linux/net/packet/internal.h
Willem de Bruijn 77f65ebdca packet: packet fanout rollover during socket overload
Changes:
  v3->v2: rebase (no other changes)
          passes selftest
  v2->v1: read f->num_members only once
          fix bug: test rollover mode + flag

Minimize packet drop in a fanout group. If one socket is full,
roll over packets to another from the group. Maintain flow
affinity during normal load using an rxhash fanout policy, while
dispersing unexpected traffic storms that hit a single cpu, such
as spoofed-source DoS flows. Rollover breaks affinity for flows
arriving at saturated sockets during those conditions.

The patch adds a fanout policy ROLLOVER that rotates between sockets,
filling each socket before moving to the next. It also adds a fanout
flag ROLLOVER. If passed along with any other fanout policy, the
primary policy is applied until the chosen socket is full. Then,
rollover selects another socket, to delay packet drop until the
entire system is saturated.

Probing sockets is not free. Selecting the last used socket, as
rollover does, is a greedy approach that maximizes chance of
success, at the cost of extreme load imbalance. In practice, with
sufficiently long queues to absorb bursts, sockets are drained in
parallel and load balance looks uniform in `top`.

To avoid contention, scales counters with number of sockets and
accesses them lockfree. Values are bounds checked to ensure
correctness.

Tested using an application with 9 threads pinned to CPUs, one socket
per thread and sufficient busywork per packet operation to limits each
thread to handling 32 Kpps. When sent 500 Kpps single UDP stream
packets, a FANOUT_CPU setup processes 32 Kpps in total without this
patch, 270 Kpps with the patch. Tested with read() and with a packet
ring (V1).

Also, passes psock_fanout.c unit test added to selftests.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-19 17:15:04 -04:00

124 lines
2.7 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 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;
struct tpacket_kbdq_core prb_bdqc;
atomic_t pending;
};
extern struct mutex fanout_mutex;
#define PACKET_FANOUT_MAX 256
struct packet_fanout {
#ifdef CONFIG_NET_NS
struct net *net;
#endif
unsigned int num_members;
u16 id;
u8 type;
u8 flags;
atomic_t rr_cur;
struct list_head list;
struct sock *arr[PACKET_FANOUT_MAX];
int next[PACKET_FANOUT_MAX];
spinlock_t lock;
atomic_t sk_ref;
struct packet_type prot_hook ____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;
struct tpacket_stats stats;
union tpacket_stats_u stats_u;
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 ifindex; /* bound device */
__be16 num;
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 packet_type prot_hook ____cacheline_aligned_in_smp;
};
static struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
#endif