From: Scott Mitchell <[email protected]> Add software checksum offload support and configurable TX poll behavior to improve flexibility and performance.
Add rte_net_ip_udptcp_cksum_mbuf in rte_net.h which is shared between rte_eth_tap and rte_eth_af_packet that supports IPv4/UDP/TCP checksums in software due to hardware offload and context propagation not being supported. Signed-off-by: Scott Mitchell <[email protected]> --- drivers/net/af_packet/rte_eth_af_packet.c | 15 +++- drivers/net/tap/rte_eth_tap.c | 61 +-------------- lib/net/rte_net.h | 90 +++++++++++++++++++++++ 3 files changed, 106 insertions(+), 60 deletions(-) diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c index be8e3260aa..19bafc99a6 100644 --- a/drivers/net/af_packet/rte_eth_af_packet.c +++ b/drivers/net/af_packet/rte_eth_af_packet.c @@ -10,6 +10,8 @@ #include <rte_string_fns.h> #include <rte_mbuf.h> #include <rte_atomic.h> +#include <rte_ip.h> +#include <rte_net.h> #include <rte_bitops.h> #include <ethdev_driver.h> #include <ethdev_vdev.h> @@ -102,6 +104,7 @@ struct pmd_internals { struct pkt_tx_queue *tx_queue; uint8_t vlan_strip; uint8_t timestamp_offloading; + bool tx_sw_cksum; }; static const char *valid_arguments[] = { @@ -329,6 +332,9 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) ppd->tp_len = mbuf->pkt_len; ppd->tp_snaplen = mbuf->pkt_len; + if (pkt_q->sw_cksum && !rte_net_ip_udptcp_cksum_mbuf(mbuf, false)) + continue; + struct rte_mbuf *tmp_mbuf = mbuf; do { uint16_t data_len = rte_pktmbuf_data_len(tmp_mbuf); @@ -413,10 +419,13 @@ eth_dev_configure(struct rte_eth_dev *dev __rte_unused) { struct rte_eth_conf *dev_conf = &dev->data->dev_conf; const struct rte_eth_rxmode *rxmode = &dev_conf->rxmode; + const struct rte_eth_txmode *txmode = &dev_conf->txmode; struct pmd_internals *internals = dev->data->dev_private; internals->vlan_strip = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP); internals->timestamp_offloading = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP); + internals->tx_sw_cksum = !!(txmode->offloads & (RTE_ETH_TX_OFFLOAD_IPV4_CKSUM | + RTE_ETH_TX_OFFLOAD_UDP_CKSUM | RTE_ETH_TX_OFFLOAD_TCP_CKSUM)); return 0; } @@ -434,7 +443,10 @@ eth_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) dev_info->max_tx_queues = (uint16_t)internals->nb_queues; dev_info->min_rx_bufsize = ETH_AF_PACKET_ETH_OVERHEAD; dev_info->tx_offload_capa = RTE_ETH_TX_OFFLOAD_MULTI_SEGS | - RTE_ETH_TX_OFFLOAD_VLAN_INSERT; + RTE_ETH_TX_OFFLOAD_VLAN_INSERT | + RTE_ETH_TX_OFFLOAD_IPV4_CKSUM | + RTE_ETH_TX_OFFLOAD_UDP_CKSUM | + RTE_ETH_TX_OFFLOAD_TCP_CKSUM; dev_info->rx_offload_capa = RTE_ETH_RX_OFFLOAD_VLAN_STRIP | RTE_ETH_RX_OFFLOAD_TIMESTAMP; @@ -635,6 +647,7 @@ eth_tx_queue_setup(struct rte_eth_dev *dev, { struct pmd_internals *internals = dev->data->dev_private; + internals->tx_queue[tx_queue_id].sw_cksum = internals->tx_sw_cksum; dev->data->tx_queues[tx_queue_id] = &internals->tx_queue[tx_queue_id]; return 0; diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c index 730f1859bd..55f496babe 100644 --- a/drivers/net/tap/rte_eth_tap.c +++ b/drivers/net/tap/rte_eth_tap.c @@ -560,70 +560,13 @@ tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs, if (txq->csum && (mbuf->ol_flags & RTE_MBUF_F_TX_IP_CKSUM || l4_ol_flags == RTE_MBUF_F_TX_UDP_CKSUM || l4_ol_flags == RTE_MBUF_F_TX_TCP_CKSUM)) { - unsigned int hdrlens = mbuf->l2_len + mbuf->l3_len; - uint16_t *l4_cksum; - void *l3_hdr; - - if (l4_ol_flags == RTE_MBUF_F_TX_UDP_CKSUM) - hdrlens += sizeof(struct rte_udp_hdr); - else if (l4_ol_flags == RTE_MBUF_F_TX_TCP_CKSUM) - hdrlens += sizeof(struct rte_tcp_hdr); - else if (l4_ol_flags != RTE_MBUF_F_TX_L4_NO_CKSUM) - return -1; - - /* Support only packets with at least layer 4 - * header included in the first segment - */ - if (rte_pktmbuf_data_len(mbuf) < hdrlens) - return -1; - - /* To change checksums (considering that a mbuf can be - * indirect, for example), copy l2, l3 and l4 headers - * in a new segment and chain it to existing data - */ - seg = rte_pktmbuf_copy(mbuf, mbuf->pool, 0, hdrlens); + /* Compute checksums in software, copying headers if needed */ + seg = rte_net_ip_udptcp_cksum_mbuf(mbuf, true); if (seg == NULL) return -1; - rte_pktmbuf_adj(mbuf, hdrlens); - rte_pktmbuf_chain(seg, mbuf); pmbufs[i] = mbuf = seg; - - l3_hdr = rte_pktmbuf_mtod_offset(mbuf, void *, mbuf->l2_len); - if (mbuf->ol_flags & RTE_MBUF_F_TX_IP_CKSUM) { - struct rte_ipv4_hdr *iph = l3_hdr; - - iph->hdr_checksum = 0; - iph->hdr_checksum = rte_ipv4_cksum(iph); - } - - if (l4_ol_flags == RTE_MBUF_F_TX_L4_NO_CKSUM) - goto skip_l4_cksum; - - if (l4_ol_flags == RTE_MBUF_F_TX_UDP_CKSUM) { - struct rte_udp_hdr *udp_hdr; - - udp_hdr = rte_pktmbuf_mtod_offset(mbuf, struct rte_udp_hdr *, - mbuf->l2_len + mbuf->l3_len); - l4_cksum = &udp_hdr->dgram_cksum; - } else { - struct rte_tcp_hdr *tcp_hdr; - - tcp_hdr = rte_pktmbuf_mtod_offset(mbuf, struct rte_tcp_hdr *, - mbuf->l2_len + mbuf->l3_len); - l4_cksum = &tcp_hdr->cksum; - } - - *l4_cksum = 0; - if (mbuf->ol_flags & RTE_MBUF_F_TX_IPV4) { - *l4_cksum = rte_ipv4_udptcp_cksum_mbuf(mbuf, l3_hdr, - mbuf->l2_len + mbuf->l3_len); - } else { - *l4_cksum = rte_ipv6_udptcp_cksum_mbuf(mbuf, l3_hdr, - mbuf->l2_len + mbuf->l3_len); - } } -skip_l4_cksum: for (j = 0; j < mbuf->nb_segs; j++) { iovecs[k].iov_len = rte_pktmbuf_data_len(seg); iovecs[k].iov_base = rte_pktmbuf_mtod(seg, void *); diff --git a/lib/net/rte_net.h b/lib/net/rte_net.h index 65d724b84b..c640ccbba2 100644 --- a/lib/net/rte_net.h +++ b/lib/net/rte_net.h @@ -246,6 +246,96 @@ rte_net_intel_cksum_prepare(struct rte_mbuf *m) return rte_net_intel_cksum_flags_prepare(m, m->ol_flags); } +/** + * Compute IPv4 header and UDP/TCP checksums in software. + * + * Computes checksums based on mbuf offload flags: + * - RTE_MBUF_F_TX_IP_CKSUM: Compute IPv4 header checksum + * - RTE_MBUF_F_TX_UDP_CKSUM: Compute UDP checksum (IPv4 or IPv6) + * - RTE_MBUF_F_TX_TCP_CKSUM: Compute TCP checksum (IPv4 or IPv6) + * + * @param mbuf + * The packet mbuf. Must have l2_len and l3_len set correctly. + * @param copy + * If true, copy L2/L3/L4 headers to a new segment before computing + * checksums. This is safe for indirect mbufs but has overhead. + * If false, compute checksums in place. This is only safe if the + * mbuf will be copied afterward (e.g., to a device ring buffer). + * @return + * - On success: Returns mbuf (new segment if copy=true, original if copy=false) + * - On error: Returns NULL (allocation failed or malformed packet) + */ +static inline struct rte_mbuf * +rte_net_ip_udptcp_cksum_mbuf(struct rte_mbuf *mbuf, bool copy) +{ + const uint64_t l4_ol_flags = mbuf->ol_flags & RTE_MBUF_F_TX_L4_MASK; + const uint64_t l4_offset = mbuf->l2_len + mbuf->l3_len; + uint32_t hdrlens = l4_offset; + + /* Determine total header length needed */ + if (l4_ol_flags == RTE_MBUF_F_TX_UDP_CKSUM) + hdrlens += sizeof(struct rte_udp_hdr); + else if (l4_ol_flags == RTE_MBUF_F_TX_TCP_CKSUM) + hdrlens += sizeof(struct rte_tcp_hdr); + else if (l4_ol_flags != RTE_MBUF_F_TX_L4_NO_CKSUM) + return NULL; /* Unsupported L4 checksum type */ + else if (!(mbuf->ol_flags & RTE_MBUF_F_TX_IP_CKSUM)) + return mbuf; /* Nothing to do */ + + /* Validate we at least have L2+L3 headers before doing any work */ + if (unlikely(rte_pktmbuf_data_len(mbuf) < l4_offset)) + return NULL; + + if (copy) { + /* + * Copy headers to new segment to handle indirect mbufs. + * This ensures we can safely modify checksums without + * corrupting shared/read-only data. + */ + struct rte_mbuf *seg = rte_pktmbuf_copy(mbuf, mbuf->pool, 0, hdrlens); + if (!seg) + return NULL; + + rte_pktmbuf_adj(mbuf, hdrlens); + rte_pktmbuf_chain(seg, mbuf); + mbuf = seg; + } else if (unlikely(!RTE_MBUF_DIRECT(mbuf) || rte_mbuf_refcnt_read(mbuf) > 1)) + return NULL; + + void *l3_hdr = rte_pktmbuf_mtod_offset(mbuf, void *, mbuf->l2_len); + + /* IPv4 header checksum */ + if (mbuf->ol_flags & RTE_MBUF_F_TX_IP_CKSUM) { + struct rte_ipv4_hdr *iph = (struct rte_ipv4_hdr *)l3_hdr; + iph->hdr_checksum = 0; + iph->hdr_checksum = rte_ipv4_cksum(iph); + } + + /* L4 checksum (UDP or TCP) - skip if headers not in first segment */ + if (l4_ol_flags == RTE_MBUF_F_TX_UDP_CKSUM && rte_pktmbuf_data_len(mbuf) >= hdrlens) { + struct rte_udp_hdr *udp_hdr = rte_pktmbuf_mtod_offset(mbuf, struct rte_udp_hdr *, + l4_offset); + udp_hdr->dgram_cksum = 0; + udp_hdr->dgram_cksum = (mbuf->ol_flags & RTE_MBUF_F_TX_IPV4) ? + rte_ipv4_udptcp_cksum_mbuf(mbuf, (const struct rte_ipv4_hdr *)l3_hdr, + l4_offset) : + rte_ipv6_udptcp_cksum_mbuf(mbuf, (const struct rte_ipv6_hdr *)l3_hdr, + l4_offset); + } else if (l4_ol_flags == RTE_MBUF_F_TX_TCP_CKSUM && + rte_pktmbuf_data_len(mbuf) >= hdrlens) { + struct rte_tcp_hdr *tcp_hdr = rte_pktmbuf_mtod_offset(mbuf, struct rte_tcp_hdr *, + l4_offset); + tcp_hdr->cksum = 0; + tcp_hdr->cksum = (mbuf->ol_flags & RTE_MBUF_F_TX_IPV4) ? + rte_ipv4_udptcp_cksum_mbuf(mbuf, (const struct rte_ipv4_hdr *)l3_hdr, + l4_offset) : + rte_ipv6_udptcp_cksum_mbuf(mbuf, (const struct rte_ipv6_hdr *)l3_hdr, + l4_offset); + } + + return mbuf; +} + #ifdef __cplusplus } #endif -- 2.39.5 (Apple Git-154)
