Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Don't OOPS on socket AIO, from Christoph Hellwig.

 2) Scheduled scans should be aborted upon RFKILL, from Emmanuel
    Grumbach.

 3) Fix sleep in atomic context in kvaser_usb, from Ahmed S Darwish.

 4) Fix RCU locking across copy_to_user() in bpf code, from Alexei
    Starovoitov.

 5) Lots of crash, memory leak, short TX packet et al bug fixes in
    sh_eth from Ben Hutchings.

 6) Fix memory corruption in SCTP wrt.  INIT collitions, from Daniel
    Borkmann.

 7) Fix return value logic for poll handlers in netxen, enic, and bnx2x.
    From Eric Dumazet and Govindarajulu Varadarajan.

 8) Header length calculation fix in mac80211 from Fred Chou.

 9) mv643xx_eth doesn't handle highmem correctly in non-TSO code paths.
    From Ezequiel Garcia.

10) udp_diag has bogus logic in it's hash chain skipping, copy same fix
    tcp diag used.  From Herbert Xu.

11) amd-xgbe programs wrong rx flow control register, from Thomas
    Lendacky.

12) Fix race leading to use after free in ping receive path, from Subash
    Abhinov Kasiviswanathan.

13) Cache redirect routes otherwise we can get a heavy backlog of rcu
    jobs liberating DST_NOCACHE entries.  From Hannes Frederic Sowa.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (48 commits)
  net: don't OOPS on socket aio
  stmmac: prevent probe drivers to crash kernel
  bnx2x: fix napi poll return value for repoll
  ipv6: replacing a rt6_info needs to purge possible propagated rt6_infos too
  sh_eth: Fix DMA-API usage for RX buffers
  sh_eth: Check for DMA mapping errors on transmit
  sh_eth: Ensure DMA engines are stopped before freeing buffers
  sh_eth: Remove RX overflow log messages
  ping: Fix race in free in receive path
  udp_diag: Fix socket skipping within chain
  can: kvaser_usb: Fix state handling upon BUS_ERROR events
  can: kvaser_usb: Retry the first bulk transfer on -ETIMEDOUT
  can: kvaser_usb: Send correct context to URB completion
  can: kvaser_usb: Do not sleep in atomic context
  ipv4: try to cache dst_entries which would cause a redirect
  samples: bpf: relax test_maps check
  bpf: rcu lock must not be held when calling copy_to_user()
  net: sctp: fix slab corruption from use after free on INIT collisions
  net: mv643xx_eth: Fix highmem support in non-TSO egress path
  sh_eth: Fix serialisation of interrupt disable with interrupt & NAPI handlers
  ...

2 files changed, 114 insertions, 51 deletions

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 6576243222af..04283fe0e6a7 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -396,6 +396,9 @@ static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = {
 	[TSU_ADRL31]	= 0x01fc,
 };
 
+static void sh_eth_rcv_snd_disable(struct net_device *ndev);
+static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev);
+
 static bool sh_eth_is_gether(struct sh_eth_private *mdp)
 {
 	return mdp->reg_offset == sh_eth_offset_gigabit;
@@ -1120,6 +1123,7 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring;
 	int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring;
 	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	dma_addr_t dma_addr;
 
 	mdp->cur_rx = 0;
 	mdp->cur_tx = 0;
@@ -1133,7 +1137,6 @@ static void sh_eth_ring_format(struct net_device *ndev)
 		/* skb */
 		mdp->rx_skbuff[i] = NULL;
 		skb = netdev_alloc_skb(ndev, skbuff_size);
-		mdp->rx_skbuff[i] = skb;
 		if (skb == NULL)
 			break;
 		sh_eth_set_receive_align(skb);
@@ -1142,9 +1145,15 @@ static void sh_eth_ring_format(struct net_device *ndev)
 		rxdesc = &mdp->rx_ring[i];
 		/* The size of the buffer is a multiple of 16 bytes. */
 		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
-		dma_map_single(&ndev->dev, skb->data, rxdesc->buffer_length,
-			       DMA_FROM_DEVICE);
-		rxdesc->addr = virt_to_phys(skb->data);
+		dma_addr = dma_map_single(&ndev->dev, skb->data,
+					  rxdesc->buffer_length,
+					  DMA_FROM_DEVICE);
+		if (dma_mapping_error(&ndev->dev, dma_addr)) {
+			kfree_skb(skb);
+			break;
+		}
+		mdp->rx_skbuff[i] = skb;
+		rxdesc->addr = dma_addr;
 		rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP);
 
 		/* Rx descriptor address set */
@@ -1316,8 +1325,10 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 		     RFLR);
 
 	sh_eth_write(ndev, sh_eth_read(ndev, EESR), EESR);
-	if (start)
+	if (start) {
+		mdp->irq_enabled = true;
 		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
+	}
 
 	/* PAUSE Prohibition */
 	val = (sh_eth_read(ndev, ECMR) & ECMR_DM) |
@@ -1356,6 +1367,33 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 	return ret;
 }
 
+static void sh_eth_dev_exit(struct net_device *ndev)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	int i;
+
+	/* Deactivate all TX descriptors, so DMA should stop at next
+	 * packet boundary if it's currently running
+	 */
+	for (i = 0; i < mdp->num_tx_ring; i++)
+		mdp->tx_ring[i].status &= ~cpu_to_edmac(mdp, TD_TACT);
+
+	/* Disable TX FIFO egress to MAC */
+	sh_eth_rcv_snd_disable(ndev);
+
+	/* Stop RX DMA at next packet boundary */
+	sh_eth_write(ndev, 0, EDRRR);
+
+	/* Aside from TX DMA, we can't tell when the hardware is
+	 * really stopped, so we need to reset to make sure.
+	 * Before doing that, wait for long enough to *probably*
+	 * finish transmitting the last packet and poll stats.
+	 */
+	msleep(2); /* max frame time at 10 Mbps < 1250 us */
+	sh_eth_get_stats(ndev);
+	sh_eth_reset(ndev);
+}
+
 /* free Tx skb function */
 static int sh_eth_txfree(struct net_device *ndev)
 {
@@ -1400,6 +1438,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 	u16 pkt_len = 0;
 	u32 desc_status;
 	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	dma_addr_t dma_addr;
 
 	boguscnt = min(boguscnt, *quota);
 	limit = boguscnt;
@@ -1447,9 +1486,9 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 			mdp->rx_skbuff[entry] = NULL;
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
-			dma_sync_single_for_cpu(&ndev->dev, rxdesc->addr,
-						ALIGN(mdp->rx_buf_sz, 16),
-						DMA_FROM_DEVICE);
+			dma_unmap_single(&ndev->dev, rxdesc->addr,
+					 ALIGN(mdp->rx_buf_sz, 16),
+					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
 			netif_receive_skb(skb);
@@ -1469,15 +1508,20 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 
 		if (mdp->rx_skbuff[entry] == NULL) {
 			skb = netdev_alloc_skb(ndev, skbuff_size);
-			mdp->rx_skbuff[entry] = skb;
 			if (skb == NULL)
 				break;	/* Better luck next round. */
 			sh_eth_set_receive_align(skb);
-			dma_map_single(&ndev->dev, skb->data,
-				       rxdesc->buffer_length, DMA_FROM_DEVICE);
+			dma_addr = dma_map_single(&ndev->dev, skb->data,
+						  rxdesc->buffer_length,
+						  DMA_FROM_DEVICE);
+			if (dma_mapping_error(&ndev->dev, dma_addr)) {
+				kfree_skb(skb);
+				break;
+			}
+			mdp->rx_skbuff[entry] = skb;
 
 			skb_checksum_none_assert(skb);
-			rxdesc->addr = virt_to_phys(skb->data);
+			rxdesc->addr = dma_addr;
 		}
 		if (entry >= mdp->num_rx_ring - 1)
 			rxdesc->status |=
@@ -1573,7 +1617,6 @@ ignore_link:
 		if (intr_status & EESR_RFRMER) {
 			/* Receive Frame Overflow int */
 			ndev->stats.rx_frame_errors++;
-			netif_err(mdp, rx_err, ndev, "Receive Abort\n");
 		}
 	}
 
@@ -1592,13 +1635,11 @@ ignore_link:
 	if (intr_status & EESR_RDE) {
 		/* Receive Descriptor Empty int */
 		ndev->stats.rx_over_errors++;
-		netif_err(mdp, rx_err, ndev, "Receive Descriptor Empty\n");
 	}
 
 	if (intr_status & EESR_RFE) {
 		/* Receive FIFO Overflow int */
 		ndev->stats.rx_fifo_errors++;
-		netif_err(mdp, rx_err, ndev, "Receive FIFO Overflow\n");
 	}
 
 	if (!mdp->cd->no_ade && (intr_status & EESR_ADE)) {
@@ -1653,7 +1694,12 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
 	if (intr_status & (EESR_RX_CHECK | cd->tx_check | cd->eesr_err_check))
 		ret = IRQ_HANDLED;
 	else
-		goto other_irq;
+		goto out;
+
+	if (!likely(mdp->irq_enabled)) {
+		sh_eth_write(ndev, 0, EESIPR);
+		goto out;
+	}
 
 	if (intr_status & EESR_RX_CHECK) {
 		if (napi_schedule_prep(&mdp->napi)) {
@@ -1684,7 +1730,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
 		sh_eth_error(ndev, intr_status);
 	}
 
-other_irq:
+out:
 	spin_unlock(&mdp->lock);
 
 	return ret;
@@ -1712,7 +1758,8 @@ static int sh_eth_poll(struct napi_struct *napi, int budget)
 	napi_complete(napi);
 
 	/* Reenable Rx interrupts */
-	sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
+	if (mdp->irq_enabled)
+		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 out:
 	return budget - quota;
 }
@@ -1968,40 +2015,50 @@ static int sh_eth_set_ringparam(struct net_device *ndev,
 		return -EINVAL;
 
 	if (netif_running(ndev)) {
+		netif_device_detach(ndev);
 		netif_tx_disable(ndev);
-		/* Disable interrupts by clearing the interrupt mask. */
-		sh_eth_write(ndev, 0x0000, EESIPR);
-		/* Stop the chip's Tx and Rx processes. */
-		sh_eth_write(ndev, 0, EDTRR);
-		sh_eth_write(ndev, 0, EDRRR);
+
+		/* Serialise with the interrupt handler and NAPI, then
+		 * disable interrupts.  We have to clear the
+		 * irq_enabled flag first to ensure that interrupts
+		 * won't be re-enabled.
+		 */
+		mdp->irq_enabled = false;
 		synchronize_irq(ndev->irq);
-	}
+		napi_synchronize(&mdp->napi);
+		sh_eth_write(ndev, 0x0000, EESIPR);
 
-	/* Free all the skbuffs in the Rx queue. */
-	sh_eth_ring_free(ndev);
-	/* Free DMA buffer */
-	sh_eth_free_dma_buffer(mdp);
+		sh_eth_dev_exit(ndev);
+
+		/* Free all the skbuffs in the Rx queue. */
+		sh_eth_ring_free(ndev);
+		/* Free DMA buffer */
+		sh_eth_free_dma_buffer(mdp);
+	}
 
 	/* Set new parameters */
 	mdp->num_rx_ring = ring->rx_pending;
 	mdp->num_tx_ring = ring->tx_pending;
 
-	ret = sh_eth_ring_init(ndev);
-	if (ret < 0) {
-		netdev_err(ndev, "%s: sh_eth_ring_init failed.\n", __func__);
-		return ret;
-	}
-	ret = sh_eth_dev_init(ndev, false);
-	if (ret < 0) {
-		netdev_err(ndev, "%s: sh_eth_dev_init failed.\n", __func__);
-		return ret;
-	}
-
 	if (netif_running(ndev)) {
+		ret = sh_eth_ring_init(ndev);
+		if (ret < 0) {
+			netdev_err(ndev, "%s: sh_eth_ring_init failed.\n",
+				   __func__);
+			return ret;
+		}
+		ret = sh_eth_dev_init(ndev, false);
+		if (ret < 0) {
+			netdev_err(ndev, "%s: sh_eth_dev_init failed.\n",
+				   __func__);
+			return ret;
+		}
+
+		mdp->irq_enabled = true;
 		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 		/* Setting the Rx mode will start the Rx process. */
 		sh_eth_write(ndev, EDRRR_R, EDRRR);
-		netif_wake_queue(ndev);
+		netif_device_attach(ndev);
 	}
 
 	return 0;
@@ -2117,6 +2174,9 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	}
 	spin_unlock_irqrestore(&mdp->lock, flags);
 
+	if (skb_padto(skb, ETH_ZLEN))
+		return NETDEV_TX_OK;
+
 	entry = mdp->cur_tx % mdp->num_tx_ring;
 	mdp->tx_skbuff[entry] = skb;
 	txdesc = &mdp->tx_ring[entry];
@@ -2126,10 +2186,11 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 				 skb->len + 2);
 	txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len,
 				      DMA_TO_DEVICE);
-	if (skb->len < ETH_ZLEN)
-		txdesc->buffer_length = ETH_ZLEN;
-	else
-		txdesc->buffer_length = skb->len;
+	if (dma_mapping_error(&ndev->dev, txdesc->addr)) {
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+	txdesc->buffer_length = skb->len;
 
 	if (entry >= mdp->num_tx_ring - 1)
 		txdesc->status |= cpu_to_edmac(mdp, TD_TACT | TD_TDLE);
@@ -2181,14 +2242,17 @@ static int sh_eth_close(struct net_device *ndev)
 
 	netif_stop_queue(ndev);
 
-	/* Disable interrupts by clearing the interrupt mask. */
+	/* Serialise with the interrupt handler and NAPI, then disable
+	 * interrupts.  We have to clear the irq_enabled flag first to
+	 * ensure that interrupts won't be re-enabled.
+	 */
+	mdp->irq_enabled = false;
+	synchronize_irq(ndev->irq);
+	napi_disable(&mdp->napi);
 	sh_eth_write(ndev, 0x0000, EESIPR);
 
-	/* Stop the chip's Tx and Rx processes. */
-	sh_eth_write(ndev, 0, EDTRR);
-	sh_eth_write(ndev, 0, EDRRR);
+	sh_eth_dev_exit(ndev);
 
-	sh_eth_get_stats(ndev);
 	/* PHY Disconnect */
 	if (mdp->phydev) {
 		phy_stop(mdp->phydev);
@@ -2198,8 +2262,6 @@ static int sh_eth_close(struct net_device *ndev)
 
 	free_irq(ndev->irq, ndev);
 
-	napi_disable(&mdp->napi);
-
 	/* Free all the skbuffs in the Rx queue. */
 	sh_eth_ring_free(ndev);
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 71f5de1171bd..332d3c16d483 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -513,6 +513,7 @@ struct sh_eth_private {
 	u32 rx_buf_sz;			/* Based on MTU+slack. */
 	int edmac_endian;
 	struct napi_struct napi;
+	bool irq_enabled;
 	/* MII transceiver section. */
 	u32 phy_id;			/* PHY ID */
 	struct mii_bus *mii_bus;	/* MDIO bus control */