skb); } } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index de18a0dda6df..4f7b52f5a11c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -195,8 +195,14 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_MQPRIO_LIB + tristate + help + Common library for manipulating mqprio queue configurations. + config NET_SCH_TAPRIO tristate "Time Aware Priority (taprio) Scheduler" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Time Aware Priority (taprio) packet scheduling algorithm. @@ -253,6 +259,7 @@ config NET_SCH_DRR config NET_SCH_MQPRIO tristate "Multi-queue priority scheduler (MQPRIO)" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Multi-queue Priority scheduler. This scheduler allows QOS to be offloaded on NICs that have support @@ -977,6 +984,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_CONNTRACK_OVS select NF_NAT_OVS if NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/Makefile b/net/sched/Makefile index dd14ef413fda..7911eec09837 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_MQPRIO_LIB) += sch_mqprio_lib.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b126f03c1bb6..9cc0bc7c71ed 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -726,31 +726,6 @@ drop_ct: return false; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family) -{ - unsigned int len; - - switch (family) { - case NFPROTO_IPV4: - len = skb_ip_totlen(skb); - break; - case NFPROTO_IPV6: - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - return pskb_trim_rcsum(skb, len); -} - static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; @@ -810,6 +785,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, struct nf_conn *ct; int err = 0; bool frag; + u8 proto; u16 mru; /* Previously seen (loopback)? Ignore. */ @@ -825,50 +801,14 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); - mru = tc_skb_cb(skb)->mru; - - if (family == NFPROTO_IPV4) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - local_bh_disable(); - err = ip_defrag(net, skb, user); - local_bh_enable(); - if (err && err != -EINPROGRESS) - return err; - - if (!err) { - *defrag = true; - mru = IPCB(skb)->frag_max_size; - } - } else { /* NFPROTO_IPV6 */ -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err && err != -EINPROGRESS) - goto out_free; - - if (!err) { - *defrag = true; - mru = IP6CB(skb)->frag_max_size; - } -#else - err = -EOPNOTSUPP; - goto out_free; -#endif - } + err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); + if (err) + return err; - if (err != -EINPROGRESS) - tc_skb_cb(skb)->mru = mru; - skb_clear_hash(skb); - skb->ignore_df = 1; - return err; + *defrag = true; + tc_skb_cb(skb)->mru = mru; -out_free: - kfree_skb(skb); - return err; + return 0; } static void tcf_ct_params_free(struct tcf_ct_params *params) @@ -1011,7 +951,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, if (err) goto drop; - err = tcf_ct_skb_network_trim(skb, family); + err = nf_ct_skb_network_trim(skb, family); if (err) goto drop; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c14018a8052c..e9780631b5b5 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1282,12 +1282,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (err) goto err_out3; - if (ops->init) { - err = ops->init(sch, tca[TCA_OPTIONS], extack); - if (err != 0) - goto err_out5; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { @@ -1296,11 +1290,18 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } rcu_assign_pointer(sch->stab, stab); } + + if (ops->init) { + err = ops->init(sch, tca[TCA_OPTIONS], extack); + if (err != 0) + goto err_out5; + } + if (tca[TCA_RATE]) { err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); - goto err_out4; + goto err_out5; } err = gen_new_estimator(&sch->bstats, @@ -1311,7 +1312,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); - goto err_out4; + goto err_out5; } } @@ -1321,6 +1322,8 @@ static struct Qdisc *qdisc_create(struct net_device *dev, return sch; err_out5: + qdisc_put_stab(rtnl_dereference(sch->stab)); +err_out4: /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ if (ops->destroy) ops->destroy(sch); @@ -1332,16 +1335,6 @@ err_out2: err_out: *errp = err; return NULL; - -err_out4: - /* - * Any broken qdiscs that would require a ops->reset() here? - * The qdisc was never in action so it shouldn't be necessary. - */ - qdisc_put_stab(rtnl_dereference(sch->stab)); - if (ops->destroy) - ops->destroy(sch); - goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cc28e41fb745..92f2975b6a82 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -433,7 +433,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (m) { unsigned int prio = ffz(~m); - if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break; m &= ~(1 << prio); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 4c68abaa289b..48ed87b91086 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -17,6 +17,8 @@ #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include "sch_mqprio_lib.h" + struct mqprio_sched { struct Qdisc **qdiscs; u16 mode; @@ -27,6 +29,62 @@ struct mqprio_sched { u64 max_rate[TC_QOPT_MAX_QUEUE]; }; +static int mqprio_enable_offload(struct Qdisc *sch, + const struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err, i; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + if (err) + return err; + + priv->hw_offload = mqprio.qopt.hw; + + return 0; +} + +static void mqprio_disable_offload(struct Qdisc *sch) +{ + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + } +} + static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); @@ -41,37 +99,17 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - case TC_MQPRIO_MODE_CHANNEL: - dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); - break; - default: - return; - } - } else { + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) + mqprio_disable_offload(sch); + else netdev_set_num_tc(dev, 0); - } } -static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + const struct tc_mqprio_caps *caps, + struct netlink_ext_ack *extack) { - int i, j; - - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) - return -EINVAL; - - /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) - return -EINVAL; - } + int err; /* Limit qopt->hw to maximum supported offload value. Drivers have * the option of overriding this later if they don't support the a @@ -80,31 +118,23 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* If hardware offload is requested we will leave it to the device - * to either populate the queue counts itself or to validate the - * provided queue counts. If ndo_setup_tc is not present then - * hardware doesn't support offload and we should return an error. + /* If hardware offload is requested, we will leave 3 options to the + * device driver: + * - populate the queue counts itself (and ignore what was requested) + * - validate the provided queue counts by itself (and apply them) + * - request queue count validation here (and apply them) */ - if (qopt->hw) - return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->real_num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) - return -EINVAL; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) - return -EINVAL; - } - } + err = mqprio_validate_qopt(dev, qopt, + !qopt->hw || caps->validate_queue_counts, + false, extack); + if (err) + return err; + + /* If ndo_setup_tc is not present then hardware doesn't support offload + * and we should return an error. + */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; return 0; } @@ -130,6 +160,67 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } +static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, + struct nlattr *opt) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int i, rem, err; + + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -139,9 +230,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; - struct nlattr *tb[TCA_MQPRIO_MAX + 1]; - struct nlattr *attr; - int rem; + struct tc_mqprio_caps caps; int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); @@ -160,61 +249,18 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO, + &caps, sizeof(caps)); + qopt = nla_data(opt); - if (mqprio_parse_opt(dev, qopt)) + if (mqprio_parse_opt(dev, qopt, &caps, extack)) return -EINVAL; len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); if (len > 0) { - err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, - sizeof(*qopt)); - if (err < 0) + err = mqprio_parse_nlattr(sch, qopt, opt); + if (err) return err; - - if (!qopt->hw) - return -EINVAL; - - if (tb[TCA_MQPRIO_MODE]) { - priv->flags |= TC_MQPRIO_F_MODE; - priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); - } - - if (tb[TCA_MQPRIO_SHAPER]) { - priv->flags |= TC_MQPRIO_F_SHAPER; - priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); - } - - if (tb[TCA_MQPRIO_MIN_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->min_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MIN_RATE; - } - - if (tb[TCA_MQPRIO_MAX_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->max_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MAX_RATE; - } } /* pre-allocate qdisc, attachment can't fail */ @@ -241,36 +287,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - if (priv->shaper != TC_MQPRIO_SHAPER_DCB) - return -EINVAL; - break; - case TC_MQPRIO_MODE_CHANNEL: - mqprio.flags = priv->flags; - if (priv->flags & TC_MQPRIO_F_MODE) - mqprio.mode = priv->mode; - if (priv->flags & TC_MQPRIO_F_SHAPER) - mqprio.shaper = priv->shaper; - if (priv->flags & TC_MQPRIO_F_MIN_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.min_rate[i] = priv->min_rate[i]; - if (priv->flags & TC_MQPRIO_F_MAX_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.max_rate[i] = priv->max_rate[i]; - break; - default: - return -EINVAL; - } - err = dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); + err = mqprio_enable_offload(sch, qopt, extack); if (err) return err; - - priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -387,7 +406,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; - unsigned int ntx, tc; + unsigned int ntx; sch->q.qlen = 0; gnet_stats_basic_sync_init(&sch->bstats); @@ -411,15 +430,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) spin_unlock_bh(qdisc_lock(qdisc)); } - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + mqprio_qopt_reconstruct(dev, &opt); opt.hw = priv->hw_offload; - for (tc = 0; tc < netdev_get_num_tc(dev); tc++) { - opt.count[tc] = dev->tc_to_txq[tc].count; - opt.offset[tc] = dev->tc_to_txq[tc].offset; - } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c new file mode 100644 index 000000000000..c58a533b8ec5 --- /dev/null +++ b/net/sched/sch_mqprio_lib.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <linux/types.h> +#include <net/pkt_sched.h> + +#include "sch_mqprio_lib.h" + +/* Returns true if the intervals [a, b) and [c, d) overlap. */ +static bool intervals_overlap(int a, int b, int c, int d) +{ + int left = max(a, c), right = min(b, d); + + return left < right; +} + +static int mqprio_validate_queue_counts(struct net_device *dev, + const struct tc_mqprio_qopt *qopt, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, j; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + if (!qopt->count[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, "No queues for TC %d", + i); + return -EINVAL; + } + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Queues %d:%d for TC %d exceed the %d TX queues available", + qopt->count[i], qopt->offset[i], + i, dev->real_num_tx_queues); + return -EINVAL; + } + + if (allow_overlapping_txqs) + continue; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (intervals_overlap(qopt->offset[i], last, + qopt->offset[j], + qopt->offset[j] + + qopt->count[j])) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TC %d queues %d@%d overlap with TC %d queues %d@%d", + i, qopt->count[i], qopt->offset[i], + j, qopt->count[j], qopt->offset[j]); + return -EINVAL; + } + } + } + + return 0; +} + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, err; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, + "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i <= TC_BITMASK; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, + "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + if (validate_queue_counts) { + err = mqprio_validate_queue_counts(dev, qopt, + allow_overlapping_txqs, + extack); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mqprio_validate_qopt); + +void mqprio_qopt_reconstruct(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int tc, num_tc = netdev_get_num_tc(dev); + + qopt->num_tc = num_tc; + memcpy(qopt->prio_tc_map, dev->prio_tc_map, sizeof(qopt->prio_tc_map)); + + for (tc = 0; tc < num_tc; tc++) { + qopt->count[tc] = dev->tc_to_txq[tc].count; + qopt->offset[tc] = dev->tc_to_txq[tc].offset; + } +} +EXPORT_SYMBOL_GPL(mqprio_qopt_reconstruct); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_mqprio_lib.h b/net/sched/sch_mqprio_lib.h new file mode 100644 index 000000000000..63f725ab8761 --- /dev/null +++ b/net/sched/sch_mqprio_lib.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SCH_MQPRIO_LIB_H +#define __SCH_MQPRIO_LIB_H + +#include <linux/types.h> + +struct net_device; +struct netlink_ext_ack; +struct tc_mqprio_qopt; + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack); +void mqprio_qopt_reconstruct(struct net_device *dev, + struct tc_mqprio_qopt *qopt); + +#endif diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c322a61eaeea..9781b47962bb 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -26,7 +26,11 @@ #include <net/sock.h> #include <net/tcp.h> +#include "sch_mqprio_lib.h" + static LIST_HEAD(taprio_list); +static struct static_key_false taprio_have_broken_mqprio; +static struct static_key_false taprio_have_working_mqprio; #define TAPRIO_ALL_GATES_OPEN -1 @@ -35,15 +39,19 @@ static LIST_HEAD(taprio_list); #define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { - struct list_head list; - - /* The instant that this entry "closes" and the next one - * should open, the qdisc will make some effort so that no - * packet leaves after this time. + /* Durations between this GCL entry and the GCL entry where the + * respective traffic class gate closes */ - ktime_t close_time; + u64 gate_duration[TC_MAX_QUEUE]; + atomic_t budget[TC_MAX_QUEUE]; + /* The qdisc makes some effort so that no packet leaves + * after this time + */ + ktime_t gate_close_time[TC_MAX_QUEUE]; + struct list_head list; + /* Used to calculate when to advance the schedule */ + ktime_t end_time; ktime_t next_txtime; - atomic_t budget; int index; u32 gate_mask; u32 interval; @@ -51,10 +59,16 @@ struct sched_entry { }; struct sched_gate_list { + /* Longest non-zero contiguous gate durations per traffic class, + * or 0 if a traffic class gate never opens during the schedule. + */ + u64 max_open_gate_duration[TC_MAX_QUEUE]; + u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ + u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ struct rcu_head rcu; struct list_head entries; size_t num_entries; - ktime_t cycle_close_time; + ktime_t cycle_end_time; s64 cycle_time; s64 cycle_time_extension; s64 base_time; @@ -67,6 +81,8 @@ struct taprio_sched { enum tk_offsets tk_offset; int clockid; bool offloaded; + bool detected_mqprio; + bool broken_mqprio; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ @@ -78,8 +94,8 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; - u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ - u32 max_sdu[TC_MAX_QUEUE]; /* for dump and offloading */ + int cur_txq[TC_MAX_QUEUE]; + u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ u32 txtime_delay; }; @@ -88,6 +104,57 @@ struct __tc_taprio_qopt_offload { struct tc_taprio_qopt_offload offload; }; +static void taprio_calculate_gate_durations(struct taprio_sched *q, + struct sched_gate_list *sched) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *entry, *cur; + int tc; + + list_for_each_entry(entry, &sched->entries, list) { + u32 gates_still_open = entry->gate_mask; + + /* For each traffic class, calculate each open gate duration, + * starting at this schedule entry and ending at the schedule + * entry containing a gate close event for that TC. + */ + cur = entry; + + do { + if (!gates_still_open) + break; + + for (tc = 0; tc < num_tc; tc++) { + if (!(gates_still_open & BIT(tc))) + continue; + + if (cur->gate_mask & BIT(tc)) + entry->gate_duration[tc] += cur->interval; + else + gates_still_open &= ~BIT(tc); + } + + cur = list_next_entry_circular(cur, &sched->entries, list); + } while (cur != entry); + + /* Keep track of the maximum gate duration for each traffic + * class, taking care to not confuse a traffic class which is + * temporarily closed with one that is always closed. + */ + for (tc = 0; tc < num_tc; tc++) + if (entry->gate_duration[tc] && + sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) + sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; + } +} + +static bool taprio_entry_allows_tx(ktime_t skb_end_time, + struct sched_entry *entry, int tc) +{ + return ktime_before(skb_end_time, entry->gate_close_time[tc]); +} + static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) @@ -180,6 +247,55 @@ static int length_to_duration(struct taprio_sched *q, int len) return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); } +static int duration_to_length(struct taprio_sched *q, u64 duration) +{ + return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); +} + +/* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the + * q->max_sdu[] requested by the user and the max_sdu dynamically determined by + * the maximum open gate durations at the given link speed. + */ +static void taprio_update_queue_max_sdu(struct taprio_sched *q, + struct sched_gate_list *sched, + struct qdisc_size_table *stab) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + u32 max_sdu_from_user; + u32 max_sdu_dynamic; + u32 max_sdu; + int tc; + + for (tc = 0; tc < num_tc; tc++) { + max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; + + /* TC gate never closes => keep the queueMaxSDU + * selected by the user + */ + if (sched->max_open_gate_duration[tc] == sched->cycle_time) { + max_sdu_dynamic = U32_MAX; + } else { + u32 max_frm_len; + + max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); + if (stab) + max_frm_len -= stab->szopts.overhead; + max_sdu_dynamic = max_frm_len - dev->hard_header_len; + } + + max_sdu = min(max_sdu_dynamic, max_sdu_from_user); + + if (max_sdu != U32_MAX) { + sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; + sched->max_sdu[tc] = max_sdu; + } else { + sched->max_frm_len[tc] = U32_MAX; /* never oversized */ + sched->max_sdu[tc] = 0; + } + } +} + /* Returns the entry corresponding to next available interval. If * validate_interval is set, it only validates whether the timestamp occurs * when the gate corresponding to the skb's traffic class is open. @@ -413,14 +529,33 @@ done: return txtime; } -static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, - struct Qdisc *child, struct sk_buff **to_free) +/* Devices with full offload are expected to honor this in hardware */ +static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, + struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *sched; int prio = skb->priority; + bool exceeds = false; u8 tc; + tc = netdev_get_prio_tc_map(dev, prio); + + rcu_read_lock(); + sched = rcu_dereference(q->oper_sched); + if (sched && skb->len > sched->max_frm_len[tc]) + exceeds = true; + rcu_read_unlock(); + + return exceeds; +} + +static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + /* sk_flags are only safe to use on full sockets. */ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) @@ -431,17 +566,53 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); } - /* Devices with full offload are expected to honor this in hardware */ - tc = netdev_get_prio_tc_map(dev, prio); - if (skb->len > q->max_frm_len[tc]) - return qdisc_drop(skb, sch, to_free); - qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return qdisc_enqueue(skb, child, to_free); } +static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) +{ + unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); + netdev_features_t features = netif_skb_features(skb); + struct sk_buff *segs, *nskb; + int ret; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + slen += segs->len; + + /* FIXME: we should be segmenting to a smaller size + * rather than dropping these + */ + if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) + ret = qdisc_drop(segs, sch, to_free); + else + ret = taprio_enqueue_one(segs, sch, child, to_free); + + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + numsegs++; + } + } + + if (numsegs > 1) + qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); + consume_skb(skb); + + return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ @@ -458,97 +629,190 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(!child)) return qdisc_drop(skb, sch, to_free); - /* Large packets might not be transmitted when the transmission duration - * exceeds any configured interval. Therefore, segment the skb into - * smaller chunks. Drivers with full offload are expected to handle - * this in hardware. - */ - if (skb_is_gso(skb)) { - unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); - netdev_features_t features = netif_skb_features(skb); - struct sk_buff *segs, *nskb; - int ret; - - segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); - if (IS_ERR_OR_NULL(segs)) - return qdisc_drop(skb, sch, to_free); + if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { + /* Large packets might not be transmitted when the transmission + * duration exceeds any configured interval. Therefore, segment + * the skb into smaller chunks. Drivers with full offload are + * expected to handle this in hardware. + */ + if (skb_is_gso(skb)) + return taprio_enqueue_segmented(skb, sch, child, + to_free); - skb_list_walk_safe(segs, segs, nskb) { - skb_mark_not_on_list(segs); - qdisc_skb_cb(segs)->pkt_len = segs->len; - slen += segs->len; + return qdisc_drop(skb, sch, to_free); + } - ret = taprio_enqueue_one(segs, sch, child, to_free); - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) - qdisc_qstats_drop(sch); - } else { - numsegs++; - } - } + return taprio_enqueue_one(skb, sch, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); + return NULL; +} + +static void taprio_set_budgets(struct taprio_sched *q, + struct sched_gate_list *sched, + struct sched_entry *entry) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + int tc, budget; - if (numsegs > 1) - qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); - consume_skb(skb); + for (tc = 0; tc < num_tc; tc++) { + /* Traffic classes which never close have infinite budget */ + if (entry->gate_duration[tc] == sched->cycle_time) + budget = INT_MAX; + else + budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, + atomic64_read(&q->picos_per_byte)); - return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; + atomic_set(&entry->budget[tc], budget); } +} - return taprio_enqueue_one(skb, sch, child, to_free); +/* When an skb is sent, it consumes from the budget of all traffic classes */ +static int taprio_update_budgets(struct sched_entry *entry, size_t len, + int tc_consumed, int num_tc) +{ + int tc, budget, new_budget = 0; + + for (tc = 0; tc < num_tc; tc++) { + budget = atomic_read(&entry->budget[tc]); + /* Don't consume from infinite budget */ + if (budget == INT_MAX) { + if (tc == tc_consumed) + new_budget = budget; + continue; + } + + if (tc == tc_consumed) + new_budget = atomic_sub_return(len, &entry->budget[tc]); + else + atomic_sub(len, &entry->budget[tc]); + } + + return new_budget; } -/* Will not be called in the full offload case, since the TX queues are - * attached to the Qdisc created using qdisc_create_dflt() - */ -static struct sk_buff *taprio_peek(struct Qdisc *sch) +static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, + struct sched_entry *entry, + u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - struct sched_entry *entry; + struct Qdisc *child = q->qdiscs[txq]; + int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; - u32 gate_mask; - int i; + ktime_t guard; + int prio; + int len; + u8 tc; - rcu_read_lock(); - entry = rcu_dereference(q->current_entry); - gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - rcu_read_unlock(); + if (unlikely(!child)) + return NULL; - if (!gate_mask) + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) + goto skip_peek_checks; + + skb = child->ops->peek(child); + if (!skb) return NULL; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - int prio; - u8 tc; + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); - if (unlikely(!child)) - continue; + if (!(gate_mask & BIT(tc))) + return NULL; - skb = child->ops->peek(child); - if (!skb) - continue; + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) - return skb; + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + !taprio_entry_allows_tx(guard, entry, tc)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + taprio_update_budgets(entry, len, tc, num_tc) < 0) + return NULL; + +skip_peek_checks: + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; +} + +static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) +{ + int offset = dev->tc_to_txq[tc].offset; + int count = dev->tc_to_txq[tc].count; + + (*txq)++; + if (*txq == offset + count) + *txq = offset; +} - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); +/* Prioritize higher traffic classes, and select among TXQs belonging to the + * same TC using round robin + */ +static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int num_tc = netdev_get_num_tc(dev); + struct sk_buff *skb; + int tc; + + for (tc = num_tc - 1; tc >= 0; tc--) { + int first_txq = q->cur_txq[tc]; if (!(gate_mask & BIT(tc))) continue; - return skb; + do { + skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], + entry, gate_mask); + + taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); + + if (skb) + return skb; + } while (q->cur_txq[tc] != first_txq); } return NULL; } -static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) +/* Broken way of prioritizing smaller TXQ indices and ignoring the traffic + * class other than to determine whether the gate is open or not + */ +static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) { - atomic_set(&entry->budget, - div64_u64((u64)entry->interval * PSEC_PER_NSEC, - atomic64_read(&q->picos_per_byte))); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); + if (skb) + return skb; + } + + return NULL; } /* Will not be called in the full offload case, since the TX queues are @@ -557,11 +821,9 @@ static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) static struct sk_buff *taprio_dequeue(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); struct sk_buff *skb = NULL; struct sched_entry *entry; u32 gate_mask; - int i; rcu_read_lock(); entry = rcu_dereference(q->current_entry); @@ -571,69 +833,23 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - if (!gate_mask) goto done; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - ktime_t guard; - int prio; - int len; - u8 tc; - - if (unlikely(!child)) - continue; - - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { - skb = child->ops->dequeue(child); - if (!skb) - continue; - goto skb_found; - } - - skb = child->ops->peek(child); - if (!skb) - continue; - - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); - - if (!(gate_mask & BIT(tc))) { - skb = NULL; - continue; - } - - len = qdisc_pkt_len(skb); - guard = ktime_add_ns(taprio_get_time(q), - length_to_duration(q, len)); - - /* In the case that there's no gate entry, there's no - * guard band ... - */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) { - skb = NULL; - continue; - } - - /* ... and no budget. */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) { - skb = NULL; - continue; - } - - skb = child->ops->dequeue(child); - if (unlikely(!skb)) - goto done; - -skb_found: - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - goto done; + if (static_branch_unlikely(&taprio_have_broken_mqprio) && + !static_branch_likely(&taprio_have_working_mqprio)) { + /* Single NIC kind which is broken */ + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + } else if (static_branch_likely(&taprio_have_working_mqprio) && + !static_branch_unlikely(&taprio_have_broken_mqprio)) { + /* Single NIC kind which prioritizes properly */ + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); + } else { + /* Mixed NIC kinds present in system, need dynamic testing */ + if (q->broken_mqprio) + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + else + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } done: @@ -648,7 +864,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, if (list_is_last(&entry->list, &oper->entries)) return true; - if (ktime_compare(entry->close_time, oper->cycle_close_time) == 0) + if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) return true; return false; @@ -656,7 +872,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, static bool should_change_schedules(const struct sched_gate_list *admin, const struct sched_gate_list *oper, - ktime_t close_time) + ktime_t end_time) { ktime_t next_base_time, extension_time; @@ -665,18 +881,18 @@ static bool should_change_schedules(const struct sched_gate_list *admin, next_base_time = sched_base_time(admin); - /* This is the simple case, the close_time would fall after + /* This is the simple case, the end_time would fall after * the next schedule base_time. */ - if (ktime_compare(next_base_time, close_time) <= 0) + if (ktime_compare(next_base_time, end_time) <= 0) return true; - /* This is the cycle_time_extension case, if the close_time + /* This is the cycle_time_extension case, if the end_time * plus the amount that can be extended would fall after the * next schedule base_time, we can extend the current schedule * for that amount. */ - extension_time = ktime_add_ns(close_time, oper->cycle_time_extension); + extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about * how precisely the extension should be made. So after @@ -692,10 +908,13 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, advance_timer); + struct net_device *dev = qdisc_dev(q->root); struct sched_gate_list *oper, *admin; + int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *next; struct Qdisc *sch = q->root; - ktime_t close_time; + ktime_t end_time; + int tc; spin_lock(&q->current_entry_lock); entry = rcu_dereference_protected(q->current_entry, @@ -714,41 +933,49 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) * entry of all schedules are pre-calculated during the * schedule initialization. */ - if (unlikely(!entry || entry->close_time == oper->base_time)) { + if (unlikely(!entry || entry->end_time == oper->base_time)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - close_time = next->close_time; + end_time = next->end_time; goto first_run; } if (should_restart_cycle(oper, entry)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - oper->cycle_close_time = ktime_add_ns(oper->cycle_close_time, - oper->cycle_time); + oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, + oper->cycle_time); } else { next = list_next_entry(entry, list); } - close_time = ktime_add_ns(entry->close_time, next->interval); - close_time = min_t(ktime_t, close_time, oper->cycle_close_time); + end_time = ktime_add_ns(entry->end_time, next->interval); + end_time = min_t(ktime_t, end_time, oper->cycle_end_time); + + for (tc = 0; tc < num_tc; tc++) { + if (next->gate_duration[tc] == oper->cycle_time) + next->gate_close_time[tc] = KTIME_MAX; + else + next->gate_close_time[tc] = ktime_add_ns(entry->end_time, + next->gate_duration[tc]); + } - if (should_change_schedules(admin, oper, close_time)) { + if (should_change_schedules(admin, oper, end_time)) { /* Set things so the next time this runs, the new * schedule runs. */ - close_time = sched_base_time(admin); + end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); } - next->close_time = close_time; - taprio_set_budget(q, next); + next->end_time = end_time; + taprio_set_budgets(q, oper, next); first_run: rcu_assign_pointer(q->current_entry, next); spin_unlock(&q->current_entry_lock); - hrtimer_set_expires(&q->advance_timer, close_time); + hrtimer_set_expires(&q->advance_timer, end_time); rcu_read_lock(); __netif_schedule(sch); @@ -916,6 +1143,8 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + taprio_calculate_gate_durations(q, new); + return 0; } @@ -924,7 +1153,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, struct netlink_ext_ack *extack, u32 taprio_flags) { - int i, j; + bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); if (!qopt && !dev->num_tc) { NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); @@ -937,52 +1166,17 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, if (dev->num_tc) return 0; - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) { - NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); - return -EINVAL; - } - /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); return -EINVAL; } - /* Verify priority mapping uses valid tcs */ - for (i = 0; i <= TC_BITMASK; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) { - NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); - return -EINVAL; - } - } - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) { - NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); - return -EINVAL; - } - - if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) - continue; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) { - NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); - return -EINVAL; - } - } - } - - return 0; + /* For some reason, in txtime-assist mode, we allow TXQ ranges for + * different TCs to overlap, and just validate the TXQ ranges. + */ + return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, + extack); } static int taprio_get_start_time(struct Qdisc *sch, @@ -1019,11 +1213,14 @@ static int taprio_get_start_time(struct Qdisc *sch, return 0; } -static void setup_first_close_time(struct taprio_sched *q, - struct sched_gate_list *sched, ktime_t base) +static void setup_first_end_time(struct taprio_sched *q, + struct sched_gate_list *sched, ktime_t base) { + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); struct sched_entry *first; ktime_t cycle; + int tc; first = list_first_entry(&sched->entries, struct sched_entry, list); @@ -1031,10 +1228,18 @@ static void setup_first_close_time(struct taprio_sched *q, cycle = sched->cycle_time; /* FIXME: find a better place to do this */ - sched->cycle_close_time = ktime_add_ns(base, cycle); + sched->cycle_end_time = ktime_add_ns(base, cycle); + + first->end_time = ktime_add_ns(base, first->interval); + taprio_set_budgets(q, sched, first); + + for (tc = 0; tc < num_tc; tc++) { + if (first->gate_duration[tc] == sched->cycle_time) + first->gate_close_time[tc] = KTIME_MAX; + else + first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); + } - first->close_time = ktime_add_ns(base, first->interval); - taprio_set_budget(q, first); rcu_assign_pointer(q->current_entry, NULL); } @@ -1088,6 +1293,8 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct sched_gate_list *oper, *admin; + struct qdisc_size_table *stab; struct taprio_sched *q; ASSERT_RTNL(); @@ -1100,6 +1307,17 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, continue; taprio_set_picos_per_byte(dev, q); + + stab = rtnl_dereference(q->root->stab); + + oper = rtnl_dereference(q->oper_sched); + if (oper) + taprio_update_queue_max_sdu(q, oper, stab); + + admin = rtnl_dereference(q->admin_sched); + if (admin) + taprio_update_queue_max_sdu(q, admin, stab); + break; } @@ -1203,7 +1421,8 @@ static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - struct tc_taprio_qopt_offload *offload) + struct tc_taprio_qopt_offload *offload, + const struct tc_taprio_caps *caps) { struct sched_entry *entry; int i = 0; @@ -1217,7 +1436,11 @@ static void taprio_sched_to_offload(struct net_device *dev, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + if (caps->gate_mask_per_txq) + e->gate_mask = tc_map_to_queue_mask(dev, + entry->gate_mask); + else + e->gate_mask = entry->gate_mask; i++; } @@ -1225,6 +1448,34 @@ static void taprio_sched_to_offload(struct net_device *dev, offload->num_entries = i; } +static void taprio_detect_broken_mqprio(struct taprio_sched *q) +{ + struct net_device *dev = qdisc_dev(q->root); + struct tc_taprio_caps caps; + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, + &caps, sizeof(caps)); + + q->broken_mqprio = caps.broken_mqprio; + if (q->broken_mqprio) + static_branch_inc(&taprio_have_broken_mqprio); + else + static_branch_inc(&taprio_have_working_mqprio); + + q->detected_mqprio = true; +} + +static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) +{ + if (!q->detected_mqprio) + return; + + if (q->broken_mqprio) + static_branch_dec(&taprio_have_broken_mqprio); + else + static_branch_dec(&taprio_have_working_mqprio); +} + static int taprio_enable_offload(struct net_device *dev, struct taprio_sched *q, struct sched_gate_list *sched, @@ -1261,7 +1512,8 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(dev, sched, offload); + mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); + taprio_sched_to_offload(dev, sched, offload, &caps); for (tc = 0; tc < TC_MAX_QUEUE; tc++) offload->max_sdu[tc] = q->max_sdu[tc]; @@ -1452,7 +1704,6 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); u32 max_sdu[TC_QOPT_MAX_QUEUE]; unsigned long seen_tcs = 0; struct nlattr *n; @@ -1466,18 +1717,14 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, if (nla_type(n) != TCA_TAPRIO_ATTR_TC_ENTRY) continue; - err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, extack); + err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, + extack); if (err) goto out; } - for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) q->max_sdu[tc] = max_sdu[tc]; - if (max_sdu[tc]) - q->max_frm_len[tc] = max_sdu[tc] + dev->hard_header_len; - else - q->max_frm_len[tc] = U32_MAX; /* never oversized */ - } out: return err; @@ -1533,6 +1780,7 @@ static int taprio_new_flags(const struct nlattr *attr, u32 old, static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct qdisc_size_table *stab = rtnl_dereference(sch->stab); struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; struct sched_gate_list *oper, *admin, *new_admin; struct taprio_sched *q = qdisc_priv(sch); @@ -1600,15 +1848,18 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; taprio_set_picos_per_byte(dev, q); + taprio_update_queue_max_sdu(q, new_admin, stab); if (mqprio) { err = netdev_set_num_tc(dev, mqprio->num_tc); if (err) goto free_sched; - for (i = 0; i < mqprio->num_tc; i++) + for (i = 0; i < mqprio->num_tc; i++) { netdev_set_tc_queue(dev, i, mqprio->count[i], mqprio->offset[i]); + q->cur_txq[i] = mqprio->offset[i]; + } /* Always use supplied priority mappings */ for (i = 0; i <= TC_BITMASK; i++) @@ -1663,7 +1914,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { - setup_first_close_time(q, new_admin, start); + setup_first_end_time(q, new_admin, start); /* Protects against advance_sched() */ spin_lock_irqsave(&q->current_entry_lock, flags); @@ -1683,6 +1934,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, new_admin = NULL; err = 0; + if (!stab) + NL_SET_ERR_MSG_MOD(extack, + "Size table not specified, frame length estimations may be inaccurate"); + unlock: spin_unlock_bh(qdisc_lock(sch)); @@ -1743,6 +1998,8 @@ static void taprio_destroy(struct Qdisc *sch) if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); + + taprio_cleanup_broken_mqprio(q); } static int taprio_init(struct Qdisc *sch, struct nlattr *opt, @@ -1807,6 +2064,8 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, q->qdiscs[i] = qdisc; } + taprio_detect_broken_mqprio(q); + return taprio_change(sch, opt, extack); } @@ -1947,7 +2206,8 @@ error_nest: return -1; } -static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) +static int taprio_dump_tc_entries(struct sk_buff *skb, + struct sched_gate_list *sched) { struct nlattr *n; int tc; @@ -1961,7 +2221,7 @@ static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, - q->max_sdu[tc])) + sched->max_sdu[tc])) goto nla_put_failure; nla_nest_end(skb, n); @@ -1981,18 +2241,11 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct sched_gate_list *oper, *admin; struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; - unsigned int i; oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - - for (i = 0; i < netdev_get_num_tc(dev); i++) { - opt.count[i] = dev->tc_to_txq[i].count; - opt.offset[i] = dev->tc_to_txq[i].offset; - } + mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) @@ -2012,7 +2265,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; - if (taprio_dump_tc_entries(q, skb)) + if (oper && taprio_dump_tc_entries(skb, oper)) goto options_error; if (oper && dump_schedule(skb, oper)) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 1c0fe9ba5358..b163266e581a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -502,7 +502,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, return -EINVAL; /* protect against parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -510,7 +510,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, if (rc) break; } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); return rc; } @@ -519,15 +519,30 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, struct smc_buf_desc *rmb_desc) { struct smc_link_group *lgr = link->lgr; + bool do_slow = false; int i, rc = 0; rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (rc) return rc; + + down_read(&lgr->llc_conf_mutex); + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_active(&lgr->lnk[i])) + continue; + if (!rmb_desc->is_reg_mr[link->link_idx]) { + up_read(&lgr->llc_conf_mutex); + goto slow_path; + } + } + /* mr register already */ + goto fast_path; +slow_path: + do_slow = true; /* protect against parallel smc_llc_cli_rkey_exchange() and * parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -535,7 +550,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, if (rc) goto out; } - +fast_path: /* exchange confirm_rkey msg with peer */ rc = smc_llc_do_confirm_rkey(link, rmb_desc); if (rc) { @@ -544,7 +559,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, } rmb_desc->is_conf_rkey = true; out: - mutex_unlock(&lgr->llc_conf_mutex); + do_slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 7642b16c41d1..b330a1fa453e 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -854,8 +854,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1098,7 +1098,7 @@ err_out: static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1106,10 +1106,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } @@ -1118,9 +1118,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1224,15 +1224,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1377,12 +1378,12 @@ static void smc_lgr_free(struct smc_link_group *lgr) int i; if (!lgr->is_smcd) { - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } @@ -1696,12 +1697,12 @@ static void smcr_link_down(struct smc_link *lnk) } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, @@ -1761,9 +1762,9 @@ static void smc_link_down_work(struct work_struct *work) if (list_empty(&lgr->list)) return; wake_up_all(&lgr->llc_msg_waiter); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); smcr_link_down(link); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, @@ -1990,19 +1991,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2111,13 +2112,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2126,7 +2127,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2159,37 +2160,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2247,7 +2248,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; @@ -2260,7 +2261,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, cnt++; } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; @@ -2309,8 +2310,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ int sk_buf_size; if (is_rmb) @@ -2358,9 +2359,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2434,9 +2435,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..08b457c2d294 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ @@ -298,7 +298,7 @@ struct smc_link_group { /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ - struct mutex llc_conf_mutex; + struct rw_semaphore llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 524649d0ab65..a0840b8c935b 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -608,7 +608,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -628,7 +628,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -889,7 +889,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -916,7 +916,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -999,14 +999,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1202,12 +1202,12 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); if (smc_llc_is_local_add_link(&qentry->msg)) smc_llc_cli_add_link_invite(qentry->link, qentry); else smc_llc_cli_add_link(qentry->link, qentry); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_llc_active_link_count(struct smc_link_group *lgr) @@ -1313,7 +1313,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1338,7 +1338,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1509,13 +1509,13 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); rc = smc_llc_srv_add_link(link, qentry); if (!rc && lgr->type == SMC_LGR_SYMMETRIC) { /* delete any asymmetric link */ smc_llc_delete_asym_link(lgr); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -1582,7 +1582,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); goto out; } - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); /* delete single link */ for (lnk_idx = 0; lnk_idx < SMC_LINKS_PER_LGR_MAX; lnk_idx++) { if (lgr->lnk[lnk_idx].link_id != del_llc->link_num) @@ -1616,7 +1616,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); } out_unlock: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); out: kfree(qentry); } @@ -1652,7 +1652,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) int active_links; int i; - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); lnk = qentry->link; del_llc = &qentry->msg.delete_link; @@ -1708,7 +1708,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) smc_llc_add_link_local(lnk); } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -2126,7 +2126,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) spin_lock_init(&lgr->llc_flow_lock); init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); - mutex_init(&lgr->llc_conf_mutex); + init_rwsem(&lgr->llc_conf_mutex); lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time); } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index dfea27a906f2..9b47c8409231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -39,6 +39,7 @@ #include "node.h" #include "net.h" #include <net/genetlink.h> +#include <linux/string_helpers.h> #include <linux/tipc_config.h> /* The legacy API had an artificial message length limit called @@ -173,11 +174,6 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } -static inline bool string_is_valid(char *s, int len) -{ - return memchr(s, '\0', len) ? true : false; -} - static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -445,7 +441,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(b->name, len)) + if (!string_is_terminated(b->name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) @@ -486,7 +482,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) @@ -584,7 +580,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) @@ -819,7 +815,7 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(lc->name, len)) + if (!string_is_terminated(lc->name, len)) return -EINVAL; media = tipc_media_find(lc->name); @@ -856,7 +852,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index ed6c71826d31..b2df1e0f8153 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -140,6 +140,10 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } +#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \ + NETDEV_XDP_ACT_REDIRECT | \ + NETDEV_XDP_ACT_XSK_ZEROCOPY) + int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { @@ -178,8 +182,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, /* For copy-mode, we are done. */ return 0; - if (!netdev->netdev_ops->ndo_bpf || - !netdev->netdev_ops->ndo_xsk_wakeup) { + if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) { err = -EOPNOTSUPP; goto err_unreg_pool; } diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..8cbf45a8bcdc 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> +#include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> @@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c06e54a10540..436d29640ac2 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c index 1ef2162cebcf..d74f3fd20f2b 100644 --- a/net/xfrm/xfrm_interface_bpf.c +++ b/net/xfrm/xfrm_interface_bpf.c @@ -39,8 +39,7 @@ __diag_ignore_all("-Wmissing-prototypes", * @to - Pointer to memory to which the metadata will be copied * Cannot be NULL */ -__used noinline -int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) +__bpf_kfunc int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) { struct sk_buff *skb = (struct sk_buff *)skb_ctx; struct xfrm_md_info *info; @@ -62,9 +61,7 @@ int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) * @from - Pointer to memory from which the metadata will be copied * Cannot be NULL */ -__used noinline -int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, - const struct bpf_xfrm_info *from) +__bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bpf_xfrm_info *from) { struct sk_buff *skb = (struct sk_buff *)skb_ctx; struct metadata_dst *md_dst; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc469027..35279c220bd7 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9eb82c5457d..5c61ec04b839 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; @@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = ktime_get_real_seconds(); + /* This lockless write can happen from different cpus. */ + WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; @@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, xfrm_pol_put(pols[0]); return 0; } - pols[1]->curlft.use_time = ktime_get_real_seconds(); + /* This write can happen from different cpus. */ + WRITE_ONCE(pols[1]->curlft.use_time, + ktime_get_real_seconds()); npols++; } } @@ -3742,6 +3745,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 59fffa02d1cc..2ab3e09e2227 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { - long tmo = x->lft.hard_add_expires_seconds + + time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { @@ -594,8 +594,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) next = tmo; } if (x->lft.hard_use_expires_seconds) { - long tmo = x->lft.hard_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.hard_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { - long tmo = x->lft.soft_add_expires_seconds + + time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -616,8 +616,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } } if (x->lft.soft_use_expires_seconds) { - long tmo = x->lft.soft_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.soft_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) @@ -1906,7 +1906,7 @@ out: hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); - if (x1->curlft.use_time) + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { @@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_curlft(x); - if (!x->curlft.use_time) - x->curlft.use_time = ktime_get_real_seconds(); + if (!READ_ONCE(x->curlft.use_time)) + WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { |