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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 64 insertions, 55 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index eb67cce3e8f9..003006033614 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -53,16 +53,24 @@ static void i40e_adminq_init_regs(struct i40e_hw *hw)
 		hw->aq.asq.tail = I40E_VF_ATQT1;
 		hw->aq.asq.head = I40E_VF_ATQH1;
 		hw->aq.asq.len  = I40E_VF_ATQLEN1;
+		hw->aq.asq.bal  = I40E_VF_ATQBAL1;
+		hw->aq.asq.bah  = I40E_VF_ATQBAH1;
 		hw->aq.arq.tail = I40E_VF_ARQT1;
 		hw->aq.arq.head = I40E_VF_ARQH1;
 		hw->aq.arq.len  = I40E_VF_ARQLEN1;
+		hw->aq.arq.bal  = I40E_VF_ARQBAL1;
+		hw->aq.arq.bah  = I40E_VF_ARQBAH1;
 	} else {
 		hw->aq.asq.tail = I40E_PF_ATQT;
 		hw->aq.asq.head = I40E_PF_ATQH;
 		hw->aq.asq.len  = I40E_PF_ATQLEN;
+		hw->aq.asq.bal  = I40E_PF_ATQBAL;
+		hw->aq.asq.bah  = I40E_PF_ATQBAH;
 		hw->aq.arq.tail = I40E_PF_ARQT;
 		hw->aq.arq.head = I40E_PF_ARQH;
 		hw->aq.arq.len  = I40E_PF_ARQLEN;
+		hw->aq.arq.bal  = I40E_PF_ARQBAL;
+		hw->aq.arq.bah  = I40E_PF_ARQBAH;
 	}
 }
 
@@ -294,27 +302,18 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw)
 	i40e_status ret_code = 0;
 	u32 reg = 0;
 
-	if (hw->mac.type == I40E_MAC_VF) {
-		/* configure the transmit queue */
-		wr32(hw, I40E_VF_ATQBAH1,
-		    upper_32_bits(hw->aq.asq.desc_buf.pa));
-		wr32(hw, I40E_VF_ATQBAL1,
-		    lower_32_bits(hw->aq.asq.desc_buf.pa));
-		wr32(hw, I40E_VF_ATQLEN1, (hw->aq.num_asq_entries |
-					  I40E_VF_ATQLEN1_ATQENABLE_MASK));
-		reg = rd32(hw, I40E_VF_ATQBAL1);
-	} else {
-		/* configure the transmit queue */
-		wr32(hw, I40E_PF_ATQBAH,
-		    upper_32_bits(hw->aq.asq.desc_buf.pa));
-		wr32(hw, I40E_PF_ATQBAL,
-		    lower_32_bits(hw->aq.asq.desc_buf.pa));
-		wr32(hw, I40E_PF_ATQLEN, (hw->aq.num_asq_entries |
-					  I40E_PF_ATQLEN_ATQENABLE_MASK));
-		reg = rd32(hw, I40E_PF_ATQBAL);
-	}
+	/* Clear Head and Tail */
+	wr32(hw, hw->aq.asq.head, 0);
+	wr32(hw, hw->aq.asq.tail, 0);
+
+	/* set starting point */
+	wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries |
+				  I40E_PF_ATQLEN_ATQENABLE_MASK));
+	wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa));
+	wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa));
 
 	/* Check one register to verify that config was applied */
+	reg = rd32(hw, hw->aq.asq.bal);
 	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
 		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
 
@@ -332,30 +331,21 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw)
 	i40e_status ret_code = 0;
 	u32 reg = 0;
 
-	if (hw->mac.type == I40E_MAC_VF) {
-		/* configure the receive queue */
-		wr32(hw, I40E_VF_ARQBAH1,
-		    upper_32_bits(hw->aq.arq.desc_buf.pa));
-		wr32(hw, I40E_VF_ARQBAL1,
-		    lower_32_bits(hw->aq.arq.desc_buf.pa));
-		wr32(hw, I40E_VF_ARQLEN1, (hw->aq.num_arq_entries |
-					  I40E_VF_ARQLEN1_ARQENABLE_MASK));
-		reg = rd32(hw, I40E_VF_ARQBAL1);
-	} else {
-		/* configure the receive queue */
-		wr32(hw, I40E_PF_ARQBAH,
-		    upper_32_bits(hw->aq.arq.desc_buf.pa));
-		wr32(hw, I40E_PF_ARQBAL,
-		    lower_32_bits(hw->aq.arq.desc_buf.pa));
-		wr32(hw, I40E_PF_ARQLEN, (hw->aq.num_arq_entries |
-					  I40E_PF_ARQLEN_ARQENABLE_MASK));
-		reg = rd32(hw, I40E_PF_ARQBAL);
-	}
+	/* Clear Head and Tail */
+	wr32(hw, hw->aq.arq.head, 0);
+	wr32(hw, hw->aq.arq.tail, 0);
+
+	/* set starting point */
+	wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries |
+				  I40E_PF_ARQLEN_ARQENABLE_MASK));
+	wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa));
+	wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa));
 
 	/* Update tail in the HW to post pre-allocated buffers */
 	wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
 
 	/* Check one register to verify that config was applied */
+	reg = rd32(hw, hw->aq.arq.bal);
 	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
 		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
 
@@ -497,6 +487,8 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.asq.head, 0);
 	wr32(hw, hw->aq.asq.tail, 0);
 	wr32(hw, hw->aq.asq.len, 0);
+	wr32(hw, hw->aq.asq.bal, 0);
+	wr32(hw, hw->aq.asq.bah, 0);
 
 	/* make sure lock is available */
 	mutex_lock(&hw->aq.asq_mutex);
@@ -528,6 +520,8 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.arq.head, 0);
 	wr32(hw, hw->aq.arq.tail, 0);
 	wr32(hw, hw->aq.arq.len, 0);
+	wr32(hw, hw->aq.arq.bal, 0);
+	wr32(hw, hw->aq.arq.bah, 0);
 
 	/* make sure lock is available */
 	mutex_lock(&hw->aq.arq_mutex);
@@ -573,6 +567,9 @@ i40e_status i40evf_init_adminq(struct i40e_hw *hw)
 	/* Set up register offsets */
 	i40e_adminq_init_regs(hw);
 
+	/* setup ASQ command write back timeout */
+	hw->aq.asq_cmd_timeout = I40E_ASQ_CMD_TIMEOUT;
+
 	/* allocate the ASQ */
 	ret_code = i40e_init_asq(hw);
 	if (ret_code)
@@ -630,6 +627,10 @@ static u16 i40e_clean_asq(struct i40e_hw *hw)
 	desc = I40E_ADMINQ_DESC(*asq, ntc);
 	details = I40E_ADMINQ_DETAILS(*asq, ntc);
 	while (rd32(hw, hw->aq.asq.head) != ntc) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+			   "%s: ntc %d head %d.\n", __func__, ntc,
+			   rd32(hw, hw->aq.asq.head));
+
 		if (details->callback) {
 			I40E_ADMINQ_CALLBACK cb_func =
 					(I40E_ADMINQ_CALLBACK)details->callback;
@@ -690,17 +691,20 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 	struct i40e_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	u16  retval = 0;
+	u32  val = 0;
 
-	if (hw->aq.asq.count == 0) {
+	val = rd32(hw, hw->aq.asq.head);
+	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
-			   "AQTX: Admin queue not initialized.\n");
+			   "AQTX: head overrun at %d\n", val);
 		status = I40E_ERR_QUEUE_EMPTY;
 		goto asq_send_command_exit;
 	}
 
-	if (i40e_is_nvm_update_op(desc) && hw->aq.nvm_busy) {
-		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: NVM busy.\n");
-		status = I40E_ERR_NVM;
+	if (hw->aq.asq.count == 0) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+			   "AQTX: Admin queue not initialized.\n");
+		status = I40E_ERR_QUEUE_EMPTY;
 		goto asq_send_command_exit;
 	}
 
@@ -783,6 +787,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 	}
 
 	/* bump the tail */
+	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n");
 	i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring, buff);
 	(hw->aq.asq.next_to_use)++;
 	if (hw->aq.asq.next_to_use == hw->aq.asq.count)
@@ -806,7 +811,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 			/* ugh! delay while spin_lock */
 			udelay(delay_len);
 			total_delay += delay_len;
-		} while (total_delay <  I40E_ASQ_CMD_TIMEOUT);
+		} while (total_delay < hw->aq.asq_cmd_timeout);
 	}
 
 	/* if ready, copy the desc back to temp */
@@ -820,6 +825,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 				   I40E_DEBUG_AQ_MESSAGE,
 				   "AQTX: Command completed with error 0x%X.\n",
 				   retval);
+
 			/* strip off FW internal code */
 			retval &= 0xff;
 		}
@@ -834,6 +840,10 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 	if (i40e_is_nvm_update_op(desc))
 		hw->aq.nvm_busy = true;
 
+	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+		   "AQTX: desc and buffer writeback:\n");
+	i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff);
+
 	/* update the error if time out occurred */
 	if ((!cmd_completed) &&
 	    (!details->async && !details->postpone)) {
@@ -905,10 +915,6 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
 	/* now clean the next descriptor */
 	desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc);
 	desc_idx = ntc;
-	i40evf_debug_aq(hw,
-		      I40E_DEBUG_AQ_COMMAND,
-		      (void *)desc,
-		      hw->aq.arq.r.arq_bi[desc_idx].va);
 
 	flags = le16_to_cpu(desc->flags);
 	if (flags & I40E_AQ_FLAG_ERR) {
@@ -919,18 +925,21 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
 			   I40E_DEBUG_AQ_MESSAGE,
 			   "AQRX: Event received with error 0x%X.\n",
 			   hw->aq.arq_last_status);
-	} else {
-		e->desc = *desc;
-		datalen = le16_to_cpu(desc->datalen);
-		e->msg_size = min(datalen, e->msg_size);
-		if (e->msg_buf != NULL && (e->msg_size != 0))
-			memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
-			       e->msg_size);
 	}
 
+	e->desc = *desc;
+	datalen = le16_to_cpu(desc->datalen);
+	e->msg_size = min(datalen, e->msg_size);
+	if (e->msg_buf != NULL && (e->msg_size != 0))
+		memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
+		       e->msg_size);
+
 	if (i40e_is_nvm_update_op(&e->desc))
 		hw->aq.nvm_busy = false;
 
+	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
+	i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf);
+
 	/* Restore the original datalen and buffer address in the desc,
 	 * FW updates datalen to indicate the event message
 	 * size