kernel_optimize_test/net/packet/internal.h
Willem de Bruijn 3b3a5b0aab packet: rollover huge flows before small flows
Migrate flows from a socket to another socket in the fanout group not
only when the socket is full. Start migrating huge flows early, to
divert possible 4-tuple attacks without affecting normal traffic.

Introduce fanout_flow_is_huge(). This detects huge flows, which are
defined as taking up more than half the load. It does so cheaply, by
storing the rxhashes of the N most recent packets. If over half of
these are the same rxhash as the current packet, then drop it. This
only protects against 4-tuple attacks. N is chosen to fit all data in
a single cache line.

Tested:
  Ran bench_rollover for 10 sec with 1.5 Mpps of single flow input.

    lpbb5:/export/hda3/willemb# ./bench_rollover -l 1000 -r -s
    cpu         rx       rx.k     drop.k   rollover     r.huge   r.failed
      0         14         14          0          0          0          0
      1         20         20          0          0          0          0
      2         16         16          0          0          0          0
      3    6168824    6168824          0    4867721    4867721          0
      4    4867741    4867741          0          0          0          0
      5         12         12          0          0          0          0
      6         15         15          0          0          0          0
      7         17         17          0          0          0          0

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-13 15:43:00 -04:00

133 lines
3.0 KiB
C

#ifndef __PACKET_INTERNAL_H__
#define __PACKET_INTERNAL_H__
struct packet_mclist {
struct packet_mclist *next;
int ifindex;
int count;
unsigned short type;
unsigned short alen;
unsigned char addr[MAX_ADDR_LEN];
};
/* kbdq - kernel block descriptor queue */
struct tpacket_kbdq_core {
struct pgv *pkbdq;
unsigned int feature_req_word;
unsigned int hdrlen;
unsigned char reset_pending_on_curr_blk;
unsigned char delete_blk_timer;
unsigned short kactive_blk_num;
unsigned short blk_sizeof_priv;
/* last_kactive_blk_num:
* trick to see if user-space has caught up
* in order to avoid refreshing timer when every single pkt arrives.
*/
unsigned short last_kactive_blk_num;
char *pkblk_start;
char *pkblk_end;
int kblk_size;
unsigned int max_frame_len;
unsigned int knum_blocks;
uint64_t knxt_seq_num;
char *prev;
char *nxt_offset;
struct sk_buff *skb;
atomic_t blk_fill_in_prog;
/* Default is set to 8ms */
#define DEFAULT_PRB_RETIRE_TOV (8)
unsigned short retire_blk_tov;
unsigned short version;
unsigned long tov_in_jiffies;
/* timer to retire an outstanding block */
struct timer_list retire_blk_timer;
};
struct pgv {
char *buffer;
};
struct packet_ring_buffer {
struct pgv *pg_vec;
unsigned int head;
unsigned int frames_per_block;
unsigned int frame_size;
unsigned int frame_max;
unsigned int pg_vec_order;
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
unsigned int __percpu *pending_refcnt;
struct tpacket_kbdq_core prb_bdqc;
};
extern struct mutex fanout_mutex;
#define PACKET_FANOUT_MAX 256
struct packet_fanout {
possible_net_t net;
unsigned int num_members;
u16 id;
u8 type;
u8 flags;
atomic_t rr_cur;
struct list_head list;
struct sock *arr[PACKET_FANOUT_MAX];
spinlock_t lock;
atomic_t sk_ref;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
struct packet_rollover {
int sock;
#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32))
u32 history[ROLLOVER_HLEN] ____cacheline_aligned;
} ____cacheline_aligned_in_smp;
struct packet_sock {
/* struct sock has to be the first member of packet_sock */
struct sock sk;
struct packet_fanout *fanout;
union tpacket_stats_u stats;
struct packet_ring_buffer rx_ring;
struct packet_ring_buffer tx_ring;
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
unsigned int running:1, /* prot_hook is attached*/
auxdata:1,
origdev:1,
has_vnet_hdr:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
struct packet_rollover *rollover;
struct packet_mclist *mclist;
atomic_t mapped;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
unsigned int tp_loss:1;
unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
static struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
#endif