summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
Diffstat (limited to 'include/net')
-rw-r--r--include/net/ax25.h12
-rw-r--r--include/net/gro_cells.h13
-rw-r--r--include/net/icmp.h9
-rw-r--r--include/net/inet_frag.h133
-rw-r--r--include/net/inetpeer.h1
-rw-r--r--include/net/ip.h3
-rw-r--r--include/net/ip_fib.h2
-rw-r--r--include/net/ipv6.h26
-rw-r--r--include/net/neighbour.h28
-rw-r--r--include/net/phonet/pep.h5
-rw-r--r--include/net/sock.h36
-rw-r--r--include/net/tcp.h1
12 files changed, 160 insertions, 109 deletions
diff --git a/include/net/ax25.h b/include/net/ax25.h
index e602f8177ebf..b507ce2b1952 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -199,6 +199,18 @@ static inline void ax25_hold_route(ax25_route *ax25_rt)
void __ax25_put_route(ax25_route *ax25_rt);
+extern rwlock_t ax25_route_lock;
+
+static inline void ax25_route_lock_use(void)
+{
+ read_lock(&ax25_route_lock);
+}
+
+static inline void ax25_route_lock_unuse(void)
+{
+ read_unlock(&ax25_route_lock);
+}
+
static inline void ax25_put_route(ax25_route *ax25_rt)
{
if (atomic_dec_and_test(&ax25_rt->refcount))
diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index cf6c74550baa..cd856b7a11f5 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -19,22 +19,30 @@ static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *s
struct gro_cell *cell;
struct net_device *dev = skb->dev;
+ rcu_read_lock();
+ if (unlikely(!(dev->flags & IFF_UP)))
+ goto drop;
+
if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) {
netif_rx(skb);
- return;
+ goto unlock;
}
cell = this_cpu_ptr(gcells->cells);
if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+drop:
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
- return;
+ goto unlock;
}
__skb_queue_tail(&cell->napi_skbs, skb);
if (skb_queue_len(&cell->napi_skbs) == 1)
napi_schedule(&cell->napi);
+
+unlock:
+ rcu_read_unlock();
}
/* called under BH context */
@@ -84,6 +92,7 @@ static inline void gro_cells_destroy(struct gro_cells *gcells)
for_each_possible_cpu(i) {
struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
+ napi_disable(&cell->napi);
netif_napi_del(&cell->napi);
__skb_queue_purge(&cell->napi_skbs);
}
diff --git a/include/net/icmp.h b/include/net/icmp.h
index 970028e13382..06ceb483475d 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -22,6 +22,7 @@
#include <net/inet_sock.h>
#include <net/snmp.h>
+#include <net/ip.h>
struct icmp_err {
int errno;
@@ -39,7 +40,13 @@ struct net_proto_family;
struct sk_buff;
struct net;
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ const struct ip_options *opt);
+static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+ __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
+}
+
int icmp_rcv(struct sk_buff *skb);
void icmp_err(struct sk_buff *skb, u32 info);
int icmp_init(void);
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index c26a6e4dc306..6260ec146142 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,13 +1,19 @@
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
+#include <linux/rhashtable.h>
+
struct netns_frags {
- /* Keep atomic mem on separate cachelines in structs that include it */
- atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
+ long high_thresh;
+ long low_thresh;
int timeout;
- int high_thresh;
- int low_thresh;
+ struct inet_frags *f;
+
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
+ /* Keep atomic mem on separate cachelines in structs that include it */
+ atomic_long_t mem ____cacheline_aligned_in_smp;
};
/**
@@ -23,74 +29,68 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
+struct frag_v4_compare_key {
+ __be32 saddr;
+ __be32 daddr;
+ u32 user;
+ u32 vif;
+ __be16 id;
+ u16 protocol;
+};
+
+struct frag_v6_compare_key {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 user;
+ __be32 id;
+ u32 iif;
+};
+
/**
* struct inet_frag_queue - fragment queue
*
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
* @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
+ * @rb_fragments: received fragments rb-tree root
* @fragments_tail: received fragments tail
+ * @last_run_head: the head of the last "run". see ip_fragment.c
* @stamp: timestamp of the last received fragment
* @len: total length of the original datagram
* @meat: length of received fragments so far
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
- spinlock_t lock;
+ struct rhash_head node;
+ union {
+ struct frag_v4_compare_key v4;
+ struct frag_v6_compare_key v6;
+ } key;
struct timer_list timer;
- struct hlist_node list;
+ spinlock_t lock;
atomic_t refcnt;
- struct sk_buff *fragments;
+ struct sk_buff *fragments; /* Used in IPv6. */
+ struct rb_root rb_fragments; /* Used in IPv4. */
struct sk_buff *fragments_tail;
+ struct sk_buff *last_run_head;
ktime_t stamp;
int len;
int meat;
__u8 flags;
u16 max_size;
- struct netns_frags *net;
- struct hlist_node list_evictor;
-};
-
-#define INETFRAGS_HASHSZ 1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- * struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH 128
-
-struct inet_frag_bucket {
- struct hlist_head chain;
- spinlock_t chain_lock;
+ struct netns_frags *net;
+ struct rcu_head rcu;
};
struct inet_frags {
- struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
-
- struct work_struct frags_work;
- unsigned int next_bucket;
- unsigned long last_rebuild_jiffies;
- bool rebuild;
-
- /* The first call to hashfn is responsible to initialize
- * rnd. This is best done with net_get_random_once.
- *
- * rnd_seqlock is used to let hash insertion detect
- * when it needs to re-lookup the hash chain to use.
- */
- u32 rnd;
- seqlock_t rnd_seqlock;
int qsize;
- unsigned int (*hashfn)(const struct inet_frag_queue *);
- bool (*match)(const struct inet_frag_queue *q,
- const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
@@ -98,56 +98,47 @@ struct inet_frags {
void (*frag_expire)(unsigned long data);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
+ struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
{
- atomic_set(&nf->mem, 0);
+ atomic_long_set(&nf->mem, 0);
+ return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key, unsigned int hash);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix);
+/* Free all skbs in the queue; return the sum of their truesizes. */
+unsigned int inet_frag_rbtree_purge(struct rb_root *root);
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
{
if (atomic_dec_and_test(&q->refcnt))
- inet_frag_destroy(q, f);
-}
-
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
- return !hlist_unhashed(&q->list_evictor);
+ inet_frag_destroy(q);
}
/* Memory Tracking Functions. */
-static inline int frag_mem_limit(struct netns_frags *nf)
-{
- return atomic_read(&nf->mem);
-}
-
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline long frag_mem_limit(const struct netns_frags *nf)
{
- atomic_sub(i, &nf->mem);
+ return atomic_long_read(&nf->mem);
}
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_add(i, &nf->mem);
+ atomic_long_sub(val, &nf->mem);
}
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
{
- return atomic_read(&nf->mem);
+ atomic_long_add(val, &nf->mem);
}
/* RFC 3168 support :
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 235c7811a86a..408d76f47bd2 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -40,6 +40,7 @@ struct inet_peer {
u32 metrics[RTAX_MAX];
u32 rate_tokens; /* rate limiting for ICMP */
+ u32 n_redirects;
unsigned long rate_last;
union {
struct list_head gc_list;
diff --git a/include/net/ip.h b/include/net/ip.h
index 0530bcdbc212..e2320f9e4d3e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -524,7 +524,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
return skb;
}
#endif
-int ip_frag_mem(struct net *net);
/*
* Functions provided by ip_forward.c
@@ -547,6 +546,8 @@ static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
}
void ip_options_fragment(struct sk_buff *skb);
+int __ip_options_compile(struct net *net, struct ip_options *opt,
+ struct sk_buff *skb, __be32 *info);
int ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb);
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 2a25b53cd427..f6ff83b2ac87 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -200,7 +200,7 @@ int fib_table_insert(struct fib_table *, struct fib_config *);
int fib_table_delete(struct fib_table *, struct fib_config *);
int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
struct netlink_callback *cb);
-int fib_table_flush(struct fib_table *table);
+int fib_table_flush(struct fib_table *table, bool flush_all);
struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
void fib_table_flush_external(struct fib_table *table);
void fib_free_table(struct fib_table *tb);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0e01d570fa22..c07cf9596b6f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -320,13 +320,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
idev->cnf.accept_ra;
}
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
#define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */
#define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */
#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */
@@ -505,17 +498,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
-struct ip6_create_arg {
- __be32 id;
- u32 user;
- const struct in6_addr *src;
- const struct in6_addr *dst;
- int iif;
- u8 ecn;
-};
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
@@ -523,19 +507,13 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
- __be32 id; /* fragment id */
- u32 user;
- struct in6_addr saddr;
- struct in6_addr daddr;
-
int iif;
unsigned int csum;
__u16 nhoffset;
u8 ecn;
};
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 8b683841e574..f6017ddc4ded 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -448,6 +448,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
{
+ unsigned int hh_alen = 0;
unsigned int seq;
int hh_len;
@@ -455,16 +456,33 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
seq = read_seqbegin(&hh->hh_lock);
hh_len = hh->hh_len;
if (likely(hh_len <= HH_DATA_MOD)) {
- /* this is inlined by gcc */
- memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+ hh_alen = HH_DATA_MOD;
+
+ /* skb_push() would proceed silently if we have room for
+ * the unaligned size but not for the aligned size:
+ * check headroom explicitly.
+ */
+ if (likely(skb_headroom(skb) >= HH_DATA_MOD)) {
+ /* this is inlined by gcc */
+ memcpy(skb->data - HH_DATA_MOD, hh->hh_data,
+ HH_DATA_MOD);
+ }
} else {
- int hh_alen = HH_DATA_ALIGN(hh_len);
+ hh_alen = HH_DATA_ALIGN(hh_len);
- memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+ if (likely(skb_headroom(skb) >= hh_alen)) {
+ memcpy(skb->data - hh_alen, hh->hh_data,
+ hh_alen);
+ }
}
} while (read_seqretry(&hh->hh_lock, seq));
- skb_push(skb, hh_len);
+ if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) {
+ kfree_skb(skb);
+ return NET_XMIT_DROP;
+ }
+
+ __skb_push(skb, hh_len);
return dev_queue_xmit(skb);
}
diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index b669fe6dbc3b..98f31c7ea23d 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -63,10 +63,11 @@ struct pnpipehdr {
u8 state_after_reset; /* reset request */
u8 error_code; /* any response */
u8 pep_type; /* status indication */
- u8 data[1];
+ u8 data0; /* anything else */
};
+ u8 data[];
};
-#define other_pep_type data[1]
+#define other_pep_type data[0]
static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb)
{
diff --git a/include/net/sock.h b/include/net/sock.h
index 577075713ad5..7420299c31f5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -299,6 +299,7 @@ struct cg_proto;
* @sk_filter: socket filtering instructions
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
+ * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
* @sk_tsflags: SO_TIMESTAMPING socket options
* @sk_tskey: counter to disambiguate concurrent tstamp requests
* @sk_socket: Identd and reporting IO signals
@@ -434,6 +435,9 @@ struct sock {
long sk_sndtimeo;
struct timer_list sk_timer;
ktime_t sk_stamp;
+#if BITS_PER_LONG==32
+ seqlock_t sk_stamp_seq;
+#endif
u16 sk_tsflags;
u32 sk_tskey;
struct socket *sk_socket;
@@ -2146,6 +2150,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
atomic_add(segs, &sk->sk_drops);
}
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+ unsigned int seq;
+ ktime_t kt;
+
+ do {
+ seq = read_seqbegin(&sk->sk_stamp_seq);
+ kt = sk->sk_stamp;
+ } while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+ return kt;
+#else
+ return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+ write_seqlock(&sk->sk_stamp_seq);
+ sk->sk_stamp = kt;
+ write_sequnlock(&sk->sk_stamp_seq);
+#else
+ sk->sk_stamp = kt;
+#endif
+}
+
void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb);
void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2170,7 +2202,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
(sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
__sock_recv_timestamp(msg, sk, skb);
else
- sk->sk_stamp = kt;
+ sock_write_timestamp(sk, kt);
if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
__sock_recv_wifi_status(msg, sk, skb);
@@ -2190,7 +2222,7 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
__sock_recv_ts_and_drops(msg, sk, skb);
else
- sk->sk_stamp = skb->tstamp;
+ sock_write_timestamp(sk, skb->tstamp);
}
void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a99f75ef6a73..14ec97309581 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1457,6 +1457,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
sk_wmem_free_skb(sk, skb);
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
+ inet_csk(sk)->icsk_backoff = 0;
}
static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
generated by cgit v1.2.3 (git 2.0.4) at 2024-12-25 18:32:19 +0000