324242fb51
In some situations, we would get several ip fragments, which total
data length is less than min_ip_len(64) and padding with zeros.
We simulated intermediate fragments by modifying the MTU.
To illustrate the problem, we simplify the packet format and
ignore the impact of the packet header.In namespace2,
a packet whose data length is 1520 is sent.
When the packet passes tap2, the packet is divided into two
fragments: fragment A and B, similar to (1520 = 1510 + 10).
When the packet passes tap3, the larger fragment packet A is
divided into two fragments A1 and A2, similar to (1510 = 1500 + 10).
Finally, the bond interface receives three fragments:
A1, A2, and B (1520 = 1500 + 10 + 10).
One fragmented packet A2 is smaller than the minimum Ethernet
frame length, so it needs to be padded.
|---------------------------------------------------|
| HOST |
| |--------------| |----------------------------| |
| | ns2 | | |--------------| | |
| | |--------| | | |--------| |--------| | |
| | | tap1 | | | | tap2 | ns1| tap3 | | |
| | |mtu=1510| | | |mtu=1510| |mtu=1500| | |
| |--|1.1.1.1 |--| |--|1.1.1.2 |----|2.1.1.1 |--| |
| |--------| |--------| |--------| |
| | | | |
| |-----------------| | |
| | |
| |--------| |
| | bond | |
|--------------------------------------|mtu=1500|---|
|--------|
When processing the preceding packets above,
DPDK would aggregate fragmented packets A2 and B.
And error packets are generated, which padding(zero)
is displayed in the middle of the packet.
A2 + B:
0000 fa 16 3e 9f fb 82 fa 47 b2 57 dc 20 08 00 45 00
0010 00 33 b4 66 00 ba 3f 01 c1 a5 01 01 01 01 02 01
0020 01 02 c0 c1 c2 c3 c4 c5 c6 c7 00 00 00 00 00 00
0030 00 00 00 00 00 00 00 00 00 00 00 00 c8 c9 ca cb
0040 cc cd ce cf d0 d1 d2 d3 d4 d5 d6 d7 d8 d9 da db
0050 dc dd de df e0 e1 e2 e3 e4 e5 e6
So, we would calculate the length of padding, and remove
the padding in pkt_len and data_len before aggregation.
And also we have the fix for both ipv4 and ipv6.
Fixes: 7f0983ee33
("ip_frag: check fragment length of incoming packet")
Cc: stable@dpdk.org
Signed-off-by: Yicai Lu <luyicai@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
174 lines
4.8 KiB
C
174 lines
4.8 KiB
C
/* SPDX-License-Identifier: BSD-3-Clause
|
|
* Copyright(c) 2010-2014 Intel Corporation
|
|
*/
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <rte_debug.h>
|
|
|
|
#include "ip_frag_common.h"
|
|
|
|
/*
|
|
* Reassemble fragments into one packet.
|
|
*/
|
|
struct rte_mbuf *
|
|
ipv4_frag_reassemble(struct ip_frag_pkt *fp)
|
|
{
|
|
struct rte_ipv4_hdr *ip_hdr;
|
|
struct rte_mbuf *m, *prev;
|
|
uint32_t i, n, ofs, first_len;
|
|
uint32_t curr_idx = 0;
|
|
|
|
first_len = fp->frags[IP_FIRST_FRAG_IDX].len;
|
|
n = fp->last_idx - 1;
|
|
|
|
/*start from the last fragment. */
|
|
m = fp->frags[IP_LAST_FRAG_IDX].mb;
|
|
ofs = fp->frags[IP_LAST_FRAG_IDX].ofs;
|
|
curr_idx = IP_LAST_FRAG_IDX;
|
|
|
|
while (ofs != first_len) {
|
|
|
|
prev = m;
|
|
|
|
for (i = n; i != IP_FIRST_FRAG_IDX && ofs != first_len; i--) {
|
|
|
|
/* previous fragment found. */
|
|
if(fp->frags[i].ofs + fp->frags[i].len == ofs) {
|
|
|
|
RTE_ASSERT(curr_idx != i);
|
|
|
|
/* adjust start of the last fragment data. */
|
|
rte_pktmbuf_adj(m,
|
|
(uint16_t)(m->l2_len + m->l3_len));
|
|
rte_pktmbuf_chain(fp->frags[i].mb, m);
|
|
|
|
/* this mbuf should not be accessed directly */
|
|
fp->frags[curr_idx].mb = NULL;
|
|
curr_idx = i;
|
|
|
|
/* update our last fragment and offset. */
|
|
m = fp->frags[i].mb;
|
|
ofs = fp->frags[i].ofs;
|
|
}
|
|
}
|
|
|
|
/* error - hole in the packet. */
|
|
if (m == prev) {
|
|
return NULL;
|
|
}
|
|
}
|
|
|
|
/* chain with the first fragment. */
|
|
rte_pktmbuf_adj(m, (uint16_t)(m->l2_len + m->l3_len));
|
|
rte_pktmbuf_chain(fp->frags[IP_FIRST_FRAG_IDX].mb, m);
|
|
fp->frags[curr_idx].mb = NULL;
|
|
m = fp->frags[IP_FIRST_FRAG_IDX].mb;
|
|
fp->frags[IP_FIRST_FRAG_IDX].mb = NULL;
|
|
|
|
/* update ipv4 header for the reassembled packet */
|
|
ip_hdr = rte_pktmbuf_mtod_offset(m, struct rte_ipv4_hdr *, m->l2_len);
|
|
|
|
ip_hdr->total_length = rte_cpu_to_be_16((uint16_t)(fp->total_size +
|
|
m->l3_len));
|
|
ip_hdr->fragment_offset = (uint16_t)(ip_hdr->fragment_offset &
|
|
rte_cpu_to_be_16(RTE_IPV4_HDR_DF_FLAG));
|
|
ip_hdr->hdr_checksum = 0;
|
|
|
|
return m;
|
|
}
|
|
|
|
/*
|
|
* Process new mbuf with fragment of IPV4 packet.
|
|
* Incoming mbuf should have it's l2_len/l3_len fields setuped correclty.
|
|
* @param tbl
|
|
* Table where to lookup/add the fragmented packet.
|
|
* @param mb
|
|
* Incoming mbuf with IPV4 fragment.
|
|
* @param tms
|
|
* Fragment arrival timestamp.
|
|
* @param ip_hdr
|
|
* Pointer to the IPV4 header inside the fragment.
|
|
* @return
|
|
* Pointer to mbuf for reassembled packet, or NULL if:
|
|
* - an error occurred.
|
|
* - not all fragments of the packet are collected yet.
|
|
*/
|
|
struct rte_mbuf *
|
|
rte_ipv4_frag_reassemble_packet(struct rte_ip_frag_tbl *tbl,
|
|
struct rte_ip_frag_death_row *dr, struct rte_mbuf *mb, uint64_t tms,
|
|
struct rte_ipv4_hdr *ip_hdr)
|
|
{
|
|
struct ip_frag_pkt *fp;
|
|
struct ip_frag_key key;
|
|
const unaligned_uint64_t *psd;
|
|
uint16_t flag_offset, ip_ofs, ip_flag;
|
|
int32_t ip_len;
|
|
int32_t trim;
|
|
|
|
flag_offset = rte_be_to_cpu_16(ip_hdr->fragment_offset);
|
|
ip_ofs = (uint16_t)(flag_offset & RTE_IPV4_HDR_OFFSET_MASK);
|
|
ip_flag = (uint16_t)(flag_offset & RTE_IPV4_HDR_MF_FLAG);
|
|
|
|
psd = (unaligned_uint64_t *)&ip_hdr->src_addr;
|
|
/* use first 8 bytes only */
|
|
key.src_dst[0] = psd[0];
|
|
key.id = ip_hdr->packet_id;
|
|
key.key_len = IPV4_KEYLEN;
|
|
|
|
ip_ofs *= RTE_IPV4_HDR_OFFSET_UNITS;
|
|
ip_len = rte_be_to_cpu_16(ip_hdr->total_length) - mb->l3_len;
|
|
trim = mb->pkt_len - (ip_len + mb->l3_len + mb->l2_len);
|
|
|
|
IP_FRAG_LOG(DEBUG, "%s:%d:\n"
|
|
"mbuf: %p, tms: %" PRIu64 ", key: <%" PRIx64 ", %#x>"
|
|
"ofs: %u, len: %d, padding: %d, flags: %#x\n"
|
|
"tbl: %p, max_cycles: %" PRIu64 ", entry_mask: %#x, "
|
|
"max_entries: %u, use_entries: %u\n\n",
|
|
__func__, __LINE__,
|
|
mb, tms, key.src_dst[0], key.id, ip_ofs, ip_len, trim, ip_flag,
|
|
tbl, tbl->max_cycles, tbl->entry_mask, tbl->max_entries,
|
|
tbl->use_entries);
|
|
|
|
/* check that fragment length is greater then zero. */
|
|
if (ip_len <= 0) {
|
|
IP_FRAG_MBUF2DR(dr, mb);
|
|
return NULL;
|
|
}
|
|
|
|
if (unlikely(trim > 0))
|
|
rte_pktmbuf_trim(mb, trim);
|
|
|
|
/* try to find/add entry into the fragment's table. */
|
|
if ((fp = ip_frag_find(tbl, dr, &key, tms)) == NULL) {
|
|
IP_FRAG_MBUF2DR(dr, mb);
|
|
return NULL;
|
|
}
|
|
|
|
IP_FRAG_LOG(DEBUG, "%s:%d:\n"
|
|
"tbl: %p, max_entries: %u, use_entries: %u\n"
|
|
"ipv4_frag_pkt: %p, key: <%" PRIx64 ", %#x>, start: %" PRIu64
|
|
", total_size: %u, frag_size: %u, last_idx: %u\n\n",
|
|
__func__, __LINE__,
|
|
tbl, tbl->max_entries, tbl->use_entries,
|
|
fp, fp->key.src_dst[0], fp->key.id, fp->start,
|
|
fp->total_size, fp->frag_size, fp->last_idx);
|
|
|
|
|
|
/* process the fragmented packet. */
|
|
mb = ip_frag_process(fp, dr, mb, ip_ofs, ip_len, ip_flag);
|
|
ip_frag_inuse(tbl, fp);
|
|
|
|
IP_FRAG_LOG(DEBUG, "%s:%d:\n"
|
|
"mbuf: %p\n"
|
|
"tbl: %p, max_entries: %u, use_entries: %u\n"
|
|
"ipv4_frag_pkt: %p, key: <%" PRIx64 ", %#x>, start: %" PRIu64
|
|
", total_size: %u, frag_size: %u, last_idx: %u\n\n",
|
|
__func__, __LINE__, mb,
|
|
tbl, tbl->max_entries, tbl->use_entries,
|
|
fp, fp->key.src_dst[0], fp->key.id, fp->start,
|
|
fp->total_size, fp->frag_size, fp->last_idx);
|
|
|
|
return mb;
|
|
}
|