* [PATCH net-next 1/2] net: mvneta: add xmit_more support
2016-09-13 7:00 [PATCH net-next 0/2] mvneta xmit_more and bql support Marcin Wojtas
@ 2016-09-13 7:00 ` Marcin Wojtas
2016-09-13 14:33 ` Eric Dumazet
2016-09-13 7:00 ` [PATCH net-next 2/2] net: mvneta: add BQL support Marcin Wojtas
1 sibling, 1 reply; 5+ messages in thread
From: Marcin Wojtas @ 2016-09-13 7:00 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, netdev
Cc: davem, linux, sebastian.hesselbarth, andrew, jason,
thomas.petazzoni, gregory.clement, nadavh, alior, simon.guinot,
nitroshift, mw, jaz
From: Simon Guinot <simon.guinot@sequanux.org>
Basing on xmit_more flag of the skb, TX descriptors can be concatenated
before flushing. This commit delay Tx descriptor flush if the queue is
running and if there is more skb's to send.
Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
---
drivers/net/ethernet/marvell/mvneta.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index d41c28d..b9dccea 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -512,6 +512,7 @@ struct mvneta_tx_queue {
* descriptor ring
*/
int count;
+ int pending;
int tx_stop_threshold;
int tx_wake_threshold;
@@ -802,8 +803,9 @@ static void mvneta_txq_pend_desc_add(struct mvneta_port *pp,
/* Only 255 descriptors can be added at once ; Assume caller
* process TX desriptors in quanta less than 256
*/
- val = pend_desc;
+ val = pend_desc + txq->pending;
mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+ txq->pending = 0;
}
/* Get pointer to next TX descriptor to be processed (send) by HW */
@@ -2357,11 +2359,14 @@ out:
struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
txq->count += frags;
- mvneta_txq_pend_desc_add(pp, txq, frags);
-
if (txq->count >= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
+ if (!skb->xmit_more || netif_xmit_stopped(nq))
+ mvneta_txq_pend_desc_add(pp, txq, frags);
+ else
+ txq->pending += frags;
+
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += len;
--
1.8.3.1
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH net-next 2/2] net: mvneta: add BQL support
2016-09-13 7:00 [PATCH net-next 0/2] mvneta xmit_more and bql support Marcin Wojtas
2016-09-13 7:00 ` [PATCH net-next 1/2] net: mvneta: add xmit_more support Marcin Wojtas
@ 2016-09-13 7:00 ` Marcin Wojtas
1 sibling, 0 replies; 5+ messages in thread
From: Marcin Wojtas @ 2016-09-13 7:00 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, netdev
Cc: davem, linux, sebastian.hesselbarth, andrew, jason,
thomas.petazzoni, gregory.clement, nadavh, alior, simon.guinot,
nitroshift, mw, jaz
Tests showed that when whole bandwidth is consumed, the latency for
various kind of traffic can reach high values. With saturated
link (e.g. with iperf from target to host) simple ping could take
significant amount of time. BQL proved to improve this situation
when implemented in mvneta driver. Measurements of ping latency
for 3 link speeds:
Speed | Latency w/o BQL | Latency with BQL
10 | 7-14 ms | 3.5 ms
100 | 2-12 ms | 0.6 ms
1000 | often timeout | up to 2ms
Decreasing latency as above result in sligt performance cost - 4kpps
(-1.4%) when pushing 64B packets via two bridged interfaces of Armada 38x.
For 1500B packets in the same setup, the mpstat tool showed +8% of
CPU occupation (default affinity, second CPU idle). Even though this
cost seems reasonable to take, considering other improvements.
This commit adds byte queue limit mechanism for the mvneta driver.
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
---
drivers/net/ethernet/marvell/mvneta.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index b9dccea..bb5df35 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1719,8 +1719,10 @@ static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
/* Free tx queue skbuffs */
static void mvneta_txq_bufs_free(struct mvneta_port *pp,
- struct mvneta_tx_queue *txq, int num)
+ struct mvneta_tx_queue *txq, int num,
+ struct netdev_queue *nq)
{
+ unsigned int bytes_compl = 0, pkts_compl = 0;
int i;
for (i = 0; i < num; i++) {
@@ -1728,6 +1730,11 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
txq->txq_get_index;
struct sk_buff *skb = txq->tx_skb[txq->txq_get_index];
+ if (skb) {
+ bytes_compl += skb->len;
+ pkts_compl++;
+ }
+
mvneta_txq_inc_get(txq);
if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
@@ -1738,6 +1745,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
continue;
dev_kfree_skb_any(skb);
}
+
+ netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
}
/* Handle end of transmission */
@@ -1751,7 +1760,7 @@ static void mvneta_txq_done(struct mvneta_port *pp,
if (!tx_done)
return;
- mvneta_txq_bufs_free(pp, txq, tx_done);
+ mvneta_txq_bufs_free(pp, txq, tx_done, nq);
txq->count -= tx_done;
@@ -2358,6 +2367,8 @@ out:
struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
+ netdev_tx_sent_queue(nq, len);
+
txq->count += frags;
if (txq->count >= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
@@ -2385,9 +2396,10 @@ static void mvneta_txq_done_force(struct mvneta_port *pp,
struct mvneta_tx_queue *txq)
{
+ struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
int tx_done = txq->count;
- mvneta_txq_bufs_free(pp, txq, tx_done);
+ mvneta_txq_bufs_free(pp, txq, tx_done, nq);
/* reset txq */
txq->count = 0;
@@ -2884,6 +2896,8 @@ static int mvneta_txq_init(struct mvneta_port *pp,
static void mvneta_txq_deinit(struct mvneta_port *pp,
struct mvneta_tx_queue *txq)
{
+ struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
+
kfree(txq->tx_skb);
if (txq->tso_hdrs)
@@ -2895,6 +2909,8 @@ static void mvneta_txq_deinit(struct mvneta_port *pp,
txq->size * MVNETA_DESC_ALIGNED_SIZE,
txq->descs, txq->descs_phys);
+ netdev_tx_reset_queue(nq);
+
txq->descs = NULL;
txq->last_desc = 0;
txq->next_desc_to_proc = 0;
--
1.8.3.1
^ permalink raw reply related [flat|nested] 5+ messages in thread