Hello,
On Fri, Oct 15, 2021 at 7:27 AM Xiaoyun Li <xiaoyun...@intel.com> wrote:
>
> In csum forwarding mode, software UDP/TCP csum calculation only takes
> the first segment into account while using the whole packet length so
> the calculation will read invalid memory region with multi-segments
> packets and will get wrong value.
> This patch fixes this issue.
>
> Fixes: af75078fece3 ("first public release")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Xiaoyun Li <xiaoyun...@intel.com>
> ---
> app/test-pmd/csumonly.c | 31 +++++++++++++++++++++++--------
> 1 file changed, 23 insertions(+), 8 deletions(-)
>
> diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
> index 090797318a..5df3be0a6f 100644
> --- a/app/test-pmd/csumonly.c
> +++ b/app/test-pmd/csumonly.c
> @@ -18,7 +18,7 @@
> #include <rte_log.h>
> #include <rte_debug.h>
> #include <rte_cycles.h>
> -#include <rte_memory.h>
> +#include <rte_malloc.h>
This include caught my eye.
> #include <rte_memcpy.h>
> #include <rte_launch.h>
> #include <rte_eal.h>
> @@ -56,6 +56,11 @@
> #define GRE_SUPPORTED_FIELDS (GRE_CHECKSUM_PRESENT | GRE_KEY_PRESENT |\
> GRE_SEQUENCE_PRESENT)
>
> +/* When UDP or TCP or outer UDP csum offload is off, sw l4 csum is needed */
> +#define UDP_TCP_CSUM (DEV_TX_OFFLOAD_UDP_CKSUM |\
> + DEV_TX_OFFLOAD_TCP_CKSUM |\
> + DEV_TX_OFFLOAD_OUTER_UDP_CKSUM)
> +
> /* We cannot use rte_cpu_to_be_16() on a constant in a switch/case */
> #if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
> #define _htons(x) ((uint16_t)((((x) & 0x00ffU) << 8) | (((x) & 0xff00U) >>
> 8)))
> @@ -602,12 +607,8 @@ process_outer_cksums(void *outer_l3_hdr, struct
> testpmd_offload_info *info,
> /* do not recalculate udp cksum if it was 0 */
> if (udp_hdr->dgram_cksum != 0) {
> udp_hdr->dgram_cksum = 0;
> - if (info->outer_ethertype == _htons(RTE_ETHER_TYPE_IPV4))
> - udp_hdr->dgram_cksum =
> - rte_ipv4_udptcp_cksum(ipv4_hdr, udp_hdr);
> - else
> - udp_hdr->dgram_cksum =
> - rte_ipv6_udptcp_cksum(ipv6_hdr, udp_hdr);
> + udp_hdr->dgram_cksum = get_udptcp_checksum(outer_l3_hdr,
> + udp_hdr, info->outer_ethertype);
> }
>
> return ol_flags;
> @@ -802,6 +803,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> struct rte_mbuf *m, *p;
> struct rte_ether_hdr *eth_hdr;
> void *l3_hdr = NULL, *outer_l3_hdr = NULL; /* can be IPv4 or IPv6 */
> + uint8_t *l3_buf = NULL;
> void **gro_ctx;
> uint16_t gro_pkts_num;
> uint8_t gro_enable;
> @@ -877,7 +879,19 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> rte_ether_addr_copy(&ports[fs->tx_port].eth_addr,
> ð_hdr->src_addr);
> parse_ethernet(eth_hdr, &info);
> - l3_hdr = (char *)eth_hdr + info.l2_len;
> + /* When sw csum is needed, multi-segs needs a buf to contain
> + * the whole packet for later UDP/TCP csum calculation.
> + */
> + if (m->nb_segs > 1 && !(tx_ol_flags & PKT_TX_TCP_SEG) &&
> + !(tx_offloads & UDP_TCP_CSUM)) {
> + l3_buf = rte_zmalloc("csum l3_buf",
> + info.pkt_len - info.l2_len,
> + RTE_CACHE_LINE_SIZE);
Rather than call a dyn allocation in datapath, can't we have a static
buffer on the stack?
> + rte_pktmbuf_read(m, info.l2_len,
> + info.pkt_len - info.l2_len, l3_buf);
> + l3_hdr = l3_buf;
> + } else
> + l3_hdr = (char *)eth_hdr + info.l2_len;
>
> /* check if it's a supported tunnel */
> if (txp->parse_tunnel) {
> @@ -1051,6 +1065,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
> printf("tx: flags=%s", buf);
> printf("\n");
> }
> + rte_free(l3_buf);
> }
>
> if (unlikely(gro_enable)) {
> --
> 2.25.1
>
--
David Marchand
