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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 104 insertions, 53 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ff59897a9463..f366b3b96d03 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5035,9 +5035,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 
 	skb_tx_timestamp(skb);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
-		tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
+		tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
 	}
 
 	/* record initial flags and protocol */
@@ -5384,6 +5384,80 @@ void igb_update_stats(struct igb_adapter *adapter,
 	}
 }
 
+static void igb_tsync_interrupt(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	struct ptp_clock_event event;
+	struct timespec ts;
+	u32 ack = 0, tsauxc, sec, nsec, tsicr = rd32(E1000_TSICR);
+
+	if (tsicr & TSINTR_SYS_WRAP) {
+		event.type = PTP_CLOCK_PPS;
+		if (adapter->ptp_caps.pps)
+			ptp_clock_event(adapter->ptp_clock, &event);
+		else
+			dev_err(&adapter->pdev->dev, "unexpected SYS WRAP");
+		ack |= TSINTR_SYS_WRAP;
+	}
+
+	if (tsicr & E1000_TSICR_TXTS) {
+		/* retrieve hardware timestamp */
+		schedule_work(&adapter->ptp_tx_work);
+		ack |= E1000_TSICR_TXTS;
+	}
+
+	if (tsicr & TSINTR_TT0) {
+		spin_lock(&adapter->tmreg_lock);
+		ts = timespec_add(adapter->perout[0].start,
+				  adapter->perout[0].period);
+		wr32(E1000_TRGTTIML0, ts.tv_nsec);
+		wr32(E1000_TRGTTIMH0, ts.tv_sec);
+		tsauxc = rd32(E1000_TSAUXC);
+		tsauxc |= TSAUXC_EN_TT0;
+		wr32(E1000_TSAUXC, tsauxc);
+		adapter->perout[0].start = ts;
+		spin_unlock(&adapter->tmreg_lock);
+		ack |= TSINTR_TT0;
+	}
+
+	if (tsicr & TSINTR_TT1) {
+		spin_lock(&adapter->tmreg_lock);
+		ts = timespec_add(adapter->perout[1].start,
+				  adapter->perout[1].period);
+		wr32(E1000_TRGTTIML1, ts.tv_nsec);
+		wr32(E1000_TRGTTIMH1, ts.tv_sec);
+		tsauxc = rd32(E1000_TSAUXC);
+		tsauxc |= TSAUXC_EN_TT1;
+		wr32(E1000_TSAUXC, tsauxc);
+		adapter->perout[1].start = ts;
+		spin_unlock(&adapter->tmreg_lock);
+		ack |= TSINTR_TT1;
+	}
+
+	if (tsicr & TSINTR_AUTT0) {
+		nsec = rd32(E1000_AUXSTMPL0);
+		sec  = rd32(E1000_AUXSTMPH0);
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = 0;
+		event.timestamp = sec * 1000000000ULL + nsec;
+		ptp_clock_event(adapter->ptp_clock, &event);
+		ack |= TSINTR_AUTT0;
+	}
+
+	if (tsicr & TSINTR_AUTT1) {
+		nsec = rd32(E1000_AUXSTMPL1);
+		sec  = rd32(E1000_AUXSTMPH1);
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = 1;
+		event.timestamp = sec * 1000000000ULL + nsec;
+		ptp_clock_event(adapter->ptp_clock, &event);
+		ack |= TSINTR_AUTT1;
+	}
+
+	/* acknowledge the interrupts */
+	wr32(E1000_TSICR, ack);
+}
+
 static irqreturn_t igb_msix_other(int irq, void *data)
 {
 	struct igb_adapter *adapter = data;
@@ -5415,16 +5489,8 @@ static irqreturn_t igb_msix_other(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
-	if (icr & E1000_ICR_TS) {
-		u32 tsicr = rd32(E1000_TSICR);
-
-		if (tsicr & E1000_TSICR_TXTS) {
-			/* acknowledge the interrupt */
-			wr32(E1000_TSICR, E1000_TSICR_TXTS);
-			/* retrieve hardware timestamp */
-			schedule_work(&adapter->ptp_tx_work);
-		}
-	}
+	if (icr & E1000_ICR_TS)
+		igb_tsync_interrupt(adapter);
 
 	wr32(E1000_EIMS, adapter->eims_other);
 
@@ -6011,8 +6077,12 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 	adapter->vf_data[vf].flags |= IGB_VF_FLAG_CTS;
 
 	/* reply to reset with ack and vf mac address */
-	msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK;
-	memcpy(addr, vf_mac, ETH_ALEN);
+	if (!is_zero_ether_addr(vf_mac)) {
+		msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK;
+		memcpy(addr, vf_mac, ETH_ALEN);
+	} else {
+		msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_NACK;
+	}
 	igb_write_mbx(hw, msgbuf, 3, vf);
 }
 
@@ -6203,16 +6273,8 @@ static irqreturn_t igb_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
-	if (icr & E1000_ICR_TS) {
-		u32 tsicr = rd32(E1000_TSICR);
-
-		if (tsicr & E1000_TSICR_TXTS) {
-			/* acknowledge the interrupt */
-			wr32(E1000_TSICR, E1000_TSICR_TXTS);
-			/* retrieve hardware timestamp */
-			schedule_work(&adapter->ptp_tx_work);
-		}
-	}
+	if (icr & E1000_ICR_TS)
+		igb_tsync_interrupt(adapter);
 
 	napi_schedule(&q_vector->napi);
 
@@ -6257,16 +6319,8 @@ static irqreturn_t igb_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
-	if (icr & E1000_ICR_TS) {
-		u32 tsicr = rd32(E1000_TSICR);
-
-		if (tsicr & E1000_TSICR_TXTS) {
-			/* acknowledge the interrupt */
-			wr32(E1000_TSICR, E1000_TSICR_TXTS);
-			/* retrieve hardware timestamp */
-			schedule_work(&adapter->ptp_tx_work);
-		}
-	}
+	if (icr & E1000_ICR_TS)
+		igb_tsync_interrupt(adapter);
 
 	napi_schedule(&q_vector->napi);
 
@@ -6527,15 +6581,17 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 					 DMA_FROM_DEVICE);
 }
 
+static inline bool igb_page_is_reserved(struct page *page)
+{
+	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+}
+
 static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 				  struct page *page,
 				  unsigned int truesize)
 {
 	/* avoid re-using remote pages */
-	if (unlikely(page_to_nid(page) != numa_node_id()))
-		return false;
-
-	if (unlikely(page->pfmemalloc))
+	if (unlikely(igb_page_is_reserved(page)))
 		return false;
 
 #if (PAGE_SIZE < 8192)
@@ -6545,22 +6601,19 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 
 	/* flip page offset to other buffer */
 	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
-
-	/* Even if we own the page, we are not allowed to use atomic_set()
-	 * This would break get_page_unless_zero() users.
-	 */
-	atomic_inc(&page->_count);
 #else
 	/* move offset up to the next cache line */
 	rx_buffer->page_offset += truesize;
 
 	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
 		return false;
-
-	/* bump ref count on page before it is given to the stack */
-	get_page(page);
 #endif
 
+	/* Even if we own the page, we are not allowed to use atomic_set()
+	 * This would break get_page_unless_zero() users.
+	 */
+	atomic_inc(&page->_count);
+
 	return true;
 }
 
@@ -6603,13 +6656,12 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 
 		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
 
-		/* we can reuse buffer as-is, just make sure it is local */
-		if (likely((page_to_nid(page) == numa_node_id()) &&
-			   !page->pfmemalloc))
+		/* page is not reserved, we can reuse buffer as-is */
+		if (likely(!igb_page_is_reserved(page)))
 			return true;
 
 		/* this page cannot be reused so discard it */
-		put_page(page);
+		__free_page(page);
 		return false;
 	}
 
@@ -6627,7 +6679,6 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 	struct page *page;
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-
 	page = rx_buffer->page;
 	prefetchw(page);
 
@@ -7042,8 +7093,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 			i -= rx_ring->count;
 		}
 
-		/* clear the hdr_addr for the next_to_use descriptor */
-		rx_desc->read.hdr_addr = 0;
+		/* clear the status bits for the next_to_use descriptor */
+		rx_desc->wb.upper.status_error = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);