net/igb: free consumed Tx buffers on demand

Add support to the e1000 igb driver for the new API to force free
consumed buffers on Tx ring. This API is independent of the tx_rs_thresh
setting. With this API, buffers should be free even if tx_rs_thresh is
not met.

e1000 igb driver does not implement a tx_rs_thresh to free mbufs, it
frees a slot in the ring as needed. However, it could be implemented at
some future date.

Signed-off-by: Billy McFall <bmcfall@redhat.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>

diff --git a/doc/guides/nics/features/e1000.ini b/doc/guides/nics/features/e1000.ini
index 7f6d55c..3aed7d7 100644 (file)
--- a/doc/guides/nics/features/e1000.ini
+++ b/doc/guides/nics/features/e1000.ini
@@ -7,6 +7,7 @@
 Link status          = Y
 Link status event    = Y
 Rx interrupt         = Y
+Free Tx mbuf on demand = Y
 MTU update           = Y
 Jumbo frame          = Y
 Scattered Rx         = Y

diff --git a/drivers/net/e1000/e1000_ethdev.h b/drivers/net/e1000/e1000_ethdev.h
index 81a6dbb..39b2f43 100644 (file)
--- a/drivers/net/e1000/e1000_ethdev.h
+++ b/drivers/net/e1000/e1000_ethdev.h
@@ -315,6 +315,8 @@ int eth_igb_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id,
                uint16_t nb_tx_desc, unsigned int socket_id,
                const struct rte_eth_txconf *tx_conf);
 
+int eth_igb_tx_done_cleanup(void *txq, uint32_t free_cnt);
+
 int eth_igb_rx_init(struct rte_eth_dev *dev);
 
 void eth_igb_tx_init(struct rte_eth_dev *dev);

diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index a112b38..71d05a9 100644 (file)
--- a/drivers/net/e1000/igb_ethdev.c
+++ b/drivers/net/e1000/igb_ethdev.c
@@ -408,6 +408,7 @@ static const struct eth_dev_ops eth_igb_ops = {
        .rx_descriptor_done   = eth_igb_rx_descriptor_done,
        .tx_queue_setup       = eth_igb_tx_queue_setup,
        .tx_queue_release     = eth_igb_tx_queue_release,
+       .tx_done_cleanup      = eth_igb_tx_done_cleanup,
        .dev_led_on           = eth_igb_led_on,
        .dev_led_off          = eth_igb_led_off,
        .flow_ctrl_get        = eth_igb_flow_ctrl_get,

diff --git a/drivers/net/e1000/igb_rxtx.c b/drivers/net/e1000/igb_rxtx.c
index 1bb4d85..cba3704 100644 (file)
--- a/drivers/net/e1000/igb_rxtx.c
+++ b/drivers/net/e1000/igb_rxtx.c
@@ -1283,6 +1283,132 @@ eth_igb_tx_queue_release(void *txq)
        igb_tx_queue_release(txq);
 }
 
+static int
+igb_tx_done_cleanup(struct igb_tx_queue *txq, uint32_t free_cnt)
+{
+       struct igb_tx_entry *sw_ring;
+       volatile union e1000_adv_tx_desc *txr;
+       uint16_t tx_first; /* First segment analyzed. */
+       uint16_t tx_id;    /* Current segment being processed. */
+       uint16_t tx_last;  /* Last segment in the current packet. */
+       uint16_t tx_next;  /* First segment of the next packet. */
+       int count;
+
+       if (txq != NULL) {
+               count = 0;
+               sw_ring = txq->sw_ring;
+               txr = txq->tx_ring;
+
+               /*
+                * tx_tail is the last sent packet on the sw_ring. Goto the end
+                * of that packet (the last segment in the packet chain) and
+                * then the next segment will be the start of the oldest segment
+                * in the sw_ring. This is the first packet that will be
+                * attempted to be freed.
+                */
+
+               /* Get last segment in most recently added packet. */
+               tx_first = sw_ring[txq->tx_tail].last_id;
+
+               /* Get the next segment, which is the oldest segment in ring. */
+               tx_first = sw_ring[tx_first].next_id;
+
+               /* Set the current index to the first. */
+               tx_id = tx_first;
+
+               /*
+                * Loop through each packet. For each packet, verify that an
+                * mbuf exists and that the last segment is free. If so, free
+                * it and move on.
+                */
+               while (1) {
+                       tx_last = sw_ring[tx_id].last_id;
+
+                       if (sw_ring[tx_last].mbuf) {
+                               if (txr[tx_last].wb.status &
+                                               E1000_TXD_STAT_DD) {
+                                       /*
+                                        * Increment the number of packets
+                                        * freed.
+                                        */
+                                       count++;
+
+                                       /* Get the start of the next packet. */
+                                       tx_next = sw_ring[tx_last].next_id;
+
+                                       /*
+                                        * Loop through all segments in a
+                                        * packet.
+                                        */
+                                       do {
+                                               rte_pktmbuf_free_seg(sw_ring[tx_id].mbuf);
+                                               sw_ring[tx_id].mbuf = NULL;
+                                               sw_ring[tx_id].last_id = tx_id;
+
+                                               /* Move to next segemnt. */
+                                               tx_id = sw_ring[tx_id].next_id;
+
+                                       } while (tx_id != tx_next);
+
+                                       if (unlikely(count == (int)free_cnt))
+                                               break;
+                               } else
+                                       /*
+                                        * mbuf still in use, nothing left to
+                                        * free.
+                                        */
+                                       break;
+                       } else {
+                               /*
+                                * There are multiple reasons to be here:
+                                * 1) All the packets on the ring have been
+                                *    freed - tx_id is equal to tx_first
+                                *    and some packets have been freed.
+                                *    - Done, exit
+                                * 2) Interfaces has not sent a rings worth of
+                                *    packets yet, so the segment after tail is
+                                *    still empty. Or a previous call to this
+                                *    function freed some of the segments but
+                                *    not all so there is a hole in the list.
+                                *    Hopefully this is a rare case.
+                                *    - Walk the list and find the next mbuf. If
+                                *      there isn't one, then done.
+                                */
+                               if (likely((tx_id == tx_first) && (count != 0)))
+                                       break;
+
+                               /*
+                                * Walk the list and find the next mbuf, if any.
+                                */
+                               do {
+                                       /* Move to next segemnt. */
+                                       tx_id = sw_ring[tx_id].next_id;
+
+                                       if (sw_ring[tx_id].mbuf)
+                                               break;
+
+                               } while (tx_id != tx_first);
+
+                               /*
+                                * Determine why previous loop bailed. If there
+                                * is not an mbuf, done.
+                                */
+                               if (sw_ring[tx_id].mbuf == NULL)
+                                       break;
+                       }
+               }
+       } else
+               count = -ENODEV;
+
+       return count;
+}
+
+int
+eth_igb_tx_done_cleanup(void *txq, uint32_t free_cnt)
+{
+       return igb_tx_done_cleanup(txq, free_cnt);
+}
+
 static void
 igb_reset_tx_queue_stat(struct igb_tx_queue *txq)
 {