Merge branch 'mvneta'

Willy Tarreau says:

====================
Assorted mvneta fixes and improvements

this series provides some fixes for a number of issues met with the
mvneta driver, then adds some improvements. Patches 1-5 are fixes
and would be needed in 3.13 and likely -stable. The next ones are
performance improvements and cleanups :

  - driver lockup when reading stats while sending traffic from multiple
    CPUs : this obviously only happens on SMP and is the result of missing
    locking on the driver. The problem was present since the introduction
    of the driver in 3.8. The first patch performs some changes that are
    needed for the second one which actually fixes the issue by using
    per-cpu counters. It could make sense to backport this to the relevant
    stable versions.

  - mvneta_tx_timeout calls various functions to reset the NIC, and these
    functions sleep, which is not allowed here, resulting in a panic.
    Better completely disable this Tx timeout handler for now since it is
    never called. The problem was encountered while developing some new
    features, it's uncertain whether it's possible to reproduce it with
    regular usage, so maybe a backport to stable is not needed.

  - replace the Tx timer with a real Tx IRQ. As first reported by Arnaud
    Ebalard and explained by Eric Dumazet, there is no way this driver
    can work correctly if it uses a driver to recycle the Tx descriptors.
    If too many packets are sent at once, the driver quickly ends up with
    no descriptors (which happens twice as easily in GSO) and has to wait
    10ms for recycling its descriptors and being able to send again. Eric
    has worked around this in the core GSO code. But still when routing
    traffic or sending UDP packets, the limitation is very visible. Using
    Tx IRQs allows Tx descriptors to be recycled when sent. The coalesce
    value is still configurable using ethtool. This fix turns the UDP
    send bitrate from 134 Mbps to 987 Mbps (ie: line rate). It's made of
    two patches, one to add the relevant bits from the original Marvell's
    driver, and another one to implement the change. I don't know if it
    should be backported to stable, as the bug only causes poor performance.

  - Patches 6..8 are essentially cleanups, code deduplication and minor
    optimizations for not re-fetching a value we already have (status).

  - patch 9 changes the prefetch of Rx descriptor from current one to
    next one. In benchmarks, it results in about 1% general performance
    increase on HTTP traffic, probably because prefetching the current
    descriptor does not leave enough time between the start of prefetch
    and its usage.

  - patch 10 implements support for build_skb() on Rx path. The driver
    now preallocates frags instead of skbs and builds an skb just before
    delivering it. This results in a 2% performance increase on HTTP
    traffic, and up to 5% on small packet Rx rate.

  - patch 11 implements rx_copybreak for small packets (256 bytes). It
    avoids a dma_map_single()/dma_unmap_single() and increases the Rx
    rate by 16.4%, from 486kpps to 573kpps. Further improvements up to
    711kpps are possible depending how the DMA is used.

  - patches 12 and 13 are extra cleanups made possible by some of the
    simplifications above.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/marvell/mvneta.c

@@ -101,16 +101,56 @@
 #define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
 #define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
 #define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))
+
+/* Exception Interrupt Port/Queue Cause register */
+
 #define MVNETA_INTR_NEW_CAUSE                    0x25a0
-#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
 #define MVNETA_INTR_NEW_MASK                     0x25a4
+
+/* bits  0..7  = TXQ SENT, one bit per queue.
+ * bits  8..15 = RXQ OCCUP, one bit per queue.
+ * bits 16..23 = RXQ FREE, one bit per queue.
+ * bit  29 = OLD_REG_SUM, see old reg ?
+ * bit  30 = TX_ERR_SUM, one bit for 4 ports
+ * bit  31 = MISC_SUM,   one bit for 4 ports
+ */
+#define      MVNETA_TX_INTR_MASK(nr_txqs)        (((1 << nr_txqs) - 1) << 0)
+#define      MVNETA_TX_INTR_MASK_ALL             (0xff << 0)
+#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
+#define      MVNETA_RX_INTR_MASK_ALL             (0xff << 8)
+
 #define MVNETA_INTR_OLD_CAUSE                    0x25a8
 #define MVNETA_INTR_OLD_MASK                     0x25ac
+
+/* Data Path Port/Queue Cause Register */
 #define MVNETA_INTR_MISC_CAUSE                   0x25b0
 #define MVNETA_INTR_MISC_MASK                    0x25b4
+
+#define      MVNETA_CAUSE_PHY_STATUS_CHANGE      BIT(0)
+#define      MVNETA_CAUSE_LINK_CHANGE            BIT(1)
+#define      MVNETA_CAUSE_PTP                    BIT(4)
+
+#define      MVNETA_CAUSE_INTERNAL_ADDR_ERR      BIT(7)
+#define      MVNETA_CAUSE_RX_OVERRUN             BIT(8)
+#define      MVNETA_CAUSE_RX_CRC_ERROR           BIT(9)
+#define      MVNETA_CAUSE_RX_LARGE_PKT           BIT(10)
+#define      MVNETA_CAUSE_TX_UNDERUN             BIT(11)
+#define      MVNETA_CAUSE_PRBS_ERR               BIT(12)
+#define      MVNETA_CAUSE_PSC_SYNC_CHANGE        BIT(13)
+#define      MVNETA_CAUSE_SERDES_SYNC_ERR        BIT(14)
+
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT    16
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_ALL_MASK   (0xF << MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT)
+#define      MVNETA_CAUSE_BMU_ALLOC_ERR_MASK(pool) (1 << (MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT + (pool)))
+
+#define      MVNETA_CAUSE_TXQ_ERROR_SHIFT        24
+#define      MVNETA_CAUSE_TXQ_ERROR_ALL_MASK     (0xFF << MVNETA_CAUSE_TXQ_ERROR_SHIFT)
+#define      MVNETA_CAUSE_TXQ_ERROR_MASK(q)      (1 << (MVNETA_CAUSE_TXQ_ERROR_SHIFT + (q)))
+
 #define MVNETA_INTR_ENABLE                       0x25b8
 #define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
-#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000  // note: neta says it's 0x000000FF
+
 #define MVNETA_RXQ_CMD                           0x2680
 #define      MVNETA_RXQ_DISABLE_SHIFT            8
 #define      MVNETA_RXQ_ENABLE_MASK              0x000000ff
@@ -176,9 +216,6 @@
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
-/* Timer */
-#define MVNETA_TX_DONE_TIMER_PERIOD	10
-
 /* Napi polling weight */
 #define MVNETA_RX_POLL_WEIGHT		64
 
@@ -221,27 +258,25 @@
 
 #define MVNETA_RX_BUF_SIZE(pkt_size)   ((pkt_size) + NET_SKB_PAD)
 
-struct mvneta_stats {
+struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
-	u64	packets;
-	u64	bytes;
+	u64	rx_packets;
+	u64	rx_bytes;
+	u64	tx_packets;
+	u64	tx_bytes;
 };
 
 struct mvneta_port {
 	int pkt_size;
+	unsigned int frag_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
 	struct mvneta_tx_queue *txqs;
-	struct timer_list tx_done_timer;
 	struct net_device *dev;
 
 	u32 cause_rx_tx;
 	struct napi_struct napi;
 
-	/* Flags */
-	unsigned long flags;
-#define MVNETA_F_TX_DONE_TIMER_BIT  0
-
 	/* Napi weight */
 	int weight;
 
@@ -250,8 +285,7 @@ struct mvneta_port {
 	u8 mcast_count[256];
 	u16 tx_ring_size;
 	u16 rx_ring_size;
-	struct mvneta_stats tx_stats;
-	struct mvneta_stats rx_stats;
+	struct mvneta_pcpu_stats *stats;
 
 	struct mii_bus *mii_bus;
 	struct phy_device *phy_dev;
@@ -410,6 +444,8 @@ static int txq_number = 8;
 
 static int rxq_def;
 
+static int rx_copybreak __read_mostly = 256;
+
 #define MVNETA_DRIVER_NAME "mvneta"
 #define MVNETA_DRIVER_VERSION "1.0"
 
@@ -461,21 +497,29 @@ struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 	unsigned int start;
+	int cpu;
 
-	memset(stats, 0, sizeof(struct rtnl_link_stats64));
-
-	do {
-		start = u64_stats_fetch_begin_bh(&pp->rx_stats.syncp);
-		stats->rx_packets = pp->rx_stats.packets;
-		stats->rx_bytes	= pp->rx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&pp->rx_stats.syncp, start));
+	for_each_possible_cpu(cpu) {
+		struct mvneta_pcpu_stats *cpu_stats;
+		u64 rx_packets;
+		u64 rx_bytes;
+		u64 tx_packets;
+		u64 tx_bytes;
 
+		cpu_stats = per_cpu_ptr(pp->stats, cpu);
+		do {
+			start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+			rx_packets = cpu_stats->rx_packets;
+			rx_bytes   = cpu_stats->rx_bytes;
+			tx_packets = cpu_stats->tx_packets;
+			tx_bytes   = cpu_stats->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
 
-	do {
-		start = u64_stats_fetch_begin_bh(&pp->tx_stats.syncp);
-		stats->tx_packets = pp->tx_stats.packets;
-		stats->tx_bytes	= pp->tx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&pp->tx_stats.syncp, start));
+		stats->rx_packets += rx_packets;
+		stats->rx_bytes   += rx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_bytes   += tx_bytes;
+	}
 
 	stats->rx_errors	= dev->stats.rx_errors;
 	stats->rx_dropped	= dev->stats.rx_dropped;
@@ -487,14 +531,14 @@ struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
 
 /* Rx descriptors helper methods */
 
-/* Checks whether the given RX descriptor is both the first and the
- * last descriptor for the RX packet. Each RX packet is currently
+/* Checks whether the RX descriptor having this status is both the first
+ * and the last descriptor for the RX packet. Each RX packet is currently
  * received through a single RX descriptor, so not having each RX
  * descriptor with its first and last bits set is an error
  */
-static int mvneta_rxq_desc_is_first_last(struct mvneta_rx_desc *desc)
+static int mvneta_rxq_desc_is_first_last(u32 status)
 {
-	return (desc->status & MVNETA_RXD_FIRST_LAST_DESC) ==
+	return (status & MVNETA_RXD_FIRST_LAST_DESC) ==
 		MVNETA_RXD_FIRST_LAST_DESC;
 }
 
@@ -570,6 +614,7 @@ mvneta_rxq_next_desc_get(struct mvneta_rx_queue *rxq)
 	int rx_desc = rxq->next_desc_to_proc;
 
 	rxq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(rxq, rx_desc);
+	prefetch(rxq->descs + rxq->next_desc_to_proc);
 	return rxq->descs + rx_desc;
 }
 
@@ -1100,17 +1145,6 @@ static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp,
 	txq->done_pkts_coal = value;
 }
 
-/* Trigger tx done timer in MVNETA_TX_DONE_TIMER_PERIOD msecs */
-static void mvneta_add_tx_done_timer(struct mvneta_port *pp)
-{
-	if (test_and_set_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags) == 0) {
-		pp->tx_done_timer.expires = jiffies +
-			msecs_to_jiffies(MVNETA_TX_DONE_TIMER_PERIOD);
-		add_timer(&pp->tx_done_timer);
-	}
-}
-
-
 /* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
 static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
 				u32 phys_addr, u32 cookie)
@@ -1204,10 +1238,10 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 {
 	u32 status = rx_desc->status;
 
-	if (!mvneta_rxq_desc_is_first_last(rx_desc)) {
+	if (!mvneta_rxq_desc_is_first_last(status)) {
 		netdev_err(pp->dev,
 			   "bad rx status %08x (buffer oversize), size=%d\n",
-			   rx_desc->status, rx_desc->data_size);
+			   status, rx_desc->data_size);
 		return;
 	}
 
@@ -1231,13 +1265,12 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 	}
 }
 
-/* Handle RX checksum offload */
-static void mvneta_rx_csum(struct mvneta_port *pp,
-			   struct mvneta_rx_desc *rx_desc,
+/* Handle RX checksum offload based on the descriptor's status */
+static void mvneta_rx_csum(struct mvneta_port *pp, u32 status,
 			   struct sk_buff *skb)
 {
-	if ((rx_desc->status & MVNETA_RXD_L3_IP4) &&
-	    (rx_desc->status & MVNETA_RXD_L4_CSUM_OK)) {
+	if ((status & MVNETA_RXD_L3_IP4) &&
+	    (status & MVNETA_RXD_L4_CSUM_OK)) {
 		skb->csum = 0;
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		return;
@@ -1246,13 +1279,16 @@ static void mvneta_rx_csum(struct mvneta_port *pp,
 	skb->ip_summed = CHECKSUM_NONE;
 }
 
-/* Return tx queue pointer (find last set bit) according to causeTxDone reg */
+/* Return tx queue pointer (find last set bit) according to <cause> returned
+ * form tx_done reg. <cause> must not be null. The return value is always a
+ * valid queue for matching the first one found in <cause>.
+ */
 static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
 						     u32 cause)
 {
 	int queue = fls(cause) - 1;
 
-	return (queue < 0 || queue >= txq_number) ? NULL : &pp->txqs[queue];
+	return &pp->txqs[queue];
 }
 
 /* Free tx queue skbuffs */
@@ -1278,15 +1314,16 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 }
 
 /* Handle end of transmission */
-static int mvneta_txq_done(struct mvneta_port *pp,
+static void mvneta_txq_done(struct mvneta_port *pp,
 			   struct mvneta_tx_queue *txq)
 {
 	struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
 	int tx_done;
 
 	tx_done = mvneta_txq_sent_desc_proc(pp, txq);
-	if (tx_done == 0)
-		return tx_done;
+	if (!tx_done)
+		return;
+
 	mvneta_txq_bufs_free(pp, txq, tx_done);
 
 	txq->count -= tx_done;
@@ -1295,8 +1332,22 @@ static int mvneta_txq_done(struct mvneta_port *pp,
 		if (txq->size - txq->count >= MAX_SKB_FRAGS + 1)
 			netif_tx_wake_queue(nq);
 	}
+}
 
-	return tx_done;
+static void *mvneta_frag_alloc(const struct mvneta_port *pp)
+{
+	if (likely(pp->frag_size <= PAGE_SIZE))
+		return netdev_alloc_frag(pp->frag_size);
+	else
+		return kmalloc(pp->frag_size, GFP_ATOMIC);
+}
+
+static void mvneta_frag_free(const struct mvneta_port *pp, void *data)
+{
+	if (likely(pp->frag_size <= PAGE_SIZE))
+		put_page(virt_to_head_page(data));
+	else
+		kfree(data);
 }
 
 /* Refill processing */
@@ -1305,22 +1356,21 @@ static int mvneta_rx_refill(struct mvneta_port *pp,
 
 {
 	dma_addr_t phys_addr;
-	struct sk_buff *skb;
+	void *data;
 
-	skb = netdev_alloc_skb(pp->dev, pp->pkt_size);
-	if (!skb)
+	data = mvneta_frag_alloc(pp);
+	if (!data)
 		return -ENOMEM;
 
-	phys_addr = dma_map_single(pp->dev->dev.parent, skb->head,
+	phys_addr = dma_map_single(pp->dev->dev.parent, data,
 				   MVNETA_RX_BUF_SIZE(pp->pkt_size),
 				   DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) {
-		dev_kfree_skb(skb);
+		mvneta_frag_free(pp, data);
 		return -ENOMEM;
 	}
 
-	mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)skb);
-
+	mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)data);
 	return 0;
 }
 
@@ -1374,9 +1424,9 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
 	for (i = 0; i < rxq->size; i++) {
 		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
-		struct sk_buff *skb = (struct sk_buff *)rx_desc->buf_cookie;
+		void *data = (void *)rx_desc->buf_cookie;
 
-		dev_kfree_skb_any(skb);
+		mvneta_frag_free(pp, data);
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 	}
@@ -1391,6 +1441,8 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 {
 	struct net_device *dev = pp->dev;
 	int rx_done, rx_filled;
+	u32 rcvd_pkts = 0;
+	u32 rcvd_bytes = 0;
 
 	/* Get number of received packets */
 	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
@@ -1405,53 +1457,89 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 	while (rx_done < rx_todo) {
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
 		struct sk_buff *skb;
+		unsigned char *data;
 		u32 rx_status;
 		int rx_bytes, err;
 
-		prefetch(rx_desc);
 		rx_done++;
 		rx_filled++;
 		rx_status = rx_desc->status;
-		skb = (struct sk_buff *)rx_desc->buf_cookie;
+		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
+		data = (unsigned char *)rx_desc->buf_cookie;
 
-		if (!mvneta_rxq_desc_is_first_last(rx_desc) ||
+		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
+		err_drop_frame:
 			dev->stats.rx_errors++;
 			mvneta_rx_error(pp, rx_desc);
-			mvneta_rx_desc_fill(rx_desc, rx_desc->buf_phys_addr,
-					    (u32)skb);
+			/* leave the descriptor untouched */
 			continue;
 		}
 
-		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
+		if (rx_bytes <= rx_copybreak) {
+			/* better copy a small frame and not unmap the DMA region */
+			skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
+			if (unlikely(!skb))
+				goto err_drop_frame;
+
+			dma_sync_single_range_for_cpu(dev->dev.parent,
+			                              rx_desc->buf_phys_addr,
+			                              MVNETA_MH_SIZE + NET_SKB_PAD,
+			                              rx_bytes,
+			                              DMA_FROM_DEVICE);
+			memcpy(skb_put(skb, rx_bytes),
+			       data + MVNETA_MH_SIZE + NET_SKB_PAD,
+			       rx_bytes);
+
+			skb->protocol = eth_type_trans(skb, dev);
+			mvneta_rx_csum(pp, rx_status, skb);
+			napi_gro_receive(&pp->napi, skb);
+
+			rcvd_pkts++;
+			rcvd_bytes += rx_bytes;
+
+			/* leave the descriptor and buffer untouched */
+			continue;
+		}
+
+		skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
+		if (!skb)
+			goto err_drop_frame;
+
+		dma_unmap_single(dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
-		rx_bytes = rx_desc->data_size -
-			(ETH_FCS_LEN + MVNETA_MH_SIZE);
-		u64_stats_update_begin(&pp->rx_stats.syncp);
-		pp->rx_stats.packets++;
-		pp->rx_stats.bytes += rx_bytes;
-		u64_stats_update_end(&pp->rx_stats.syncp);
+		rcvd_pkts++;
+		rcvd_bytes += rx_bytes;
 
 		/* Linux processing */
-		skb_reserve(skb, MVNETA_MH_SIZE);
+		skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD);
 		skb_put(skb, rx_bytes);
 
 		skb->protocol = eth_type_trans(skb, dev);
 
-		mvneta_rx_csum(pp, rx_desc, skb);
+		mvneta_rx_csum(pp, rx_status, skb);
 
 		napi_gro_receive(&pp->napi, skb);
 
 		/* Refill processing */
 		err = mvneta_rx_refill(pp, rx_desc);
 		if (err) {
-			netdev_err(pp->dev, "Linux processing - Can't refill\n");
+			netdev_err(dev, "Linux processing - Can't refill\n");
 			rxq->missed++;
 			rx_filled--;
 		}
 	}
 
+	if (rcvd_pkts) {
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->rx_packets += rcvd_pkts;
+		stats->rx_bytes   += rcvd_bytes;
+		u64_stats_update_end(&stats->syncp);
+	}
+
 	/* Update rxq management counters */
 	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
 
@@ -1582,25 +1670,17 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 
 out:
 	if (frags > 0) {
-		u64_stats_update_begin(&pp->tx_stats.syncp);
-		pp->tx_stats.packets++;
-		pp->tx_stats.bytes += skb->len;
-		u64_stats_update_end(&pp->tx_stats.syncp);
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 
+		u64_stats_update_begin(&stats->syncp);
+		stats->tx_packets++;
+		stats->tx_bytes  += skb->len;
+		u64_stats_update_end(&stats->syncp);
 	} else {
 		dev->stats.tx_dropped++;
 		dev_kfree_skb_any(skb);
 	}
 
-	if (txq->count >= MVNETA_TXDONE_COAL_PKTS)
-		mvneta_txq_done(pp, txq);
-
-	/* If after calling mvneta_txq_done, count equals
-	 * frags, we need to set the timer
-	 */
-	if (txq->count == frags && frags > 0)
-		mvneta_add_tx_done_timer(pp);
-
 	return NETDEV_TX_OK;
 }
 
@@ -1620,33 +1700,26 @@ static void mvneta_txq_done_force(struct mvneta_port *pp,
 	txq->txq_get_index = 0;
 }
 
-/* handle tx done - called from tx done timer callback */
-static u32 mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done,
-			      int *tx_todo)
+/* Handle tx done - called in softirq context. The <cause_tx_done> argument
+ * must be a valid cause according to MVNETA_TXQ_INTR_MASK_ALL.
+ */
+static void mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done)
 {
 	struct mvneta_tx_queue *txq;
-	u32 tx_done = 0;
 	struct netdev_queue *nq;
 
-	*tx_todo = 0;
-	while (cause_tx_done != 0) {
+	while (cause_tx_done) {
 		txq = mvneta_tx_done_policy(pp, cause_tx_done);
-		if (!txq)
-			break;
 
 		nq = netdev_get_tx_queue(pp->dev, txq->id);
 		__netif_tx_lock(nq, smp_processor_id());
 
-		if (txq->count) {
-			tx_done += mvneta_txq_done(pp, txq);
-			*tx_todo += txq->count;
-		}
+		if (txq->count)
+			mvneta_txq_done(pp, txq);
 
 		__netif_tx_unlock(nq);
 		cause_tx_done &= ~((1 << txq->id));
 	}
-
-	return tx_done;
 }
 
 /* Compute crc8 of the specified address, using a unique algorithm ,
@@ -1876,14 +1949,20 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 
 	/* Read cause register */
 	cause_rx_tx = mvreg_read(pp, MVNETA_INTR_NEW_CAUSE) &
-		MVNETA_RX_INTR_MASK(rxq_number);
+		(MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
+
+	/* Release Tx descriptors */
+	if (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL) {
+		mvneta_tx_done_gbe(pp, (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL));
+		cause_rx_tx &= ~MVNETA_TX_INTR_MASK_ALL;
+	}
 
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
 	cause_rx_tx |= pp->cause_rx_tx;
 	if (rxq_number > 1) {
-		while ((cause_rx_tx != 0) && (budget > 0)) {
+		while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) {
 			int count;
 			struct mvneta_rx_queue *rxq;
 			/* get rx queue number from cause_rx_tx */
@@ -1915,7 +1994,7 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 		napi_complete(napi);
 		local_irq_save(flags);
 		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			    MVNETA_RX_INTR_MASK(rxq_number));
+			    MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
 		local_irq_restore(flags);
 	}
 
@@ -1923,56 +2002,19 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	return rx_done;
 }
 
-/* tx done timer callback */
-static void mvneta_tx_done_timer_callback(unsigned long data)
-{
-	struct net_device *dev = (struct net_device *)data;
-	struct mvneta_port *pp = netdev_priv(dev);
-	int tx_done = 0, tx_todo = 0;
-
-	if (!netif_running(dev))
-		return ;
-
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
-	tx_done = mvneta_tx_done_gbe(pp,
-				     (((1 << txq_number) - 1) &
-				      MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK),
-				     &tx_todo);
-	if (tx_todo > 0)
-		mvneta_add_tx_done_timer(pp);
-}
-
 /* Handle rxq fill: allocates rxq skbs; called when initializing a port */
 static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 			   int num)
 {
-	struct net_device *dev = pp->dev;
 	int i;
 
 	for (i = 0; i < num; i++) {
-		struct sk_buff *skb;
-		struct mvneta_rx_desc *rx_desc;
-		unsigned long phys_addr;
-
-		skb = dev_alloc_skb(pp->pkt_size);
-		if (!skb) {
-			netdev_err(dev, "%s:rxq %d, %d of %d buffs  filled\n",
+		memset(rxq->descs + i, 0, sizeof(struct mvneta_rx_desc));
+		if (mvneta_rx_refill(pp, rxq->descs + i) != 0) {
+			netdev_err(pp->dev, "%s:rxq %d, %d of %d buffs  filled\n",
 				__func__, rxq->id, i, num);
 			break;
 		}
-
-		rx_desc = rxq->descs + i;
-		memset(rx_desc, 0, sizeof(struct mvneta_rx_desc));
-		phys_addr = dma_map_single(dev->dev.parent, skb->head,
-					   MVNETA_RX_BUF_SIZE(pp->pkt_size),
-					   DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(dev->dev.parent, phys_addr))) {
-			dev_kfree_skb(skb);
-			break;
-		}
-
-		mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)skb);
 	}
 
 	/* Add this number of RX descriptors as non occupied (ready to
@@ -2192,7 +2234,7 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	/* Unmask interrupts */
 	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-		    MVNETA_RX_INTR_MASK(rxq_number));
+		    MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
 
 	phy_start(pp->phy_dev);
 	netif_tx_start_all_queues(pp->dev);
@@ -2225,16 +2267,6 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 	mvneta_rx_reset(pp);
 }
 
-/* tx timeout callback - display a message and stop/start the network device */
-static void mvneta_tx_timeout(struct net_device *dev)
-{
-	struct mvneta_port *pp = netdev_priv(dev);
-
-	netdev_info(dev, "tx timeout\n");
-	mvneta_stop_dev(pp);
-	mvneta_start_dev(pp);
-}
-
 /* Return positive if MTU is valid */
 static int mvneta_check_mtu_valid(struct net_device *dev, int mtu)
 {
@@ -2282,6 +2314,8 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 	mvneta_cleanup_rxqs(pp);
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
+	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret) {
@@ -2429,6 +2463,8 @@ static int mvneta_open(struct net_device *dev)
 	mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def);
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
+	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret)
@@ -2478,8 +2514,6 @@ static int mvneta_stop(struct net_device *dev)
 	free_irq(dev->irq, pp);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
-	del_timer(&pp->tx_done_timer);
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
 
 	return 0;
 }
@@ -2615,7 +2649,6 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
-	.ndo_tx_timeout      = mvneta_tx_timeout,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -2751,6 +2784,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	const char *mac_from;
 	int phy_mode;
 	int err;
+	int cpu;
 
 	/* Our multiqueue support is not complete, so for now, only
 	 * allow the usage of the first RX queue
@@ -2792,9 +2826,6 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp = netdev_priv(dev);
 
-	u64_stats_init(&pp->tx_stats.syncp);
-	u64_stats_init(&pp->rx_stats.syncp);
-
 	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
@@ -2813,6 +2844,19 @@ static int mvneta_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
+	/* Alloc per-cpu stats */
+	pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
+	if (!pp->stats) {
+		err = -ENOMEM;
+		goto err_unmap;
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct mvneta_pcpu_stats *stats;
+		stats = per_cpu_ptr(pp->stats, cpu);
+		u64_stats_init(&stats->syncp);
+	}
+
 	dt_mac_addr = of_get_mac_address(dn);
 	if (dt_mac_addr) {
 		mac_from = "device tree";
@@ -2828,11 +2872,6 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
-	pp->tx_done_timer.data = (unsigned long)dev;
-	pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
-	init_timer(&pp->tx_done_timer);
-	clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
@@ -2842,7 +2881,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = mvneta_init(pp, phy_addr);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't init eth hal\n");
-		goto err_unmap;
+		goto err_free_stats;
 	}
 	mvneta_port_power_up(pp, phy_mode);
 
@@ -2872,6 +2911,8 @@ static int mvneta_probe(struct platform_device *pdev)
 
 err_deinit:
 	mvneta_deinit(pp);
+err_free_stats:
+	free_percpu(pp->stats);
 err_unmap:
 	iounmap(pp->base);
 err_clk:
@@ -2892,6 +2933,7 @@ static int mvneta_remove(struct platform_device *pdev)
 	unregister_netdev(dev);
 	mvneta_deinit(pp);
 	clk_disable_unprepare(pp->clk);
+	free_percpu(pp->stats);
 	iounmap(pp->base);
 	irq_dispose_mapping(dev->irq);
 	free_netdev(dev);
@@ -2924,3 +2966,4 @@ module_param(rxq_number, int, S_IRUGO);
 module_param(txq_number, int, S_IRUGO);
 
 module_param(rxq_def, int, S_IRUGO);
+module_param(rx_copybreak, int, S_IRUGO | S_IWUSR);