diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 33 | ||||
-rw-r--r-- | net/core/devlink.c | 70 | ||||
-rw-r--r-- | net/core/flow_offload.c | 4 | ||||
-rw-r--r-- | net/core/gro_cells.c | 7 | ||||
-rw-r--r-- | net/core/lwt_bpf.c | 12 | ||||
-rw-r--r-- | net/core/neighbour.c | 2 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 6 | ||||
-rw-r--r-- | net/core/net_namespace.c | 6 | ||||
-rw-r--r-- | net/core/netpoll.c | 22 | ||||
-rw-r--r-- | net/core/skbuff.c | 5 | ||||
-rw-r--r-- | net/core/skmsg.c | 87 | ||||
-rw-r--r-- | net/core/xdp.c | 29 |
12 files changed, 199 insertions, 84 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 82dc6b48e45f..ac7a7ae4614a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) } EXPORT_SYMBOL(dev_queue_xmit_accel); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; @@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: atomic_long_inc(&dev->tx_dropped); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines @@ -8921,6 +8917,17 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } +static u8 dev_xdp_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog || dev->xdp_state[i].link) + count++; + return count; +} + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -9011,6 +9018,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { + unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; @@ -9026,11 +9034,17 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } - /* just one XDP mode bit should be set, zero defaults to SKB mode */ - if (hweight32(flags & XDP_FLAGS_MODES) > 1) { + /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ + if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } + /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ + if (!num_modes && dev_xdp_prog_count(dev) > 1) { + NL_SET_ERR_MSG(extack, + "More than one program loaded, unset mode is ambiguous"); + return -EINVAL; + } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); @@ -11165,8 +11179,7 @@ static int __init net_dev_init(void) INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS - sd->csd.func = rps_trigger_softirq; - sd->csd.info = sd; + INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif diff --git a/net/core/devlink.c b/net/core/devlink.c index a932d95be798..8c5ddffd707d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -517,7 +517,7 @@ devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_l return test_bit(limit, &devlink->ops->reload_limits); } -static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_limit limit, u32 value) { struct nlattr *reload_stats_entry; @@ -526,8 +526,7 @@ static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_acti if (!reload_stats_entry) return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || - nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + 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); @@ -540,7 +539,7 @@ nla_put_failure: static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) { - struct nlattr *reload_stats_attr; + struct nlattr *reload_stats_attr, *act_info, *act_stats; int i, j, stat_idx; u32 value; @@ -552,17 +551,29 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink if (!reload_stats_attr) return -EMSGSIZE; - 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)) + 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; - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC || + 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; @@ -571,13 +582,19 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink value = devlink->stats.reload_stats[stat_idx]; else value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, i, j, value)) - goto nla_put_failure; + 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; @@ -755,6 +772,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; + /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -763,9 +782,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net *net = devlink_net(devlink_port->devlink); struct net_device *netdev = devlink_port->type_dev; - if (netdev && + if (netdev && net_eq(net, dev_net(netdev)) && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, netdev->ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, @@ -781,6 +801,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -791,6 +812,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -1448,7 +1470,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) - return err; + goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; @@ -1461,8 +1483,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, return 0; nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, @@ -8254,8 +8278,6 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port, { struct devlink_port_attrs *attrs = &devlink_port->attrs; - if (WARN_ON(devlink_port->registered)) - return -EEXIST; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { @@ -8279,6 +8301,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, { int ret; + if (WARN_ON(devlink_port->registered)) + return; devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) @@ -8301,6 +8325,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) @@ -8326,6 +8352,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d4474c812b64..715b67f6c62f 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && - this->indr.cb_priv == cb_priv) { + this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); - return; - } } } diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index e095fb871d91..6eb2e5ec2c50 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells) struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); napi_disable(&cell->napi); - netif_napi_del(&cell->napi); + __netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } + /* This barrier is needed because netpoll could access dev->napi_list + * under rcu protection. + */ + synchronize_net(); + free_percpu(gcells->cells); gcells->cells = NULL; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 7d3438215f32..2f7940bcf715 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -39,12 +39,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable is needed to protect per-cpu redirect_info between - * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and - * access to maps strictly require a rcu_read_lock() for protection, - * mixing with BH RCU lock doesn't work. + /* Migration disable and BH disable are needed to protect per-cpu + * redirect_info between BPF prog and skb_do_redirect(). */ - preempt_disable(); + migrate_disable(); + local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -78,7 +77,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } - preempt_enable(); + local_bh_enable(); + migrate_enable(); return ret; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e39e28b0a8d..9500d28a43b0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (tbl->is_multicast && + tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) remove = true; write_unlock(&n->lock); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 94fff0700bdd..999b70c59761 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1027,7 +1027,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; - if (!refcount_read(&dev_net(dev)->count)) + if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); @@ -1605,7 +1605,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; - if (!refcount_read(&dev_net(dev)->count)) + if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); @@ -1852,7 +1852,7 @@ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; - if (!refcount_read(&dev_net(ndev)->count)) + if (!refcount_read(&dev_net(ndev)->ns.count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dbc66b896287..2ef3b4557f40 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -45,7 +45,7 @@ static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif struct net init_net = { - .count = REFCOUNT_INIT(1), + .ns.count = REFCOUNT_INIT(1), .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), #ifdef CONFIG_KEYS .key_domain = &init_net_key_domain, @@ -249,7 +249,7 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { int id; - if (refcount_read(&net->count) == 0) + if (refcount_read(&net->ns.count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); @@ -329,7 +329,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) int error = 0; LIST_HEAD(net_exit_list); - refcount_set(&net->count, 1); + refcount_set(&net->ns.count, 1); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..960948290001 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> +#include <net/dsa.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> @@ -657,15 +658,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; + struct net_device *ndev = NULL, *dev = NULL; + struct net *net = current->nsproxy->net_ns; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -673,6 +674,19 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); + /* bring up DSA management network devices up first */ + for_each_netdev(net, dev) { + if (!netdev_uses_dsa(dev)) + continue; + + err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); + if (err < 0) { + np_err(np, "%s failed to open %s\n", + np->dev_name, dev->name); + goto put; + } + } + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1ba8f0163744..e578544b2cc7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4549,7 +4549,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); @@ -5786,6 +5786,9 @@ int skb_mpls_dec_ttl(struct sk_buff *skb) if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 654182ecf87b..25cdbb20f3a0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; - if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -397,28 +399,45 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, + struct sk_buff *skb) { - struct sock *sk = psock->sk; - int copied = 0, num_sge; struct sk_msg *msg; + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return NULL; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return NULL; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) - return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(msg); - return -EAGAIN; - } + return NULL; sk_msg_init(msg); + return msg; +} + +static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + struct sk_psock *psock, + struct sock *sk, + struct sk_msg *msg) +{ + int num_sge, copied; + + /* skb linearize may fail with ENOMEM, but lets simply try again + * later if this happens. Under memory pressure we don't want to + * drop the skb. We need to linearize the skb so that the mapping + * in skb_to_sgvec can not error. + */ + if (skb_linearize(skb)) + return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; } - sk_mem_charge(sk, skb->len); copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; @@ -430,6 +449,48 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return copied; } +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); + +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + struct sk_msg *msg; + + /* If we are receiving on the same sock skb->sk is already assigned, + * skip memory accounting and owner transition seeing it already set + * correctly. + */ + if (unlikely(skb->sk == sk)) + return sk_psock_skb_ingress_self(psock, skb); + msg = sk_psock_create_ingress_msg(sk, skb); + if (!msg) + return -EAGAIN; + + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + +/* Puts an skb on the ingress queue of the socket already assigned to the + * skb. In this case we do not need to check memory limits or skb_set_owner_r + * because the skb is already accounted for here. + */ +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + struct sock *sk = psock->sk; + + if (unlikely(!msg)) + return -EAGAIN; + sk_msg_init(msg); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { @@ -789,7 +850,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress(psock, skb); + err = sk_psock_skb_ingress_self(psock, skb); } if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); diff --git a/net/core/xdp.c b/net/core/xdp.c index 48aba933a5a8..d900cebc0acd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -335,11 +335,10 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling - * of xdp_frames/pages in those cases. This path is never used by the - * MEM_TYPE_XSK_BUFF_POOL memory type, so it's explicitly not part of - * the switch-statement. + * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) +static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -361,6 +360,10 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; + case MEM_TYPE_XSK_BUFF_POOL: + /* NB! Only valid from an xdp_buff! */ + xsk_buff_free(xdp); + break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); @@ -370,19 +373,19 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) void xdp_return_frame(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, false); + __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, true); + __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); void xdp_return_buff(struct xdp_buff *xdp) { - __xdp_return(xdp->data, &xdp->rxq->mem, true); + __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ @@ -400,18 +403,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) } EXPORT_SYMBOL_GPL(__xdp_release_frame); -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf) -{ - if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { - NL_SET_ERR_MSG(bpf->extack, - "program loaded with different flags"); - return false; - } - return true; -} -EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); - void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { |