gianfar: Use Single-Queue polling for "fsl,etsec2"
For the "fsl,etsec2" compatible models the driver currently
supports 8 Tx and Rx DMA rings (aka HW queues). However, there
are only 2 pairs of Rx/Tx interrupt lines, as these controllers
are integrated in low power SoCs with 2 CPUs at most. As a result,
there are at most 2 NAPI instances that have to service multiple
Tx and Rx queues for these devices. This complicates the NAPI
polling routine having to iterate over the mutiple Rx/Tx queues
hooked to the same interrupt lines. And there's also an overhead
at HW level, as the controller needs to service all the 8 Tx rings
in a round robin manner. The combined overhead shows up for multi
parallel Tx flows transmitted by the kernel stack, when the driver
usually starts returning NETDEV_TX_BUSY leading to NETDEV WATCHDOG
Tx timeout triggering if the Tx path is congested for too long.
As an alternative, this patch makes the driver support only one
Tx/Rx DMA ring per NAPI instance (per interrupt group or pair
of Tx/Rx interrupt lines) by default. The simplified single queue
polling routine (gfar_poll_sq) will be the default napi poll routine
for the etsec2 devices too. Some adjustments needed to be made to
link the Tx/Rx HW queues with each NAPI instance (2 in this case).
The gfar_poll_sq() is already successfully used by older SQ_SG_MODE
(single interrupt group) controllers.
This patch fixes Tx timeout triggering under heavy Tx traffic load
(i.e. iperf -c -P 8) for the "fsl,etsec2" (currently the only
MQ_MG_MODE devices). There's also a significant memory footprint
reduction by supporting 2 Rx/Tx DMA rings (at most), instead of 8,
for these devices.
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 1aa2d55..28effbe 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -363,7 +363,10 @@
if (priv->rx_filer_enable) {
rctrl |= RCTRL_FILREN;
/* Program the RIR0 reg with the required distribution */
- gfar_write(®s->rir0, DEFAULT_RIR0);
+ if (priv->poll_mode == GFAR_SQ_POLLING)
+ gfar_write(®s->rir0, DEFAULT_2RXQ_RIR0);
+ else /* GFAR_MQ_POLLING */
+ gfar_write(®s->rir0, DEFAULT_8RXQ_RIR0);
}
/* Restore PROMISC mode */
@@ -636,7 +639,6 @@
struct gfar_private *priv, const char *model)
{
struct gfar_priv_grp *grp = &priv->gfargrp[priv->num_grps];
- u32 *queue_mask;
int i;
for (i = 0; i < GFAR_NUM_IRQS; i++) {
@@ -665,12 +667,20 @@
grp->priv = priv;
spin_lock_init(&grp->grplock);
if (priv->mode == MQ_MG_MODE) {
- queue_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
- grp->rx_bit_map = queue_mask ?
- *queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
- queue_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
- grp->tx_bit_map = queue_mask ?
- *queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ u32 *rxq_mask, *txq_mask;
+ rxq_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
+ txq_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
+
+ if (priv->poll_mode == GFAR_SQ_POLLING) {
+ /* One Q per interrupt group: Q0 to G0, Q1 to G1 */
+ grp->rx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+ grp->tx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+ } else { /* GFAR_MQ_POLLING */
+ grp->rx_bit_map = rxq_mask ?
+ *rxq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ grp->tx_bit_map = txq_mask ?
+ *txq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ }
} else {
grp->rx_bit_map = 0xFF;
grp->tx_bit_map = 0xFF;
@@ -686,6 +696,8 @@
* also assign queues to groups
*/
for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) {
+ if (!grp->rx_queue)
+ grp->rx_queue = priv->rx_queue[i];
grp->num_rx_queues++;
grp->rstat |= (RSTAT_CLEAR_RHALT >> i);
priv->rqueue |= ((RQUEUE_EN0 | RQUEUE_EX0) >> i);
@@ -693,6 +705,8 @@
}
for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) {
+ if (!grp->tx_queue)
+ grp->tx_queue = priv->tx_queue[i];
grp->num_tx_queues++;
grp->tstat |= (TSTAT_CLEAR_THALT >> i);
priv->tqueue |= (TQUEUE_EN0 >> i);
@@ -723,9 +737,22 @@
if (!np || !of_device_is_available(np))
return -ENODEV;
- /* parse the num of tx and rx queues */
+ /* parse the num of HW tx and rx queues */
tx_queues = (u32 *)of_get_property(np, "fsl,num_tx_queues", NULL);
- num_tx_qs = tx_queues ? *tx_queues : 1;
+ rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
+
+ if (priv->mode == SQ_SG_MODE) {
+ num_tx_qs = 1;
+ num_rx_qs = 1;
+ } else { /* MQ_MG_MODE */
+ if (priv->poll_mode == GFAR_SQ_POLLING) {
+ num_tx_qs = 2; /* one q per int group */
+ num_rx_qs = 2; /* one q per int group */
+ } else { /* GFAR_MQ_POLLING */
+ num_tx_qs = tx_queues ? *tx_queues : 1;
+ num_rx_qs = rx_queues ? *rx_queues : 1;
+ }
+ }
if (num_tx_qs > MAX_TX_QS) {
pr_err("num_tx_qs(=%d) greater than MAX_TX_QS(=%d)\n",
@@ -734,9 +761,6 @@
return -EINVAL;
}
- rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
- num_rx_qs = rx_queues ? *rx_queues : 1;
-
if (num_rx_qs > MAX_RX_QS) {
pr_err("num_rx_qs(=%d) greater than MAX_RX_QS(=%d)\n",
num_rx_qs, MAX_RX_QS);
@@ -777,6 +801,7 @@
/* Parse and initialize group specific information */
if (of_device_is_compatible(np, "fsl,etsec2")) {
priv->mode = MQ_MG_MODE;
+ priv->poll_mode = GFAR_SQ_POLLING;
for_each_child_of_node(np, child) {
err = gfar_parse_group(child, priv, model);
if (err)
@@ -784,6 +809,7 @@
}
} else {
priv->mode = SQ_SG_MODE;
+ priv->poll_mode = GFAR_SQ_POLLING;
err = gfar_parse_group(np, priv, model);
if (err)
goto err_grp_init;
@@ -1263,13 +1289,13 @@
dev->ethtool_ops = &gfar_ethtool_ops;
/* Register for napi ...We are registering NAPI for each grp */
- if (priv->mode == SQ_SG_MODE) {
- netif_napi_add(dev, &priv->gfargrp[0].napi_rx, gfar_poll_rx_sq,
- GFAR_DEV_WEIGHT);
- netif_napi_add(dev, &priv->gfargrp[0].napi_tx, gfar_poll_tx_sq,
- 2);
- } else {
- for (i = 0; i < priv->num_grps; i++) {
+ for (i = 0; i < priv->num_grps; i++) {
+ if (priv->poll_mode == GFAR_SQ_POLLING) {
+ netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
+ gfar_poll_rx_sq, GFAR_DEV_WEIGHT);
+ netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
+ gfar_poll_tx_sq, 2);
+ } else {
netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
gfar_poll_rx, GFAR_DEV_WEIGHT);
netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
@@ -2819,7 +2845,7 @@
struct gfar_priv_grp *gfargrp =
container_of(napi, struct gfar_priv_grp, napi_rx);
struct gfar __iomem *regs = gfargrp->regs;
- struct gfar_priv_rx_q *rx_queue = gfargrp->priv->rx_queue[0];
+ struct gfar_priv_rx_q *rx_queue = gfargrp->rx_queue;
int work_done = 0;
/* Clear IEVENT, so interrupts aren't called again
@@ -2850,7 +2876,7 @@
struct gfar_priv_grp *gfargrp =
container_of(napi, struct gfar_priv_grp, napi_tx);
struct gfar __iomem *regs = gfargrp->regs;
- struct gfar_priv_tx_q *tx_queue = gfargrp->priv->tx_queue[0];
+ struct gfar_priv_tx_q *tx_queue = gfargrp->tx_queue;
u32 imask;
/* Clear IEVENT, so interrupts aren't called again