[Patch net-next v2 0/4] net: fec: add interrupt coalescence

[Patch net-next v2 0/4] net: fec: add interrupt coalescence

[Frank.Li]

From: Frank Li <Frank.Li@freescale.com>

improve error handle when parse queue number.
add interrupt coalescence feature.

Change from v1 to v2
 - fix indention
 - use errata number instead of TKT

Frank Li (1):
  net: fec: refine error handle of parser queue number from DT

Fugang Duan (3):
  net: fec: add interrupt coalescence feature support
  net:fec: increase DMA queue number
  net: fec: Workaround for imx6sx enet tx hang when enable three queues

 drivers/net/ethernet/freescale/fec.h      |  16 +++-
 drivers/net/ethernet/freescale/fec_main.c | 144 ++++++++++++++++++++++++++++--
 2 files changed, 150 insertions(+), 10 deletions(-)

-- 
1.9.1

[Patch net-next v2 1/4] net: fec: refine error handle of parser queue number from DT

[Frank.Li]

From: Frank Li <Frank.Li@freescale.com>

check tx and rx queue seperately.
fix typo, "Invalidate" and "fail".
change pr_err to pr_warn.

Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
 drivers/net/ethernet/freescale/fec_main.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8f8e55e..d209d2e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2890,23 +2890,23 @@ fec_enet_get_queue_num(struct platform_device *pdev, int *num_tx, int *num_rx)
 
 	/* parse the num of tx and rx queues */
 	err = of_property_read_u32(np, "fsl,num-tx-queues", num_tx);
-	err |= of_property_read_u32(np, "fsl,num-rx-queues", num_rx);
-	if (err) {
+	if (err)
 		*num_tx = 1;
+
+	err = of_property_read_u32(np, "fsl,num-rx-queues", num_rx);
+	if (err)
 		*num_rx = 1;
-		return;
-	}
 
 	if (*num_tx < 1 || *num_tx > FEC_ENET_MAX_TX_QS) {
-		dev_err(&pdev->dev, "Invalidate num_tx(=%d), fail back to 1\n",
-			*num_tx);
+		dev_warn(&pdev->dev, "Invalid num_tx(=%d), fall back to 1\n",
+			 *num_tx);
 		*num_tx = 1;
 		return;
 	}
 
 	if (*num_rx < 1 || *num_rx > FEC_ENET_MAX_RX_QS) {
-		dev_err(&pdev->dev, "Invalidate num_rx(=%d), fail back to 1\n",
-			*num_rx);
+		dev_warn(&pdev->dev, "Invalid num_rx(=%d), fall back to 1\n",
+			 *num_rx);
 		*num_rx = 1;
 		return;
 	}
@@ -2924,8 +2924,8 @@ fec_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	static int dev_id;
 	struct device_node *np = pdev->dev.of_node, *phy_node;
-	int num_tx_qs = 1;
-	int num_rx_qs = 1;
+	int num_tx_qs;
+	int num_rx_qs;
 
 	of_id = of_match_device(fec_dt_ids, &pdev->dev);
 	if (of_id)
-- 
1.9.1

[Patch net-next v2 2/4] net: fec: add interrupt coalescence feature support

[Frank.Li]

From: Fugang Duan <B38611@freescale.com>

i.MX6 SX support interrupt coalescence feature
By default, init the interrupt coalescing frame count threshold and
timer threshold.

Supply the ethtool interfaces as below for user tuning to improve
enet performance:
	rx_max_coalesced_frames
	rx_coalesce_usecs
	tx_max_coalesced_frames
	tx_coalesce_usecs

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
 drivers/net/ethernet/freescale/fec.h      |  14 ++++
 drivers/net/ethernet/freescale/fec_main.c | 110 ++++++++++++++++++++++++++++++
 2 files changed, 124 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index b7c7722..bd70811 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -335,6 +335,14 @@ struct bufdesc_ex {
 #define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER)
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
+/* ENET interrupt coalescing macro define */
+#define FEC_ITR_CLK_SEL		(0x1 << 30)
+#define FEC_ITR_EN		(0x1 << 31)
+#define FEC_ITR_ICFT(X)		((X & 0xFF) << 20)
+#define FEC_ITR_ICTT(X)		((X) & 0xFFFF)
+#define FEC_ITR_ICFT_DEFAULT	200  /* Set 200 frame count threshold */
+#define FEC_ITR_ICTT_DEFAULT	1000 /* Set 1000us timer threshold */
+
 #define FEC_VLAN_TAG_LEN       0x04
 #define FEC_ETHTYPE_LEN                0x02
 
@@ -446,6 +454,12 @@ struct fec_enet_private {
 
 	unsigned int tx_align;
 	unsigned int rx_align;
+
+	/* hw interrupt coalesce */
+	unsigned int rx_pkts_itr;
+	unsigned int rx_time_itr;
+	unsigned int tx_pkts_itr;
+	unsigned int tx_time_itr;
 };
 
 void fec_ptp_init(struct platform_device *pdev);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d209d2e..3a735ef 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -63,6 +63,7 @@
 #include "fec.h"
 
 static void set_multicast_list(struct net_device *ndev);
+static void fec_enet_itr_coal_init(struct net_device *ndev);
 
 #define DRIVER_NAME	"fec"
 
@@ -1095,6 +1096,10 @@ fec_restart(struct net_device *ndev)
 
 	/* Enable interrupts we wish to service */
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
+
+	/* Init the interrupt coalescing */
+	fec_enet_itr_coal_init(ndev);
+
 }
 
 static void
@@ -2234,12 +2239,117 @@ static int fec_enet_nway_reset(struct net_device *dev)
 	return genphy_restart_aneg(phydev);
 }
 
+/* ITR clock source is enet system clock (clk_ahb).
+ * TCTT unit is cycle_ns * 64 cycle
+ * So, the ICTT value = X us / (cycle_ns * 64)
+ */
+static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return us * (clk_get_rate(fep->clk_ahb) / 64000) / 1000;
+}
+
+/* Set threshold for interrupt coalescing */
+static void fec_enet_itr_coal_set(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	int rx_itr, tx_itr;
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return;
+
+	/* Must be greater than zero to avoid unpredictable behavior */
+	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
+	    !fep->tx_time_itr || !fep->tx_pkts_itr)
+		return;
+
+	/* Select enet system clock as Interrupt Coalescing
+	 * timer Clock Source
+	 */
+	rx_itr = FEC_ITR_CLK_SEL;
+	tx_itr = FEC_ITR_CLK_SEL;
+
+	/* set ICFT and ICTT */
+	rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
+	rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
+	tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
+	tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
+
+	rx_itr |= FEC_ITR_EN;
+	tx_itr |= FEC_ITR_EN;
+
+	writel(tx_itr, fep->hwp + FEC_TXIC0);
+	writel(rx_itr, fep->hwp + FEC_RXIC0);
+	writel(tx_itr, fep->hwp + FEC_TXIC1);
+	writel(rx_itr, fep->hwp + FEC_RXIC1);
+	writel(tx_itr, fep->hwp + FEC_TXIC2);
+	writel(rx_itr, fep->hwp + FEC_RXIC2);
+}
+
+static int
+fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return -EOPNOTSUPP;
+
+	ec->rx_coalesce_usecs = fep->rx_time_itr;
+	ec->rx_max_coalesced_frames = fep->rx_pkts_itr;
+
+	ec->tx_coalesce_usecs = fep->tx_time_itr;
+	ec->tx_max_coalesced_frames = fep->tx_pkts_itr;
+
+	return 0;
+}
+
+static int
+fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return -EOPNOTSUPP;
+
+	fep->rx_time_itr = ec->rx_coalesce_usecs;
+	fep->rx_pkts_itr = ec->rx_max_coalesced_frames;
+
+	fep->tx_time_itr = ec->tx_coalesce_usecs;
+	fep->tx_pkts_itr = ec->tx_max_coalesced_frames;
+
+	fec_enet_itr_coal_set(ndev);
+
+	return 0;
+}
+
+static void fec_enet_itr_coal_init(struct net_device *ndev)
+{
+	struct ethtool_coalesce ec;
+
+	ec.rx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
+	ec.rx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
+
+	ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
+	ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
+
+	fec_enet_set_coalesce(ndev, &ec);
+}
+
 static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_settings		= fec_enet_get_settings,
 	.set_settings		= fec_enet_set_settings,
 	.get_drvinfo		= fec_enet_get_drvinfo,
 	.nway_reset		= fec_enet_nway_reset,
 	.get_link		= ethtool_op_get_link,
+	.get_coalesce		= fec_enet_get_coalesce,
+	.set_coalesce		= fec_enet_set_coalesce,
 #ifndef CONFIG_M5272
 	.get_pauseparam		= fec_enet_get_pauseparam,
 	.set_pauseparam		= fec_enet_set_pauseparam,
-- 
1.9.1

Re: [Patch net-next v2 2/4] net: fec: add interrupt coalescence feature support

[David Miller]

From: <Frank.Li@freescale.com>
Date: Wed, 17 Sep 2014 01:58:08 +0800

> +/* ENET interrupt coalescing macro define */
> +#define FEC_ITR_CLK_SEL		(0x1 << 30)
> +#define FEC_ITR_EN		(0x1 << 31)
> +#define FEC_ITR_ICFT(X)		((X & 0xFF) << 20)
> +#define FEC_ITR_ICTT(X)		((X) & 0xFFFF)
> +#define FEC_ITR_ICFT_DEFAULT	200  /* Set 200 frame count threshold */
> +#define FEC_ITR_ICTT_DEFAULT	1000 /* Set 1000us timer threshold */
 ...
> +static int
> +fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)

The size of these fields in the register determines the limitations of
the various parameters that this chip can support.

Therefore you must validate the user's request and signal an error if
the user asks for coalescing parameters that don't fit into those
fields.

[Patch net-next v2 3/4] net:fec: increase DMA queue number

[Frank.Li]

From: Fugang Duan <B38611@freescale.com>

when enable interrupt coalesce, 8 BD is not enough.

Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
 drivers/net/ethernet/freescale/fec.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index bd70811..2814610 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -296,7 +296,7 @@ struct bufdesc_ex {
  * the skbuffer directly.
  */
 
-#define FEC_ENET_RX_PAGES	8
+#define FEC_ENET_RX_PAGES	256
 #define FEC_ENET_RX_FRSIZE	2048
 #define FEC_ENET_RX_FRPPG	(PAGE_SIZE / FEC_ENET_RX_FRSIZE)
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
-- 
1.9.1

[Patch net-next v2 4/4] net: fec: Workaround for imx6sx enet tx hang when enable three queues

[Frank.Li]

From: Fugang Duan <B38611@freescale.com>

When enable three queues on imx6sx enet, and then do tx performance
test with iperf tool, after some time running, tx hang.

Found that:
	If uDMA is running, software set TDAR may cause tx hang.
	If uDMA is in idle, software set TDAR don't cause tx hang.

There is a TDAR race condition for mutliQ when the software sets TDAR
and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
This will cause the udma_tx and udma_tx_arbiter state machines to hang.
The issue exist at i.MX6SX enet IP.

So, the Workaround is checking TDAR status four time, if TDAR cleared by
hardware and then write TDAR, otherwise don't set TDAR.

The patch is only one Workaround for the issue TKT210582.

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
 drivers/net/ethernet/freescale/fec_main.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3a735ef..cc8c934 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -111,6 +111,12 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
  *   independent rings
  */
 #define FEC_QUIRK_HAS_AVB		(1 << 8)
+/* There is a TDAR race condition for mutliQ when the software sets TDAR
+ * and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
+ * This will cause the udma_tx and udma_tx_arbiter state machines to hang.
+ * The issue exist at i.MX6SX enet IP.
+ */
+#define FEC_QUIRK_ERR007885		(1 << 9)
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -139,7 +145,7 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
-				FEC_QUIRK_HAS_AVB,
+				FEC_QUIRK_HAS_AVB | FEC_QUIRK_ERR007885,
 	}, {
 		/* sentinel */
 	}
@@ -709,6 +715,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
 
 	if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep, txq)) {
 		dev_kfree_skb_any(skb);
@@ -770,7 +778,12 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	txq->cur_tx = bdp;
 
 	/* Trigger transmission start */
-	writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
+	if (!(id_entry->driver_data & FEC_QUIRK_ERR007885) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)))
+		writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
 
 	return 0;
 
-- 
1.9.1

Re: [Patch net-next v2 4/4] net: fec: Workaround for imx6sx enet tx hang when enable three queues

[Fabio Estevam]

On Tue, Sep 16, 2014 at 2:58 PM,  <Frank.Li@freescale.com> wrote:
> From: Fugang Duan <B38611@freescale.com>
>
> When enable three queues on imx6sx enet, and then do tx performance
> test with iperf tool, after some time running, tx hang.
>
> Found that:
>         If uDMA is running, software set TDAR may cause tx hang.
>         If uDMA is in idle, software set TDAR don't cause tx hang.
>
> There is a TDAR race condition for mutliQ when the software sets TDAR
> and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
> This will cause the udma_tx and udma_tx_arbiter state machines to hang.
> The issue exist at i.MX6SX enet IP.
>
> So, the Workaround is checking TDAR status four time, if TDAR cleared by
> hardware and then write TDAR, otherwise don't set TDAR.
>
> The patch is only one Workaround for the issue TKT210582.

As Shawn pointed out, it is better to use the ERR007885 instead of an
internal bug numbering.

Re: [Patch net-next v2 4/4] net: fec: Workaround for imx6sx enet tx hang when enable three queues

[Zhi Li]

On Tue, Sep 16, 2014 at 3:52 PM, Fabio Estevam <festevam@gmail.com> wrote:
> On Tue, Sep 16, 2014 at 2:58 PM,  <Frank.Li@freescale.com> wrote:
>> From: Fugang Duan <B38611@freescale.com>
>>
>> When enable three queues on imx6sx enet, and then do tx performance
>> test with iperf tool, after some time running, tx hang.
>>
>> Found that:
>>         If uDMA is running, software set TDAR may cause tx hang.
>>         If uDMA is in idle, software set TDAR don't cause tx hang.
>>
>> There is a TDAR race condition for mutliQ when the software sets TDAR
>> and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
>> This will cause the udma_tx and udma_tx_arbiter state machines to hang.
>> The issue exist at i.MX6SX enet IP.
>>
>> So, the Workaround is checking TDAR status four time, if TDAR cleared by
>> hardware and then write TDAR, otherwise don't set TDAR.
>>
>> The patch is only one Workaround for the issue TKT210582.
>
> As Shawn pointed out, it is better to use the ERR007885 instead of an
> internal bug numbering.

Sorry, I forget change commit message.

best regards
Frank Li