diff options
Diffstat (limited to 'net')
49 files changed, 415 insertions, 318 deletions
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index fec11e576f31..b22078b67972 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -632,7 +632,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) test_bit(FLAG_HOLD_HCI_CONN, &chan->flags)) hci_conn_hold(conn->hcon); - list_add(&chan->list, &conn->chan_l); + /* Append to the list since the order matters for ECRED */ + list_add_tail(&chan->list, &conn->chan_l); } void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) @@ -3771,7 +3772,11 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); - if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) + /* Check if channel for outgoing connection or if it wasn't deferred + * since in those cases it must be skipped. + */ + if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags) || + !test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) return; /* Reset ident so only one response is sent */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8f6f7db48d4e..7cb192cbd65f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -660,12 +660,9 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, void __user *data_in = u64_to_user_ptr(kattr->test.data_in); void *data; - if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) + if (user_size < ETH_HLEN || user_size > PAGE_SIZE - headroom - tailroom) return ERR_PTR(-EINVAL); - if (user_size > size) - return ERR_PTR(-EMSGSIZE); - size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 7d41cde1bcca..2e538399757f 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -355,11 +355,6 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { - const struct btf *btf_vmlinux; - const struct btf_type *t; - const char *tname; - u32 btf_id; - if (prog->aux->dst_prog) return false; @@ -374,13 +369,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - btf_vmlinux = bpf_get_btf_vmlinux(); - if (IS_ERR_OR_NULL(btf_vmlinux)) - return false; - btf_id = prog->aux->attach_btf_id; - t = btf_type_by_id(btf_vmlinux, btf_id); - tname = btf_name_by_offset(btf_vmlinux, t->name_off); - return !!strncmp(tname, "bpf_sk_storage", + return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; diff --git a/net/core/dev.c b/net/core/dev.c index b91658e8aedb..30da277c5a6f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1121,6 +1121,12 @@ out: return ret; } +static bool dev_addr_cmp(struct net_device *dev, unsigned short type, + const char *ha) +{ + return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); +} + /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace @@ -1129,7 +1135,7 @@ out: * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. - * The caller must hold RCU or RTNL. + * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1141,14 +1147,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, struct net_device *dev; for_each_netdev_rcu(net, dev) - if (dev->type == type && - !memcmp(dev->dev_addr, ha, dev->addr_len)) + if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); +/** + * dev_getbyhwaddr() - find a device by its hardware address + * @net: the applicable net namespace + * @type: media type of device + * @ha: hardware address + * + * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold + * rtnl_lock. + * + * Context: rtnl_lock() must be held. + * Return: pointer to the net_device, or NULL if not found + */ +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *ha) +{ + struct net_device *dev; + + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev_addr_cmp(dev, type, ha)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -2070,20 +2101,55 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } +static void rtnl_net_dev_lock(struct net_device *dev) +{ + bool again; + + do { + struct net *net; + + again = false; + + /* netns might be being dismantled. */ + rcu_read_lock(); + net = dev_net_rcu(dev); + net_passive_inc(net); + rcu_read_unlock(); + + rtnl_net_lock(net); + +#ifdef CONFIG_NET_NS + /* dev might have been moved to another netns. */ + if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { + rtnl_net_unlock(net); + net_passive_dec(net); + again = true; + } +#endif + } while (again); +} + +static void rtnl_net_dev_unlock(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + rtnl_net_unlock(net); + net_passive_dec(net); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); - err = __register_netdevice_notifier_net(net, nb, false); + rtnl_net_dev_lock(dev); + err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); return err; } @@ -2093,13 +2159,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(net, nb); - rtnl_net_unlock(net); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_net_dev_unlock(dev); return err; } @@ -4692,7 +4757,7 @@ use_local_napi: * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) - __raise_softirq_irqoff(NET_RX_SOFTIRQ); + raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS @@ -6920,6 +6985,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -11880,11 +11962,9 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - struct net *net = dev_net(dev); - - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); unregister_netdevice(dev); - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 6efd4cccc9dd..212f0a048cab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1734,30 +1734,30 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - rc = genl_register_family(&net_drop_monitor_family); - if (rc) { - pr_err("Could not create drop monitor netlink family\n"); - return rc; + for_each_possible_cpu(cpu) { + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); + return rc; + } + + rc = genl_register_family(&net_drop_monitor_family); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; - for_each_possible_cpu(cpu) { - net_dm_cpu_data_init(cpu); - net_dm_hw_cpu_data_init(cpu); - } - goto out; out_unreg: - genl_unregister_family(&net_drop_monitor_family); + WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } @@ -1766,19 +1766,18 @@ static void exit_net_drop_monitor(void) { int cpu; - BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); - /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } - - BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 5db41bf2ed93..9cd8de6bebb5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -853,23 +853,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { - enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; - struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_ports_range *key_ports_range = NULL; + struct flow_dissector_key_ports *key_ports = NULL; + __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS; - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); - if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + + if (!key_ports && !key_ports_range) return; - key_ports = skb_flow_dissector_target(flow_dissector, - dissector_ports, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); + + if (key_ports) + key_ports->ports = ports; + + if (key_ports_range) + key_ports_range->tp.ports = ports; } static void @@ -924,6 +931,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -968,20 +976,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE, - target_container); - - if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) { + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + key_ports_range->tp.src = flow_keys->sport; + key_ports_range->tp.dst = flow_keys->dport; + } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { diff --git a/net/core/gro.c b/net/core/gro.c index d1f44084e978..0ad549b07e03 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -7,9 +7,6 @@ #define MAX_GRO_SKBS 8 -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) - static DEFINE_SPINLOCK(offload_lock); /** @@ -656,6 +653,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; + skb->ip_summed = CHECKSUM_NONE; skb_shinfo(skb)->gso_type = 0; skb_shinfo(skb)->gso_size = 0; if (unlikely(skb->slow_gro)) { diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb39a12b2f82..4303f2a49262 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -464,7 +464,7 @@ static void net_complete_free(void) } -static void net_free(struct net *net) +void net_passive_dec(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); @@ -482,7 +482,7 @@ void net_drop_ns(void *p) struct net *net = (struct net *)p; if (net) - net_free(net); + net_passive_dec(net); } struct net *copy_net_ns(unsigned long flags, @@ -523,7 +523,7 @@ put_userns: key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); - net_free(net); + net_passive_dec(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -672,7 +672,7 @@ static void cleanup_net(struct work_struct *work) key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); - net_free(net); + net_passive_dec(net); } cleanup_net_task = NULL; } diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..733c0cbd393d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -282,6 +282,16 @@ efault: } EXPORT_SYMBOL(put_cmsg); +int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data) +{ + /* Don't produce truncated CMSGs */ + if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) + return -ETOOSMALL; + + return put_cmsg(msg, level, type, len, data); +} + void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..b1c81687e9d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> @@ -95,7 +96,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif -#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) +#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ + GRO_MAX_HEAD_PAD)) /* 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 @@ -220,67 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +235,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -736,7 +664,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ - if (len <= SKB_WITH_OVERHEAD(1024) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); @@ -813,10 +741,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +752,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) @@ -6123,11 +6033,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif + ipvs_reset(skb); if (!xnet) return; - ipvs_reset(skb); skb->mark = 0; skb_clear_tstamp(skb); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 61f3f3d4e528..0ddc4c718833 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -549,6 +549,9 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return num_sge; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) + psock->ingress_bytes += len; +#endif copied = len; msg->sg.start = 0; msg->sg.size = copied; @@ -1144,6 +1147,10 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) if (!ret) sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + if (sk_is_tcp(sk)) { + psock->strp.cb.read_sock = tcp_bpf_strp_read_sock; + psock->copied_seq = tcp_sk(sk)->copied_seq; + } return ret; } diff --git a/net/core/sock.c b/net/core/sock.c index eae2ae70a2e0..6c0e87f97fa4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2246,6 +2246,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { + net_passive_inc(net); __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } @@ -2270,6 +2271,7 @@ EXPORT_SYMBOL(sk_alloc); static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); + struct net *net = sock_net(sk); struct sk_filter *filter; if (sk->sk_destruct) @@ -2301,14 +2303,28 @@ static void __sk_destruct(struct rcu_head *head) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); - if (likely(sk->sk_net_refcnt)) - put_net_track(sock_net(sk), &sk->ns_tracker); - else - __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); - + if (likely(sk->sk_net_refcnt)) { + put_net_track(net, &sk->ns_tracker); + } else { + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + } sk_prot_free(sk->sk_prot_creator, sk); } +void sk_net_refcnt_upgrade(struct sock *sk) +{ + struct net *net = sock_net(sk); + + WARN_ON_ONCE(sk->sk_net_refcnt); + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); +} +EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade); + void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); @@ -2405,6 +2421,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * is not properly dismantling its kernel sockets at netns * destroy time. */ + net_passive_inc(sock_net(newsk)); __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f1b9b3958792..82a14f131d00 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -303,7 +303,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { - ret = sk_psock_init_strp(sk, psock); + if (sk_is_tcp(sk)) + ret = sk_psock_init_strp(sk, psock); + else + ret = -EOPNOTSUPP; if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); @@ -541,6 +544,9 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; + if (sk_is_vsock(sk) && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index ad2741f1346a..c7769ee0d9c5 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -34,6 +34,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; +static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .extra1 = &netdev_budget_usecs_min, }, { .procname = "fb_tunnels_only_for_init_net", diff --git a/net/ethtool/common.c b/net/ethtool/common.c index d88e9080643b..b97374b508f6 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,6 +6,7 @@ #include <linux/rtnetlink.h> #include <linux/ptp_clock_kernel.h> #include <linux/phy_link_topology.h> +#include <net/netdev_queues.h> #include "netlink.h" #include "common.h" @@ -771,6 +772,21 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return 0; } +void ethtool_ringparam_get_cfg(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kparam, + struct netlink_ext_ack *extack) +{ + memset(param, 0, sizeof(*param)); + memset(kparam, 0, sizeof(*kparam)); + + param->cmd = ETHTOOL_GRINGPARAM; + dev->ethtool_ops->get_ringparam(dev, param, kparam, extack); + + /* Driver gives us current state, we want to return current config */ + kparam->tcp_data_split = dev->cfg->hds_config; +} + static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info) { memset(info, 0, sizeof(*info)); diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 58e9e7db06f9..a1088c2441d0 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -51,6 +51,12 @@ int ethtool_check_max_channel(struct net_device *dev, struct ethtool_channels channels, struct genl_info *info); int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context); + +void ethtool_ringparam_get_cfg(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kparam, + struct netlink_ext_ack *extack); + int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); int ethtool_get_ts_info_by_phc(struct net_device *dev, struct kernel_ethtool_ts_info *info, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7609ce2b2c5e..1c3ba2247776 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2059,8 +2059,8 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM }; struct kernel_ethtool_ringparam kernel_ringparam; + struct ethtool_ringparam ringparam, max; int ret; if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam) @@ -2069,7 +2069,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) if (copy_from_user(&ringparam, useraddr, sizeof(ringparam))) return -EFAULT; - dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL); + ethtool_ringparam_get_cfg(dev, &max, &kernel_ringparam, NULL); /* ensure new ring parameters are within the maximums */ if (ringparam.rx_pending > max.rx_max_pending || diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 7839bfd1ac6a..aeedd5ec6b8c 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -215,17 +215,16 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, static int ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) { - struct kernel_ethtool_ringparam kernel_ringparam = {}; - struct ethtool_ringparam ringparam = {}; + struct kernel_ethtool_ringparam kernel_ringparam; struct net_device *dev = req_info->dev; + struct ethtool_ringparam ringparam; struct nlattr **tb = info->attrs; const struct nlattr *err_attr; bool mod = false; int ret; - dev->ethtool_ops->get_ringparam(dev, &ringparam, - &kernel_ringparam, info->extack); - kernel_ringparam.tcp_data_split = dev->cfg->hds_config; + ethtool_ringparam_get_cfg(dev, &ringparam, &kernel_ringparam, + info->extack); ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); ethnl_update_u32(&ringparam.rx_mini_pending, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f23a1ec6694c..814300eee39d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1077,7 +1077,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d704bda6c41..57df7c1d2faa 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1565,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb); * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ -int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; + u32 seq = *copied_seq; u32 offset; int copied = 0; @@ -1624,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_eat_recv_skb(sk, skb); if (!desc->count) break; - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); } - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); + + if (noack) + goto out; tcp_rcv_space_adjust(sk); @@ -1635,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } +out: return copied; } + +int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + return __tcp_read_sock(sk, desc, recv_actor, false, + &tcp_sk(sk)->copied_seq); +} EXPORT_SYMBOL(tcp_read_sock); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) +{ + return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq); +} + int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; @@ -2438,14 +2457,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; - err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, - sizeof(dmabuf_cmsg), &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } sent += copy; @@ -2499,16 +2516,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, offset += copy; remaining_len -= copy; - err = put_cmsg(msg, SOL_SOCKET, - SO_DEVMEM_DMABUF, - sizeof(dmabuf_cmsg), - &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } atomic_long_inc(&niov->pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 47f65b1b70ca..ba581785adb4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -646,6 +646,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops) ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct sock *sk = strp->sk; + struct sk_psock *psock; + struct tcp_sock *tp; + int copied = 0; + + tp = tcp_sk(sk); + rcu_read_lock(); + psock = sk_psock(sk); + if (WARN_ON_ONCE(!psock)) { + desc->error = -EINVAL; + goto out; + } + + psock->ingress_bytes = 0; + copied = tcp_read_sock_noack(sk, desc, recv_actor, true, + &psock->copied_seq); + if (copied < 0) + goto out; + /* recv_actor may redirect skb to another socket (SK_REDIRECT) or + * just put skb into ingress queue of current socket (SK_PASS). + * For SK_REDIRECT, we need to ack the frame immediately but for + * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser(). + */ + tp->copied_seq = psock->copied_seq - psock->ingress_bytes; + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes); +out: + rcu_read_unlock(); + return copied; +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 0f523cbfe329..32b28fc21b63 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -178,7 +178,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) if (!skb) return; - skb_dst_drop(skb); + tcp_cleanup_skb(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects @@ -195,7 +195,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb82e01da911..0cbf81bf3d45 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -243,9 +243,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; - if (old_ratio != tcp_sk(sk)->scaling_ratio) - WRITE_ONCE(tcp_sk(sk)->window_clamp, - tcp_win_from_space(sk, sk->sk_rcvbuf)); + if (old_ratio != tcp_sk(sk)->scaling_ratio) { + struct tcp_sock *tp = tcp_sk(sk); + + val = tcp_win_from_space(sk, sk->sk_rcvbuf); + tcp_set_window_clamp(sk, val); + + if (tp->window_clamp < tp->rcvq_space.space) + tp->rcvq_space.space = tp->window_clamp; + } } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -4970,7 +4976,7 @@ static void tcp_ofo_queue(struct sock *sk) tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); else kfree_skb_partial(skb, fragstolen); @@ -5162,7 +5168,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); skb_set_owner_r(skb, sk); } return eaten; @@ -5245,7 +5251,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); return; } - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -6226,7 +6232,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_header_len); eaten = tcp_queue_rcv(sk, skb, &fragstolen); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cc2b5194a18d..2632844d2c35 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2027,7 +2027,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ skb_condense(skb); - skb_dst_drop(skb); + tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b089b08e9617..dfdb7a4608a8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -815,12 +815,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ - /* TODO: We probably should defer ts_recent change once - * we take ownership of @req. - */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); - if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting at tcp_rsk(req)->rcv_isn + 1. */ @@ -869,6 +863,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + if (own_req && tmp_opt.saw_tstamp && + !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) + tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval; + if (own_req && rsk_drop_req(req)) { reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 0ac4283acdf2..7c05ac846646 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -262,10 +262,18 @@ static int rpl_input(struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; + struct lwtunnel_state *lwtst; struct rpl_lwt *rlwt; int err; - rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); + /* We cannot dereference "orig_dst" once ip6_route_input() or + * skb_dst_drop() is called. However, in order to detect a dst loop, we + * need the address of its lwtstate. So, save the address of lwtstate + * now and use it later as a comparison. + */ + lwtst = orig_dst->lwtstate; + + rlwt = rpl_lwt_lwtunnel(lwtst); local_bh_disable(); dst = dst_cache_get(&rlwt->cache); @@ -280,7 +288,9 @@ static int rpl_input(struct sk_buff *skb) if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); - if (!dst->error) { + + /* cache only if we don't create a dst reference loop */ + if (!dst->error && lwtst != dst->lwtstate) { local_bh_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &ipv6_hdr(skb)->saddr); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 33833b2064c0..51583461ae29 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -472,10 +472,18 @@ static int seg6_input_core(struct net *net, struct sock *sk, { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; + struct lwtunnel_state *lwtst; struct seg6_lwt *slwt; int err; - slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + /* We cannot dereference "orig_dst" once ip6_route_input() or + * skb_dst_drop() is called. However, in order to detect a dst loop, we + * need the address of its lwtstate. So, save the address of lwtstate + * now and use it later as a comparison. + */ + lwtst = orig_dst->lwtstate; + + slwt = seg6_lwt_lwtunnel(lwtst); local_bh_disable(); dst = dst_cache_get(&slwt->cache); @@ -490,7 +498,9 @@ static int seg6_input_core(struct net *net, struct sock *sk, if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); - if (!dst->error) { + + /* cache only if we don't create a dst reference loop */ + if (!dst->error && lwtst != dst->lwtstate) { local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 572d160edca3..c0e47f4f7b1a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1514,11 +1514,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, if (mptcp_pm_is_userspace(msk)) goto next; - if (list_empty(&msk->conn_list)) { - mptcp_pm_remove_anno_addr(msk, addr, false); - goto next; - } - lock_sock(sk); remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f6a207958459..ad21925af061 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1199,6 +1199,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } + if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback))) + return; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fd021cf8286e..9f18217dddc8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1142,7 +1142,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (data_len == 0) { pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); - subflow->map_data_len = 0; return MAPPING_INVALID; } @@ -1286,18 +1285,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss mptcp_schedule_work(sk); } -static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) -{ - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - - if (subflow->mp_join) - return false; - else if (READ_ONCE(msk->csum_enabled)) - return !subflow->valid_csum_seen; - else - return READ_ONCE(msk->allow_infinite_fallback); -} - static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1393,7 +1380,7 @@ fallback: return true; } - if (!subflow_can_fallback(subflow) && subflow->map_data_len) { + if (!READ_ONCE(msk->allow_infinite_fallback)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1772,10 +1759,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, * needs it. * Update ns_tracker to current stack trace and refcounted tracker. */ - __netns_tracker_free(net, &sf->sk->ns_tracker, false); - sf->sk->sk_net_refcnt = 1; - get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sf->sk); err = tcp_set_ulp(sf->sk, "mptcp"); if (err) goto err_free; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 85311226183a..a53ea60d0a78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -795,16 +795,6 @@ static int netlink_release(struct socket *sock) sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); - /* Because struct net might disappear soon, do not keep a pointer. */ - if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { - __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); - /* Because of deferred_put_nlk_sk and use of work queue, - * it is possible netns will be freed before this socket. - */ - sock_net_set(sk, &init_net); - __netns_tracker_alloc(&init_net, &sk->ns_tracker, - false, GFP_KERNEL); - } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 0581c53e6517..3cc2f303bf78 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -504,12 +504,8 @@ bool rds_tcp_tune(struct socket *sock) release_sock(sk); return false; } - /* Update ns_tracker to current stack trace and refcounted tracker */ - __netns_tracker_free(net, &sk->ns_tracker, false); - - sk->sk_net_refcnt = 1; - netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sk); + put_net(net); } rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5e740c486203..a64a0cab1bf7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -360,7 +360,6 @@ struct rxrpc_peer { u8 pmtud_jumbo; /* Max jumbo packets for the MTU */ bool ackr_adv_pmtud; /* T if the peer advertises path-MTU */ unsigned int ackr_max_data; /* Maximum data advertised by peer */ - seqcount_t mtu_lock; /* Lockless MTU access management */ unsigned int if_mtu; /* Local interface MTU (- hdrsize) for this peer */ unsigned int max_data; /* Maximum packet data capacity for this peer */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9047ba13bd31..24aceb183c2c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -810,9 +810,7 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb if (max_mtu < peer->max_data) { trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu, rxrpc_pmtud_reduce_ack); - write_seqcount_begin(&peer->mtu_lock); peer->max_data = max_mtu; - write_seqcount_end(&peer->mtu_lock); } max_data = umin(max_mtu, peer->max_data); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bc283da9ee40..7f4729234957 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -130,9 +130,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu) peer->pmtud_bad = max_data + 1; trace_rxrpc_pmtud_reduce(peer, 0, max_data, rxrpc_pmtud_reduce_icmp); - write_seqcount_begin(&peer->mtu_lock); peer->max_data = max_data; - write_seqcount_end(&peer->mtu_lock); } } @@ -408,13 +406,8 @@ void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t a } max_data = umin(max_data, peer->ackr_max_data); - if (max_data != peer->max_data) { - preempt_disable(); - write_seqcount_begin(&peer->mtu_lock); + if (max_data != peer->max_data) peer->max_data = max_data; - write_seqcount_end(&peer->mtu_lock); - preempt_enable(); - } jumbo = max_data + sizeof(struct rxrpc_jumbo_header); jumbo /= RXRPC_JUMBO_SUBPKTLEN; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 0fcc87f0409f..56e09d161a97 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -235,7 +235,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); - seqcount_init(&peer->mtu_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); peer->recent_srtt_us = UINT_MAX; peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; @@ -325,10 +324,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) hash_key = rxrpc_peer_hash_key(local, &peer->srx); rxrpc_init_peer(local, peer, hash_key); - spin_lock_bh(&rxnet->peer_hash_lock); + spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - spin_unlock_bh(&rxnet->peer_hash_lock); + spin_unlock(&rxnet->peer_hash_lock); } /* diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index 7ef93407be83..e848a4777b8c 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -478,6 +478,18 @@ static int rxperf_deliver_request(struct rxperf_call *call) call->unmarshal++; fallthrough; case 2: + ret = rxperf_extract_data(call, true); + if (ret < 0) + return ret; + + /* Deal with the terminal magic cookie. */ + call->iov_len = 4; + call->kvec[0].iov_len = call->iov_len; + call->kvec[0].iov_base = call->tmp; + iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len); + call->unmarshal++; + fallthrough; + case 3: ret = rxperf_extract_data(call, false); if (ret < 0) return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e47e5355be6..4f648af8cfaa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -97,7 +97,7 @@ tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, n, xa_limit_32b, &next, GFP_KERNEL); - if (err) + if (err < 0) goto err_xa_alloc; exts->miss_cookie_node = n; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c241cc552e8d..bfcff6d6a438 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index ca6984541edb..3e6cb35baf25 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3337,10 +3337,7 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family) * which need net ref. */ sk = smc->clcsock->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sk); return 0; } diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 8299ceb3e373..95696f42647e 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -347,7 +347,10 @@ static int strp_read_sock(struct strparser *strp) struct socket *sock = strp->sk->sk_socket; read_descriptor_t desc; - if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) + if (unlikely(!sock || !sock->ops)) + return -EBUSY; + + if (unlikely(!strp->cb.read_sock && !sock->ops->read_sock)) return -EBUSY; desc.arg.data = strp; @@ -355,7 +358,10 @@ static int strp_read_sock(struct strparser *strp) desc.count = 1; /* give more than one skb per call */ /* sk should be locked here, so okay to do read_sock */ - sock->ops->read_sock(strp->sk, &desc, strp_recv); + if (strp->cb.read_sock) + strp->cb.read_sock(strp, &desc, strp_recv); + else + sock->ops->read_sock(strp->sk, &desc, strp_recv); desc.error = strp->cb.read_sock_done(strp, desc.error); @@ -468,6 +474,7 @@ int strp_init(struct strparser *strp, struct sock *sk, strp->cb.unlock = cb->unlock ? : strp_sock_unlock; strp->cb.rcv_msg = cb->rcv_msg; strp->cb.parse_msg = cb->parse_msg; + strp->cb.read_sock = cb->read_sock; strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index cb279eb9ac4b..7ce5e28a6c03 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1674,12 +1674,14 @@ static void remove_cache_proc_entries(struct cache_detail *cd) } } -#ifdef CONFIG_PROC_FS static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) { struct proc_dir_entry *p; struct sunrpc_net *sn; + if (!IS_ENABLED(CONFIG_PROC_FS)) + return 0; + sn = net_generic(net, sunrpc_net_id); cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc); if (cd->procfs == NULL) @@ -1707,12 +1709,6 @@ out_nomem: remove_cache_proc_entries(cd); return -ENOMEM; } -#else /* CONFIG_PROC_FS */ -static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) -{ - return 0; -} -#endif void __init cache_initialize(void) { diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index cef623ea1506..9b45fbdc90ca 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -864,8 +864,6 @@ void rpc_signal_task(struct rpc_task *task) if (!rpc_task_set_rpc_status(task, -ERESTARTSYS)) return; trace_rpc_task_signalled(task, task->tk_action); - set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate); - smp_mb__after_atomic(); queue = READ_ONCE(task->tk_waitqueue); if (queue) rpc_wake_up_queued_task(queue, task); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index cb3bd12f5818..72e5a01df3d3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1541,10 +1541,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, newlen = error; if (protocol == IPPROTO_TCP) { - __netns_tracker_free(net, &sock->sk->ns_tracker, false); - sock->sk->sk_net_refcnt = 1; - get_net_track(net, &sock->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sock->sk); if ((error = kernel_listen(sock, 64)) < 0) goto bummer; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c60936d8cef7..83cc095846d3 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1941,12 +1941,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, goto out; } - if (protocol == IPPROTO_TCP) { - __netns_tracker_free(xprt->xprt_net, &sock->sk->ns_tracker, false); - sock->sk->sk_net_refcnt = 1; - get_net_track(xprt->xprt_net, &sock->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(xprt->xprt_net, 1); - } + if (protocol == IPPROTO_TCP) + sk_net_refcnt_upgrade(sock->sk); filp = sock_alloc_file(sock, O_NONBLOCK, NULL); if (IS_ERR(filp)) @@ -2581,7 +2577,15 @@ static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid) struct sock_xprt *lower_transport = container_of(lower_xprt, struct sock_xprt, xprt); - lower_transport->xprt_err = status ? -EACCES : 0; + switch (status) { + case 0: + case -EACCES: + case -ETIMEDOUT: + lower_transport->xprt_err = status; + break; + default: + lower_transport->xprt_err = -EACCES; + } complete(&lower_transport->handshake_done); xprt_put(lower_xprt); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 34945de1fb1f..f0e613d97664 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2102,6 +2102,7 @@ restart_locked: goto out_sock_put; } + sock_put(other); goto lookup; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 53a081d49d28..7e3db87ae433 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1189,6 +1189,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); + if (WARN_ON_ONCE(!vsk->transport)) + return -ENODEV; + return vsk->transport->read_skb(vsk, read_actor); } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index b58c3818f284..f0e48e6911fc 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -670,6 +670,13 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) }; int ret; + mutex_lock(&vsock->rx_lock); + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + mutex_unlock(&vsock->rx_lock); + + atomic_set(&vsock->queued_replies, 0); + ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, vqs_info, NULL); if (ret < 0) return ret; @@ -779,9 +786,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->vdev = vdev; - vsock->rx_buf_nr = 0; - vsock->rx_buf_max_nr = 0; - atomic_set(&vsock->queued_replies, 0); mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index f201d9eca1df..07b96d56f3a5 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -87,7 +87,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, lock_sock(sk); vsk = vsock_sk(sk); - if (!vsk->transport) { + if (WARN_ON_ONCE(!vsk->transport)) { copied = -ENODEV; goto out; } |