#include <ena_eth_io_defs.h>
#define DRV_MODULE_VER_MAJOR 2
-#define DRV_MODULE_VER_MINOR 0
-#define DRV_MODULE_VER_SUBMINOR 3
+#define DRV_MODULE_VER_MINOR 1
+#define DRV_MODULE_VER_SUBMINOR 0
#define ENA_IO_TXQ_IDX(q) (2 * (q))
#define ENA_IO_RXQ_IDX(q) (2 * (q) + 1)
/*reverse version of ENA_IO_RXQ_IDX*/
#define ENA_IO_RXQ_IDX_REV(q) ((q - 1) / 2)
-/* While processing submitted and completed descriptors (rx and tx path
- * respectively) in a loop it is desired to:
- * - perform batch submissions while populating sumbissmion queue
- * - avoid blocking transmission of other packets during cleanup phase
- * Hence the utilization ratio of 1/8 of a queue size.
- */
-#define ENA_RING_DESCS_RATIO(ring_size) (ring_size / 8)
-
#define __MERGE_64B_H_L(h, l) (((uint64_t)h << 32) | l)
#define TEST_BIT(val, bit_shift) (val & (1UL << bit_shift))
#define ENA_STAT_TX_ENTRY(stat) \
ENA_STAT_ENTRY(stat, tx)
+#define ENA_STAT_ENI_ENTRY(stat) \
+ ENA_STAT_ENTRY(stat, eni)
+
#define ENA_STAT_GLOBAL_ENTRY(stat) \
ENA_STAT_ENTRY(stat, dev)
ENA_STAT_GLOBAL_ENTRY(tx_drops),
};
+static const struct ena_stats ena_stats_eni_strings[] = {
+ ENA_STAT_ENI_ENTRY(bw_in_allowance_exceeded),
+ ENA_STAT_ENI_ENTRY(bw_out_allowance_exceeded),
+ ENA_STAT_ENI_ENTRY(pps_allowance_exceeded),
+ ENA_STAT_ENI_ENTRY(conntrack_allowance_exceeded),
+ ENA_STAT_ENI_ENTRY(linklocal_allowance_exceeded),
+};
+
static const struct ena_stats ena_stats_tx_strings[] = {
ENA_STAT_TX_ENTRY(cnt),
ENA_STAT_TX_ENTRY(bytes),
};
#define ENA_STATS_ARRAY_GLOBAL ARRAY_SIZE(ena_stats_global_strings)
+#define ENA_STATS_ARRAY_ENI ARRAY_SIZE(ena_stats_eni_strings)
#define ENA_STATS_ARRAY_TX ARRAY_SIZE(ena_stats_tx_strings)
#define ENA_STATS_ARRAY_RX ARRAY_SIZE(ena_stats_rx_strings)
#define ENA_TX_OFFLOAD_NOTSUP_MASK \
(PKT_TX_OFFLOAD_MASK ^ ENA_TX_OFFLOAD_MASK)
-int ena_logtype_init;
-int ena_logtype_driver;
-
-#ifdef RTE_LIBRTE_ENA_DEBUG_RX
-int ena_logtype_rx;
-#endif
-#ifdef RTE_LIBRTE_ENA_DEBUG_TX
-int ena_logtype_tx;
-#endif
-#ifdef RTE_LIBRTE_ENA_DEBUG_TX_FREE
-int ena_logtype_tx_free;
-#endif
-#ifdef RTE_LIBRTE_ENA_COM_DEBUG
-int ena_logtype_com;
-#endif
-
static const struct rte_pci_id pci_id_ena_map[] = {
{ RTE_PCI_DEVICE(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_ENA_VF) },
{ RTE_PCI_DEVICE(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_ENA_LLQ_VF) },
struct ena_com_dev_get_features_ctx *get_feat_ctx,
bool *wd_state);
static int ena_dev_configure(struct rte_eth_dev *dev);
+static void ena_tx_map_mbuf(struct ena_ring *tx_ring,
+ struct ena_tx_buffer *tx_info,
+ struct rte_mbuf *mbuf,
+ void **push_header,
+ uint16_t *header_len);
+static int ena_xmit_mbuf(struct ena_ring *tx_ring, struct rte_mbuf *mbuf);
+static void ena_tx_cleanup(struct ena_ring *tx_ring);
static uint16_t eth_ena_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts);
static uint16_t eth_ena_prep_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_desc, unsigned int socket_id,
const struct rte_eth_rxconf *rx_conf,
struct rte_mempool *mp);
+static inline void ena_init_rx_mbuf(struct rte_mbuf *mbuf, uint16_t len);
+static struct rte_mbuf *ena_rx_mbuf(struct ena_ring *rx_ring,
+ struct ena_com_rx_buf_info *ena_bufs,
+ uint32_t descs,
+ uint16_t *next_to_clean,
+ uint8_t offset);
static uint16_t eth_ena_recv_pkts(void *rx_queue,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+static int ena_add_single_rx_desc(struct ena_com_io_sq *io_sq,
+ struct rte_mbuf *mbuf, uint16_t id);
static int ena_populate_rx_queue(struct ena_ring *rxq, unsigned int count);
static void ena_init_rings(struct ena_adapter *adapter,
bool disable_meta_caching);
static int ena_mtu_set(struct rte_eth_dev *dev, uint16_t mtu);
static int ena_start(struct rte_eth_dev *dev);
static void ena_stop(struct rte_eth_dev *dev);
-static void ena_close(struct rte_eth_dev *dev);
+static int ena_close(struct rte_eth_dev *dev);
static int ena_dev_reset(struct rte_eth_dev *dev);
static int ena_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats);
static void ena_rx_queue_release_all(struct rte_eth_dev *dev);
void *opaque);
static int ena_parse_devargs(struct ena_adapter *adapter,
struct rte_devargs *devargs);
+static int ena_copy_eni_stats(struct ena_adapter *adapter);
static const struct eth_dev_ops ena_dev_ops = {
.dev_configure = ena_dev_configure,
/* This function calculates the number of xstats based on the current config */
static unsigned int ena_xstats_calc_num(struct rte_eth_dev *dev)
{
- return ENA_STATS_ARRAY_GLOBAL +
+ return ENA_STATS_ARRAY_GLOBAL + ENA_STATS_ARRAY_ENI +
(dev->data->nb_tx_queues * ENA_STATS_ARRAY_TX) +
(dev->data->nb_rx_queues * ENA_STATS_ARRAY_RX);
}
ena_com_delete_debug_area(&adapter->ena_dev);
}
-static void ena_close(struct rte_eth_dev *dev)
+static int ena_close(struct rte_eth_dev *dev)
{
struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;
struct ena_adapter *adapter = dev->data->dev_private;
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+ return 0;
+
if (adapter->state == ENA_ADAPTER_STATE_RUNNING)
ena_stop(dev);
adapter->state = ENA_ADAPTER_STATE_CLOSED;
* release of the resource in the rte_eth_dev_release_port().
*/
dev->data->mac_addrs = NULL;
+
+ return 0;
}
static int
}
}
+ rte_spinlock_lock(&adapter->admin_lock);
rc = ena_com_indirect_table_set(ena_dev);
+ rte_spinlock_unlock(&adapter->admin_lock);
if (unlikely(rc && rc != ENA_COM_UNSUPPORTED)) {
PMD_DRV_LOG(ERR, "Cannot flush the indirect table\n");
return rc;
(reta_size > RTE_RETA_GROUP_SIZE && ((reta_conf + 1) == NULL)))
return -EINVAL;
+ rte_spinlock_lock(&adapter->admin_lock);
rc = ena_com_indirect_table_get(ena_dev, indirect_table);
+ rte_spinlock_unlock(&adapter->admin_lock);
if (unlikely(rc && rc != ENA_COM_UNSUPPORTED)) {
PMD_DRV_LOG(ERR, "cannot get indirect table\n");
return -ENOTSUP;
{
unsigned int i;
- for (i = 0; i < ring->ring_size; ++i)
- if (ring->rx_buffer_info[i]) {
- rte_mbuf_raw_free(ring->rx_buffer_info[i]);
- ring->rx_buffer_info[i] = NULL;
+ for (i = 0; i < ring->ring_size; ++i) {
+ struct ena_rx_buffer *rx_info = &ring->rx_buffer_info[i];
+ if (rx_info->mbuf) {
+ rte_mbuf_raw_free(rx_info->mbuf);
+ rx_info->mbuf = NULL;
}
+ }
}
static void ena_tx_queue_release_bufs(struct ena_ring *ring)
return -ENOTSUP;
memset(&ena_stats, 0, sizeof(ena_stats));
+
+ rte_spinlock_lock(&adapter->admin_lock);
rc = ena_com_get_dev_basic_stats(ena_dev, &ena_stats);
+ rte_spinlock_unlock(&adapter->admin_lock);
if (unlikely(rc)) {
PMD_DRV_LOG(ERR, "Could not retrieve statistics from ENA\n");
return rc;
txq->next_to_clean = 0;
txq->next_to_use = 0;
txq->ring_size = nb_desc;
+ txq->size_mask = nb_desc - 1;
txq->numa_socket_id = socket_id;
txq->tx_buffer_info = rte_zmalloc("txq->tx_buffer_info",
rxq->next_to_clean = 0;
rxq->next_to_use = 0;
rxq->ring_size = nb_desc;
+ rxq->size_mask = nb_desc - 1;
rxq->numa_socket_id = socket_id;
rxq->mb_pool = mp;
rxq->rx_buffer_info = rte_zmalloc("rxq->buffer_info",
- sizeof(struct rte_mbuf *) * nb_desc,
- RTE_CACHE_LINE_SIZE);
+ sizeof(struct ena_rx_buffer) * nb_desc,
+ RTE_CACHE_LINE_SIZE);
if (!rxq->rx_buffer_info) {
PMD_DRV_LOG(ERR, "failed to alloc mem for rx buffer info\n");
return -ENOMEM;
return 0;
}
+static int ena_add_single_rx_desc(struct ena_com_io_sq *io_sq,
+ struct rte_mbuf *mbuf, uint16_t id)
+{
+ struct ena_com_buf ebuf;
+ int rc;
+
+ /* prepare physical address for DMA transaction */
+ ebuf.paddr = mbuf->buf_iova + RTE_PKTMBUF_HEADROOM;
+ ebuf.len = mbuf->buf_len - RTE_PKTMBUF_HEADROOM;
+
+ /* pass resource to device */
+ rc = ena_com_add_single_rx_desc(io_sq, &ebuf, id);
+ if (unlikely(rc != 0))
+ PMD_DRV_LOG(WARNING, "failed adding rx desc\n");
+
+ return rc;
+}
+
static int ena_populate_rx_queue(struct ena_ring *rxq, unsigned int count)
{
unsigned int i;
int rc;
- uint16_t ring_size = rxq->ring_size;
- uint16_t ring_mask = ring_size - 1;
uint16_t next_to_use = rxq->next_to_use;
uint16_t in_use, req_id;
struct rte_mbuf **mbufs = rxq->rx_refill_buffer;
if (unlikely(!count))
return 0;
- in_use = rxq->next_to_use - rxq->next_to_clean;
- ena_assert_msg(((in_use + count) < ring_size), "bad ring state\n");
+ in_use = rxq->ring_size - 1 -
+ ena_com_free_q_entries(rxq->ena_com_io_sq);
+ ena_assert_msg(((in_use + count) < rxq->ring_size),
+ "bad ring state\n");
/* get resources for incoming packets */
rc = rte_mempool_get_bulk(rxq->mb_pool, (void **)mbufs, count);
}
for (i = 0; i < count; i++) {
- uint16_t next_to_use_masked = next_to_use & ring_mask;
struct rte_mbuf *mbuf = mbufs[i];
- struct ena_com_buf ebuf;
+ struct ena_rx_buffer *rx_info;
if (likely((i + 4) < count))
rte_prefetch0(mbufs[i + 4]);
- req_id = rxq->empty_rx_reqs[next_to_use_masked];
+ req_id = rxq->empty_rx_reqs[next_to_use];
rc = validate_rx_req_id(rxq, req_id);
- if (unlikely(rc < 0))
+ if (unlikely(rc))
break;
- rxq->rx_buffer_info[req_id] = mbuf;
-
- /* prepare physical address for DMA transaction */
- ebuf.paddr = mbuf->buf_iova + RTE_PKTMBUF_HEADROOM;
- ebuf.len = mbuf->buf_len - RTE_PKTMBUF_HEADROOM;
- /* pass resource to device */
- rc = ena_com_add_single_rx_desc(rxq->ena_com_io_sq,
- &ebuf, req_id);
- if (unlikely(rc)) {
- PMD_DRV_LOG(WARNING, "failed adding rx desc\n");
- rxq->rx_buffer_info[req_id] = NULL;
+
+ rx_info = &rxq->rx_buffer_info[req_id];
+
+ rc = ena_add_single_rx_desc(rxq->ena_com_io_sq, mbuf, req_id);
+ if (unlikely(rc != 0))
break;
- }
- next_to_use++;
+
+ rx_info->mbuf = mbuf;
+ next_to_use = ENA_IDX_NEXT_MASKED(next_to_use, rxq->size_mask);
}
if (unlikely(i < count)) {
if (unlikely(adapter->trigger_reset)) {
PMD_DRV_LOG(ERR, "Trigger reset is on\n");
- _rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_RESET,
+ rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_RESET,
NULL);
}
}
int rc;
static int adapters_found;
bool disable_meta_caching;
- bool wd_state;
+ bool wd_state = false;
eth_dev->dev_ops = &ena_dev_ops;
eth_dev->rx_pkt_burst = ð_ena_recv_pkts;
get_feat_ctx.dev_attr.mac_addr,
(struct rte_ether_addr *)adapter->mac_addr);
- /*
- * Pass the information to the rte_eth_dev_close() that it should also
- * release the private port resources.
- */
- eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
-
adapter->drv_stats = rte_zmalloc("adapter stats",
sizeof(*adapter->drv_stats),
RTE_CACHE_LINE_SIZE);
goto err_delete_debug_area;
}
+ rte_spinlock_init(&adapter->admin_lock);
+
rte_intr_callback_register(intr_handle,
ena_interrupt_handler_rte,
adapter);
return 0;
}
+static inline void ena_init_rx_mbuf(struct rte_mbuf *mbuf, uint16_t len)
+{
+ mbuf->data_len = len;
+ mbuf->data_off = RTE_PKTMBUF_HEADROOM;
+ mbuf->refcnt = 1;
+ mbuf->next = NULL;
+}
+
+static struct rte_mbuf *ena_rx_mbuf(struct ena_ring *rx_ring,
+ struct ena_com_rx_buf_info *ena_bufs,
+ uint32_t descs,
+ uint16_t *next_to_clean,
+ uint8_t offset)
+{
+ struct rte_mbuf *mbuf;
+ struct rte_mbuf *mbuf_head;
+ struct ena_rx_buffer *rx_info;
+ int rc;
+ uint16_t ntc, len, req_id, buf = 0;
+
+ if (unlikely(descs == 0))
+ return NULL;
+
+ ntc = *next_to_clean;
+
+ len = ena_bufs[buf].len;
+ req_id = ena_bufs[buf].req_id;
+ if (unlikely(validate_rx_req_id(rx_ring, req_id)))
+ return NULL;
+
+ rx_info = &rx_ring->rx_buffer_info[req_id];
+
+ mbuf = rx_info->mbuf;
+ RTE_ASSERT(mbuf != NULL);
+
+ ena_init_rx_mbuf(mbuf, len);
+
+ /* Fill the mbuf head with the data specific for 1st segment. */
+ mbuf_head = mbuf;
+ mbuf_head->nb_segs = descs;
+ mbuf_head->port = rx_ring->port_id;
+ mbuf_head->pkt_len = len;
+ mbuf_head->data_off += offset;
+
+ rx_info->mbuf = NULL;
+ rx_ring->empty_rx_reqs[ntc] = req_id;
+ ntc = ENA_IDX_NEXT_MASKED(ntc, rx_ring->size_mask);
+
+ while (--descs) {
+ ++buf;
+ len = ena_bufs[buf].len;
+ req_id = ena_bufs[buf].req_id;
+ if (unlikely(validate_rx_req_id(rx_ring, req_id))) {
+ rte_mbuf_raw_free(mbuf_head);
+ return NULL;
+ }
+
+ rx_info = &rx_ring->rx_buffer_info[req_id];
+ RTE_ASSERT(rx_info->mbuf != NULL);
+
+ if (unlikely(len == 0)) {
+ /*
+ * Some devices can pass descriptor with the length 0.
+ * To avoid confusion, the PMD is simply putting the
+ * descriptor back, as it was never used. We'll avoid
+ * mbuf allocation that way.
+ */
+ rc = ena_add_single_rx_desc(rx_ring->ena_com_io_sq,
+ rx_info->mbuf, req_id);
+ if (unlikely(rc != 0)) {
+ /* Free the mbuf in case of an error. */
+ rte_mbuf_raw_free(rx_info->mbuf);
+ } else {
+ /*
+ * If there was no error, just exit the loop as
+ * 0 length descriptor is always the last one.
+ */
+ break;
+ }
+ } else {
+ /* Create an mbuf chain. */
+ mbuf->next = rx_info->mbuf;
+ mbuf = mbuf->next;
+
+ ena_init_rx_mbuf(mbuf, len);
+ mbuf_head->pkt_len += len;
+ }
+
+ /*
+ * Mark the descriptor as depleted and perform necessary
+ * cleanup.
+ * This code will execute in two cases:
+ * 1. Descriptor len was greater than 0 - normal situation.
+ * 2. Descriptor len was 0 and we failed to add the descriptor
+ * to the device. In that situation, we should try to add
+ * the mbuf again in the populate routine and mark the
+ * descriptor as used up by the device.
+ */
+ rx_info->mbuf = NULL;
+ rx_ring->empty_rx_reqs[ntc] = req_id;
+ ntc = ENA_IDX_NEXT_MASKED(ntc, rx_ring->size_mask);
+ }
+
+ *next_to_clean = ntc;
+
+ return mbuf_head;
+}
+
static uint16_t eth_ena_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts)
{
struct ena_ring *rx_ring = (struct ena_ring *)(rx_queue);
- unsigned int ring_size = rx_ring->ring_size;
- unsigned int ring_mask = ring_size - 1;
+ unsigned int free_queue_entries;
+ unsigned int refill_threshold;
uint16_t next_to_clean = rx_ring->next_to_clean;
- uint16_t desc_in_use = 0;
- uint16_t req_id;
- unsigned int recv_idx = 0;
- struct rte_mbuf *mbuf = NULL;
- struct rte_mbuf *mbuf_head = NULL;
- struct rte_mbuf *mbuf_prev = NULL;
- struct rte_mbuf **rx_buff_info = rx_ring->rx_buffer_info;
- unsigned int completed;
-
+ uint16_t descs_in_use;
+ struct rte_mbuf *mbuf;
+ uint16_t completed;
struct ena_com_rx_ctx ena_rx_ctx;
- int rc = 0;
+ int i, rc = 0;
/* Check adapter state */
if (unlikely(rx_ring->adapter->state != ENA_ADAPTER_STATE_RUNNING)) {
return 0;
}
- desc_in_use = rx_ring->next_to_use - next_to_clean;
- if (unlikely(nb_pkts > desc_in_use))
- nb_pkts = desc_in_use;
+ descs_in_use = rx_ring->ring_size -
+ ena_com_free_q_entries(rx_ring->ena_com_io_sq) - 1;
+ nb_pkts = RTE_MIN(descs_in_use, nb_pkts);
for (completed = 0; completed < nb_pkts; completed++) {
- int segments = 0;
-
ena_rx_ctx.max_bufs = rx_ring->sgl_size;
ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
ena_rx_ctx.descs = 0;
return 0;
}
- if (unlikely(ena_rx_ctx.descs == 0))
- break;
-
- while (segments < ena_rx_ctx.descs) {
- req_id = ena_rx_ctx.ena_bufs[segments].req_id;
- rc = validate_rx_req_id(rx_ring, req_id);
- if (unlikely(rc)) {
- if (segments != 0)
- rte_mbuf_raw_free(mbuf_head);
- break;
+ mbuf = ena_rx_mbuf(rx_ring,
+ ena_rx_ctx.ena_bufs,
+ ena_rx_ctx.descs,
+ &next_to_clean,
+ ena_rx_ctx.pkt_offset);
+ if (unlikely(mbuf == NULL)) {
+ for (i = 0; i < ena_rx_ctx.descs; ++i) {
+ rx_ring->empty_rx_reqs[next_to_clean] =
+ rx_ring->ena_bufs[i].req_id;
+ next_to_clean = ENA_IDX_NEXT_MASKED(
+ next_to_clean, rx_ring->size_mask);
}
-
- mbuf = rx_buff_info[req_id];
- rx_buff_info[req_id] = NULL;
- mbuf->data_len = ena_rx_ctx.ena_bufs[segments].len;
- mbuf->data_off = RTE_PKTMBUF_HEADROOM;
- mbuf->refcnt = 1;
- mbuf->next = NULL;
- if (unlikely(segments == 0)) {
- mbuf->nb_segs = ena_rx_ctx.descs;
- mbuf->port = rx_ring->port_id;
- mbuf->pkt_len = 0;
- mbuf->data_off += ena_rx_ctx.pkt_offset;
- mbuf_head = mbuf;
- } else {
- /* for multi-segment pkts create mbuf chain */
- mbuf_prev->next = mbuf;
- }
- mbuf_head->pkt_len += mbuf->data_len;
-
- mbuf_prev = mbuf;
- rx_ring->empty_rx_reqs[next_to_clean & ring_mask] =
- req_id;
- segments++;
- next_to_clean++;
- }
- if (unlikely(rc))
break;
+ }
/* fill mbuf attributes if any */
- ena_rx_mbuf_prepare(mbuf_head, &ena_rx_ctx);
+ ena_rx_mbuf_prepare(mbuf, &ena_rx_ctx);
- if (unlikely(mbuf_head->ol_flags &
+ if (unlikely(mbuf->ol_flags &
(PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD))) {
rte_atomic64_inc(&rx_ring->adapter->drv_stats->ierrors);
++rx_ring->rx_stats.bad_csum;
}
- mbuf_head->hash.rss = ena_rx_ctx.hash;
+ mbuf->hash.rss = ena_rx_ctx.hash;
- /* pass to DPDK application head mbuf */
- rx_pkts[recv_idx] = mbuf_head;
- recv_idx++;
- rx_ring->rx_stats.bytes += mbuf_head->pkt_len;
+ rx_pkts[completed] = mbuf;
+ rx_ring->rx_stats.bytes += mbuf->pkt_len;
}
- rx_ring->rx_stats.cnt += recv_idx;
+ rx_ring->rx_stats.cnt += completed;
rx_ring->next_to_clean = next_to_clean;
- desc_in_use = desc_in_use - completed + 1;
+ free_queue_entries = ena_com_free_q_entries(rx_ring->ena_com_io_sq);
+ refill_threshold =
+ RTE_MIN(rx_ring->ring_size / ENA_REFILL_THRESH_DIVIDER,
+ (unsigned int)ENA_REFILL_THRESH_PACKET);
+
/* Burst refill to save doorbells, memory barriers, const interval */
- if (ring_size - desc_in_use > ENA_RING_DESCS_RATIO(ring_size)) {
+ if (free_queue_entries > refill_threshold) {
ena_com_update_dev_comp_head(rx_ring->ena_com_io_cq);
- ena_populate_rx_queue(rx_ring, ring_size - desc_in_use);
+ ena_populate_rx_queue(rx_ring, free_queue_entries);
}
- return recv_idx;
+ return completed;
}
static uint16_t
return rc;
}
-static uint16_t eth_ena_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
- uint16_t nb_pkts)
+static void ena_tx_map_mbuf(struct ena_ring *tx_ring,
+ struct ena_tx_buffer *tx_info,
+ struct rte_mbuf *mbuf,
+ void **push_header,
+ uint16_t *header_len)
{
- struct ena_ring *tx_ring = (struct ena_ring *)(tx_queue);
- uint16_t next_to_use = tx_ring->next_to_use;
- uint16_t next_to_clean = tx_ring->next_to_clean;
- struct rte_mbuf *mbuf;
- uint16_t seg_len;
- unsigned int ring_size = tx_ring->ring_size;
- unsigned int ring_mask = ring_size - 1;
- struct ena_com_tx_ctx ena_tx_ctx;
- struct ena_tx_buffer *tx_info;
- struct ena_com_buf *ebuf;
- uint16_t rc, req_id, total_tx_descs = 0;
- uint16_t sent_idx = 0, empty_tx_reqs;
- uint16_t push_len = 0;
- uint16_t delta = 0;
- int nb_hw_desc;
- uint32_t total_length;
+ struct ena_com_buf *ena_buf;
+ uint16_t delta, seg_len, push_len;
- /* Check adapter state */
- if (unlikely(tx_ring->adapter->state != ENA_ADAPTER_STATE_RUNNING)) {
- PMD_DRV_LOG(ALERT,
- "Trying to xmit pkts while device is NOT running\n");
- return 0;
- }
+ delta = 0;
+ seg_len = mbuf->data_len;
- empty_tx_reqs = ring_size - (next_to_use - next_to_clean);
- if (nb_pkts > empty_tx_reqs)
- nb_pkts = empty_tx_reqs;
+ tx_info->mbuf = mbuf;
+ ena_buf = tx_info->bufs;
- for (sent_idx = 0; sent_idx < nb_pkts; sent_idx++) {
- mbuf = tx_pkts[sent_idx];
- total_length = 0;
+ if (tx_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
+ /*
+ * Tx header might be (and will be in most cases) smaller than
+ * tx_max_header_size. But it's not an issue to send more data
+ * to the device, than actually needed if the mbuf size is
+ * greater than tx_max_header_size.
+ */
+ push_len = RTE_MIN(mbuf->pkt_len, tx_ring->tx_max_header_size);
+ *header_len = push_len;
- rc = ena_check_and_linearize_mbuf(tx_ring, mbuf);
- if (unlikely(rc))
- break;
+ if (likely(push_len <= seg_len)) {
+ /* If the push header is in the single segment, then
+ * just point it to the 1st mbuf data.
+ */
+ *push_header = rte_pktmbuf_mtod(mbuf, uint8_t *);
+ } else {
+ /* If the push header lays in the several segments, copy
+ * it to the intermediate buffer.
+ */
+ rte_pktmbuf_read(mbuf, 0, push_len,
+ tx_ring->push_buf_intermediate_buf);
+ *push_header = tx_ring->push_buf_intermediate_buf;
+ delta = push_len - seg_len;
+ }
+ } else {
+ *push_header = NULL;
+ *header_len = 0;
+ push_len = 0;
+ }
- req_id = tx_ring->empty_tx_reqs[next_to_use & ring_mask];
- tx_info = &tx_ring->tx_buffer_info[req_id];
- tx_info->mbuf = mbuf;
- tx_info->num_of_bufs = 0;
- ebuf = tx_info->bufs;
+ /* Process first segment taking into consideration pushed header */
+ if (seg_len > push_len) {
+ ena_buf->paddr = mbuf->buf_iova +
+ mbuf->data_off +
+ push_len;
+ ena_buf->len = seg_len - push_len;
+ ena_buf++;
+ tx_info->num_of_bufs++;
+ }
- /* Prepare TX context */
- memset(&ena_tx_ctx, 0x0, sizeof(struct ena_com_tx_ctx));
- memset(&ena_tx_ctx.ena_meta, 0x0,
- sizeof(struct ena_com_tx_meta));
- ena_tx_ctx.ena_bufs = ebuf;
- ena_tx_ctx.req_id = req_id;
+ while ((mbuf = mbuf->next) != NULL) {
+ seg_len = mbuf->data_len;
+
+ /* Skip mbufs if whole data is pushed as a header */
+ if (unlikely(delta > seg_len)) {
+ delta -= seg_len;
+ continue;
+ }
+
+ ena_buf->paddr = mbuf->buf_iova + mbuf->data_off + delta;
+ ena_buf->len = seg_len - delta;
+ ena_buf++;
+ tx_info->num_of_bufs++;
delta = 0;
- seg_len = mbuf->data_len;
+ }
+}
- if (tx_ring->tx_mem_queue_type ==
- ENA_ADMIN_PLACEMENT_POLICY_DEV) {
- push_len = RTE_MIN(mbuf->pkt_len,
- tx_ring->tx_max_header_size);
- ena_tx_ctx.header_len = push_len;
+static int ena_xmit_mbuf(struct ena_ring *tx_ring, struct rte_mbuf *mbuf)
+{
+ struct ena_tx_buffer *tx_info;
+ struct ena_com_tx_ctx ena_tx_ctx = { { 0 } };
+ uint16_t next_to_use;
+ uint16_t header_len;
+ uint16_t req_id;
+ void *push_header;
+ int nb_hw_desc;
+ int rc;
- if (likely(push_len <= seg_len)) {
- /* If the push header is in the single segment,
- * then just point it to the 1st mbuf data.
- */
- ena_tx_ctx.push_header =
- rte_pktmbuf_mtod(mbuf, uint8_t *);
- } else {
- /* If the push header lays in the several
- * segments, copy it to the intermediate buffer.
- */
- rte_pktmbuf_read(mbuf, 0, push_len,
- tx_ring->push_buf_intermediate_buf);
- ena_tx_ctx.push_header =
- tx_ring->push_buf_intermediate_buf;
- delta = push_len - seg_len;
- }
- } /* there's no else as we take advantage of memset zeroing */
+ rc = ena_check_and_linearize_mbuf(tx_ring, mbuf);
+ if (unlikely(rc))
+ return rc;
- /* Set TX offloads flags, if applicable */
- ena_tx_mbuf_prepare(mbuf, &ena_tx_ctx, tx_ring->offloads,
- tx_ring->disable_meta_caching);
+ next_to_use = tx_ring->next_to_use;
- rte_prefetch0(tx_pkts[(sent_idx + 4) & ring_mask]);
+ req_id = tx_ring->empty_tx_reqs[next_to_use];
+ tx_info = &tx_ring->tx_buffer_info[req_id];
+ tx_info->num_of_bufs = 0;
- /* Process first segment taking into
- * consideration pushed header
- */
- if (seg_len > push_len) {
- ebuf->paddr = mbuf->buf_iova +
- mbuf->data_off +
- push_len;
- ebuf->len = seg_len - push_len;
- ebuf++;
- tx_info->num_of_bufs++;
- }
- total_length += mbuf->data_len;
+ ena_tx_map_mbuf(tx_ring, tx_info, mbuf, &push_header, &header_len);
- while ((mbuf = mbuf->next) != NULL) {
- seg_len = mbuf->data_len;
+ ena_tx_ctx.ena_bufs = tx_info->bufs;
+ ena_tx_ctx.push_header = push_header;
+ ena_tx_ctx.num_bufs = tx_info->num_of_bufs;
+ ena_tx_ctx.req_id = req_id;
+ ena_tx_ctx.header_len = header_len;
- /* Skip mbufs if whole data is pushed as a header */
- if (unlikely(delta > seg_len)) {
- delta -= seg_len;
- continue;
- }
+ /* Set Tx offloads flags, if applicable */
+ ena_tx_mbuf_prepare(mbuf, &ena_tx_ctx, tx_ring->offloads,
+ tx_ring->disable_meta_caching);
- ebuf->paddr = mbuf->buf_iova + mbuf->data_off + delta;
- ebuf->len = seg_len - delta;
- total_length += ebuf->len;
- ebuf++;
- tx_info->num_of_bufs++;
+ if (unlikely(ena_com_is_doorbell_needed(tx_ring->ena_com_io_sq,
+ &ena_tx_ctx))) {
+ PMD_DRV_LOG(DEBUG,
+ "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n",
+ tx_ring->id);
+ ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+ }
- delta = 0;
- }
+ /* prepare the packet's descriptors to dma engine */
+ rc = ena_com_prepare_tx(tx_ring->ena_com_io_sq, &ena_tx_ctx,
+ &nb_hw_desc);
+ if (unlikely(rc)) {
+ ++tx_ring->tx_stats.prepare_ctx_err;
+ return rc;
+ }
- ena_tx_ctx.num_bufs = tx_info->num_of_bufs;
+ tx_info->tx_descs = nb_hw_desc;
- if (ena_com_is_doorbell_needed(tx_ring->ena_com_io_sq,
- &ena_tx_ctx)) {
- PMD_DRV_LOG(DEBUG, "llq tx max burst size of queue %d"
- " achieved, writing doorbell to send burst\n",
- tx_ring->id);
- ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
- }
+ tx_ring->tx_stats.cnt++;
+ tx_ring->tx_stats.bytes += mbuf->pkt_len;
- /* prepare the packet's descriptors to dma engine */
- rc = ena_com_prepare_tx(tx_ring->ena_com_io_sq,
- &ena_tx_ctx, &nb_hw_desc);
- if (unlikely(rc)) {
- ++tx_ring->tx_stats.prepare_ctx_err;
- break;
- }
- tx_info->tx_descs = nb_hw_desc;
+ tx_ring->next_to_use = ENA_IDX_NEXT_MASKED(next_to_use,
+ tx_ring->size_mask);
- next_to_use++;
- tx_ring->tx_stats.cnt++;
- tx_ring->tx_stats.bytes += total_length;
- }
- tx_ring->tx_stats.available_desc =
- ena_com_free_q_entries(tx_ring->ena_com_io_sq);
+ return 0;
+}
- /* If there are ready packets to be xmitted... */
- if (sent_idx > 0) {
- /* ...let HW do its best :-) */
- ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
- tx_ring->tx_stats.doorbells++;
- tx_ring->next_to_use = next_to_use;
- }
+static void ena_tx_cleanup(struct ena_ring *tx_ring)
+{
+ unsigned int cleanup_budget;
+ unsigned int total_tx_descs = 0;
+ uint16_t next_to_clean = tx_ring->next_to_clean;
- /* Clear complete packets */
- while (ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq, &req_id) >= 0) {
- rc = validate_tx_req_id(tx_ring, req_id);
- if (rc)
+ cleanup_budget = RTE_MIN(tx_ring->ring_size / ENA_REFILL_THRESH_DIVIDER,
+ (unsigned int)ENA_REFILL_THRESH_PACKET);
+
+ while (likely(total_tx_descs < cleanup_budget)) {
+ struct rte_mbuf *mbuf;
+ struct ena_tx_buffer *tx_info;
+ uint16_t req_id;
+
+ if (ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq, &req_id) != 0)
+ break;
+
+ if (unlikely(validate_tx_req_id(tx_ring, req_id) != 0))
break;
/* Get Tx info & store how many descs were processed */
tx_info = &tx_ring->tx_buffer_info[req_id];
- total_tx_descs += tx_info->tx_descs;
- /* Free whole mbuf chain */
mbuf = tx_info->mbuf;
rte_pktmbuf_free(mbuf);
+
tx_info->mbuf = NULL;
+ tx_ring->empty_tx_reqs[next_to_clean] = req_id;
- /* Put back descriptor to the ring for reuse */
- tx_ring->empty_tx_reqs[next_to_clean & ring_mask] = req_id;
- next_to_clean++;
+ total_tx_descs += tx_info->tx_descs;
- /* If too many descs to clean, leave it for another run */
- if (unlikely(total_tx_descs > ENA_RING_DESCS_RATIO(ring_size)))
- break;
+ /* Put back descriptor to the ring for reuse */
+ next_to_clean = ENA_IDX_NEXT_MASKED(next_to_clean,
+ tx_ring->size_mask);
}
- tx_ring->tx_stats.available_desc =
- ena_com_free_q_entries(tx_ring->ena_com_io_sq);
- if (total_tx_descs > 0) {
+ if (likely(total_tx_descs > 0)) {
/* acknowledge completion of sent packets */
tx_ring->next_to_clean = next_to_clean;
ena_com_comp_ack(tx_ring->ena_com_io_sq, total_tx_descs);
ena_com_update_dev_comp_head(tx_ring->ena_com_io_cq);
}
+}
+static uint16_t eth_ena_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ struct ena_ring *tx_ring = (struct ena_ring *)(tx_queue);
+ uint16_t sent_idx = 0;
+
+ /* Check adapter state */
+ if (unlikely(tx_ring->adapter->state != ENA_ADAPTER_STATE_RUNNING)) {
+ PMD_DRV_LOG(ALERT,
+ "Trying to xmit pkts while device is NOT running\n");
+ return 0;
+ }
+
+ nb_pkts = RTE_MIN(ena_com_free_q_entries(tx_ring->ena_com_io_sq),
+ nb_pkts);
+
+ for (sent_idx = 0; sent_idx < nb_pkts; sent_idx++) {
+ if (ena_xmit_mbuf(tx_ring, tx_pkts[sent_idx]))
+ break;
+
+ rte_prefetch0(tx_pkts[ENA_IDX_ADD_MASKED(sent_idx, 4,
+ tx_ring->size_mask)]);
+ }
+
+ tx_ring->tx_stats.available_desc =
+ ena_com_free_q_entries(tx_ring->ena_com_io_sq);
+
+ /* If there are ready packets to be xmitted... */
+ if (sent_idx > 0) {
+ /* ...let HW do its best :-) */
+ ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+ tx_ring->tx_stats.doorbells++;
+ }
+
+ ena_tx_cleanup(tx_ring);
+
+ tx_ring->tx_stats.available_desc =
+ ena_com_free_q_entries(tx_ring->ena_com_io_sq);
tx_ring->tx_stats.tx_poll++;
return sent_idx;
}
+int ena_copy_eni_stats(struct ena_adapter *adapter)
+{
+ struct ena_admin_eni_stats admin_eni_stats;
+ int rc;
+
+ rte_spinlock_lock(&adapter->admin_lock);
+ rc = ena_com_get_eni_stats(&adapter->ena_dev, &admin_eni_stats);
+ rte_spinlock_unlock(&adapter->admin_lock);
+ if (rc != 0) {
+ if (rc == ENA_COM_UNSUPPORTED) {
+ PMD_DRV_LOG(DEBUG,
+ "Retrieving ENI metrics is not supported.\n");
+ } else {
+ PMD_DRV_LOG(WARNING,
+ "Failed to get ENI metrics: %d\n", rc);
+ }
+ return rc;
+ }
+
+ rte_memcpy(&adapter->eni_stats, &admin_eni_stats,
+ sizeof(struct ena_stats_eni));
+
+ return 0;
+}
+
/**
* DPDK callback to retrieve names of extended device statistics
*
strcpy(xstats_names[count].name,
ena_stats_global_strings[stat].name);
+ for (stat = 0; stat < ENA_STATS_ARRAY_ENI; stat++, count++)
+ strcpy(xstats_names[count].name,
+ ena_stats_eni_strings[stat].name);
+
for (stat = 0; stat < ENA_STATS_ARRAY_RX; stat++)
for (i = 0; i < dev->data->nb_rx_queues; i++, count++)
snprintf(xstats_names[count].name,
((char *)stats_begin + stat_offset));
}
+ /* Even if the function below fails, we should copy previous (or initial
+ * values) to keep structure of rte_eth_xstat consistent.
+ */
+ ena_copy_eni_stats(adapter);
+ for (stat = 0; stat < ENA_STATS_ARRAY_ENI; stat++, count++) {
+ stat_offset = ena_stats_eni_strings[stat].stat_offset;
+ stats_begin = &adapter->eni_stats;
+
+ xstats[count].id = count;
+ xstats[count].value = *((uint64_t *)
+ ((char *)stats_begin + stat_offset));
+ }
+
for (stat = 0; stat < ENA_STATS_ARRAY_RX; stat++) {
for (i = 0; i < dev->data->nb_rx_queues; i++, count++) {
stat_offset = ena_stats_rx_strings[stat].stat_offset;
unsigned int i;
int qid;
int valid = 0;
+ bool was_eni_copied = false;
+
for (i = 0; i < n; ++i) {
id = ids[i];
/* Check if id belongs to global statistics */
continue;
}
- /* Check if id belongs to rx queue statistics */
+ /* Check if id belongs to ENI statistics */
id -= ENA_STATS_ARRAY_GLOBAL;
+ if (id < ENA_STATS_ARRAY_ENI) {
+ /* Avoid reading ENI stats multiple times in a single
+ * function call, as it requires communication with the
+ * admin queue.
+ */
+ if (!was_eni_copied) {
+ was_eni_copied = true;
+ ena_copy_eni_stats(adapter);
+ }
+ values[i] = *((uint64_t *)&adapter->eni_stats + id);
+ ++valid;
+ continue;
+ }
+
+ /* Check if id belongs to rx queue statistics */
+ id -= ENA_STATS_ARRAY_ENI;
rx_entries = ENA_STATS_ARRAY_RX * dev->data->nb_rx_queues;
if (id < rx_entries) {
qid = id % dev->data->nb_rx_queues;
RTE_PMD_REGISTER_PCI_TABLE(net_ena, pci_id_ena_map);
RTE_PMD_REGISTER_KMOD_DEP(net_ena, "* igb_uio | uio_pci_generic | vfio-pci");
RTE_PMD_REGISTER_PARAM_STRING(net_ena, ENA_DEVARG_LARGE_LLQ_HDR "=<0|1>");
-
-RTE_INIT(ena_init_log)
-{
- ena_logtype_init = rte_log_register("pmd.net.ena.init");
- if (ena_logtype_init >= 0)
- rte_log_set_level(ena_logtype_init, RTE_LOG_NOTICE);
- ena_logtype_driver = rte_log_register("pmd.net.ena.driver");
- if (ena_logtype_driver >= 0)
- rte_log_set_level(ena_logtype_driver, RTE_LOG_NOTICE);
-
+RTE_LOG_REGISTER(ena_logtype_init, pmd.net.ena.init, NOTICE);
+RTE_LOG_REGISTER(ena_logtype_driver, pmd.net.ena.driver, NOTICE);
#ifdef RTE_LIBRTE_ENA_DEBUG_RX
- ena_logtype_rx = rte_log_register("pmd.net.ena.rx");
- if (ena_logtype_rx >= 0)
- rte_log_set_level(ena_logtype_rx, RTE_LOG_NOTICE);
+RTE_LOG_REGISTER(ena_logtype_rx, pmd.net.ena.rx, NOTICE);
#endif
-
#ifdef RTE_LIBRTE_ENA_DEBUG_TX
- ena_logtype_tx = rte_log_register("pmd.net.ena.tx");
- if (ena_logtype_tx >= 0)
- rte_log_set_level(ena_logtype_tx, RTE_LOG_NOTICE);
+RTE_LOG_REGISTER(ena_logtype_tx, pmd.net.ena.tx, NOTICE);
#endif
-
#ifdef RTE_LIBRTE_ENA_DEBUG_TX_FREE
- ena_logtype_tx_free = rte_log_register("pmd.net.ena.tx_free");
- if (ena_logtype_tx_free >= 0)
- rte_log_set_level(ena_logtype_tx_free, RTE_LOG_NOTICE);
+RTE_LOG_REGISTER(ena_logtype_tx_free, pmd.net.ena.tx_free, NOTICE);
#endif
-
#ifdef RTE_LIBRTE_ENA_COM_DEBUG
- ena_logtype_com = rte_log_register("pmd.net.ena.com");
- if (ena_logtype_com >= 0)
- rte_log_set_level(ena_logtype_com, RTE_LOG_NOTICE);
+RTE_LOG_REGISTER(ena_logtype_com, pmd.net.ena.com, NOTICE);
#endif
-}
/******************************************************************************
******************************** AENQ Handlers *******************************
adapter->link_status = status;
ena_link_update(eth_dev, 0);
- _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
+ rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
}
static void ena_notification(void *data,
git.droids-corp.org / dpdk.git / blobdiff