[PATCH v2 1/4] net: emac: implement 802.1Q VLAN TX tagging support

[PATCH v2 1/4] net: emac: implement 802.1Q VLAN TX tagging support

[Christian Lamparter]

As per' APM82181 Embedded Processor User Manual 26.1 EMAC Features:
VLAN:
 - Support for VLAN tag ID in compliance with IEEE 802.3ac.
 - VLAN tag insertion or replacement for transmit packets

This patch completes the missing code for the VLAN tx tagging
support, as the the EMAC_MR1_VLE was already enabled.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
---
 drivers/net/ethernet/ibm/emac/core.c | 32 ++++++++++++++++++++++++----
 drivers/net/ethernet/ibm/emac/core.h |  6 +++++-
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 760b2ad8e295..be560f9031f4 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -37,6 +37,7 @@
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/bitops.h>
+#include <linux/if_vlan.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -674,7 +675,7 @@ static int emac_configure(struct emac_instance *dev)
 		 ndev->dev_addr[5]);
 
 	/* VLAN Tag Protocol ID */
-	out_be32(&p->vtpid, 0x8100);
+	out_be32(&p->vtpid, ETH_P_8021Q);
 
 	/* Receive mode register */
 	r = emac_iff2rmr(ndev);
@@ -1435,6 +1436,22 @@ static inline netdev_tx_t emac_xmit_finish(struct emac_instance *dev, int len)
 	return NETDEV_TX_OK;
 }
 
+static inline u16 emac_tx_vlan(struct emac_instance *dev, struct sk_buff *skb)
+{
+	/* Handle VLAN TPID and TCI insert if this is a VLAN skb */
+	if (emac_has_feature(dev, EMAC_FTR_HAS_VLAN_CTAG_TX) &&
+	    skb_vlan_tag_present(skb)) {
+		struct emac_regs __iomem *p = dev->emacp;
+
+		/* update the VLAN TCI */
+		out_be32(&p->vtci, (u32)skb_vlan_tag_get(skb));
+
+		/* Insert VLAN tag */
+		return EMAC_TX_CTRL_IVT;
+	}
+	return 0;
+}
+
 /* Tx lock BH */
 static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
@@ -1443,7 +1460,7 @@ static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	int slot;
 
 	u16 ctrl = EMAC_TX_CTRL_GFCS | EMAC_TX_CTRL_GP | MAL_TX_CTRL_READY |
-	    MAL_TX_CTRL_LAST | emac_tx_csum(dev, skb);
+	    MAL_TX_CTRL_LAST | emac_tx_csum(dev, skb) | emac_tx_vlan(dev, skb);
 
 	slot = dev->tx_slot++;
 	if (dev->tx_slot == NUM_TX_BUFF) {
@@ -1518,7 +1535,7 @@ emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev)
 		goto stop_queue;
 
 	ctrl = EMAC_TX_CTRL_GFCS | EMAC_TX_CTRL_GP | MAL_TX_CTRL_READY |
-	    emac_tx_csum(dev, skb);
+	    emac_tx_csum(dev, skb) | emac_tx_vlan(dev, skb);
 	slot = dev->tx_slot;
 
 	/* skb data */
@@ -2891,7 +2908,8 @@ static int emac_init_config(struct emac_instance *dev)
 		if (of_device_is_compatible(np, "ibm,emac-apm821xx")) {
 			dev->features |= (EMAC_APM821XX_REQ_JUMBO_FRAME_SIZE |
 					  EMAC_FTR_APM821XX_NO_HALF_DUPLEX |
-					  EMAC_FTR_460EX_PHY_CLK_FIX);
+					  EMAC_FTR_460EX_PHY_CLK_FIX |
+					  EMAC_FTR_HAS_VLAN_CTAG_TX);
 		}
 	} else if (of_device_is_compatible(np, "ibm,emac4")) {
 		dev->features |= EMAC_FTR_EMAC4;
@@ -3148,6 +3166,12 @@ static int emac_probe(struct platform_device *ofdev)
 
 	if (dev->tah_dev) {
 		ndev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG;
+
+		if (emac_has_feature(dev, EMAC_FTR_HAS_VLAN_CTAG_TX)) {
+			ndev->vlan_features |= ndev->hw_features;
+			ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+		}
+
 		ndev->features |= ndev->hw_features | NETIF_F_RXCSUM;
 	}
 	ndev->watchdog_timeo = 5 * HZ;
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 84caa4a3fc52..8d84d439168c 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -334,6 +334,8 @@ struct emac_instance {
  * APM821xx does not support Half Duplex mode
  */
 #define EMAC_FTR_APM821XX_NO_HALF_DUPLEX	0x00001000
+/* EMAC can insert 802.1Q tag */
+#define EMAC_FTR_HAS_VLAN_CTAG_TX		0x00002000
 
 /* Right now, we don't quite handle the always/possible masks on the
  * most optimal way as we don't have a way to say something like
@@ -363,7 +365,9 @@ enum {
 	EMAC_FTR_460EX_PHY_CLK_FIX |
 	EMAC_FTR_440EP_PHY_CLK_FIX |
 	EMAC_APM821XX_REQ_JUMBO_FRAME_SIZE |
-	EMAC_FTR_APM821XX_NO_HALF_DUPLEX,
+	EMAC_FTR_APM821XX_NO_HALF_DUPLEX |
+	EMAC_FTR_HAS_VLAN_CTAG_TX |
+	0,
 };
 
 static inline int emac_has_feature(struct emac_instance *dev,
-- 
2.19.1

[PATCH v2 2/4] net: emac: implement TCP segmentation offload (TSO)

[Christian Lamparter]

This patch enables TSO(v4) hw feature for emac driver.
As atleast the APM82181's TCP/IP acceleration hardware
controller (TAH) provides TCP segmentation support in
the transmit path.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
---
 drivers/net/ethernet/ibm/emac/core.c | 113 ++++++++++++++++++++++++++-
 drivers/net/ethernet/ibm/emac/core.h |   7 ++
 drivers/net/ethernet/ibm/emac/emac.h |   7 ++
 drivers/net/ethernet/ibm/emac/tah.c  |  22 +++++-
 drivers/net/ethernet/ibm/emac/tah.h  |   2 +
 5 files changed, 148 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index be560f9031f4..b5c4b7d3057d 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -38,6 +38,9 @@
 #include <linux/mii.h>
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -1118,6 +1121,32 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 	return ret;
 }
 
+/* Restriction applied for the segmentation size
+ * to use HW segmentation offload feature. the size
+ * of the segment must not be less than 168 bytes for
+ * DIX formatted segments, or 176 bytes for
+ * IEEE formatted segments. However based on actual
+ * tests any MTU less than 416 causes excessive retries
+ * due to TX FIFO underruns.
+ */
+const u32 tah_ss[TAH_NO_SSR] = { 1500, 1344, 1152, 960, 768, 416 };
+
+/* look-up matching segment size for the given mtu */
+static void emac_find_tso_ss_for_mtu(struct emac_instance *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tah_ss); i++) {
+		if (tah_ss[i] <= dev->ndev->mtu)
+			break;
+	}
+	/* if no matching segment size is found, set the tso_ss_mtu_start
+	 * variable anyway. This will cause the emac_tx_tso to skip straight
+	 * to the software fallback.
+	 */
+	dev->tso_ss_mtu_start = i;
+}
+
 /* Process ctx, rtnl_lock semaphore */
 static int emac_change_mtu(struct net_device *ndev, int new_mtu)
 {
@@ -1134,6 +1163,7 @@ static int emac_change_mtu(struct net_device *ndev, int new_mtu)
 
 	if (!ret) {
 		ndev->mtu = new_mtu;
+		emac_find_tso_ss_for_mtu(dev);
 		dev->rx_skb_size = emac_rx_skb_size(new_mtu);
 		dev->rx_sync_size = emac_rx_sync_size(new_mtu);
 	}
@@ -1410,6 +1440,33 @@ static inline u16 emac_tx_csum(struct emac_instance *dev,
 	return 0;
 }
 
+static int emac_tx_tso(struct emac_instance *dev, struct sk_buff *skb,
+		       u16 *ctrl)
+{
+	if (emac_has_feature(dev, EMAC_FTR_TAH_HAS_TSO) && skb_is_gso(skb) &&
+	    !!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
+		u32 seg_size = 0, i;
+
+		/* Get the MTU */
+		seg_size = skb_shinfo(skb)->gso_size + tcp_hdrlen(skb) +
+			   skb_network_header_len(skb);
+
+		for (i = dev->tso_ss_mtu_start; i < ARRAY_SIZE(tah_ss); i++) {
+			if (tah_ss[i] > seg_size)
+				continue;
+
+			*ctrl |= EMAC_TX_CTRL_TAH_SSR(i);
+			return 0;
+		}
+
+		/* none found fall back to software */
+		return -EINVAL;
+	}
+
+	*ctrl |= emac_tx_csum(dev, skb);
+	return 0;
+}
+
 static inline netdev_tx_t emac_xmit_finish(struct emac_instance *dev, int len)
 {
 	struct emac_regs __iomem *p = dev->emacp;
@@ -1452,8 +1509,49 @@ static inline u16 emac_tx_vlan(struct emac_instance *dev, struct sk_buff *skb)
 	return 0;
 }
 
+static netdev_tx_t
+emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev);
+
+static netdev_tx_t
+emac_sw_tso(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct emac_instance *dev = netdev_priv(ndev);
+	struct sk_buff *segs, *curr;
+	unsigned int i, frag_slots;
+
+	/* make sure to not overflow the tx ring */
+	frag_slots = dev->tx_cnt;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+
+		frag_slots += mal_tx_chunks(skb_frag_size(frag));
+
+		if (frag_slots >= NUM_TX_BUFF)
+			return NETDEV_TX_BUSY;
+	};
+
+	segs = skb_gso_segment(skb, ndev->features &
+					~(NETIF_F_TSO | NETIF_F_TSO6));
+	if (IS_ERR_OR_NULL(segs)) {
+		++dev->estats.tx_dropped;
+		dev_kfree_skb_any(skb);
+	} else {
+		while (segs) {
+			curr = segs;
+			segs = curr->next;
+			curr->next = NULL;
+
+			emac_start_xmit_sg(curr, ndev);
+		}
+		dev_consume_skb_any(skb);
+	}
+
+	return NETDEV_TX_OK;
+}
+
 /* Tx lock BH */
-static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t
+emac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct emac_instance *dev = netdev_priv(ndev);
 	unsigned int len = skb->len;
@@ -1535,7 +1633,10 @@ emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev)
 		goto stop_queue;
 
 	ctrl = EMAC_TX_CTRL_GFCS | EMAC_TX_CTRL_GP | MAL_TX_CTRL_READY |
-	    emac_tx_csum(dev, skb) | emac_tx_vlan(dev, skb);
+	    emac_tx_vlan(dev, skb);
+	if (emac_tx_tso(dev, skb, &ctrl))
+		return emac_sw_tso(skb, ndev);
+
 	slot = dev->tx_slot;
 
 	/* skb data */
@@ -2946,6 +3047,9 @@ static int emac_init_config(struct emac_instance *dev)
 	if (dev->tah_ph != 0) {
 #ifdef CONFIG_IBM_EMAC_TAH
 		dev->features |= EMAC_FTR_HAS_TAH;
+
+		if (of_device_is_compatible(np, "ibm,emac-apm821xx"))
+			dev->features |= EMAC_FTR_TAH_HAS_TSO;
 #else
 		printk(KERN_ERR "%pOF: TAH support not enabled !\n", np);
 		return -ENXIO;
@@ -3113,6 +3217,8 @@ static int emac_probe(struct platform_device *ofdev)
 	}
 	dev->rx_skb_size = emac_rx_skb_size(ndev->mtu);
 	dev->rx_sync_size = emac_rx_sync_size(ndev->mtu);
+	ndev->gso_max_segs = NUM_TX_BUFF / 2;
+	emac_find_tso_ss_for_mtu(dev);
 
 	/* Get pointers to BD rings */
 	dev->tx_desc =
@@ -3167,6 +3273,9 @@ static int emac_probe(struct platform_device *ofdev)
 	if (dev->tah_dev) {
 		ndev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG;
 
+		if (emac_has_feature(dev, EMAC_FTR_TAH_HAS_TSO))
+			ndev->hw_features |= NETIF_F_TSO;
+
 		if (emac_has_feature(dev, EMAC_FTR_HAS_VLAN_CTAG_TX)) {
 			ndev->vlan_features |= ndev->hw_features;
 			ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 8d84d439168c..0bcfe952a3cf 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -245,6 +245,9 @@ struct emac_instance {
 	u32				xaht_slots_shift;
 	u32				xaht_width_shift;
 
+	/* TAH TSO start index */
+	int				tso_ss_mtu_start;
+
 	/* Descriptor management
 	 */
 	struct mal_descriptor		*tx_desc;
@@ -336,6 +339,8 @@ struct emac_instance {
 #define EMAC_FTR_APM821XX_NO_HALF_DUPLEX	0x00001000
 /* EMAC can insert 802.1Q tag */
 #define EMAC_FTR_HAS_VLAN_CTAG_TX		0x00002000
+/* TAH can do TCP segmentation offload */
+#define EMAC_FTR_TAH_HAS_TSO			0x00004000
 
 /* Right now, we don't quite handle the always/possible masks on the
  * most optimal way as we don't have a way to say something like
@@ -352,6 +357,8 @@ enum {
 #endif
 #ifdef CONFIG_IBM_EMAC_TAH
 	    EMAC_FTR_HAS_TAH	|
+	    EMAC_FTR_TAH_HAS_TSO	|
+
 #endif
 #ifdef CONFIG_IBM_EMAC_ZMII
 	    EMAC_FTR_HAS_ZMII	|
diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h
index e2f80cca9bed..833967aceb2f 100644
--- a/drivers/net/ethernet/ibm/emac/emac.h
+++ b/drivers/net/ethernet/ibm/emac/emac.h
@@ -266,6 +266,13 @@ struct emac_regs {
 #define EMAC_TX_CTRL_IVT		0x0020
 #define EMAC_TX_CTRL_RVT		0x0010
 #define EMAC_TX_CTRL_TAH_CSUM		0x000e
+#define EMAC_TX_CTRL_TAH_SSR(idx)	(((idx) + 1) << 1)
+#define EMAC_TX_CTRL_TAH_SSR5		0x000c
+#define EMAC_TX_CTRL_TAH_SSR4		0x000a
+#define EMAC_TX_CTRL_TAH_SSR3		0x0008
+#define EMAC_TX_CTRL_TAH_SSR2		0x0006
+#define EMAC_TX_CTRL_TAH_SSR1		0x0004
+#define EMAC_TX_CTRL_TAH_SSR0		0x0002
 
 /* EMAC specific TX descriptor status fields (read access) */
 #define EMAC_TX_ST_BFCS			0x0200
diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c
index 9912456dca48..619c08ee22f7 100644
--- a/drivers/net/ethernet/ibm/emac/tah.c
+++ b/drivers/net/ethernet/ibm/emac/tah.c
@@ -45,6 +45,24 @@ void tah_detach(struct platform_device *ofdev, int channel)
 	mutex_unlock(&dev->lock);
 }
 
+static void tah_set_ssr(struct platform_device *ofdev)
+{
+	struct tah_instance *dev = dev_get_drvdata(&ofdev->dev);
+	struct tah_regs __iomem *p = dev->base;
+	int i;
+
+	mutex_lock(&dev->lock);
+
+	for (i = 0; i < ARRAY_SIZE(tah_ss); i++) {
+		/* Segment size can be up to 16K, but needs
+		 * to be a multiple of 2 bytes
+		 */
+		out_be32(&p->ssr0 + i, (tah_ss[i] & 0x3ffc) << 16);
+	}
+
+	mutex_unlock(&dev->lock);
+}
+
 void tah_reset(struct platform_device *ofdev)
 {
 	struct tah_instance *dev = platform_get_drvdata(ofdev);
@@ -64,6 +82,8 @@ void tah_reset(struct platform_device *ofdev)
 	out_be32(&p->mr,
 		 TAH_MR_CVR | TAH_MR_ST_768 | TAH_MR_TFS_10KB | TAH_MR_DTFP |
 		 TAH_MR_DIG);
+
+	tah_set_ssr(ofdev);
 }
 
 int tah_get_regs_len(struct platform_device *ofdev)
@@ -118,7 +138,7 @@ static int tah_probe(struct platform_device *ofdev)
 
 	platform_set_drvdata(ofdev, dev);
 
-	/* Initialize TAH and enable IPv4 checksum verification, no TSO yet */
+	/* Initialize TAH and enable IPv4 checksum verification */
 	tah_reset(ofdev);
 
 	printk(KERN_INFO "TAH %pOF initialized\n", ofdev->dev.of_node);
diff --git a/drivers/net/ethernet/ibm/emac/tah.h b/drivers/net/ethernet/ibm/emac/tah.h
index 4d5f336f07b3..2cb0629f30e2 100644
--- a/drivers/net/ethernet/ibm/emac/tah.h
+++ b/drivers/net/ethernet/ibm/emac/tah.h
@@ -36,6 +36,8 @@ struct tah_regs {
 	u32 tsr;
 };
 
+#define TAH_NO_SSR	6
+extern const u32 tah_ss[TAH_NO_SSR];
 
 /* TAH device */
 struct tah_instance {
-- 
2.19.1

[PATCH v2 3/4] net: emac: remove IBM_EMAC_RX_SKB_HEADROOM

[Christian Lamparter]

The EMAC driver had a custom IBM_EMAC_RX_SKB_HEADROOM
Kconfig option that reserved additional skb headroom for RX.
This patch removes the option and migrates the code
to use napi_alloc_skb() and netdev_alloc_skb_ip_align()
in its place.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
---
 drivers/net/ethernet/ibm/emac/Kconfig | 12 ------
 drivers/net/ethernet/ibm/emac/core.c  | 57 +++++++++++++++++++--------
 drivers/net/ethernet/ibm/emac/core.h  | 10 ++---
 3 files changed, 43 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/Kconfig b/drivers/net/ethernet/ibm/emac/Kconfig
index 90d49191beb3..eacf7e141fdc 100644
--- a/drivers/net/ethernet/ibm/emac/Kconfig
+++ b/drivers/net/ethernet/ibm/emac/Kconfig
@@ -28,18 +28,6 @@ config IBM_EMAC_RX_COPY_THRESHOLD
 	depends on IBM_EMAC
 	default "256"
 
-config IBM_EMAC_RX_SKB_HEADROOM
-	int "Additional RX skb headroom (bytes)"
-	depends on IBM_EMAC
-	default "0"
-	help
-	  Additional receive skb headroom. Note, that driver
-	  will always reserve at least 2 bytes to make IP header
-	  aligned, so usually there is no need to add any additional
-	  headroom.
-
-	  If unsure, set to 0.
-
 config IBM_EMAC_DEBUG
 	bool "Debugging"
 	depends on IBM_EMAC
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index b5c4b7d3057d..388443e08674 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1075,7 +1075,9 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 
 	/* Second pass, allocate new skbs */
 	for (i = 0; i < NUM_RX_BUFF; ++i) {
-		struct sk_buff *skb = alloc_skb(rx_skb_size, GFP_ATOMIC);
+		struct sk_buff *skb;
+
+		skb = netdev_alloc_skb_ip_align(dev->ndev, rx_skb_size);
 		if (!skb) {
 			ret = -ENOMEM;
 			goto oom;
@@ -1084,7 +1086,6 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 		BUG_ON(!dev->rx_skb[i]);
 		dev_kfree_skb(dev->rx_skb[i]);
 
-		skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 		dev->rx_desc[i].data_ptr =
 		    dma_map_single(&dev->ofdev->dev, skb->data - 2, rx_sync_size,
 				   DMA_FROM_DEVICE) + 2;
@@ -1205,20 +1206,18 @@ static void emac_clean_rx_ring(struct emac_instance *dev)
 	}
 }
 
-static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
-				    gfp_t flags)
+static inline int
+__emac_prepare_rx_skb(struct sk_buff *skb, struct emac_instance *dev, int slot)
 {
-	struct sk_buff *skb = alloc_skb(dev->rx_skb_size, flags);
 	if (unlikely(!skb))
 		return -ENOMEM;
 
 	dev->rx_skb[slot] = skb;
 	dev->rx_desc[slot].data_len = 0;
 
-	skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 	dev->rx_desc[slot].data_ptr =
-	    dma_map_single(&dev->ofdev->dev, skb->data - 2, dev->rx_sync_size,
-			   DMA_FROM_DEVICE) + 2;
+	    dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			   dev->rx_sync_size, DMA_FROM_DEVICE) + NET_IP_ALIGN;
 	wmb();
 	dev->rx_desc[slot].ctrl = MAL_RX_CTRL_EMPTY |
 	    (slot == (NUM_RX_BUFF - 1) ? MAL_RX_CTRL_WRAP : 0);
@@ -1226,6 +1225,27 @@ static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
 	return 0;
 }
 
+static inline int
+emac_alloc_rx_skb(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = __netdev_alloc_skb_ip_align(dev->ndev, dev->rx_skb_size,
+					  GFP_KERNEL);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
+static inline int
+emac_alloc_rx_skb_napi(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = napi_alloc_skb(&dev->mal->napi, dev->rx_skb_size);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
 static void emac_print_link_status(struct emac_instance *dev)
 {
 	if (netif_carrier_ok(dev->ndev))
@@ -1256,7 +1276,7 @@ static int emac_open(struct net_device *ndev)
 
 	/* Allocate RX ring */
 	for (i = 0; i < NUM_RX_BUFF; ++i)
-		if (emac_alloc_rx_skb(dev, i, GFP_KERNEL)) {
+		if (emac_alloc_rx_skb(dev, i)) {
 			printk(KERN_ERR "%s: failed to allocate RX ring\n",
 			       ndev->name);
 			goto oom;
@@ -1778,8 +1798,9 @@ static inline void emac_recycle_rx_skb(struct emac_instance *dev, int slot,
 	DBG2(dev, "recycle %d %d" NL, slot, len);
 
 	if (len)
-		dma_map_single(&dev->ofdev->dev, skb->data - 2,
-			       EMAC_DMA_ALIGN(len + 2), DMA_FROM_DEVICE);
+		dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			       SKB_DATA_ALIGN(len + NET_IP_ALIGN),
+			       DMA_FROM_DEVICE);
 
 	dev->rx_desc[slot].data_len = 0;
 	wmb();
@@ -1887,16 +1908,18 @@ static int emac_poll_rx(void *param, int budget)
 		}
 
 		if (len && len < EMAC_RX_COPY_THRESH) {
-			struct sk_buff *copy_skb =
-			    alloc_skb(len + EMAC_RX_SKB_HEADROOM + 2, GFP_ATOMIC);
+			struct sk_buff *copy_skb;
+
+			copy_skb = napi_alloc_skb(&dev->mal->napi, len);
 			if (unlikely(!copy_skb))
 				goto oom;
 
-			skb_reserve(copy_skb, EMAC_RX_SKB_HEADROOM + 2);
-			memcpy(copy_skb->data - 2, skb->data - 2, len + 2);
+			memcpy(copy_skb->data - NET_IP_ALIGN,
+			       skb->data - NET_IP_ALIGN,
+			       len + NET_IP_ALIGN);
 			emac_recycle_rx_skb(dev, slot, len);
 			skb = copy_skb;
-		} else if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC)))
+		} else if (unlikely(emac_alloc_rx_skb_napi(dev, slot)))
 			goto oom;
 
 		skb_put(skb, len);
@@ -1917,7 +1940,7 @@ static int emac_poll_rx(void *param, int budget)
 	sg:
 		if (ctrl & MAL_RX_CTRL_FIRST) {
 			BUG_ON(dev->rx_sg_skb);
-			if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC))) {
+			if (unlikely(emac_alloc_rx_skb_napi(dev, slot))) {
 				DBG(dev, "rx OOM %d" NL, slot);
 				++dev->estats.rx_dropped_oom;
 				emac_recycle_rx_skb(dev, slot, 0);
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 0bcfe952a3cf..0faeb7c7e958 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -68,22 +68,18 @@ static inline int emac_rx_size(int mtu)
 		return mal_rx_size(ETH_DATA_LEN + EMAC_MTU_OVERHEAD);
 }
 
-#define EMAC_DMA_ALIGN(x)		ALIGN((x), dma_get_cache_alignment())
-
-#define EMAC_RX_SKB_HEADROOM		\
-	EMAC_DMA_ALIGN(CONFIG_IBM_EMAC_RX_SKB_HEADROOM)
-
 /* Size of RX skb for the given MTU */
 static inline int emac_rx_skb_size(int mtu)
 {
 	int size = max(mtu + EMAC_MTU_OVERHEAD, emac_rx_size(mtu));
-	return EMAC_DMA_ALIGN(size + 2) + EMAC_RX_SKB_HEADROOM;
+
+	return SKB_DATA_ALIGN(size + NET_SKB_PAD + NET_IP_ALIGN);
 }
 
 /* RX DMA sync size */
 static inline int emac_rx_sync_size(int mtu)
 {
-	return EMAC_DMA_ALIGN(emac_rx_size(mtu) + 2);
+	return SKB_DATA_ALIGN(emac_rx_size(mtu) + NET_IP_ALIGN);
 }
 
 /* Driver statistcs is split into two parts to make it more cache friendly:
-- 
2.19.1

[PATCH v2 4/4] net: emac: add deprecation notice to emac custom phy users

[Christian Lamparter]

From: Christian Lamparter <chunkeey@googlemail.com>

This patch starts the deprecation process of emac's small library of
supported phys by adding a message to inform all remaining users to
start looking into converting their platform's device-tree to PHYLIB.

EMAC's phy.c support is limited to mostly single ethernet transceivers:
CIS8201, BCM5248, ET1011C, Marvell 88E1111 and 88E1112, AR8035.

And Linux has dedicated PHYLIB drivers for all but the BCM5248 which
can be supported by the generic phy driver.

Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
---
 drivers/net/ethernet/ibm/emac/phy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/ibm/emac/phy.c b/drivers/net/ethernet/ibm/emac/phy.c
index aa070c063e48..143b4c688ee9 100644
--- a/drivers/net/ethernet/ibm/emac/phy.c
+++ b/drivers/net/ethernet/ibm/emac/phy.c
@@ -496,6 +496,7 @@ static struct mii_phy_def ar8035_phy_def = {
 };
 
 static struct mii_phy_def *mii_phy_table[] = {
+	/* DEPRECATED: Do not add any new PHY drivers to this list. */
 	&et1011c_phy_def,
 	&cis8201_phy_def,
 	&bcm5248_phy_def,
@@ -512,6 +513,9 @@ int emac_mii_phy_probe(struct mii_phy *phy, int address)
 	int i;
 	u32 id;
 
+	pr_info("EMAC's custom phy code has been deprecated.\n"
+		"Please convert your EMAC device to PHYLIB.\n");
+
 	phy->autoneg = AUTONEG_DISABLE;
 	phy->advertising = 0;
 	phy->address = address;
-- 
2.19.1

Re: [PATCH v2 2/4] net: emac: implement TCP segmentation offload (TSO)

[David Miller]

From: Christian Lamparter <chunkeey@gmail.com>
Date: Mon, 22 Oct 2018 13:04:12 +0200

> @@ -1452,8 +1509,49 @@ static inline u16 emac_tx_vlan(struct emac_instance *dev, struct sk_buff *skb)
>  	return 0;
>  }
>  
> +static netdev_tx_t
> +emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev);
> +
> +static netdev_tx_t
> +emac_sw_tso(struct sk_buff *skb, struct net_device *ndev)
> +{
> +	struct emac_instance *dev = netdev_priv(ndev);
> +	struct sk_buff *segs, *curr;
> +	unsigned int i, frag_slots;
> +
> +	/* make sure to not overflow the tx ring */
> +	frag_slots = dev->tx_cnt;
> +	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
> +		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
> +
> +		frag_slots += mal_tx_chunks(skb_frag_size(frag));
> +
> +		if (frag_slots >= NUM_TX_BUFF)
> +			return NETDEV_TX_BUSY;
> +	};
> +
> +	segs = skb_gso_segment(skb, ndev->features &
> +					~(NETIF_F_TSO | NETIF_F_TSO6));

This NETDEV_TX_BUSY isn't going to work.

Your TX queue is awake.  So there won't be any guaranteed event to "wake up"
the queue and try sending this SKB again.

Please take a look at how the tg3.c driver handles this situation.  You have
to first stop the queue, do you overflow test, and then you can return
NETDEV_TX_BUSY if necessary.