Florian Westphal e3a57d18b0 inet: frag: remove periodic secret rebuild timer
merge functionality into the eviction workqueue.

Instead of rebuilding every n seconds, take advantage of the upper
hash chain length limit.

If we hit it, mark table for rebuild and schedule workqueue.
To prevent frequent rebuilds when we're completely overloaded,
don't rebuild more than once every 5 seconds.

ipfrag_secret_interval sysctl is now obsolete and has been marked as
deprecated, it still can be changed so scripts won't be broken but it
won't have any effect. A comment is left above each unused secret_timer
variable to avoid confusion.

Joint work with Nikolay Aleksandrov.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-27 22:34:36 -07:00

155 lines
4.2 KiB
C

#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
#include <linux/percpu_counter.h>
struct netns_frags {
/* The percpu_counter "mem" need to be cacheline aligned.
* mem.count must not share cacheline with other writers
*/
struct percpu_counter mem ____cacheline_aligned_in_smp;
/* sysctls */
int timeout;
int high_thresh;
int low_thresh;
};
struct inet_frag_queue {
spinlock_t lock;
struct timer_list timer; /* when will this queue expire? */
struct hlist_node list;
atomic_t refcnt;
struct sk_buff *fragments; /* list of received fragments */
struct sk_buff *fragments_tail;
ktime_t stamp;
int len; /* total length of orig datagram */
int meat;
__u8 last_in; /* first/last segment arrived? */
#define INET_FRAG_EVICTED 8
#define INET_FRAG_COMPLETE 4
#define INET_FRAG_FIRST_IN 2
#define INET_FRAG_LAST_IN 1
u16 max_size;
struct netns_frags *net;
};
#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 inet_frags {
struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
/* This rwlock is a global lock (seperate per IPv4, IPv6 and
* netfilter). Important to keep this on a seperate cacheline.
* Its primarily a rebuild protection rwlock.
*/
rwlock_t lock ____cacheline_aligned_in_smp;
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.
*/
u32 rnd;
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 *);
void (*skb_free)(struct sk_buff *);
void (*frag_expire)(unsigned long data);
};
void inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
void inet_frags_init_net(struct netns_frags *nf);
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
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)
__releases(&f->lock);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
{
if (atomic_dec_and_test(&q->refcnt))
inet_frag_destroy(q, f);
}
/* Memory Tracking Functions. */
/* The default percpu_counter batch size is not big enough to scale to
* fragmentation mem acct sizes.
* The mem size of a 64K fragment is approx:
* (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
*/
static unsigned int frag_percpu_counter_batch = 130000;
static inline int frag_mem_limit(struct netns_frags *nf)
{
return percpu_counter_read(&nf->mem);
}
static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i)
{
__percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch);
}
static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
{
__percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch);
}
static inline void init_frag_mem_limit(struct netns_frags *nf)
{
percpu_counter_init(&nf->mem, 0);
}
static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
{
unsigned int res;
local_bh_disable();
res = percpu_counter_sum_positive(&nf->mem);
local_bh_enable();
return res;
}
/* 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