This commit implements TCP segmentation offload in TAP.
Dpdk rte_gso library is used to segment large TCP payloads (e.g. 64K bytes)
into smaller MTU size buffers.
By supporting TSO offload capability in software a TAP device can be used
as a failsafe sub device and be paired with another PCI device which
supports TSO capability in HW.
For more details on dpdk librte_gso implementation please refer to dpdk
documentation.
The number of newly generated TSO segments is limited to 64.
Signed-off-by: Ophir Munk <ophi...@mellanox.com>
---
drivers/net/tap/Makefile | 2 +-
drivers/net/tap/rte_eth_tap.c | 157 ++++++++++++++++++++++++++++++++----------
drivers/net/tap/rte_eth_tap.h | 4 ++
3 files changed, 126 insertions(+), 37 deletions(-)
diff --git a/drivers/net/tap/Makefile b/drivers/net/tap/Makefile
index ccc5c5f..3243365 100644
--- a/drivers/net/tap/Makefile
+++ b/drivers/net/tap/Makefile
@@ -24,7 +24,7 @@ CFLAGS += -I.
CFLAGS += $(WERROR_FLAGS)
LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs -lrte_hash
-LDLIBS += -lrte_bus_vdev
+LDLIBS += -lrte_bus_vdev -lrte_gso
CFLAGS += -DTAP_MAX_QUEUES=$(TAP_MAX_QUEUES)
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index f312084..4dda100 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -473,40 +473,37 @@ tap_tx_offload(char *packet, uint64_t ol_flags, unsigned
int l2_len,
}
}
-/* Callback to handle sending packets from the tap interface
- */
-static uint16_t
-pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+static void
+tap_mbuf_pool_create(struct rte_mempool **mp)
{
- struct tx_queue *txq = queue;
- uint16_t num_tx = 0;
- unsigned long num_tx_bytes = 0;
- uint32_t max_size;
- int i;
+ *mp = NULL; /* TODO - create mp */
+}
- if (unlikely(nb_pkts == 0))
- return 0;
+static inline void
+tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs,
+ struct rte_mbuf **pmbufs,
+ uint16_t *num_packets, unsigned long *num_tx_bytes)
+{
+ int i;
- max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4);
- for (i = 0; i < nb_pkts; i++) {
- struct rte_mbuf *mbuf = bufs[num_tx];
- struct iovec iovecs[mbuf->nb_segs + 1];
+ for (i = 0; i < num_mbufs; i++) {
+ struct rte_mbuf *mbuf = pmbufs[i];
+ struct iovec iovecs[mbuf->nb_segs + 2];
struct tun_pi pi = { .flags = 0 };
struct rte_mbuf *seg = mbuf;
char m_copy[mbuf->data_len];
int n;
int j;
- int k; /* first index in iovecs for copying segments */
+ int k; /* current index in iovecs for copying segments */
uint16_t l234_len; /* length of layers 2,3,4 headers */
uint16_t seg_len; /* length of first segment */
+ uint16_t nb_segs;
- /* stats.errs will be incremented */
- if (rte_pktmbuf_pkt_len(mbuf) > max_size)
- break;
-
- iovecs[0].iov_base = π
- iovecs[0].iov_len = sizeof(pi);
- k = 1;
+ k = 0;
+ iovecs[k].iov_base = π
+ iovecs[k].iov_len = sizeof(pi);
+ k++;
+ nb_segs = mbuf->nb_segs;
if (txq->csum &&
((mbuf->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_IPV4) ||
(mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM ||
@@ -523,39 +520,99 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs,
uint16_t nb_pkts)
/* To change checksums, work on a
* copy of l2, l3 l4 headers.
*/
- rte_memcpy(m_copy, rte_pktmbuf_mtod(mbuf, void *),
- l234_len);
+ rte_memcpy(m_copy,
+ rte_pktmbuf_mtod(mbuf, void *), l234_len);
tap_tx_offload(m_copy, mbuf->ol_flags,
mbuf->l2_len, mbuf->l3_len);
- iovecs[1].iov_base = m_copy;
- iovecs[1].iov_len = l234_len;
+ iovecs[k].iov_base = m_copy;
+ iovecs[k].iov_len = l234_len;
k++;
+
/* Adjust data pointer beyond l2, l3, l4 headers.
* If this segment becomes empty - skip it
*/
if (seg_len > l234_len) {
- rte_pktmbuf_adj(mbuf, l234_len);
- } else {
- seg = seg->next;
- mbuf->nb_segs--;
+ iovecs[k].iov_len = seg_len - l234_len;
+ iovecs[k].iov_base =
+ rte_pktmbuf_mtod(seg, char *) +
+ l234_len;
+ k++;
+ } else { /* seg_len == l234_len */
+ nb_segs--;
}
+
+ seg = seg->next;
}
- for (j = k; j <= mbuf->nb_segs; j++) {
+ for (j = k; j <= nb_segs; j++) {
iovecs[j].iov_len = rte_pktmbuf_data_len(seg);
iovecs[j].iov_base = rte_pktmbuf_mtod(seg, void *);
seg = seg->next;
}
/* copy the tx frame data */
- n = writev(txq->fd, iovecs, mbuf->nb_segs + 1);
+ n = writev(txq->fd, iovecs, j);
if (n <= 0)
break;
+ (*num_packets)++;
+ (*num_tx_bytes) += rte_pktmbuf_pkt_len(mbuf);
+ }
+}
+/* Callback to handle sending packets from the tap interface
+ */
+static uint16_t
+pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+ struct tx_queue *txq = queue;
+ uint16_t num_tx = 0;
+ uint16_t num_packets = 0;
+ unsigned long num_tx_bytes = 0;
+ uint32_t max_size;
+ int i;
+ uint64_t tso;
+ int ret;
+
+ if (unlikely(nb_pkts == 0))
+ return 0;
+
+ struct rte_mbuf *gso_mbufs[MAX_GSO_MBUFS];
+ max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4);
+ for (i = 0; i < nb_pkts; i++) {
+ struct rte_mbuf *mbuf_in = bufs[num_tx];
+ struct rte_mbuf **mbuf;
+ uint16_t num_mbufs;
+
+ tso = mbuf_in->ol_flags & PKT_TX_TCP_SEG;
+ if (tso) {
+ struct rte_gso_ctx *gso_ctx = &txq->gso_ctx;
+ /* gso size is calculated without ETHER_CRC_LEN */
+ gso_ctx->gso_size = *txq->mtu + ETHER_HDR_LEN;
+ ret = rte_gso_segment(mbuf_in, /* packet to segment */
+ gso_ctx, /* gso control block */
+ (struct rte_mbuf **)&gso_mbufs, /* out mbufs */
+ RTE_DIM(gso_mbufs)); /* max tso mbufs */
+
+ /* ret contains the number of new created mbufs */
+ if (ret < 0)
+ break;
+
+ mbuf = gso_mbufs;
+ num_mbufs = ret;
+ } else {
+ /* stats.errs will be incremented */
+ if (rte_pktmbuf_pkt_len(mbuf_in) > max_size)
+ break;
+
+ mbuf = &mbuf_in;
+ num_mbufs = 1;
+ }
+
+ tap_write_mbufs(txq, num_mbufs, mbuf,
+ &num_packets, &num_tx_bytes);
num_tx++;
- num_tx_bytes += mbuf->pkt_len;
- rte_pktmbuf_free(mbuf);
+ rte_pktmbuf_free(mbuf_in);
}
- txq->stats.opackets += num_tx;
+ txq->stats.opackets += num_packets;
txq->stats.errs += nb_pkts - num_tx;
txq->stats.obytes += num_tx_bytes;
@@ -996,11 +1053,35 @@ tap_mac_set(struct rte_eth_dev *dev, struct ether_addr
*mac_addr)
}
static int
+tap_init_gso_ctx(struct tx_queue *tx)
+{
+ uint32_t gso_types;
+
+ /* Create private mbuf pool with 128 bytes size
+ * use this pool for both direct and indirect mbufs
+ */
+ struct rte_mempool *mp; /* Mempool for TX/GSO packets */
+ tap_mbuf_pool_create(&mp); /* tx->mp or maybe embedded in gso_ctx */
+
+ /* initialize GSO context */
+ gso_types = DEV_TX_OFFLOAD_TCP_TSO | DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
+ DEV_TX_OFFLOAD_GRE_TNL_TSO;
+ tx->gso_ctx.direct_pool = mp;
+ tx->gso_ctx.indirect_pool = mp;
+ tx->gso_ctx.gso_types = gso_types;
+ tx->gso_ctx.gso_size = ETHER_MAX_LEN - ETHER_CRC_LEN;
+ tx->gso_ctx.flag = 0;
+
+ return 0;
+}
+
+static int
tap_setup_queue(struct rte_eth_dev *dev,
struct pmd_internals *internals,
uint16_t qid,
int is_rx)
{
+ int ret;
int *fd;
int *other_fd;
const char *dir;
@@ -1048,6 +1129,10 @@ tap_setup_queue(struct rte_eth_dev *dev,
tx->mtu = &dev->data->mtu;
rx->rxmode = &dev->data->dev_conf.rxmode;
+ ret = tap_init_gso_ctx(tx);
+ if (ret)
+ return -1;
+
return *fd;
}
diff --git a/drivers/net/tap/rte_eth_tap.h b/drivers/net/tap/rte_eth_tap.h
index 53a506a..65da5f8 100644
--- a/drivers/net/tap/rte_eth_tap.h
+++ b/drivers/net/tap/rte_eth_tap.h
@@ -15,6 +15,7 @@
#include <rte_ethdev_driver.h>
#include <rte_ether.h>
+#include <rte_gso.h>
#ifdef IFF_MULTI_QUEUE
#define RTE_PMD_TAP_MAX_QUEUES TAP_MAX_QUEUES
@@ -22,6 +23,8 @@
#define RTE_PMD_TAP_MAX_QUEUES 1
#endif
+#define MAX_GSO_MBUFS 64
+
struct pkt_stats {
uint64_t opackets; /* Number of output packets */
uint64_t ipackets; /* Number of input packets */
@@ -50,6 +53,7 @@ struct tx_queue {
uint16_t *mtu; /* Pointer to MTU from dev_data */
uint16_t csum:1; /* Enable checksum offloading */
struct pkt_stats stats; /* Stats for this TX queue */
+ struct rte_gso_ctx gso_ctx; /* GSO context */
};
struct pmd_internals {
--
2.7.4
