In the AF_PACKET fanout mode, packet reception can be load balanced among
processes. This also works in combination with mmap(2) on packet sockets.
+Currently implemented fanout policies are:
+
+ - PACKET_FANOUT_HASH: schedule to socket by skb's rxhash
+ - PACKET_FANOUT_LB: schedule to socket by round-robin
+ - PACKET_FANOUT_CPU: schedule to socket by CPU packet arrives on
+ - PACKET_FANOUT_RND: schedule to socket by random selection
+ - PACKET_FANOUT_ROLLOVER: if one socket is full, rollover to another
+
Minimal example code by David S. Miller (try things like "./test eth0 hash",
"./test eth0 lb", etc.):
Minimal example code by Daniel Borkmann based on Chetan Loke's lolpcap (compile
it with gcc -Wall -O2 blob.c, and try things like "./a.out eth0", etc.):
+/* Written from scratch, but kernel-to-user space API usage
+ * dissected from lolpcap:
+ * Copyright 2011, Chetan Loke <loke.chetan@gmail.com>
+ * License: GPL, version 2.0
+ */
+
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
-#define BLOCK_SIZE (1 << 22)
-#define FRAME_SIZE 2048
-
-#define NUM_BLOCKS 64
-#define NUM_FRAMES ((BLOCK_SIZE * NUM_BLOCKS) / FRAME_SIZE)
-
-#define BLOCK_RETIRE_TOV_IN_MS 64
-#define BLOCK_PRIV_AREA_SZ 13
-
-#define ALIGN_8(x) (((x) + 8 - 1) & ~(8 - 1))
-
-#define BLOCK_STATUS(x) ((x)->h1.block_status)
-#define BLOCK_NUM_PKTS(x) ((x)->h1.num_pkts)
-#define BLOCK_O2FP(x) ((x)->h1.offset_to_first_pkt)
-#define BLOCK_LEN(x) ((x)->h1.blk_len)
-#define BLOCK_SNUM(x) ((x)->h1.seq_num)
-#define BLOCK_O2PRIV(x) ((x)->offset_to_priv)
-#define BLOCK_PRIV(x) ((void *) ((uint8_t *) (x) + BLOCK_O2PRIV(x)))
-#define BLOCK_HDR_LEN (ALIGN_8(sizeof(struct block_desc)))
-#define BLOCK_PLUS_PRIV(sz_pri) (BLOCK_HDR_LEN + ALIGN_8((sz_pri)))
-
#ifndef likely
# define likely(x) __builtin_expect(!!(x), 1)
#endif
static unsigned long packets_total = 0, bytes_total = 0;
static sig_atomic_t sigint = 0;
-void sighandler(int num)
+static void sighandler(int num)
{
sigint = 1;
}
{
int err, i, fd, v = TPACKET_V3;
struct sockaddr_ll ll;
+ unsigned int blocksiz = 1 << 22, framesiz = 1 << 11;
+ unsigned int blocknum = 64;
fd = socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
if (fd < 0) {
}
memset(&ring->req, 0, sizeof(ring->req));
- ring->req.tp_block_size = BLOCK_SIZE;
- ring->req.tp_frame_size = FRAME_SIZE;
- ring->req.tp_block_nr = NUM_BLOCKS;
- ring->req.tp_frame_nr = NUM_FRAMES;
- ring->req.tp_retire_blk_tov = BLOCK_RETIRE_TOV_IN_MS;
- ring->req.tp_sizeof_priv = BLOCK_PRIV_AREA_SZ;
- ring->req.tp_feature_req_word |= TP_FT_REQ_FILL_RXHASH;
+ ring->req.tp_block_size = blocksiz;
+ ring->req.tp_frame_size = framesiz;
+ ring->req.tp_block_nr = blocknum;
+ ring->req.tp_frame_nr = (blocksiz * blocknum) / framesiz;
+ ring->req.tp_retire_blk_tov = 60;
+ ring->req.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
err = setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &ring->req,
sizeof(ring->req));
}
ring->map = mmap(NULL, ring->req.tp_block_size * ring->req.tp_block_nr,
- PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED,
- fd, 0);
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED, fd, 0);
if (ring->map == MAP_FAILED) {
perror("mmap");
exit(1);
return fd;
}
-#ifdef __checked
-static uint64_t prev_block_seq_num = 0;
-
-void assert_block_seq_num(struct block_desc *pbd)
-{
- if (unlikely(prev_block_seq_num + 1 != BLOCK_SNUM(pbd))) {
- printf("prev_block_seq_num:%"PRIu64", expected seq:%"PRIu64" != "
- "actual seq:%"PRIu64"\n", prev_block_seq_num,
- prev_block_seq_num + 1, (uint64_t) BLOCK_SNUM(pbd));
- exit(1);
- }
-
- prev_block_seq_num = BLOCK_SNUM(pbd);
-}
-
-static void assert_block_len(struct block_desc *pbd, uint32_t bytes, int block_num)
-{
- if (BLOCK_NUM_PKTS(pbd)) {
- if (unlikely(bytes != BLOCK_LEN(pbd))) {
- printf("block:%u with %upackets, expected len:%u != actual len:%u\n",
- block_num, BLOCK_NUM_PKTS(pbd), bytes, BLOCK_LEN(pbd));
- exit(1);
- }
- } else {
- if (unlikely(BLOCK_LEN(pbd) != BLOCK_PLUS_PRIV(BLOCK_PRIV_AREA_SZ))) {
- printf("block:%u, expected len:%lu != actual len:%u\n",
- block_num, BLOCK_HDR_LEN, BLOCK_LEN(pbd));
- exit(1);
- }
- }
-}
-
-static void assert_block_header(struct block_desc *pbd, const int block_num)
-{
- uint32_t block_status = BLOCK_STATUS(pbd);
-
- if (unlikely((block_status & TP_STATUS_USER) == 0)) {
- printf("block:%u, not in TP_STATUS_USER\n", block_num);
- exit(1);
- }
-
- assert_block_seq_num(pbd);
-}
-#else
-static inline void assert_block_header(struct block_desc *pbd, const int block_num)
-{
-}
-static void assert_block_len(struct block_desc *pbd, uint32_t bytes, int block_num)
-{
-}
-#endif
-
static void display(struct tpacket3_hdr *ppd)
{
struct ethhdr *eth = (struct ethhdr *) ((uint8_t *) ppd + ppd->tp_mac);
static void walk_block(struct block_desc *pbd, const int block_num)
{
- int num_pkts = BLOCK_NUM_PKTS(pbd), i;
+ int num_pkts = pbd->h1.num_pkts, i;
unsigned long bytes = 0;
- unsigned long bytes_with_padding = BLOCK_PLUS_PRIV(BLOCK_PRIV_AREA_SZ);
struct tpacket3_hdr *ppd;
- assert_block_header(pbd, block_num);
-
- ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd + BLOCK_O2FP(pbd));
+ ppd = (struct tpacket3_hdr *) ((uint8_t *) pbd +
+ pbd->h1.offset_to_first_pkt);
for (i = 0; i < num_pkts; ++i) {
bytes += ppd->tp_snaplen;
- if (ppd->tp_next_offset)
- bytes_with_padding += ppd->tp_next_offset;
- else
- bytes_with_padding += ALIGN_8(ppd->tp_snaplen + ppd->tp_mac);
-
display(ppd);
- ppd = (struct tpacket3_hdr *) ((uint8_t *) ppd + ppd->tp_next_offset);
- __sync_synchronize();
+ ppd = (struct tpacket3_hdr *) ((uint8_t *) ppd +
+ ppd->tp_next_offset);
}
- assert_block_len(pbd, bytes_with_padding, block_num);
-
packets_total += num_pkts;
bytes_total += bytes;
}
-void flush_block(struct block_desc *pbd)
+static void flush_block(struct block_desc *pbd)
{
- BLOCK_STATUS(pbd) = TP_STATUS_KERNEL;
- __sync_synchronize();
+ pbd->h1.block_status = TP_STATUS_KERNEL;
}
static void teardown_socket(struct ring *ring, int fd)
socklen_t len;
struct ring ring;
struct pollfd pfd;
- unsigned int block_num = 0;
+ unsigned int block_num = 0, blocks = 64;
struct block_desc *pbd;
struct tpacket_stats_v3 stats;
while (likely(!sigint)) {
pbd = (struct block_desc *) ring.rd[block_num].iov_base;
-retry_block:
- if ((BLOCK_STATUS(pbd) & TP_STATUS_USER) == 0) {
+
+ if ((pbd->h1.block_status & TP_STATUS_USER) == 0) {
poll(&pfd, 1, -1);
- goto retry_block;
+ continue;
}
walk_block(pbd, block_num);
flush_block(pbd);
- block_num = (block_num + 1) % NUM_BLOCKS;
+ block_num = (block_num + 1) % blocks;
}
len = sizeof(stats);