1 files changed, 387 insertions, 169 deletions

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 033064b7b576..6a59bce38a8c 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -14,8 +14,10 @@
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/circ_buf.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -26,37 +28,74 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/pinctrl/consumer.h>
 
 #include "macb.h"
 
 #define RX_BUFFER_SIZE          128
-#define RX_RING_SIZE            512
-#define RX_RING_BYTES           (sizeof(struct dma_desc) * RX_RING_SIZE)
+#define RX_RING_SIZE            512 /* must be power of 2 */
+#define RX_RING_BYTES           (sizeof(struct macb_dma_desc) * RX_RING_SIZE)
 
-/* Make the IP header word-aligned (the ethernet header is 14 bytes) */
-#define RX_OFFSET               2
+#define TX_RING_SIZE            128 /* must be power of 2 */
+#define TX_RING_BYTES           (sizeof(struct macb_dma_desc) * TX_RING_SIZE)
 
-#define TX_RING_SIZE            128
-#define DEF_TX_RING_PENDING     (TX_RING_SIZE - 1)
-#define TX_RING_BYTES           (sizeof(struct dma_desc) * TX_RING_SIZE)
+/* level of occupied TX descriptors under which we wake up TX process */
+#define MACB_TX_WAKEUP_THRESH   (3 * TX_RING_SIZE / 4)
 
-#define TX_RING_GAP(bp)                                         \
-        (TX_RING_SIZE - (bp)->tx_pending)
-#define TX_BUFFS_AVAIL(bp)                                      \
-        (((bp)->tx_tail <= (bp)->tx_head) ?                     \
-         (bp)->tx_tail + (bp)->tx_pending - (bp)->tx_head :     \
-         (bp)->tx_tail - (bp)->tx_head - TX_RING_GAP(bp))
-#define NEXT_TX(n)              (((n) + 1) & (TX_RING_SIZE - 1))
+#define MACB_RX_INT_FLAGS       (MACB_BIT(RCOMP) | MACB_BIT(RXUBR)      \
+                                 | MACB_BIT(ISR_ROVR))
+#define MACB_TX_ERR_FLAGS       (MACB_BIT(ISR_TUND)                     \
+                                        | MACB_BIT(ISR_RLE)             \
+                                        | MACB_BIT(TXERR))
+#define MACB_TX_INT_FLAGS       (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP))
 
-#define NEXT_RX(n)              (((n) + 1) & (RX_RING_SIZE - 1))
+/*
+ * Graceful stop timeouts in us. We should allow up to
+ * 1 frame time (10 Mbits/s, full-duplex, ignoring collisions)
+ */
+#define MACB_HALT_TIMEOUT       1230
 
-/* minimum number of free TX descriptors before waking up TX process */
-#define MACB_TX_WAKEUP_THRESH   (TX_RING_SIZE / 4)
+/* Ring buffer accessors */
+static unsigned int macb_tx_ring_wrap(unsigned int index)
+{
+        return index & (TX_RING_SIZE - 1);
+}
 
-#define MACB_RX_INT_FLAGS       (MACB_BIT(RCOMP) | MACB_BIT(RXUBR)      \
-                                 | MACB_BIT(ISR_ROVR))
+static struct macb_dma_desc *macb_tx_desc(struct macb *bp, unsigned int index)
+{
+        return &bp->tx_ring[macb_tx_ring_wrap(index)];
+}
 
-static void __macb_set_hwaddr(struct macb *bp)
+static struct macb_tx_skb *macb_tx_skb(struct macb *bp, unsigned int index)
+{
+        return &bp->tx_skb[macb_tx_ring_wrap(index)];
+}
+
+static dma_addr_t macb_tx_dma(struct macb *bp, unsigned int index)
+{
+        dma_addr_t offset;
+
+        offset = macb_tx_ring_wrap(index) * sizeof(struct macb_dma_desc);
+
+        return bp->tx_ring_dma + offset;
+}
+
+static unsigned int macb_rx_ring_wrap(unsigned int index)
+{
+        return index & (RX_RING_SIZE - 1);
+}
+
+static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
+{
+        return &bp->rx_ring[macb_rx_ring_wrap(index)];
+}
+
+static void *macb_rx_buffer(struct macb *bp, unsigned int index)
+{
+        return bp->rx_buffers + RX_BUFFER_SIZE * macb_rx_ring_wrap(index);
+}
+
+void macb_set_hwaddr(struct macb *bp)
 {
         u32 bottom;
         u16 top;
@@ -65,31 +104,58 @@ static void __macb_set_hwaddr(struct macb *bp)
         macb_or_gem_writel(bp, SA1B, bottom);
         top = cpu_to_le16(*((u16 *)(bp->dev->dev_addr + 4)));
         macb_or_gem_writel(bp, SA1T, top);
+
+        /* Clear unused address register sets */
+        macb_or_gem_writel(bp, SA2B, 0);
+        macb_or_gem_writel(bp, SA2T, 0);
+        macb_or_gem_writel(bp, SA3B, 0);
+        macb_or_gem_writel(bp, SA3T, 0);
+        macb_or_gem_writel(bp, SA4B, 0);
+        macb_or_gem_writel(bp, SA4T, 0);
 }
+EXPORT_SYMBOL_GPL(macb_set_hwaddr);
 
-static void __init macb_get_hwaddr(struct macb *bp)
+void macb_get_hwaddr(struct macb *bp)
 {
+        struct macb_platform_data *pdata;
         u32 bottom;
         u16 top;
         u8 addr[6];
+        int i;
 
-        bottom = macb_or_gem_readl(bp, SA1B);
-        top = macb_or_gem_readl(bp, SA1T);
+        pdata = bp->pdev->dev.platform_data;
 
-        addr[0] = bottom & 0xff;
-        addr[1] = (bottom >> 8) & 0xff;
-        addr[2] = (bottom >> 16) & 0xff;
-        addr[3] = (bottom >> 24) & 0xff;
-        addr[4] = top & 0xff;
-        addr[5] = (top >> 8) & 0xff;
+        /* Check all 4 address register for vaild address */
+        for (i = 0; i < 4; i++) {
+                bottom = macb_or_gem_readl(bp, SA1B + i * 8);
+                top = macb_or_gem_readl(bp, SA1T + i * 8);
+
+                if (pdata && pdata->rev_eth_addr) {
+                        addr[5] = bottom & 0xff;
+                        addr[4] = (bottom >> 8) & 0xff;
+                        addr[3] = (bottom >> 16) & 0xff;
+                        addr[2] = (bottom >> 24) & 0xff;
+                        addr[1] = top & 0xff;
+                        addr[0] = (top & 0xff00) >> 8;
+                } else {
+                        addr[0] = bottom & 0xff;
+                        addr[1] = (bottom >> 8) & 0xff;
+                        addr[2] = (bottom >> 16) & 0xff;
+                        addr[3] = (bottom >> 24) & 0xff;
+                        addr[4] = top & 0xff;
+                        addr[5] = (top >> 8) & 0xff;
+                }
 
-        if (is_valid_ether_addr(addr)) {
-                memcpy(bp->dev->dev_addr, addr, sizeof(addr));
-        } else {
-                netdev_info(bp->dev, "invalid hw address, using random\n");
-                eth_hw_addr_random(bp->dev);
+                if (is_valid_ether_addr(addr)) {
+                        memcpy(bp->dev->dev_addr, addr, sizeof(addr));
+                        return;
+                }
         }
+
+        netdev_info(bp->dev, "invalid hw address, using random\n");
+        eth_hw_addr_random(bp->dev);
 }
+EXPORT_SYMBOL_GPL(macb_get_hwaddr);
 
 static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
@@ -152,13 +218,17 @@ static void macb_handle_link_change(struct net_device *dev)
 
                         reg = macb_readl(bp, NCFGR);
                         reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
+                        if (macb_is_gem(bp))
+                                reg &= ~GEM_BIT(GBE);
 
                         if (phydev->duplex)
                                 reg |= MACB_BIT(FD);
                         if (phydev->speed == SPEED_100)
                                 reg |= MACB_BIT(SPD);
+                        if (phydev->speed == SPEED_1000)
+                                reg |= GEM_BIT(GBE);
 
-                        macb_writel(bp, NCFGR, reg);
+                        macb_or_gem_writel(bp, NCFGR, reg);
 
                         bp->speed = phydev->speed;
                         bp->duplex = phydev->duplex;
@@ -196,7 +266,9 @@ static void macb_handle_link_change(struct net_device *dev)
 static int macb_mii_probe(struct net_device *dev)
 {
         struct macb *bp = netdev_priv(dev);
+        struct macb_platform_data *pdata;
         struct phy_device *phydev;
+        int phy_irq;
         int ret;
 
         phydev = phy_find_first(bp->mii_bus);
@@ -205,7 +277,14 @@ static int macb_mii_probe(struct net_device *dev)
                 return -1;
         }
 
-        /* TODO : add pin_irq */
+        pdata = dev_get_platdata(&bp->pdev->dev);
+        if (pdata && gpio_is_valid(pdata->phy_irq_pin)) {
+                ret = devm_gpio_request(&bp->pdev->dev, pdata->phy_irq_pin, "phy int");
+                if (!ret) {
+                        phy_irq = gpio_to_irq(pdata->phy_irq_pin);
+                        phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+                }
+        }
 
         /* attach the mac to the phy */
         ret = phy_connect_direct(dev, phydev, &macb_handle_link_change, 0,
@@ -216,7 +295,10 @@ static int macb_mii_probe(struct net_device *dev)
         }
 
         /* mask with MAC supported features */
-        phydev->supported &= PHY_BASIC_FEATURES;
+        if (macb_is_gem(bp))
+                phydev->supported &= PHY_GBIT_FEATURES;
+        else
+                phydev->supported &= PHY_BASIC_FEATURES;
 
         phydev->advertising = phydev->supported;
 
@@ -228,7 +310,7 @@ static int macb_mii_probe(struct net_device *dev)
         return 0;
 }
 
-static int macb_mii_init(struct macb *bp)
+int macb_mii_init(struct macb *bp)
 {
         struct macb_platform_data *pdata;
         int err = -ENXIO, i;
@@ -284,6 +366,7 @@ err_out_free_mdiobus:
 err_out:
         return err;
 }
+EXPORT_SYMBOL_GPL(macb_mii_init);
 
 static void macb_update_stats(struct macb *bp)
 {
@@ -297,93 +380,148 @@ static void macb_update_stats(struct macb *bp)
                 *p += __raw_readl(reg);
 }
 
-static void macb_tx(struct macb *bp)
+static int macb_halt_tx(struct macb *bp)
 {
-        unsigned int tail;
-        unsigned int head;
-        u32 status;
+        unsigned long   halt_time, timeout;
+        u32             status;
 
-        status = macb_readl(bp, TSR);
-        macb_writel(bp, TSR, status);
+        macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
 
-        netdev_dbg(bp->dev, "macb_tx status = %02lx\n", (unsigned long)status);
+        timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
+        do {
+                halt_time = jiffies;
+                status = macb_readl(bp, TSR);
+                if (!(status & MACB_BIT(TGO)))
+                        return 0;
 
-        if (status & (MACB_BIT(UND) | MACB_BIT(TSR_RLE))) {
-                int i;
-                netdev_err(bp->dev, "TX %s, resetting buffers\n",
-                           status & MACB_BIT(UND) ?
-                           "underrun" : "retry limit exceeded");
+                usleep_range(10, 250);
+        } while (time_before(halt_time, timeout));
 
-                /* Transfer ongoing, disable transmitter, to avoid confusion */
-                if (status & MACB_BIT(TGO))
-                        macb_writel(bp, NCR, macb_readl(bp, NCR) & ~MACB_BIT(TE));
+        return -ETIMEDOUT;
+}
 
-                head = bp->tx_head;
+static void macb_tx_error_task(struct work_struct *work)
+{
+        struct macb     *bp = container_of(work, struct macb, tx_error_task);
+        struct macb_tx_skb      *tx_skb;
+        struct sk_buff          *skb;
+        unsigned int            tail;
 
-                /*Mark all the buffer as used to avoid sending a lost buffer*/
-                for (i = 0; i < TX_RING_SIZE; i++)
-                        bp->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+        netdev_vdbg(bp->dev, "macb_tx_error_task: t = %u, h = %u\n",
+                    bp->tx_tail, bp->tx_head);
 
-                /* Add wrap bit */
-                bp->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+        /* Make sure nobody is trying to queue up new packets */
+        netif_stop_queue(bp->dev);
 
-                /* free transmit buffer in upper layer*/
-                for (tail = bp->tx_tail; tail != head; tail = NEXT_TX(tail)) {
-                        struct ring_info *rp = &bp->tx_skb[tail];
-                        struct sk_buff *skb = rp->skb;
+        /*
+         * Stop transmission now
+         * (in case we have just queued new packets)
+         */
+        if (macb_halt_tx(bp))
+                /* Just complain for now, reinitializing TX path can be good */
+                netdev_err(bp->dev, "BUG: halt tx timed out\n");
 
-                        BUG_ON(skb == NULL);
+        /* No need for the lock here as nobody will interrupt us anymore */
 
-                        rmb();
+        /*
+         * Treat frames in TX queue including the ones that caused the error.
+         * Free transmit buffers in upper layer.
+         */
+        for (tail = bp->tx_tail; tail != bp->tx_head; tail++) {
+                struct macb_dma_desc    *desc;
+                u32                     ctrl;
+
+                desc = macb_tx_desc(bp, tail);
+                ctrl = desc->ctrl;
+                tx_skb = macb_tx_skb(bp, tail);
+                skb = tx_skb->skb;
+
+                if (ctrl & MACB_BIT(TX_USED)) {
+                        netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n",
+                                    macb_tx_ring_wrap(tail), skb->data);
+                        bp->stats.tx_packets++;
+                        bp->stats.tx_bytes += skb->len;
+                } else {
+                        /*
+                         * "Buffers exhausted mid-frame" errors may only happen
+                         * if the driver is buggy, so complain loudly about those.
+                         * Statistics are updated by hardware.
+                         */
+                        if (ctrl & MACB_BIT(TX_BUF_EXHAUSTED))
+                                netdev_err(bp->dev,
+                                           "BUG: TX buffers exhausted mid-frame\n");
 
-                        dma_unmap_single(&bp->pdev->dev, rp->mapping, skb->len,
-                                                         DMA_TO_DEVICE);
-                        rp->skb = NULL;
-                        dev_kfree_skb_irq(skb);
+                        desc->ctrl = ctrl | MACB_BIT(TX_USED);
                 }
 
-                bp->tx_head = bp->tx_tail = 0;
-
-                /* Enable the transmitter again */
-                if (status & MACB_BIT(TGO))
-                        macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TE));
+                dma_unmap_single(&bp->pdev->dev, tx_skb->mapping, skb->len,
+                                 DMA_TO_DEVICE);
+                tx_skb->skb = NULL;
+                dev_kfree_skb(skb);
         }
 
-        if (!(status & MACB_BIT(COMP)))
-                /*
-                 * This may happen when a buffer becomes complete
-                 * between reading the ISR and scanning the
-                 * descriptors.  Nothing to worry about.
-                 */
-                return;
+        /* Make descriptor updates visible to hardware */
+        wmb();
+
+        /* Reinitialize the TX desc queue */
+        macb_writel(bp, TBQP, bp->tx_ring_dma);
+        /* Make TX ring reflect state of hardware */
+        bp->tx_head = bp->tx_tail = 0;
+
+        /* Now we are ready to start transmission again */
+        netif_wake_queue(bp->dev);
+
+        /* Housework before enabling TX IRQ */
+        macb_writel(bp, TSR, macb_readl(bp, TSR));
+        macb_writel(bp, IER, MACB_TX_INT_FLAGS);
+}
+
+static void macb_tx_interrupt(struct macb *bp)
+{
+        unsigned int tail;
+        unsigned int head;
+        u32 status;
+
+        status = macb_readl(bp, TSR);
+        macb_writel(bp, TSR, status);
+
+        netdev_vdbg(bp->dev, "macb_tx_interrupt status = 0x%03lx\n",
+                (unsigned long)status);
 
         head = bp->tx_head;
-        for (tail = bp->tx_tail; tail != head; tail = NEXT_TX(tail)) {
-                struct ring_info *rp = &bp->tx_skb[tail];
-                struct sk_buff *skb = rp->skb;
-                u32 bufstat;
+        for (tail = bp->tx_tail; tail != head; tail++) {
+                struct macb_tx_skb      *tx_skb;
+                struct sk_buff          *skb;
+                struct macb_dma_desc    *desc;
+                u32                     ctrl;
 
-                BUG_ON(skb == NULL);
+                desc = macb_tx_desc(bp, tail);
 
+                /* Make hw descriptor updates visible to CPU */
                 rmb();
-                bufstat = bp->tx_ring[tail].ctrl;
 
-                if (!(bufstat & MACB_BIT(TX_USED)))
+                ctrl = desc->ctrl;
+
+                if (!(ctrl & MACB_BIT(TX_USED)))
                         break;
 
-                netdev_dbg(bp->dev, "skb %u (data %p) TX complete\n",
-                           tail, skb->data);
-                dma_unmap_single(&bp->pdev->dev, rp->mapping, skb->len,
+                tx_skb = macb_tx_skb(bp, tail);
+                skb = tx_skb->skb;
+
+                netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
+                        macb_tx_ring_wrap(tail), skb->data);
+                dma_unmap_single(&bp->pdev->dev, tx_skb->mapping, skb->len,
                                  DMA_TO_DEVICE);
                 bp->stats.tx_packets++;
                 bp->stats.tx_bytes += skb->len;
-                rp->skb = NULL;
+                tx_skb->skb = NULL;
                 dev_kfree_skb_irq(skb);
         }
 
         bp->tx_tail = tail;
-        if (netif_queue_stopped(bp->dev) &&
-            TX_BUFFS_AVAIL(bp) > MACB_TX_WAKEUP_THRESH)
+        if (netif_queue_stopped(bp->dev)
+                        && CIRC_CNT(bp->tx_head, bp->tx_tail,
+                                    TX_RING_SIZE) <= MACB_TX_WAKEUP_THRESH)
                 netif_wake_queue(bp->dev);
 }
 
@@ -392,31 +530,48 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 {
         unsigned int len;
         unsigned int frag;
-        unsigned int offset = 0;
+        unsigned int offset;
         struct sk_buff *skb;
+        struct macb_dma_desc *desc;
 
-        len = MACB_BFEXT(RX_FRMLEN, bp->rx_ring[last_frag].ctrl);
+        desc = macb_rx_desc(bp, last_frag);
+        len = MACB_BFEXT(RX_FRMLEN, desc->ctrl);
 
-        netdev_dbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
-                   first_frag, last_frag, len);
+        netdev_vdbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
+                macb_rx_ring_wrap(first_frag),
+                macb_rx_ring_wrap(last_frag), len);
 
-        skb = netdev_alloc_skb(bp->dev, len + RX_OFFSET);
+        /*
+         * The ethernet header starts NET_IP_ALIGN bytes into the
+         * first buffer. Since the header is 14 bytes, this makes the
+         * payload word-aligned.
+         *
+         * Instead of calling skb_reserve(NET_IP_ALIGN), we just copy
+         * the two padding bytes into the skb so that we avoid hitting
+         * the slowpath in memcpy(), and pull them off afterwards.
+         */
+        skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN);
         if (!skb) {
                 bp->stats.rx_dropped++;
-                for (frag = first_frag; ; frag = NEXT_RX(frag)) {
-                        bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
+                for (frag = first_frag; ; frag++) {
+                        desc = macb_rx_desc(bp, frag);
+                        desc->addr &= ~MACB_BIT(RX_USED);
                         if (frag == last_frag)
                                 break;
                 }
+
+                /* Make descriptor updates visible to hardware */
                 wmb();
+
                 return 1;
         }
 
-        skb_reserve(skb, RX_OFFSET);
+        offset = 0;
+        len += NET_IP_ALIGN;
         skb_checksum_none_assert(skb);
         skb_put(skb, len);
 
-        for (frag = first_frag; ; frag = NEXT_RX(frag)) {
+        for (frag = first_frag; ; frag++) {
                 unsigned int frag_len = RX_BUFFER_SIZE;
 
                 if (offset + frag_len > len) {
@@ -424,22 +579,24 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
                         frag_len = len - offset;
                 }
                 skb_copy_to_linear_data_offset(skb, offset,
-                                               (bp->rx_buffers +
-                                                (RX_BUFFER_SIZE * frag)),
-                                               frag_len);
+                                macb_rx_buffer(bp, frag), frag_len);
                 offset += RX_BUFFER_SIZE;
-                bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
-                wmb();
+                desc = macb_rx_desc(bp, frag);
+                desc->addr &= ~MACB_BIT(RX_USED);
 
                 if (frag == last_frag)
                         break;
         }
 
+        /* Make descriptor updates visible to hardware */
+        wmb();
+
+        __skb_pull(skb, NET_IP_ALIGN);
         skb->protocol = eth_type_trans(skb, bp->dev);
 
         bp->stats.rx_packets++;
-        bp->stats.rx_bytes += len;
-        netdev_dbg(bp->dev, "received skb of length %u, csum: %08x\n",
+        bp->stats.rx_bytes += skb->len;
+        netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
                    skb->len, skb->csum);
         netif_receive_skb(skb);
 
@@ -452,8 +609,12 @@ static void discard_partial_frame(struct macb *bp, unsigned int begin,
 {
         unsigned int frag;
 
-        for (frag = begin; frag != end; frag = NEXT_RX(frag))
-                bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
+        for (frag = begin; frag != end; frag++) {
+                struct macb_dma_desc *desc = macb_rx_desc(bp, frag);
+                desc->addr &= ~MACB_BIT(RX_USED);
+        }
+
+        /* Make descriptor updates visible to hardware */
         wmb();
 
         /*
@@ -466,15 +627,18 @@ static void discard_partial_frame(struct macb *bp, unsigned int begin,
 static int macb_rx(struct macb *bp, int budget)
 {
         int received = 0;
-        unsigned int tail = bp->rx_tail;
+        unsigned int tail;
         int first_frag = -1;
 
-        for (; budget > 0; tail = NEXT_RX(tail)) {
+        for (tail = bp->rx_tail; budget > 0; tail++) {
+                struct macb_dma_desc *desc = macb_rx_desc(bp, tail);
                 u32 addr, ctrl;
 
+                /* Make hw descriptor updates visible to CPU */
                 rmb();
-                addr = bp->rx_ring[tail].addr;
-                ctrl = bp->rx_ring[tail].ctrl;
+
+                addr = desc->addr;
+                ctrl = desc->ctrl;
 
                 if (!(addr & MACB_BIT(RX_USED)))
                         break;
@@ -517,7 +681,7 @@ static int macb_poll(struct napi_struct *napi, int budget)
 
         work_done = 0;
 
-        netdev_dbg(bp->dev, "poll: status = %08lx, budget = %d\n",
+        netdev_vdbg(bp->dev, "poll: status = %08lx, budget = %d\n",
                    (unsigned long)status, budget);
 
         work_done = macb_rx(bp, budget);
@@ -552,10 +716,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
         while (status) {
                 /* close possible race with dev_close */
                 if (unlikely(!netif_running(dev))) {
-                        macb_writel(bp, IDR, ~0UL);
+                        macb_writel(bp, IDR, -1);
                         break;
                 }
 
+                netdev_vdbg(bp->dev, "isr = 0x%08lx\n", (unsigned long)status);
+
                 if (status & MACB_RX_INT_FLAGS) {
                         /*
                          * There's no point taking any more interrupts
@@ -567,14 +733,19 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
                         macb_writel(bp, IDR, MACB_RX_INT_FLAGS);
 
                         if (napi_schedule_prep(&bp->napi)) {
-                                netdev_dbg(bp->dev, "scheduling RX softirq\n");
+                                netdev_vdbg(bp->dev, "scheduling RX softirq\n");
                                 __napi_schedule(&bp->napi);
                         }
                 }
 
-                if (status & (MACB_BIT(TCOMP) | MACB_BIT(ISR_TUND) |
-                            MACB_BIT(ISR_RLE)))
-                        macb_tx(bp);
+                if (unlikely(status & (MACB_TX_ERR_FLAGS))) {
+                        macb_writel(bp, IDR, MACB_TX_INT_FLAGS);
+                        schedule_work(&bp->tx_error_task);
+                        break;
+                }
+
+                if (status & MACB_BIT(TCOMP))
+                        macb_tx_interrupt(bp);
 
                 /*
                  * Link change detection isn't possible with RMII, so we'll
@@ -626,11 +797,13 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
         struct macb *bp = netdev_priv(dev);
         dma_addr_t mapping;
         unsigned int len, entry;
+        struct macb_dma_desc *desc;
+        struct macb_tx_skb *tx_skb;
         u32 ctrl;
         unsigned long flags;
 
-#ifdef DEBUG
-        netdev_dbg(bp->dev,
+#if defined(DEBUG) && defined(VERBOSE_DEBUG)
+        netdev_vdbg(bp->dev,
                    "start_xmit: len %u head %p data %p tail %p end %p\n",
                    skb->len, skb->head, skb->data,
                    skb_tail_pointer(skb), skb_end_pointer(skb));
@@ -642,7 +815,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
         spin_lock_irqsave(&bp->lock, flags);
 
         /* This is a hard error, log it. */
-        if (TX_BUFFS_AVAIL(bp) < 1) {
+        if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1) {
                 netif_stop_queue(dev);
                 spin_unlock_irqrestore(&bp->lock, flags);
                 netdev_err(bp->dev, "BUG! Tx Ring full when queue awake!\n");
@@ -651,13 +824,16 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
                 return NETDEV_TX_BUSY;
         }
 
-        entry = bp->tx_head;
-        netdev_dbg(bp->dev, "Allocated ring entry %u\n", entry);
+        entry = macb_tx_ring_wrap(bp->tx_head);
+        bp->tx_head++;
+        netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry);
         mapping = dma_map_single(&bp->pdev->dev, skb->data,
                                  len, DMA_TO_DEVICE);
-        bp->tx_skb[entry].skb = skb;
-        bp->tx_skb[entry].mapping = mapping;
-        netdev_dbg(bp->dev, "Mapped skb data %p to DMA addr %08lx\n",
+
+        tx_skb = &bp->tx_skb[entry];
+        tx_skb->skb = skb;
+        tx_skb->mapping = mapping;
+        netdev_vdbg(bp->dev, "Mapped skb data %p to DMA addr %08lx\n",
                    skb->data, (unsigned long)mapping);
 
         ctrl = MACB_BF(TX_FRMLEN, len);
@@ -665,18 +841,18 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
         if (entry == (TX_RING_SIZE - 1))
                 ctrl |= MACB_BIT(TX_WRAP);
 
-        bp->tx_ring[entry].addr = mapping;
-        bp->tx_ring[entry].ctrl = ctrl;
-        wmb();
+        desc = &bp->tx_ring[entry];
+        desc->addr = mapping;
+        desc->ctrl = ctrl;
 
-        entry = NEXT_TX(entry);
-        bp->tx_head = entry;
+        /* Make newly initialized descriptor visible to hardware */
+        wmb();
 
         skb_tx_timestamp(skb);
 
         macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
 
-        if (TX_BUFFS_AVAIL(bp) < 1)
+        if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1)
                 netif_stop_queue(dev);
 
         spin_unlock_irqrestore(&bp->lock, flags);
@@ -712,7 +888,7 @@ static int macb_alloc_consistent(struct macb *bp)
 {
         int size;
 
-        size = TX_RING_SIZE * sizeof(struct ring_info);
+        size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
         bp->tx_skb = kmalloc(size, GFP_KERNEL);
         if (!bp->tx_skb)
                 goto out_err;
@@ -775,9 +951,6 @@ static void macb_init_rings(struct macb *bp)
 
 static void macb_reset_hw(struct macb *bp)
 {
-        /* Make sure we have the write buffer for ourselves */
-        wmb();
-
         /*
          * Disable RX and TX (XXX: Should we halt the transmission
          * more gracefully?)
@@ -788,11 +961,11 @@ static void macb_reset_hw(struct macb *bp)
         macb_writel(bp, NCR, MACB_BIT(CLRSTAT));
 
         /* Clear all status flags */
-        macb_writel(bp, TSR, ~0UL);
-        macb_writel(bp, RSR, ~0UL);
+        macb_writel(bp, TSR, -1);
+        macb_writel(bp, RSR, -1);
 
         /* Disable all interrupts */
-        macb_writel(bp, IDR, ~0UL);
+        macb_writel(bp, IDR, -1);
         macb_readl(bp, ISR);
 }
 
@@ -860,8 +1033,12 @@ static u32 macb_dbw(struct macb *bp)
 }
 
 /*
- * Configure the receive DMA engine to use the correct receive buffer size.
- * This is a configurable parameter for GEM.
+ * Configure the receive DMA engine
+ * - use the correct receive buffer size
+ * - set the possibility to use INCR16 bursts
+ *   (if not supported by FIFO, it will fallback to default)
+ * - set both rx/tx packet buffers to full memory size
+ * These are configurable parameters for GEM.
  */
 static void macb_configure_dma(struct macb *bp)
 {
@@ -870,6 +1047,8 @@ static void macb_configure_dma(struct macb *bp)
         if (macb_is_gem(bp)) {
                 dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
                 dmacfg |= GEM_BF(RXBS, RX_BUFFER_SIZE / 64);
+                dmacfg |= GEM_BF(FBLDO, 16);
+                dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
                 gem_writel(bp, DMACFG, dmacfg);
         }
 }
@@ -879,9 +1058,10 @@ static void macb_init_hw(struct macb *bp)
         u32 config;
 
         macb_reset_hw(bp);
-        __macb_set_hwaddr(bp);
+        macb_set_hwaddr(bp);
 
         config = macb_mdc_clk_div(bp);
+        config |= MACB_BF(RBOF, NET_IP_ALIGN);  /* Make eth data aligned */
         config |= MACB_BIT(PAE);                /* PAuse Enable */
         config |= MACB_BIT(DRFCS);              /* Discard Rx FCS */
         config |= MACB_BIT(BIG);                /* Receive oversized frames */
@@ -891,6 +1071,8 @@ static void macb_init_hw(struct macb *bp)
                 config |= MACB_BIT(NBC);        /* No BroadCast */
         config |= macb_dbw(bp);
         macb_writel(bp, NCFGR, config);
+        bp->speed = SPEED_10;
+        bp->duplex = DUPLEX_HALF;
 
         macb_configure_dma(bp);
 
@@ -902,13 +1084,8 @@ static void macb_init_hw(struct macb *bp)
         macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE));
 
         /* Enable interrupts */
-        macb_writel(bp, IER, (MACB_BIT(RCOMP)
-                              | MACB_BIT(RXUBR)
-                              | MACB_BIT(ISR_TUND)
-                              | MACB_BIT(ISR_RLE)
-                              | MACB_BIT(TXERR)
-                              | MACB_BIT(TCOMP)
-                              | MACB_BIT(ISR_ROVR)
+        macb_writel(bp, IER, (MACB_RX_INT_FLAGS
+                              | MACB_TX_INT_FLAGS
                               | MACB_BIT(HRESP)));
 
 }
@@ -996,7 +1173,7 @@ static void macb_sethashtable(struct net_device *dev)
 /*
  * Enable/Disable promiscuous and multicast modes.
  */
-static void macb_set_rx_mode(struct net_device *dev)
+void macb_set_rx_mode(struct net_device *dev)
 {
         unsigned long cfg;
         struct macb *bp = netdev_priv(dev);
@@ -1028,6 +1205,7 @@ static void macb_set_rx_mode(struct net_device *dev)
 
         macb_writel(bp, NCFGR, cfg);
 }
+EXPORT_SYMBOL_GPL(macb_set_rx_mode);
 
 static int macb_open(struct net_device *dev)
 {
@@ -1043,9 +1221,6 @@ static int macb_open(struct net_device *dev)
         if (!bp->phy_dev)
                 return -EAGAIN;
 
-        if (!is_valid_ether_addr(dev->dev_addr))
-                return -EADDRNOTAVAIL;
-
         err = macb_alloc_consistent(bp);
         if (err) {
                 netdev_err(dev, "Unable to allocate DMA memory (error %d)\n",
@@ -1135,7 +1310,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
         return nstat;
 }
 
-static struct net_device_stats *macb_get_stats(struct net_device *dev)
+struct net_device_stats *macb_get_stats(struct net_device *dev)
 {
         struct macb *bp = netdev_priv(dev);
         struct net_device_stats *nstat = &bp->stats;
@@ -1181,6 +1356,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 
         return nstat;
 }
+EXPORT_SYMBOL_GPL(macb_get_stats);
 
 static int macb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
@@ -1204,25 +1380,55 @@ static int macb_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
         return phy_ethtool_sset(phydev, cmd);
 }
 
-static void macb_get_drvinfo(struct net_device *dev,
-                             struct ethtool_drvinfo *info)
+static int macb_get_regs_len(struct net_device *netdev)
+{
+        return MACB_GREGS_NBR * sizeof(u32);
+}
+
+static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs,
+                          void *p)
 {
         struct macb *bp = netdev_priv(dev);
+        unsigned int tail, head;
+        u32 *regs_buff = p;
+
+        regs->version = (macb_readl(bp, MID) & ((1 << MACB_REV_SIZE) - 1))
+                        | MACB_GREGS_VERSION;
+
+        tail = macb_tx_ring_wrap(bp->tx_tail);
+        head = macb_tx_ring_wrap(bp->tx_head);
+
+        regs_buff[0]  = macb_readl(bp, NCR);
+        regs_buff[1]  = macb_or_gem_readl(bp, NCFGR);
+        regs_buff[2]  = macb_readl(bp, NSR);
+        regs_buff[3]  = macb_readl(bp, TSR);
+        regs_buff[4]  = macb_readl(bp, RBQP);
+        regs_buff[5]  = macb_readl(bp, TBQP);
+        regs_buff[6]  = macb_readl(bp, RSR);
+        regs_buff[7]  = macb_readl(bp, IMR);
 
-        strcpy(info->driver, bp->pdev->dev.driver->name);
-        strcpy(info->version, "$Revision: 1.14 $");
-        strcpy(info->bus_info, dev_name(&bp->pdev->dev));
+        regs_buff[8]  = tail;
+        regs_buff[9]  = head;
+        regs_buff[10] = macb_tx_dma(bp, tail);
+        regs_buff[11] = macb_tx_dma(bp, head);
+
+        if (macb_is_gem(bp)) {
+                regs_buff[12] = gem_readl(bp, USRIO);
+                regs_buff[13] = gem_readl(bp, DMACFG);
+        }
 }
 
-static const struct ethtool_ops macb_ethtool_ops = {
+const struct ethtool_ops macb_ethtool_ops = {
         .get_settings           = macb_get_settings,
         .set_settings           = macb_set_settings,
-        .get_drvinfo            = macb_get_drvinfo,
+        .get_regs_len           = macb_get_regs_len,
+        .get_regs               = macb_get_regs,
         .get_link               = ethtool_op_get_link,
         .get_ts_info            = ethtool_op_get_ts_info,
 };
+EXPORT_SYMBOL_GPL(macb_ethtool_ops);
 
-static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
         struct macb *bp = netdev_priv(dev);
         struct phy_device *phydev = bp->phy_dev;
@@ -1235,6 +1441,7 @@ static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
         return phy_mii_ioctl(phydev, rq, cmd);
 }
+EXPORT_SYMBOL_GPL(macb_ioctl);
 
 static const struct net_device_ops macb_netdev_ops = {
         .ndo_open               = macb_open,
@@ -1306,6 +1513,7 @@ static int __init macb_probe(struct platform_device *pdev)
         struct phy_device *phydev;
         u32 config;
         int err = -ENXIO;
+        struct pinctrl *pinctrl;
 
         regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
         if (!regs) {
@@ -1313,6 +1521,15 @@ static int __init macb_probe(struct platform_device *pdev)
                 goto err_out;
         }
 
+        pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
+        if (IS_ERR(pinctrl)) {
+                err = PTR_ERR(pinctrl);
+                if (err == -EPROBE_DEFER)
+                        goto err_out;
+
+                dev_warn(&pdev->dev, "No pinctrl provided\n");
+        }
+
         err = -ENOMEM;
         dev = alloc_etherdev(sizeof(*bp));
         if (!dev)
@@ -1328,6 +1545,7 @@ static int __init macb_probe(struct platform_device *pdev)
         bp->dev = dev;
 
         spin_lock_init(&bp->lock);
+        INIT_WORK(&bp->tx_error_task, macb_tx_error_task);
 
         bp->pclk = clk_get(&pdev->dev, "pclk");
         if (IS_ERR(bp->pclk)) {
@@ -1384,7 +1602,9 @@ static int __init macb_probe(struct platform_device *pdev)
                 bp->phy_interface = err;
         }
 
-        if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
+        if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII)
+                macb_or_gem_writel(bp, USRIO, GEM_BIT(RGMII));
+        else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
 #if defined(CONFIG_ARCH_AT91)
                 macb_or_gem_writel(bp, USRIO, (MACB_BIT(RMII) |
                                                MACB_BIT(CLKEN)));
@@ -1398,8 +1618,6 @@ static int __init macb_probe(struct platform_device *pdev)
                 macb_or_gem_writel(bp, USRIO, MACB_BIT(MII));
 #endif
 
-        bp->tx_pending = DEF_TX_RING_PENDING;
-
         err = register_netdev(dev);
         if (err) {
                 dev_err(&pdev->dev, "Cannot register net device, aborting.\n");