mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-25 10:19:47 +00:00
![Peter Oskolkov](/assets/img/avatar_default.png)
This patch introduces several helper functions/macros that will be used in the follow-up patch. No runtime changes yet. The new logic (fully implemented in the second patch) is as follows: * Nodes in the rb-tree will now contain not single fragments, but lists of consecutive fragments ("runs"). * At each point in time, the current "active" run at the tail is maintained/tracked. Fragments that arrive in-order, adjacent to the previous tail fragment, are added to this tail run without triggering the re-balancing of the rb-tree. * If a fragment arrives out of order with the offset _before_ the tail run, it is inserted into the rb-tree as a single fragment. * If a fragment arrives after the current tail fragment (with a gap), it starts a new "tail" run, as is inserted into the rb-tree at the end as the head of the new run. skb->cb is used to store additional information needed here (suggested by Eric Dumazet). Reported-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Peter Oskolkov <posk@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
156 lines
4 KiB
C
156 lines
4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __NET_FRAG_H__
|
|
#define __NET_FRAG_H__
|
|
|
|
#include <linux/rhashtable-types.h>
|
|
|
|
struct netns_frags {
|
|
/* sysctls */
|
|
long high_thresh;
|
|
long low_thresh;
|
|
int timeout;
|
|
int max_dist;
|
|
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;
|
|
};
|
|
|
|
/**
|
|
* fragment queue flags
|
|
*
|
|
* @INET_FRAG_FIRST_IN: first fragment has arrived
|
|
* @INET_FRAG_LAST_IN: final fragment has arrived
|
|
* @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
|
|
*/
|
|
enum {
|
|
INET_FRAG_FIRST_IN = BIT(0),
|
|
INET_FRAG_LAST_IN = BIT(1),
|
|
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
|
|
*
|
|
* @node: rhash node
|
|
* @key: keys identifying this frag.
|
|
* @timer: queue expiration timer
|
|
* @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
|
|
* @rcu: rcu head for freeing deferall
|
|
*/
|
|
struct inet_frag_queue {
|
|
struct rhash_head node;
|
|
union {
|
|
struct frag_v4_compare_key v4;
|
|
struct frag_v6_compare_key v6;
|
|
} key;
|
|
struct timer_list timer;
|
|
spinlock_t lock;
|
|
refcount_t refcnt;
|
|
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 rcu_head rcu;
|
|
};
|
|
|
|
struct inet_frags {
|
|
unsigned int qsize;
|
|
|
|
void (*constructor)(struct inet_frag_queue *q,
|
|
const void *arg);
|
|
void (*destructor)(struct inet_frag_queue *);
|
|
void (*frag_expire)(struct timer_list *t);
|
|
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 int inet_frags_init_net(struct netns_frags *nf)
|
|
{
|
|
atomic_long_set(&nf->mem, 0);
|
|
return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
|
|
}
|
|
void inet_frags_exit_net(struct netns_frags *nf);
|
|
|
|
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);
|
|
|
|
/* 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)
|
|
{
|
|
if (refcount_dec_and_test(&q->refcnt))
|
|
inet_frag_destroy(q);
|
|
}
|
|
|
|
/* Memory Tracking Functions. */
|
|
|
|
static inline long frag_mem_limit(const struct netns_frags *nf)
|
|
{
|
|
return atomic_long_read(&nf->mem);
|
|
}
|
|
|
|
static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
|
|
{
|
|
atomic_long_sub(val, &nf->mem);
|
|
}
|
|
|
|
static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
|
|
{
|
|
atomic_long_add(val, &nf->mem);
|
|
}
|
|
|
|
/* RFC 3168 support :
|
|
* We want to check ECN values of all fragments, do detect invalid combinations.
|
|
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
|
|
*/
|
|
#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */
|
|
#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */
|
|
#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */
|
|
#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */
|
|
|
|
extern const u8 ip_frag_ecn_table[16];
|
|
|
|
#endif
|