@@ -43,27 +43,27 @@
struct nfp_net_nfdk_tx_desc {
union {
struct {
- __le16 dma_addr_hi; /* High bits of host buf address */
- __le16 dma_len_type; /* Length to DMA for this desc */
- __le32 dma_addr_lo; /* Low 32bit of host buf addr */
+ uint16_t dma_addr_hi; /* High bits of host buf address */
+ uint16_t dma_len_type; /* Length to DMA for this desc */
+ uint32_t dma_addr_lo; /* Low 32bit of host buf addr */
};
struct {
- __le16 mss; /* MSS to be used for LSO */
- uint8_t lso_hdrlen; /* LSO, TCP payload offset */
- uint8_t lso_totsegs; /* LSO, total segments */
- uint8_t l3_offset; /* L3 header offset */
- uint8_t l4_offset; /* L4 header offset */
- __le16 lso_meta_res; /* Rsvd bits in TSO metadata */
+ uint16_t mss; /* MSS to be used for LSO */
+ uint8_t lso_hdrlen; /* LSO, TCP payload offset */
+ uint8_t lso_totsegs; /* LSO, total segments */
+ uint8_t l3_offset; /* L3 header offset */
+ uint8_t l4_offset; /* L4 header offset */
+ uint16_t lso_meta_res; /* Rsvd bits in TSO metadata */
};
struct {
- uint8_t flags; /* TX Flags, see @NFDK_DESC_TX_* */
- uint8_t reserved[7]; /* meta byte placeholder */
+ uint8_t flags; /* TX Flags, see @NFDK_DESC_TX_* */
+ uint8_t reserved[7]; /* meta byte placeholder */
};
- __le32 vals[2];
- __le64 raw;
+ uint32_t vals[2];
+ uint64_t raw;
};
};
@@ -89,7 +89,7 @@ nfp_net_nfdk_free_tx_desc(struct nfp_net_txq *txq)
*
* This function uses the host copy* of read/write pointers.
*/
-static inline uint32_t
+static inline bool
nfp_net_nfdk_txq_full(struct nfp_net_txq *txq)
{
return (nfp_net_nfdk_free_tx_desc(txq) < txq->tx_free_thresh);
@@ -97,7 +97,8 @@ nfp_net_nfdk_txq_full(struct nfp_net_txq *txq)
/* nfp_net_nfdk_tx_cksum() - Set TX CSUM offload flags in TX descriptor of nfdk */
static inline uint64_t
-nfp_net_nfdk_tx_cksum(struct nfp_net_txq *txq, struct rte_mbuf *mb,
+nfp_net_nfdk_tx_cksum(struct nfp_net_txq *txq,
+ struct rte_mbuf *mb,
uint64_t flags)
{
uint64_t ol_flags;
@@ -109,17 +110,17 @@ nfp_net_nfdk_tx_cksum(struct nfp_net_txq *txq, struct rte_mbuf *mb,
ol_flags = mb->ol_flags;
/* Set TCP csum offload if TSO enabled. */
- if (ol_flags & RTE_MBUF_F_TX_TCP_SEG)
+ if ((ol_flags & RTE_MBUF_F_TX_TCP_SEG) != 0)
flags |= NFDK_DESC_TX_L4_CSUM;
- if (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK)
+ if ((ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) != 0)
flags |= NFDK_DESC_TX_ENCAP;
/* IPv6 does not need checksum */
- if (ol_flags & RTE_MBUF_F_TX_IP_CKSUM)
+ if ((ol_flags & RTE_MBUF_F_TX_IP_CKSUM) != 0)
flags |= NFDK_DESC_TX_L3_CSUM;
- if (ol_flags & RTE_MBUF_F_TX_L4_MASK)
+ if ((ol_flags & RTE_MBUF_F_TX_L4_MASK) != 0)
flags |= NFDK_DESC_TX_L4_CSUM;
return flags;
@@ -127,19 +128,22 @@ nfp_net_nfdk_tx_cksum(struct nfp_net_txq *txq, struct rte_mbuf *mb,
/* nfp_net_nfdk_tx_tso() - Set TX descriptor for TSO of nfdk */
static inline uint64_t
-nfp_net_nfdk_tx_tso(struct nfp_net_txq *txq, struct rte_mbuf *mb)
+nfp_net_nfdk_tx_tso(struct nfp_net_txq *txq,
+ struct rte_mbuf *mb)
{
+ uint8_t outer_len;
uint64_t ol_flags;
struct nfp_net_nfdk_tx_desc txd;
struct nfp_net_hw *hw = txq->hw;
+ txd.raw = 0;
+
if ((hw->cap & NFP_NET_CFG_CTRL_LSO_ANY) == 0)
- goto clean_txd;
+ return txd.raw;
ol_flags = mb->ol_flags;
-
if ((ol_flags & RTE_MBUF_F_TX_TCP_SEG) == 0)
- goto clean_txd;
+ return txd.raw;
txd.l3_offset = mb->l2_len;
txd.l4_offset = mb->l2_len + mb->l3_len;
@@ -148,22 +152,13 @@ nfp_net_nfdk_tx_tso(struct nfp_net_txq *txq, struct rte_mbuf *mb)
txd.lso_hdrlen = mb->l2_len + mb->l3_len + mb->l4_len;
txd.lso_totsegs = (mb->pkt_len + mb->tso_segsz) / mb->tso_segsz;
- if (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
- txd.l3_offset += mb->outer_l2_len + mb->outer_l3_len;
- txd.l4_offset += mb->outer_l2_len + mb->outer_l3_len;
- txd.lso_hdrlen += mb->outer_l2_len + mb->outer_l3_len;
+ if ((ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) != 0) {
+ outer_len = mb->outer_l2_len + mb->outer_l3_len;
+ txd.l3_offset += outer_len;
+ txd.l4_offset += outer_len;
+ txd.lso_hdrlen += outer_len;
}
- return txd.raw;
-
-clean_txd:
- txd.l3_offset = 0;
- txd.l4_offset = 0;
- txd.lso_hdrlen = 0;
- txd.mss = 0;
- txd.lso_totsegs = 0;
- txd.lso_meta_res = 0;
-
return txd.raw;
}
@@ -24,14 +24,18 @@ nfp_net_nfdk_headlen_to_segs(unsigned int headlen)
}
static int
-nfp_net_nfdk_tx_maybe_close_block(struct nfp_net_txq *txq, struct rte_mbuf *pkt)
+nfp_net_nfdk_tx_maybe_close_block(struct nfp_net_txq *txq,
+ struct rte_mbuf *pkt)
{
- unsigned int n_descs, wr_p, i, nop_slots;
+ uint32_t i;
+ uint32_t wr_p;
+ uint16_t n_descs;
+ uint32_t nop_slots;
struct rte_mbuf *pkt_temp;
pkt_temp = pkt;
n_descs = nfp_net_nfdk_headlen_to_segs(pkt_temp->data_len);
- while (pkt_temp->next) {
+ while (pkt_temp->next != NULL) {
pkt_temp = pkt_temp->next;
n_descs += DIV_ROUND_UP(pkt_temp->data_len, NFDK_TX_MAX_DATA_PER_DESC);
}
@@ -39,14 +43,14 @@ nfp_net_nfdk_tx_maybe_close_block(struct nfp_net_txq *txq, struct rte_mbuf *pkt)
if (unlikely(n_descs > NFDK_TX_DESC_GATHER_MAX))
return -EINVAL;
- /* Under count by 1 (don't count meta) for the round down to work out */
- n_descs += !!(pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG);
+ if ((pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG) != 0)
+ n_descs++;
if (round_down(txq->wr_p, NFDK_TX_DESC_BLOCK_CNT) !=
round_down(txq->wr_p + n_descs, NFDK_TX_DESC_BLOCK_CNT))
goto close_block;
- if ((uint32_t)txq->data_pending + pkt->pkt_len > NFDK_TX_MAX_DATA_PER_BLOCK)
+ if (txq->data_pending + pkt->pkt_len > NFDK_TX_MAX_DATA_PER_BLOCK)
goto close_block;
return 0;
@@ -126,39 +130,47 @@ nfp_net_nfdk_set_meta_data(struct rte_mbuf *pkt,
}
uint16_t
-nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+nfp_net_nfdk_xmit_pkts(void *tx_queue,
+ struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
{
uint32_t buf_idx;
uint64_t dma_addr;
- uint16_t free_descs;
+ uint32_t free_descs;
uint32_t npkts = 0;
uint64_t metadata = 0;
- uint16_t issued_descs = 0;
- struct nfp_net_txq *txq;
+ struct rte_mbuf *pkt;
struct nfp_net_hw *hw;
- struct nfp_net_nfdk_tx_desc *ktxds;
- struct rte_mbuf *pkt, *temp_pkt;
struct rte_mbuf **lmbuf;
+ struct nfp_net_txq *txq;
+ uint32_t issued_descs = 0;
+ struct rte_mbuf *temp_pkt;
+ struct nfp_net_nfdk_tx_desc *ktxds;
txq = tx_queue;
hw = txq->hw;
PMD_TX_LOG(DEBUG, "working for queue %u at pos %d and %u packets",
- txq->qidx, txq->wr_p, nb_pkts);
+ txq->qidx, txq->wr_p, nb_pkts);
- if ((nfp_net_nfdk_free_tx_desc(txq) < NFDK_TX_DESC_PER_SIMPLE_PKT *
- nb_pkts) || (nfp_net_nfdk_txq_full(txq)))
+ if (nfp_net_nfdk_free_tx_desc(txq) < NFDK_TX_DESC_PER_SIMPLE_PKT * nb_pkts ||
+ nfp_net_nfdk_txq_full(txq))
nfp_net_tx_free_bufs(txq);
- free_descs = (uint16_t)nfp_net_nfdk_free_tx_desc(txq);
+ free_descs = nfp_net_nfdk_free_tx_desc(txq);
if (unlikely(free_descs == 0))
return 0;
PMD_TX_LOG(DEBUG, "queue: %u. Sending %u packets", txq->qidx, nb_pkts);
+
/* Sending packets */
- while ((npkts < nb_pkts) && free_descs) {
- uint32_t type, dma_len, dlen_type, tmp_dlen;
- int nop_descs, used_descs;
+ while (npkts < nb_pkts && free_descs > 0) {
+ int nop_descs;
+ uint32_t type;
+ uint32_t dma_len;
+ uint32_t tmp_dlen;
+ uint32_t dlen_type;
+ uint32_t used_descs;
pkt = *(tx_pkts + npkts);
nop_descs = nfp_net_nfdk_tx_maybe_close_block(txq, pkt);
@@ -167,6 +179,7 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
issued_descs += nop_descs;
ktxds = &txq->ktxds[txq->wr_p];
+
/* Grabbing the mbuf linked to the current descriptor */
buf_idx = txq->wr_p;
lmbuf = &txq->txbufs[buf_idx++].mbuf;
@@ -177,8 +190,8 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
nfp_net_nfdk_set_meta_data(pkt, txq, &metadata);
if (unlikely(pkt->nb_segs > 1 &&
- !(hw->cap & NFP_NET_CFG_CTRL_GATHER))) {
- PMD_INIT_LOG(ERR, "Multisegment packet not supported");
+ (hw->cap & NFP_NET_CFG_CTRL_GATHER) == 0)) {
+ PMD_TX_LOG(ERR, "Multisegment packet not supported");
goto xmit_end;
}
@@ -186,10 +199,9 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
* Checksum and VLAN flags just in the first descriptor for a
* multisegment packet, but TSO info needs to be in all of them.
*/
-
dma_len = pkt->data_len;
- if ((hw->cap & NFP_NET_CFG_CTRL_LSO_ANY) &&
- (pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG)) {
+ if ((hw->cap & NFP_NET_CFG_CTRL_LSO_ANY) != 0 &&
+ (pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG) != 0) {
type = NFDK_DESC_TX_TYPE_TSO;
} else if (pkt->next == NULL && dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) {
type = NFDK_DESC_TX_TYPE_SIMPLE;
@@ -207,13 +219,11 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
* value of 'dma_len & NFDK_DESC_TX_DMA_LEN_HEAD' will be less
* than packet head len.
*/
- dlen_type = (dma_len > NFDK_DESC_TX_DMA_LEN_HEAD ?
- NFDK_DESC_TX_DMA_LEN_HEAD : dma_len) |
- (NFDK_DESC_TX_TYPE_HEAD & (type << 12));
+ if (dma_len > NFDK_DESC_TX_DMA_LEN_HEAD)
+ dma_len = NFDK_DESC_TX_DMA_LEN_HEAD;
+ dlen_type = dma_len | (NFDK_DESC_TX_TYPE_HEAD & (type << 12));
ktxds->dma_len_type = rte_cpu_to_le_16(dlen_type);
dma_addr = rte_mbuf_data_iova(pkt);
- PMD_TX_LOG(DEBUG, "Working with mbuf at dma address:"
- "%" PRIx64 "", dma_addr);
ktxds->dma_addr_hi = rte_cpu_to_le_16(dma_addr >> 32);
ktxds->dma_addr_lo = rte_cpu_to_le_32(dma_addr & 0xffffffff);
ktxds++;
@@ -230,8 +240,8 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
* The rest of the data (if any) will be in larger DMA descriptors
* and is handled with the dma_len loop.
*/
- while (pkt) {
- if (*lmbuf)
+ while (pkt != NULL) {
+ if (*lmbuf != NULL)
rte_pktmbuf_free_seg(*lmbuf);
*lmbuf = pkt;
while (dma_len > 0) {
@@ -253,8 +263,6 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
pkt = pkt->next;
dma_len = pkt->data_len;
dma_addr = rte_mbuf_data_iova(pkt);
- PMD_TX_LOG(DEBUG, "Working with mbuf at dma address:"
- "%" PRIx64 "", dma_addr);
lmbuf = &txq->txbufs[buf_idx++].mbuf;
}
@@ -264,16 +272,16 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
ktxds->raw = rte_cpu_to_le_64(nfp_net_nfdk_tx_cksum(txq, temp_pkt, metadata));
ktxds++;
- if ((hw->cap & NFP_NET_CFG_CTRL_LSO_ANY) &&
- (temp_pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG)) {
+ if ((hw->cap & NFP_NET_CFG_CTRL_LSO_ANY) != 0 &&
+ (temp_pkt->ol_flags & RTE_MBUF_F_TX_TCP_SEG) != 0) {
ktxds->raw = rte_cpu_to_le_64(nfp_net_nfdk_tx_tso(txq, temp_pkt));
ktxds++;
}
used_descs = ktxds - txq->ktxds - txq->wr_p;
if (round_down(txq->wr_p, NFDK_TX_DESC_BLOCK_CNT) !=
- round_down(txq->wr_p + used_descs - 1, NFDK_TX_DESC_BLOCK_CNT)) {
- PMD_INIT_LOG(INFO, "Used descs cross block boundary");
+ round_down(txq->wr_p + used_descs - 1, NFDK_TX_DESC_BLOCK_CNT)) {
+ PMD_TX_LOG(INFO, "Used descs cross block boundary");
goto xmit_end;
}
@@ -285,7 +293,7 @@ nfp_net_nfdk_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pk
issued_descs += used_descs;
npkts++;
- free_descs = (uint16_t)nfp_net_nfdk_free_tx_desc(txq);
+ free_descs = nfp_net_nfdk_free_tx_desc(txq);
}
xmit_end:
@@ -304,13 +312,14 @@ nfp_net_nfdk_tx_queue_setup(struct rte_eth_dev *dev,
const struct rte_eth_txconf *tx_conf)
{
int ret;
+ size_t size;
+ uint32_t tx_desc_sz;
uint16_t min_tx_desc;
uint16_t max_tx_desc;
- const struct rte_memzone *tz;
- struct nfp_net_txq *txq;
- uint16_t tx_free_thresh;
struct nfp_net_hw *hw;
- uint32_t tx_desc_sz;
+ uint16_t tx_free_thresh;
+ struct nfp_net_txq *txq;
+ const struct rte_memzone *tz;
hw = NFP_NET_DEV_PRIVATE_TO_HW(dev->data->dev_private);
@@ -323,30 +332,27 @@ nfp_net_nfdk_tx_queue_setup(struct rte_eth_dev *dev,
/* Validating number of descriptors */
tx_desc_sz = nb_desc * sizeof(struct nfp_net_nfdk_tx_desc);
if ((NFDK_TX_DESC_PER_SIMPLE_PKT * tx_desc_sz) % NFP_ALIGN_RING_DESC != 0 ||
- (NFDK_TX_DESC_PER_SIMPLE_PKT * nb_desc) % NFDK_TX_DESC_BLOCK_CNT != 0 ||
- nb_desc > max_tx_desc || nb_desc < min_tx_desc) {
+ (NFDK_TX_DESC_PER_SIMPLE_PKT * nb_desc) % NFDK_TX_DESC_BLOCK_CNT != 0 ||
+ nb_desc > max_tx_desc || nb_desc < min_tx_desc) {
PMD_DRV_LOG(ERR, "Wrong nb_desc value");
return -EINVAL;
}
- tx_free_thresh = (uint16_t)((tx_conf->tx_free_thresh) ?
- tx_conf->tx_free_thresh :
- DEFAULT_TX_FREE_THRESH);
-
- if (tx_free_thresh > (nb_desc)) {
- PMD_DRV_LOG(ERR,
- "tx_free_thresh must be less than the number of TX "
- "descriptors. (tx_free_thresh=%u port=%d "
- "queue=%d)", (unsigned int)tx_free_thresh,
- dev->data->port_id, (int)queue_idx);
- return -(EINVAL);
+ tx_free_thresh = tx_conf->tx_free_thresh;
+ if (tx_free_thresh == 0)
+ tx_free_thresh = DEFAULT_TX_FREE_THRESH;
+ if (tx_free_thresh > nb_desc) {
+ PMD_DRV_LOG(ERR, "tx_free_thresh must be less than the number of TX "
+ "descriptors. (tx_free_thresh=%u port=%d queue=%d)",
+ tx_free_thresh, dev->data->port_id, queue_idx);
+ return -EINVAL;
}
/*
* Free memory prior to re-allocation if needed. This is the case after
* calling nfp_net_stop
*/
- if (dev->data->tx_queues[queue_idx]) {
+ if (dev->data->tx_queues[queue_idx] != NULL) {
PMD_TX_LOG(DEBUG, "Freeing memory prior to re-allocation %d",
queue_idx);
nfp_net_tx_queue_release(dev, queue_idx);
@@ -366,11 +372,10 @@ nfp_net_nfdk_tx_queue_setup(struct rte_eth_dev *dev,
* handle the maximum ring size is allocated in order to allow for
* resizing in later calls to the queue setup function.
*/
- tz = rte_eth_dma_zone_reserve(dev, "tx_ring", queue_idx,
- sizeof(struct nfp_net_nfdk_tx_desc) *
- NFDK_TX_DESC_PER_SIMPLE_PKT *
- max_tx_desc, NFP_MEMZONE_ALIGN,
- socket_id);
+ size = sizeof(struct nfp_net_nfdk_tx_desc) * max_tx_desc *
+ NFDK_TX_DESC_PER_SIMPLE_PKT;
+ tz = rte_eth_dma_zone_reserve(dev, "tx_ring", queue_idx, size,
+ NFP_MEMZONE_ALIGN, socket_id);
if (tz == NULL) {
PMD_DRV_LOG(ERR, "Error allocating tx dma");
nfp_net_tx_queue_release(dev, queue_idx);
@@ -387,29 +392,26 @@ nfp_net_nfdk_tx_queue_setup(struct rte_eth_dev *dev,
txq->qidx = queue_idx;
txq->tx_qcidx = queue_idx * hw->stride_tx;
txq->qcp_q = hw->tx_bar + NFP_QCP_QUEUE_OFF(txq->tx_qcidx);
-
txq->port_id = dev->data->port_id;
/* Saving physical and virtual addresses for the TX ring */
- txq->dma = (uint64_t)tz->iova;
- txq->ktxds = (struct nfp_net_nfdk_tx_desc *)tz->addr;
+ txq->dma = tz->iova;
+ txq->ktxds = tz->addr;
/* mbuf pointers array for referencing mbufs linked to TX descriptors */
txq->txbufs = rte_zmalloc_socket("txq->txbufs",
- sizeof(*txq->txbufs) * txq->tx_count,
- RTE_CACHE_LINE_SIZE, socket_id);
-
+ sizeof(*txq->txbufs) * txq->tx_count,
+ RTE_CACHE_LINE_SIZE, socket_id);
if (txq->txbufs == NULL) {
nfp_net_tx_queue_release(dev, queue_idx);
return -ENOMEM;
}
- PMD_TX_LOG(DEBUG, "txbufs=%p hw_ring=%p dma_addr=0x%" PRIx64,
- txq->txbufs, txq->ktxds, (unsigned long)txq->dma);
nfp_net_reset_tx_queue(txq);
dev->data->tx_queues[queue_idx] = txq;
txq->hw = hw;
+
/*
* Telling the HW about the physical address of the TX ring and number
* of descriptors in log2 format