[net-next 00/17][pull request] Intel Wired LAN Driver Updates 2015-10-15

[net-next 00/17][pull request] Intel Wired LAN Driver Updates 2015-10-15

[Jeff Kirsher]

This series contains updates to e1000, e1000e, igb, igbvf, ixgbe, ixgbevf,
i40e, i40evf and fm10k.

Alex Duyck fixes the polling routine for i40e/i40evf were the NAPI budget
for receive cleanup was being rounded up to 1 but the netpoll call was
expecting no Rx to be processed as the budget passed was 0.  Also cleaned
up IN_NETPOLL flag that was not adding any value due to the receive
cleanup was handled in NAPI.  Added support for netpoll for i40evf as
well.

Jesse updates all of our drivers to use napi_complete_done() instead of
napi_complete(), which allows us to use
/sys/class/net/ethX/gro_flush_timeout.  Added ethtool support to control
and report the new Interrupt Limit register, since the XL710 hardware
has a different interrupt moderation design that can support a limit of
total interrupts per second per vector.

Shannon cleans up startup log entries to cut down the number by putting
a couple behind debug flags and combining others into single line.  Added
support to enable/disable printing VEB statistics via ethtool.

Jingjing fixes a compile issue by adding const to functions that return
strings that are not going to be modified.

Greg Rose cleans up defines that were not used and were causing customer
confusion.

Greg Bowers adds support for setting a new bit in the Set Local LLDP MIB
admin queue command Type field.

Mitch fixes an issue where vlan_features field was set to the same value
as netdev features field, but before the features were actually being
set up, leaving the vlan_features empty.  Resolve the issue by setting
up the netdev features first, then mask out the VLAN feature bits when
assigning vlan_features.  Fixed VF init timing, where in some instances
the VFs would fail to initialize the first time you loaded the driver.
To correct this, increased the delay time for the init task and wait
longer before giving up.

The following are changes since commit 96aec911482246a319bf457f39fa848ce436c8fd:
  amd-xgbe: Use system workqueue for device restart
and are available in the git repository at:
  git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue master

Alexander Duyck (3):
  i40e/i40evf: Fix handling of napi budget
  i40e/i40evf: Drop useless "IN_NETPOLL" flag
  i40evf: Add support for netpoll

Catherine Sullivan (2):
  i40e: Recognize 1000Base_T_Optical phy type when link is up
  i40e/i40evf: Bump i40e to 1.3.34 and i40evf to 1.3.21

Greg Bowers (1):
  i40e: Add support for non-willing Apps

Greg Rose (1):
  i40e: Removed unused defines

Jesse Brandeburg (2):
  drivers/net/intel: use napi_complete_done()
  i40e/i40evf: moderate interrupts differently

Jingjing Wu (2):
  i40e/i40evf: Fix compile issue related to const string
  i40e: reset the invalid msg counter in vf when a valid msg is received

Mitch Williams (3):
  i40evf: correctly populate vlan_features
  i40evf: relax and stagger init timing a bit
  i40e: increase AQ work limit

Shannon Nelson (3):
  i40e: generate fewer startup messages
  i40e: remove read/write failed messages from nvmupdate
  i40e: priv flag for controlling VEB stats

 drivers/net/ethernet/intel/e1000/e1000_main.c      |  2 +-
 drivers/net/ethernet/intel/e1000e/netdev.c         |  2 +-
 drivers/net/ethernet/intel/fm10k/fm10k_main.c      | 21 ++++++----
 drivers/net/ethernet/intel/i40e/i40e.h             |  9 ++--
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h  |  7 ++++
 drivers/net/ethernet/intel/i40e/i40e_common.c      |  4 +-
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c     | 49 ++++++++++++++++++----
 drivers/net/ethernet/intel/i40e/i40e_main.c        | 34 ++++++++-------
 drivers/net/ethernet/intel/i40e/i40e_nvm.c         |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_prototype.h   |  4 +-
 drivers/net/ethernet/intel/i40e/i40e_ptp.c         |  4 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        | 20 +++++----
 drivers/net/ethernet/intel/i40e/i40e_txrx.h        | 10 +++++
 drivers/net/ethernet/intel/i40e/i40e_type.h        |  2 +
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c |  2 +
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h |  5 +--
 drivers/net/ethernet/intel/i40evf/i40e_common.c    |  4 +-
 drivers/net/ethernet/intel/i40evf/i40e_prototype.h |  4 +-
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c      | 20 +++++----
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h      | 10 +++++
 drivers/net/ethernet/intel/i40evf/i40evf.h         |  4 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c    | 37 ++++++++++++++--
 drivers/net/ethernet/intel/igb/igb_main.c          | 17 +++++---
 drivers/net/ethernet/intel/igbvf/netdev.c          |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      | 14 ++++---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c  | 14 ++++---
 26 files changed, 211 insertions(+), 92 deletions(-)

-- 
2.4.3

[net-next 01/17] i40e/i40evf: Fix handling of napi budget

[Jeff Kirsher]

From: Alexander Duyck <aduyck@mirantis.com>

The polling routine for i40e was rounding up the budget for Rx cleanup to
1.  This is incorrect as the netpoll poll call is expecting no Rx to be
processed as the budget passed was 0.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 5 +++++
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 01e5ece..b560e02 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1846,6 +1846,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 		ring->arm_wb = false;
 	}
 
+	/* Handle case where we are called by netpoll with a budget of 0 */
+	if (budget <= 0)
+		goto tx_only;
+
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
 	 */
@@ -1862,6 +1866,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
+tx_only:
 		if (arm_wb)
 			i40e_force_wb(vsi, q_vector);
 		return budget;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 0e71eb4..1894cc8 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1287,6 +1287,10 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 		ring->arm_wb = false;
 	}
 
+	/* Handle case where we are called by netpoll with a budget of 0 */
+	if (budget <= 0)
+		goto tx_only;
+
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
 	 */
@@ -1303,6 +1307,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
+tx_only:
 		if (arm_wb)
 			i40evf_force_wb(vsi, q_vector);
 		return budget;
-- 
2.4.3

[net-next 02/17] i40e/i40evf: Drop useless "IN_NETPOLL" flag

[Jeff Kirsher]

From: Alexander Duyck <aduyck@mirantis.com>

The code in i40e and i40evf is using an "IN_NETPOLL" flag that has never
added any value due to the fact that the Rx clean-up is handled in NAPI.
As such the flag was set, the queue was scheduled via NAPI, and then polled
from the netpoll controller and if any Rx packets were processed the were
processed in the wrong context.

In addition the flag itself just added an unneeded conditional to the
hot-path so it can safely be dropped and save us a few instructions.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h        | 1 -
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 2 --
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 7 +------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 7 +------
 drivers/net/ethernet/intel/i40evf/i40evf.h    | 2 --
 5 files changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d587a05..91f8cbf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -307,7 +307,6 @@ struct i40e_pf {
 #ifdef I40E_FCOE
 #define I40E_FLAG_FCOE_ENABLED			BIT_ULL(11)
 #endif /* I40E_FCOE */
-#define I40E_FLAG_IN_NETPOLL			BIT_ULL(12)
 #define I40E_FLAG_16BYTE_RX_DESC_ENABLED	BIT_ULL(13)
 #define I40E_FLAG_CLEAN_ADMINQ			BIT_ULL(14)
 #define I40E_FLAG_FILTER_SYNC			BIT_ULL(15)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ed844b..389f110 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3574,14 +3574,12 @@ static void i40e_netpoll(struct net_device *netdev)
 	if (test_bit(__I40E_DOWN, &vsi->state))
 		return;
 
-	pf->flags |= I40E_FLAG_IN_NETPOLL;
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_msix_clean_rings(0, vsi->q_vectors[i]);
 	} else {
 		i40e_intr(pf->pdev->irq, netdev);
 	}
-	pf->flags &= ~I40E_FLAG_IN_NETPOLL;
 }
 #endif
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b560e02..e1fac3b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1268,16 +1268,11 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring,
 			     struct sk_buff *skb, u16 vlan_tag)
 {
 	struct i40e_q_vector *q_vector = rx_ring->q_vector;
-	struct i40e_vsi *vsi = rx_ring->vsi;
-	u64 flags = vsi->back->flags;
 
 	if (vlan_tag & VLAN_VID_MASK)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 
-	if (flags & I40E_FLAG_IN_NETPOLL)
-		netif_rx(skb);
-	else
-		napi_gro_receive(&q_vector->napi, skb);
+	napi_gro_receive(&q_vector->napi, skb);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 1894cc8..5d3a8bd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -742,16 +742,11 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring,
 			     struct sk_buff *skb, u16 vlan_tag)
 {
 	struct i40e_q_vector *q_vector = rx_ring->q_vector;
-	struct i40e_vsi *vsi = rx_ring->vsi;
-	u64 flags = vsi->back->flags;
 
 	if (vlan_tag & VLAN_VID_MASK)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 
-	if (flags & I40E_FLAG_IN_NETPOLL)
-		netif_rx(skb);
-	else
-		napi_gro_receive(&q_vector->napi, skb);
+	napi_gro_receive(&q_vector->napi, skb);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 6f42711..c74f614 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -211,7 +211,6 @@ struct i40evf_adapter {
 #define I40EVF_FLAG_RX_1BUF_CAPABLE              BIT(1)
 #define I40EVF_FLAG_RX_PS_CAPABLE                BIT(2)
 #define I40EVF_FLAG_RX_PS_ENABLED                BIT(3)
-#define I40EVF_FLAG_IN_NETPOLL                   BIT(4)
 #define I40EVF_FLAG_IMIR_ENABLED                 BIT(5)
 #define I40EVF_FLAG_MQ_CAPABLE                   BIT(6)
 #define I40EVF_FLAG_NEED_LINK_UPDATE             BIT(7)
@@ -224,7 +223,6 @@ struct i40evf_adapter {
 /* duplicates for common code */
 #define I40E_FLAG_FDIR_ATR_ENABLED		 0
 #define I40E_FLAG_DCB_ENABLED			 0
-#define I40E_FLAG_IN_NETPOLL			 I40EVF_FLAG_IN_NETPOLL
 #define I40E_FLAG_RX_CSUM_ENABLED                I40EVF_FLAG_RX_CSUM_ENABLED
 #define I40E_FLAG_WB_ON_ITR_CAPABLE		I40EVF_FLAG_WB_ON_ITR_CAPABLE
 #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE	I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE
-- 
2.4.3

[net-next 03/17] i40evf: Add support for netpoll

[Jeff Kirsher]

From: Alexander Duyck <aduyck@mirantis.com>

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 26 +++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 429a46c..5e13363 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -444,6 +444,29 @@ out:
 	return err;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * i40evf_netpoll - A Polling 'interrupt'handler
+ * @netdev: network interface device structure
+ *
+ * This is used by netconsole to send skbs without having to re-enable
+ * interrupts.  It's not called while the normal interrupt routine is executing.
+ **/
+static void i40evf_netpoll(struct net_device *netdev)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
+	int i;
+
+	/* if interface is down do nothing */
+	if (test_bit(__I40E_DOWN, &adapter->vsi.state))
+		return;
+
+	for (i = 0; i < q_vectors; i++)
+		i40evf_msix_clean_rings(0, adapter->q_vector[i]);
+}
+
+#endif
 /**
  * i40evf_request_traffic_irqs - Initialize MSI-X interrupts
  * @adapter: board private structure
@@ -2049,6 +2072,9 @@ static const struct net_device_ops i40evf_netdev_ops = {
 	.ndo_tx_timeout		= i40evf_tx_timeout,
 	.ndo_vlan_rx_add_vid	= i40evf_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= i40evf_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= i40evf_netpoll,
+#endif
 };
 
 /**
-- 
2.4.3

Re: [net-next 03/17] i40evf: Add support for netpoll

[Sergei Shtylyov]

Hello.

On 10/16/2015 12:43 AM, Jeff Kirsher wrote:

> From: Alexander Duyck <aduyck@mirantis.com>
>
> Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
> Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> ---
>   drivers/net/ethernet/intel/i40evf/i40evf_main.c | 26 +++++++++++++++++++++++++
>   1 file changed, 26 insertions(+)
>
> diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
> index 429a46c..5e13363 100644
> --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
> +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
> @@ -444,6 +444,29 @@ out:
>   	return err;
>   }
>
> +#ifdef CONFIG_NET_POLL_CONTROLLER
> +/**
> + * i40evf_netpoll - A Polling 'interrupt'handler

    Space obviously missing.

[...]

MBR, Sergei

[net-next 04/17] drivers/net/intel: use napi_complete_done()

[Jeff Kirsher]

From: Jesse Brandeburg <jesse.brandeburg@intel.com>

As per Eric Dumazet's previous patches:
(see commit (24d2e4a50737) - tg3: use napi_complete_done())

Quoting verbatim:
Using napi_complete_done() instead of napi_complete() allows
us to use /sys/class/net/ethX/gro_flush_timeout

GRO layer can aggregate more packets if the flush is delayed a bit,
without having to set too big coalescing parameters that impact
latencies.
</end quote>

Tested
configuration: low latency via ethtool -C ethx adaptive-rx off
				rx-usecs 10 adaptive-tx off tx-usecs 15
workload: streaming rx using netperf TCP_MAERTS

igb:
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result:  941.48 10^6bits/s over 1.000 seconds ending at 1440193171.589

Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
Local  Remote  Local  Remote  Xfered   Per                 Per
Recv   Send    Recv   Send             Recv (avg)          Send (avg)
    8       8      0       0 1176930056  1475.36    797726   16384.00  71905

MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
...
Interim result:  941.49 10^6bits/s over 0.997 seconds ending at 1440193142.763

Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
Local  Remote  Local  Remote  Xfered   Per                 Per
Recv   Send    Recv   Send             Recv (avg)          Send (avg)
    8       8      0       0 1175182320  50476.00     23282   16384.00  71816

i40e:
Hard to test because the traffic is incoming so fast (24Gb/s) that GRO
always receives 87kB, even at the highest interrupt rate.

Other drivers were only compile tested.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c     |  2 +-
 drivers/net/ethernet/intel/e1000e/netdev.c        |  2 +-
 drivers/net/ethernet/intel/fm10k/fm10k_main.c     | 21 ++++++++++++---------
 drivers/net/ethernet/intel/i40e/i40e_txrx.c       |  8 ++++++--
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c     |  8 ++++++--
 drivers/net/ethernet/intel/igb/igb_main.c         | 17 +++++++++++------
 drivers/net/ethernet/intel/igbvf/netdev.c         |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 14 +++++++++-----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 14 ++++++++------
 9 files changed, 55 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 74dc150..fd7be86 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3820,7 +3820,7 @@ static int e1000_clean(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		if (likely(adapter->itr_setting & 3))
 			e1000_set_itr(adapter);
-		napi_complete(napi);
+		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->flags))
 			e1000_irq_enable(adapter);
 	}
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 2e2ddec0..0a854a4 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2693,7 +2693,7 @@ static int e1000e_poll(struct napi_struct *napi, int weight)
 	if (work_done < weight) {
 		if (adapter->itr_setting & 3)
 			e1000_set_itr(adapter);
-		napi_complete(napi);
+		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
 				ew32(IMS, adapter->rx_ring->ims_val);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 537d81a..e76a44c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -593,9 +593,9 @@ static void fm10k_receive_skb(struct fm10k_q_vector *q_vector,
 	napi_gro_receive(&q_vector->napi, skb);
 }
 
-static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
-			       struct fm10k_ring *rx_ring,
-			       int budget)
+static int fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
+			      struct fm10k_ring *rx_ring,
+			      int budget)
 {
 	struct sk_buff *skb = rx_ring->skb;
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -662,7 +662,7 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
 	q_vector->rx.total_packets += total_packets;
 	q_vector->rx.total_bytes += total_bytes;
 
-	return total_packets < budget;
+	return total_packets;
 }
 
 #define VXLAN_HLEN (sizeof(struct udphdr) + 8)
@@ -1422,7 +1422,7 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	struct fm10k_q_vector *q_vector =
 			       container_of(napi, struct fm10k_q_vector, napi);
 	struct fm10k_ring *ring;
-	int per_ring_budget;
+	int per_ring_budget, work_done = 0;
 	bool clean_complete = true;
 
 	fm10k_for_each_ring(ring, q_vector->tx)
@@ -1436,16 +1436,19 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	else
 		per_ring_budget = budget;
 
-	fm10k_for_each_ring(ring, q_vector->rx)
-		clean_complete &= fm10k_clean_rx_irq(q_vector, ring,
-						     per_ring_budget);
+	fm10k_for_each_ring(ring, q_vector->rx) {
+		int work = fm10k_clean_rx_irq(q_vector, ring, per_ring_budget);
+
+		work_done += work;
+		clean_complete &= !!(work < per_ring_budget);
+	}
 
 	/* If all work not completed, return budget and keep polling */
 	if (!clean_complete)
 		return budget;
 
 	/* all work done, exit the polling mode */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 
 	/* re-enable the q_vector */
 	fm10k_qv_enable(q_vector);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index e1fac3b..512707c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1825,7 +1825,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	bool clean_complete = true;
 	bool arm_wb = false;
 	int budget_per_ring;
-	int cleaned;
+	int work_done = 0;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
 		napi_complete(napi);
@@ -1851,10 +1851,14 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
 
 	i40e_for_each_ring(ring, q_vector->rx) {
+		int cleaned;
+
 		if (ring_is_ps_enabled(ring))
 			cleaned = i40e_clean_rx_irq_ps(ring, budget_per_ring);
 		else
 			cleaned = i40e_clean_rx_irq_1buf(ring, budget_per_ring);
+
+		work_done += cleaned;
 		/* if we didn't clean as many as budgeted, we must be done */
 		clean_complete &= (budget_per_ring != cleaned);
 	}
@@ -1871,7 +1875,7 @@ tx_only:
 		q_vector->arm_wb_state = false;
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
 		i40e_update_enable_itr(vsi, q_vector);
 	} else { /* Legacy mode */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 5d3a8bd..97493a4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1266,7 +1266,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	bool clean_complete = true;
 	bool arm_wb = false;
 	int budget_per_ring;
-	int cleaned;
+	int work_done = 0;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
 		napi_complete(napi);
@@ -1292,10 +1292,14 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
 
 	i40e_for_each_ring(ring, q_vector->rx) {
+		int cleaned;
+
 		if (ring_is_ps_enabled(ring))
 			cleaned = i40e_clean_rx_irq_ps(ring, budget_per_ring);
 		else
 			cleaned = i40e_clean_rx_irq_1buf(ring, budget_per_ring);
+
+		work_done += cleaned;
 		/* if we didn't clean as many as budgeted, we must be done */
 		clean_complete &= (budget_per_ring != cleaned);
 	}
@@ -1312,7 +1316,7 @@ tx_only:
 		q_vector->arm_wb_state = false;
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	i40e_update_enable_itr(vsi, q_vector);
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 7e62675..ea7b098 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -151,7 +151,7 @@ static void igb_setup_dca(struct igb_adapter *);
 #endif /* CONFIG_IGB_DCA */
 static int igb_poll(struct napi_struct *, int);
 static bool igb_clean_tx_irq(struct igb_q_vector *);
-static bool igb_clean_rx_irq(struct igb_q_vector *, int);
+static int igb_clean_rx_irq(struct igb_q_vector *, int);
 static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
 static void igb_tx_timeout(struct net_device *);
 static void igb_reset_task(struct work_struct *);
@@ -6364,6 +6364,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 						     struct igb_q_vector,
 						     napi);
 	bool clean_complete = true;
+	int work_done = 0;
 
 #ifdef CONFIG_IGB_DCA
 	if (q_vector->adapter->flags & IGB_FLAG_DCA_ENABLED)
@@ -6372,15 +6373,19 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	if (q_vector->tx.ring)
 		clean_complete = igb_clean_tx_irq(q_vector);
 
-	if (q_vector->rx.ring)
-		clean_complete &= igb_clean_rx_irq(q_vector, budget);
+	if (q_vector->rx.ring) {
+		int cleaned = igb_clean_rx_irq(q_vector, budget);
+
+		work_done += cleaned;
+		clean_complete &= (cleaned < budget);
+	}
 
 	/* If all work not completed, return budget and keep polling */
 	if (!clean_complete)
 		return budget;
 
 	/* If not enough Rx work done, exit the polling mode */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	igb_ring_irq_enable(q_vector);
 
 	return 0;
@@ -6904,7 +6909,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
-static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
+static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
 	struct igb_ring *rx_ring = q_vector->rx.ring;
 	struct sk_buff *skb = rx_ring->skb;
@@ -6978,7 +6983,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	if (cleaned_count)
 		igb_alloc_rx_buffers(rx_ring, cleaned_count);
 
-	return total_packets < budget;
+	return total_packets;
 }
 
 static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index e86d41e..297af80 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1211,7 +1211,7 @@ static int igbvf_poll(struct napi_struct *napi, int budget)
 
 	/* If not enough Rx work done, exit the polling mode */
 	if (work_done < budget) {
-		napi_complete(napi);
+		napi_complete_done(napi, work_done);
 
 		if (adapter->requested_itr & 3)
 			igbvf_set_itr(adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1b2ad39..9f8a7fd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2775,7 +2775,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 				container_of(napi, struct ixgbe_q_vector, napi);
 	struct ixgbe_adapter *adapter = q_vector->adapter;
 	struct ixgbe_ring *ring;
-	int per_ring_budget;
+	int per_ring_budget, work_done = 0;
 	bool clean_complete = true;
 
 #ifdef CONFIG_IXGBE_DCA
@@ -2796,9 +2796,13 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 	else
 		per_ring_budget = budget;
 
-	ixgbe_for_each_ring(ring, q_vector->rx)
-		clean_complete &= (ixgbe_clean_rx_irq(q_vector, ring,
-				   per_ring_budget) < per_ring_budget);
+	ixgbe_for_each_ring(ring, q_vector->rx) {
+		int cleaned = ixgbe_clean_rx_irq(q_vector, ring,
+						 per_ring_budget);
+
+		work_done += cleaned;
+		clean_complete &= (cleaned < per_ring_budget);
+	}
 
 	ixgbe_qv_unlock_napi(q_vector);
 	/* If all work not completed, return budget and keep polling */
@@ -2806,7 +2810,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 		return budget;
 
 	/* all work done, exit the polling mode */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	if (adapter->rx_itr_setting & 1)
 		ixgbe_set_itr(q_vector);
 	if (!test_bit(__IXGBE_DOWN, &adapter->state))
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 35da2d7..7570b5c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1008,7 +1008,7 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct ixgbevf_q_vector, napi);
 	struct ixgbevf_adapter *adapter = q_vector->adapter;
 	struct ixgbevf_ring *ring;
-	int per_ring_budget;
+	int per_ring_budget, work_done = 0;
 	bool clean_complete = true;
 
 	ixgbevf_for_each_ring(ring, q_vector->tx)
@@ -1027,10 +1027,12 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 	else
 		per_ring_budget = budget;
 
-	ixgbevf_for_each_ring(ring, q_vector->rx)
-		clean_complete &= (ixgbevf_clean_rx_irq(q_vector, ring,
-							per_ring_budget)
-				   < per_ring_budget);
+	ixgbevf_for_each_ring(ring, q_vector->rx) {
+		int cleaned = ixgbevf_clean_rx_irq(q_vector, ring,
+						   per_ring_budget);
+		work_done += cleaned;
+		clean_complete &= (cleaned < per_ring_budget);
+	}
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	ixgbevf_qv_unlock_napi(q_vector);
@@ -1040,7 +1042,7 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 	/* all work done, exit the polling mode */
-	napi_complete(napi);
+	napi_complete_done(napi, work_done);
 	if (adapter->rx_itr_setting & 1)
 		ixgbevf_set_itr(q_vector);
 	if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
-- 
2.4.3

Re: [net-next 04/17] drivers/net/intel: use napi_complete_done()

[Eric Dumazet]

On Thu, 2015-10-15 at 14:43 -0700, Jeff Kirsher wrote:
> From: Jesse Brandeburg <jesse.brandeburg@intel.com>
> 
> As per Eric Dumazet's previous patches:
> (see commit (24d2e4a50737) - tg3: use napi_complete_done())
> 
> Quoting verbatim:
> Using napi_complete_done() instead of napi_complete() allows
> us to use /sys/class/net/ethX/gro_flush_timeout
> 
> GRO layer can aggregate more packets if the flush is delayed a bit,
> without having to set too big coalescing parameters that impact
> latencies.
> </end quote>
> 
> Tested
> configuration: low latency via ethtool -C ethx adaptive-rx off
> 				rx-usecs 10 adaptive-tx off tx-usecs 15
> workload: streaming rx using netperf TCP_MAERTS
> 
> igb:
> MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
> ...
> Interim result:  941.48 10^6bits/s over 1.000 seconds ending at 1440193171.589
> 
> Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
> Local  Remote  Local  Remote  Xfered   Per                 Per
> Recv   Send    Recv   Send             Recv (avg)          Send (avg)
>     8       8      0       0 1176930056  1475.36    797726   16384.00  71905
> 
> MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
> ...
> Interim result:  941.49 10^6bits/s over 0.997 seconds ending at 1440193142.763
> 
> Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
> Local  Remote  Local  Remote  Xfered   Per                 Per
> Recv   Send    Recv   Send             Recv (avg)          Send (avg)
>     8       8      0       0 1175182320  50476.00     23282   16384.00  71816
> 
> i40e:
> Hard to test because the traffic is incoming so fast (24Gb/s) that GRO
> always receives 87kB, even at the highest interrupt rate.
> 
> Other drivers were only compile tested.
> 
> Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
> Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>


Hi guys

I am not sure the ixgbe part is working :

ixgbe_qv_unlock_napi() does :

/* flush any outstanding Rx frames */
if (q_vector->napi.gro_list)
        napi_gro_flush(&q_vector->napi, false);

And it is called before napi_complete_done(napi, work_done);

Re: [net-next 04/17] drivers/net/intel: use napi_complete_done()

[Alexander Duyck]

On 11/12/2015 09:18 PM, Eric Dumazet wrote:
> On Thu, 2015-10-15 at 14:43 -0700, Jeff Kirsher wrote:
>> From: Jesse Brandeburg <jesse.brandeburg@intel.com>
>>
>> As per Eric Dumazet's previous patches:
>> (see commit (24d2e4a50737) - tg3: use napi_complete_done())
>>
>> Quoting verbatim:
>> Using napi_complete_done() instead of napi_complete() allows
>> us to use /sys/class/net/ethX/gro_flush_timeout
>>
>> GRO layer can aggregate more packets if the flush is delayed a bit,
>> without having to set too big coalescing parameters that impact
>> latencies.
>> </end quote>
>>
>> Tested
>> configuration: low latency via ethtool -C ethx adaptive-rx off
>> 				rx-usecs 10 adaptive-tx off tx-usecs 15
>> workload: streaming rx using netperf TCP_MAERTS
>>
>> igb:
>> MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
>> ...
>> Interim result:  941.48 10^6bits/s over 1.000 seconds ending at 1440193171.589
>>
>> Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
>> Local  Remote  Local  Remote  Xfered   Per                 Per
>> Recv   Send    Recv   Send             Recv (avg)          Send (avg)
>>      8       8      0       0 1176930056  1475.36    797726   16384.00  71905
>>
>> MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET : demo
>> ...
>> Interim result:  941.49 10^6bits/s over 0.997 seconds ending at 1440193142.763
>>
>> Alignment      Offset         Bytes    Bytes       Recvs   Bytes    Sends
>> Local  Remote  Local  Remote  Xfered   Per                 Per
>> Recv   Send    Recv   Send             Recv (avg)          Send (avg)
>>      8       8      0       0 1175182320  50476.00     23282   16384.00  71816
>>
>> i40e:
>> Hard to test because the traffic is incoming so fast (24Gb/s) that GRO
>> always receives 87kB, even at the highest interrupt rate.
>>
>> Other drivers were only compile tested.
>>
>> Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
>> Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
>> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
>
> Hi guys
>
> I am not sure the ixgbe part is working :
>
> ixgbe_qv_unlock_napi() does :
>
> /* flush any outstanding Rx frames */
> if (q_vector->napi.gro_list)
>          napi_gro_flush(&q_vector->napi, false);
>
> And it is called before napi_complete_done(napi, work_done);

Yes, I'm pretty certain you cannot use this napi_complete_done with 
anything that support busy poll sockets.  The problem is you need to 
flush any existing lists before yielding to the socket polling in order 
to avoid packet ordering issues between the NAPI polling routine and the 
socket polling routine.

- Alex

Re: [net-next 04/17] drivers/net/intel: use napi_complete_done()

[Eric Dumazet]

On Fri, 2015-11-13 at 08:06 -0800, Alexander Duyck wrote:

> Yes, I'm pretty certain you cannot use this napi_complete_done with 
> anything that support busy poll sockets.  The problem is you need to 
> flush any existing lists before yielding to the socket polling in order 
> to avoid packet ordering issues between the NAPI polling routine and the 
> socket polling routine.

My plan is to make busy poll independent of GRO / RPS / RFS, and generic
if possible, for all NAPI drivers. (No need to absolutely provide
ndo_busy_poll()

I really do not see GRO being a problem for low latency : RPC messages
are terminated by PSH flag that take care of flushing GRO engine.

For mixed use, (low latency and other kind of flows), GRO is a win.

With the following sk_busy_loop() , we :

- allow tunneling traffic to use busy poll as well as native traffic.
- allow RFS/RPS being used (sending IPI to other cpus if needed)
- use the 'lets burn cpu cycles' to do useful work (like TX completions, RCU callbacks...)
- Implement busy poll for all NAPI drivers.

        rcu_read_lock();
        napi = napi_by_id(sk->sk_napi_id);
        if (!napi)
                goto out;
        ops = napi->dev->netdev_ops;

        for (;;) {
                local_bh_disable();
                rc = 0;
                if (ops->ndo_busy_poll) {
                        rc = ops->ndo_busy_poll(napi);
                } else if (napi_schedule_prep(napi)) {
                        rc = napi->poll(napi, 4);
                        if (rc == 4) {
                                napi_complete_done(napi, rc);
                                napi_schedule(napi);
                        }
                }
                if (rc > 0)
                        NET_ADD_STATS_BH(sock_net(sk),
                                         LINUX_MIB_BUSYPOLLRXPACKETS, rc);
                local_bh_enable();

                if (rc == LL_FLUSH_FAILED ||
                    nonblock ||
                    !skb_queue_empty(&sk->sk_receive_queue) ||
                    need_resched() ||
                    busy_loop_timeout(end_time))
                        break;

                cpu_relax();
        }
        rcu_read_unlock();

Re: [net-next 04/17] drivers/net/intel: use napi_complete_done()

[Alexander Duyck]

On 11/13/2015 08:49 AM, Eric Dumazet wrote:
> On Fri, 2015-11-13 at 08:06 -0800, Alexander Duyck wrote:
>
>> Yes, I'm pretty certain you cannot use this napi_complete_done with
>> anything that support busy poll sockets.  The problem is you need to
>> flush any existing lists before yielding to the socket polling in order
>> to avoid packet ordering issues between the NAPI polling routine and the
>> socket polling routine.
> My plan is to make busy poll independent of GRO / RPS / RFS, and generic
> if possible, for all NAPI drivers. (No need to absolutely provide
> ndo_busy_poll()
>
> I really do not see GRO being a problem for low latency : RPC messages
> are terminated by PSH flag that take care of flushing GRO engine.

Right.  I wasn't thinking so much about GRO delaying the frames as the 
fact that ixgbe will call netif_receive_skb if busy polling instead of 
napi_gro_receive.  So you might have frames left in the GRO list that 
would get bypassed if pulled out during busy polling.

> For mixed use, (low latency and other kind of flows), GRO is a win.

Agreed.

> With the following sk_busy_loop() , we :
>
> - allow tunneling traffic to use busy poll as well as native traffic.
> - allow RFS/RPS being used (sending IPI to other cpus if needed)
> - use the 'lets burn cpu cycles' to do useful work (like TX completions, RCU callbacks...)
> - Implement busy poll for all NAPI drivers.
>
>          rcu_read_lock();
>          napi = napi_by_id(sk->sk_napi_id);
>          if (!napi)
>                  goto out;
>          ops = napi->dev->netdev_ops;
>
>          for (;;) {
>                  local_bh_disable();
>                  rc = 0;
>                  if (ops->ndo_busy_poll) {
>                          rc = ops->ndo_busy_poll(napi);
>                  } else if (napi_schedule_prep(napi)) {
>                          rc = napi->poll(napi, 4);
>                          if (rc == 4) {
>                                  napi_complete_done(napi, rc);
>                                  napi_schedule(napi);
>                          }
>                  }
>                  if (rc > 0)
>                          NET_ADD_STATS_BH(sock_net(sk),
>                                           LINUX_MIB_BUSYPOLLRXPACKETS, rc);
>                  local_bh_enable();
>
>                  if (rc == LL_FLUSH_FAILED ||
>                      nonblock ||
>                      !skb_queue_empty(&sk->sk_receive_queue) ||
>                      need_resched() ||
>                      busy_loop_timeout(end_time))
>                          break;
>
>                  cpu_relax();
>          }
>          rcu_read_unlock();

Sounds good.

- Alex

[net-next 05/17] i40e: generate fewer startup messages

[Jeff Kirsher]

From: Shannon Nelson <shannon.nelson@intel.com>

Cut down on the number of startup log entries by putting a couple behind
debug flags and combining a couple others into a single line.

Change-ID: I708089f086308f84d43f8b6f0e8a634a02d058fb
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h         |  4 ++--
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 20 ++++++++++++--------
 drivers/net/ethernet/intel/i40e/i40e_ptp.c     |  4 ++--
 4 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 91f8cbf..7aaead3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -582,10 +582,10 @@ struct i40e_device {
 };
 
 /**
- * i40e_fw_version_str - format the FW and NVM version strings
+ * i40e_nvm_version_str - format the NVM version strings
  * @hw: ptr to the hardware info
  **/
-static inline char *i40e_fw_version_str(struct i40e_hw *hw)
+static inline char *i40e_nvm_version_str(struct i40e_hw *hw)
 {
 	static char buf[32];
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index ed70a3f..923f95e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1122,7 +1122,7 @@ static void i40e_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->driver, i40e_driver_name, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, i40e_driver_version_str,
 		sizeof(drvinfo->version));
-	strlcpy(drvinfo->fw_version, i40e_fw_version_str(&pf->hw),
+	strlcpy(drvinfo->fw_version, i40e_nvm_version_str(&pf->hw),
 		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
 		sizeof(drvinfo->bus_info));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 389f110..d731095 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6218,8 +6218,9 @@ static void i40e_config_bridge_mode(struct i40e_veb *veb)
 {
 	struct i40e_pf *pf = veb->pf;
 
-	dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n",
-		 veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
+	if (pf->hw.debug_mask & I40E_DEBUG_LAN)
+		dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n",
+			 veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
 	if (veb->bridge_mode & BRIDGE_MODE_VEPA)
 		i40e_disable_pf_switch_lb(pf);
 	else
@@ -9923,6 +9924,10 @@ static void i40e_print_features(struct i40e_pf *pf)
 	if (pf->flags & I40E_FLAG_FCOE_ENABLED)
 		buf += sprintf(buf, "FCOE ");
 #endif
+	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+		buf += sprintf(buf, "VEB ");
+	else
+		buf += sprintf(buf, "VEPA ");
 
 	BUG_ON(buf > (string + INFO_STRING_LEN));
 	dev_info(&pf->pdev->dev, "%s\n", string);
@@ -10062,13 +10067,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pf->hw.fc.requested_mode = I40E_FC_NONE;
 
 	err = i40e_init_adminq(hw);
-	dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw));
 
-	/* provide additional fw info, like api and ver */
-	dev_info(&pdev->dev, "fw_version:%d.%d.%05d\n",
-		 hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build);
-	dev_info(&pdev->dev, "fw api version:%d.%d\n",
-		 hw->aq.api_maj_ver, hw->aq.api_min_ver);
+	/* provide nvm, fw, api versions */
+	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+		 hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
+		 hw->aq.api_maj_ver, hw->aq.api_min_ver,
+		 i40e_nvm_version_str(hw));
 
 	if (err) {
 		dev_info(&pdev->dev,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 552c84e..565ca7c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -674,8 +674,8 @@ void i40e_ptp_init(struct i40e_pf *pf)
 		struct timespec64 ts;
 		u32 regval;
 
-		dev_info(&pf->pdev->dev, "%s: added PHC on %s\n", __func__,
-			 netdev->name);
+		if (pf->hw.debug_mask & I40E_DEBUG_LAN)
+			dev_info(&pf->pdev->dev, "PHC enabled\n");
 		pf->flags |= I40E_FLAG_PTP;
 
 		/* Ensure the clocks are running. */
-- 
2.4.3

[net-next 06/17] i40e/i40evf: Fix compile issue related to const string

[Jeff Kirsher]

From: Jingjing Wu <jingjing.wu@intel.com>

Add const to functions that return strings that aren't going to be
modified. This addresses some reported compile complaints.

Change-ID: Ic56b1e814ab4d23a50480e7fdec652445f776ee8
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_common.c      | 4 ++--
 drivers/net/ethernet/intel/i40e/i40e_nvm.c         | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_prototype.h   | 4 ++--
 drivers/net/ethernet/intel/i40evf/i40e_common.c    | 4 ++--
 drivers/net/ethernet/intel/i40evf/i40e_prototype.h | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d1ee174..daa6b17 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -87,7 +87,7 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
  * @hw: pointer to the HW structure
  * @aq_err: the AQ error code to convert
  **/
-char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
+const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
 {
 	switch (aq_err) {
 	case I40E_AQ_RC_OK:
@@ -147,7 +147,7 @@ char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
  * @hw: pointer to the HW structure
  * @stat_err: the status error code to convert
  **/
-char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err)
+const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err)
 {
 	switch (stat_err) {
 	case 0:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 2142e10..875a8cc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -632,7 +632,7 @@ static inline u8 i40e_nvmupd_get_transaction(u32 val)
 	return (u8)((val & I40E_NVM_TRANS_MASK) >> I40E_NVM_TRANS_SHIFT);
 }
 
-static char *i40e_nvm_update_state_str[] = {
+static const char * const i40e_nvm_update_state_str[] = {
 	"I40E_NVMUPD_INVALID",
 	"I40E_NVMUPD_READ_CON",
 	"I40E_NVMUPD_READ_SNT",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 4454974..10bf2ba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -58,8 +58,8 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
 void i40e_idle_aq(struct i40e_hw *hw);
 bool i40e_check_asq_alive(struct i40e_hw *hw);
 i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
-char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
-char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err);
+const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
+const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err);
 
 i40e_status i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid,
 				bool pf_lut, u8 *lut, u16 lut_size);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index b98b642..7435fb3 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -87,7 +87,7 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw)
  * @hw: pointer to the HW structure
  * @aq_err: the AQ error code to convert
  **/
-char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
+const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
 {
 	switch (aq_err) {
 	case I40E_AQ_RC_OK:
@@ -147,7 +147,7 @@ char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
  * @hw: pointer to the HW structure
  * @stat_err: the status error code to convert
  **/
-char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err)
+const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err)
 {
 	switch (stat_err) {
 	case 0:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index 55ae4b0..8ed0edf 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -60,8 +60,8 @@ void i40e_idle_aq(struct i40e_hw *hw);
 void i40evf_resume_aq(struct i40e_hw *hw);
 bool i40evf_check_asq_alive(struct i40e_hw *hw);
 i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
-char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
-char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err);
+const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
+const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err);
 
 i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 seid,
 				  bool pf_lut, u8 *lut, u16 lut_size);
-- 
2.4.3

[net-next 07/17] i40e: remove read/write failed messages from nvmupdate

[Jeff Kirsher]

From: Shannon Nelson <shannon.nelson@intel.com>

Allow the nvmupdate application to decide when a read or write error
should be exposed to the user.  Since the application needs to use
write probes to find the ReadOnly sections on a potentially unknown NVM
version in the HW and read probes to check the status of the last write,
some error messages are expected, but need not be shown to the users.
The driver doesn't know which are ignorable from real errors, so needs
to let the application make the decision.

Change-ID: I78fca8ab672bede11c10c820b83c26adfd536d03
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 923f95e..d9c4f07 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -993,9 +993,7 @@ static int i40e_get_eeprom(struct net_device *netdev,
 
 		cmd = (struct i40e_nvm_access *)eeprom;
 		ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
-		if (ret_val &&
-		    ((hw->aq.asq_last_status != I40E_AQ_RC_EACCES) ||
-		     (hw->debug_mask & I40E_DEBUG_NVM)))
+		if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM))
 			dev_info(&pf->pdev->dev,
 				 "NVMUpdate read failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n",
 				 ret_val, hw->aq.asq_last_status, errno,
@@ -1099,10 +1097,7 @@ static int i40e_set_eeprom(struct net_device *netdev,
 
 	cmd = (struct i40e_nvm_access *)eeprom;
 	ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno);
-	if (ret_val &&
-	    ((hw->aq.asq_last_status != I40E_AQ_RC_EPERM &&
-	      hw->aq.asq_last_status != I40E_AQ_RC_EBUSY) ||
-	     (hw->debug_mask & I40E_DEBUG_NVM)))
+	if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM))
 		dev_info(&pf->pdev->dev,
 			 "NVMUpdate write failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n",
 			 ret_val, hw->aq.asq_last_status, errno,
-- 
2.4.3

[net-next 08/17] i40e: Removed unused defines

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

Two defines that are not used are causing customer confusion - remove
them.

Change-ID: Icef0325aca8e0f4fcdfc519e026bdd375e791200
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 736f6f0..7fe94e8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -29,8 +29,6 @@
 
 #include "i40e.h"
 
-#define I40E_MAX_MACVLAN_FILTERS 256
-#define I40E_MAX_VLAN_FILTERS 256
 #define I40E_MAX_VLANID 4095
 
 #define I40E_VIRTCHNL_SUPPORTED_QTYPES 2
-- 
2.4.3

[net-next 09/17] i40e: priv flag for controlling VEB stats

[Jeff Kirsher]

From: Shannon Nelson <shannon.nelson@intel.com>

Add an ethtool priv flag to enable and disable printing
the VEB statistics.

Change-ID: I7654054a3a73b08aa8310d94ee8fce6219107dd8
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h         | 1 +
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 8 ++++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 7aaead3..1125464 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -103,6 +103,7 @@
 #define I40E_PRIV_FLAGS_NPAR_FLAG	BIT(0)
 #define I40E_PRIV_FLAGS_LINKPOLL_FLAG	BIT(1)
 #define I40E_PRIV_FLAGS_FD_ATR		BIT(2)
+#define I40E_PRIV_FLAGS_VEB_STATS	BIT(3)
 
 #define I40E_NVM_VERSION_LO_SHIFT  0
 #define I40E_NVM_VERSION_LO_MASK   (0xff << I40E_NVM_VERSION_LO_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index d9c4f07..1df222a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -229,6 +229,7 @@ static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = {
 	"NPAR",
 	"LinkPolling",
 	"flow-director-atr",
+	"veb-stats",
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings)
@@ -2671,6 +2672,8 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 		I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0;
 	ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ?
 		I40E_PRIV_FLAGS_FD_ATR : 0;
+	ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ?
+		I40E_PRIV_FLAGS_VEB_STATS : 0;
 
 	return ret_flags;
 }
@@ -2702,6 +2705,11 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
 	}
 
+	if (flags & I40E_PRIV_FLAGS_VEB_STATS)
+		pf->flags |= I40E_FLAG_VEB_STATS_ENABLED;
+	else
+		pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
+
 	return 0;
 }
 
-- 
2.4.3

[net-next 10/17] i40e: Add support for non-willing Apps

[Jeff Kirsher]

From: Greg Bowers <gregory.j.bowers@intel.com>

Adds support for setting a new bit in the Set Local LLDP MIB AQ command
Type field.  When set to 1, the bit indicates to FW that Apps should be
treated as non-willing.  When 0, FW behaves as before.

Change-ID: I0d2101c1606c59c7188d3e6a0c7810e0f205233a
Signed-off-by: Greg Bowers <gregory.j.bowers@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 7 +++++++
 drivers/net/ethernet/intel/i40e/i40e_type.h       | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 02d5225..6584b6c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -2132,6 +2132,13 @@ I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_cee_dcb_cfg_resp);
 struct i40e_aqc_lldp_set_local_mib {
 #define SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT	0
 #define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK	(1 << SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT)
+#define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK	(1 << \
+					SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT)
+#define SET_LOCAL_MIB_AC_TYPE_LOCAL_MIB	0x0
+#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT	(1)
+#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_MASK	(1 << \
+				SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT)
+#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS		0x1
 	u8	type;
 	u8	reserved0;
 	__le16	length;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 6f69576..9c4a457 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -475,6 +475,8 @@ struct i40e_dcbx_config {
 	u8  dcbx_mode;
 #define I40E_DCBX_MODE_CEE	0x1
 #define I40E_DCBX_MODE_IEEE	0x2
+	u8  app_mode;
+#define I40E_DCBX_APPS_NON_WILLING	0x1
 	u32 numapps;
 	u32 tlv_status; /* CEE mode TLV status */
 	struct i40e_dcb_ets_config etscfg;
-- 
2.4.3

[net-next 11/17] i40e/i40evf: moderate interrupts differently

[Jeff Kirsher]

From: Jesse Brandeburg <jesse.brandeburg@intel.com>

The XL710 hardware has a different interrupt moderation design
that can support a limit of total interrupts per second per
vector, in addition to the "number of interrupts per second"
controls already established in the driver.  This combination
of hardware features allows us to set very low default latency
settings but minimize the total CPU utilization by not
making too many interrupts, should the user desire.

The current driver implementation is still enabling the dynamic
moderation in the driver, and only using the rx/tx-usecs
limit in ethtool to limit the interrupt rate per second, by default.

The new code implemented in this patch
2) adds init/use of the new "Interrupt Limit" register
3) adds ethtool knob to control/report the limits above

Usage is ethtool -C ethx rx-usecs-high <value> Where <value> is number
of microseconds to create a rate of 1/N interrupts per second,
regardless of rx-usecs or tx-usecs values. Since there is a credit based
scheme in the hardware, the rx-usecs and tx-usecs can be configured for
very low latency for short bursts, but once the credit runs out the
refill rate on the credits is limited by rx-usecs-high.

Change-ID: I3a1075d3296123b0f4f50623c779b027af5b188d
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h         |  1 +
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 24 ++++++++++++++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 10 +++++++---
 drivers/net/ethernet/intel/i40e/i40e_txrx.h    | 10 ++++++++++
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h  | 10 ++++++++++
 5 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 1125464..ad48f52 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -498,6 +498,7 @@ struct i40e_vsi {
 	 */
 	u16 rx_itr_setting;
 	u16 tx_itr_setting;
+	u16 int_rate_limit;  /* value in usecs */
 
 	u16 rss_table_size;
 	u16 rss_size;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 1df222a..822649f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1846,6 +1846,14 @@ static int i40e_get_coalesce(struct net_device *netdev,
 
 	ec->rx_coalesce_usecs = vsi->rx_itr_setting & ~I40E_ITR_DYNAMIC;
 	ec->tx_coalesce_usecs = vsi->tx_itr_setting & ~I40E_ITR_DYNAMIC;
+	/* we use the _usecs_high to store/set the interrupt rate limit
+	 * that the hardware supports, that almost but not quite
+	 * fits the original intent of the ethtool variable,
+	 * the rx_coalesce_usecs_high limits total interrupts
+	 * per second from both tx/rx sources.
+	 */
+	ec->rx_coalesce_usecs_high = vsi->int_rate_limit;
+	ec->tx_coalesce_usecs_high = vsi->int_rate_limit;
 
 	return 0;
 }
@@ -1864,6 +1872,17 @@ static int i40e_set_coalesce(struct net_device *netdev,
 	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
 		vsi->work_limit = ec->tx_max_coalesced_frames_irq;
 
+	/* tx_coalesce_usecs_high is ignored, use rx-usecs-high instead */
+	if (ec->tx_coalesce_usecs_high != vsi->int_rate_limit) {
+		netif_info(pf, drv, netdev, "tx-usecs-high is not used, please program rx-usecs-high\n");
+		return -EINVAL;
+	}
+
+	if (ec->rx_coalesce_usecs_high >= INTRL_REG_TO_USEC(I40E_MAX_INTRL)) {
+		netif_info(pf, drv, netdev, "Invalid value, rx-usecs-high range is 0-235\n");
+		return -EINVAL;
+	}
+
 	vector = vsi->base_vector;
 	if ((ec->rx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
 	    (ec->rx_coalesce_usecs <= (I40E_MAX_ITR << 1))) {
@@ -1877,6 +1896,8 @@ static int i40e_set_coalesce(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	vsi->int_rate_limit = ec->rx_coalesce_usecs_high;
+
 	if ((ec->tx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
 	    (ec->tx_coalesce_usecs <= (I40E_MAX_ITR << 1))) {
 		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
@@ -1901,11 +1922,14 @@ static int i40e_set_coalesce(struct net_device *netdev,
 		vsi->tx_itr_setting &= ~I40E_ITR_DYNAMIC;
 
 	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+		u16 intrl = INTRL_USEC_TO_REG(vsi->int_rate_limit);
+
 		q_vector = vsi->q_vectors[i];
 		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
 		wr32(hw, I40E_PFINT_ITRN(0, vector - 1), q_vector->rx.itr);
 		q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
 		wr32(hw, I40E_PFINT_ITRN(1, vector - 1), q_vector->tx.itr);
+		wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl);
 		i40e_flush(hw);
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d731095..722b0a1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2901,11 +2901,9 @@ static int i40e_vsi_configure(struct i40e_vsi *vsi)
 static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_q_vector *q_vector;
 	struct i40e_hw *hw = &pf->hw;
 	u16 vector;
 	int i, q;
-	u32 val;
 	u32 qp;
 
 	/* The interrupt indexing is offset by 1 in the PFINT_ITRn
@@ -2915,7 +2913,8 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 	qp = vsi->base_queue;
 	vector = vsi->base_vector;
 	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
-		q_vector = vsi->q_vectors[i];
+		struct i40e_q_vector *q_vector = vsi->q_vectors[i];
+
 		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
 		q_vector->rx.latency_range = I40E_LOW_LATENCY;
 		wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
@@ -2924,10 +2923,14 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 		q_vector->tx.latency_range = I40E_LOW_LATENCY;
 		wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1),
 		     q_vector->tx.itr);
+		wr32(hw, I40E_PFINT_RATEN(vector - 1),
+		     INTRL_USEC_TO_REG(vsi->int_rate_limit));
 
 		/* Linked list for the queuepairs assigned to this vector */
 		wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp);
 		for (q = 0; q < q_vector->num_ringpairs; q++) {
+			u32 val;
+
 			val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
 			      (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT)  |
 			      (vector      << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) |
@@ -7040,6 +7043,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	vsi->idx = vsi_idx;
 	vsi->rx_itr_setting = pf->rx_itr_default;
 	vsi->tx_itr_setting = pf->tx_itr_default;
+	vsi->int_rate_limit = 0;
 	vsi->rss_table_size = (vsi->type == I40E_VSI_MAIN) ?
 				pf->rss_table_size : 64;
 	vsi->netdev_registered = false;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 75cecfa..7c0ed84 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -35,6 +35,7 @@
 #define I40E_ITR_20K               0x0019
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
+#define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
 #define I40E_ITR_RX_DEF            I40E_ITR_8K
 #define I40E_ITR_TX_DEF            I40E_ITR_4K
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
@@ -44,6 +45,15 @@
 #define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1)
 #define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC))
 #define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1)
+/* 0x40 is the enable bit for interrupt rate limiting, and must be set if
+ * the value of the rate limit is non-zero
+ */
+#define INTRL_ENA                  BIT(6)
+#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2)
+#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0)
+#define I40E_INTRL_8K              125     /* 8000 ints/sec */
+#define I40E_INTRL_62K             16      /* 62500 ints/sec */
+#define I40E_INTRL_83K             12      /* 83333 ints/sec */
 
 #define I40E_QUEUE_END_OF_LIST 0x7FF
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 0c13ece..c4f5a4e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -35,6 +35,7 @@
 #define I40E_ITR_20K               0x0019
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
+#define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
 #define I40E_ITR_RX_DEF            I40E_ITR_8K
 #define I40E_ITR_TX_DEF            I40E_ITR_4K
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
@@ -44,6 +45,15 @@
 #define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1)
 #define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC))
 #define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1)
+/* 0x40 is the enable bit for interrupt rate limiting, and must be set if
+ * the value of the rate limit is non-zero
+ */
+#define INTRL_ENA                  BIT(6)
+#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2)
+#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0)
+#define I40E_INTRL_8K              125     /* 8000 ints/sec */
+#define I40E_INTRL_62K             16      /* 62500 ints/sec */
+#define I40E_INTRL_83K             12      /* 83333 ints/sec */
 
 #define I40E_QUEUE_END_OF_LIST 0x7FF
 
-- 
2.4.3

[net-next 12/17] i40e: reset the invalid msg counter in vf when a valid msg is received

[Jeff Kirsher]

From: Jingjing Wu <jingjing.wu@intel.com>

When the number of invalid messages from a VF is exceeded, the VF
will be disabled, due to the invalid messages.  This happens if
other VF drivers (like DPDK) send a message through the driver's
mailbox (aka virtchannel) interface, but the message is not
supported by the i40e pf driver, such as CONFIG_PROMISCUOUS_MODE.

This patch changes the num_invalid_msgs in struct i40e_vf to record
the continuous invalid msgs, and it will be reset when a valid msg
is received.

Change-ID: Iaec42fd3dcdd281476b3518be23261dd46fc3718
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 ++
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index fd99cd2..a35a204 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1102,6 +1102,8 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode,
 		}
 	} else {
 		vf->num_valid_msgs++;
+		/* reset the invalid counter, if a valid message is received. */
+		vf->num_invalid_msgs = 0;
 	}
 
 	aq_ret = i40e_aq_send_msg_to_vf(hw, abs_vf_id,	v_opcode, v_retval,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 7fe94e8..da44995 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -96,7 +96,8 @@ struct i40e_vf {
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
 	u64 num_mdd_events;	/* num of mdd events detected */
-	u64 num_invalid_msgs;	/* num of malformed or invalid msgs detected */
+	/* num of continuous malformed or invalid msgs detected */
+	u64 num_invalid_msgs;
 	u64 num_valid_msgs;	/* num of valid msgs detected */
 
 	unsigned long vf_caps;	/* vf's adv. capabilities */
-- 
2.4.3

[net-next 13/17] i40evf: correctly populate vlan_features

[Jeff Kirsher]

From: Mitch Williams <mitch.a.williams@intel.com>

The vlan_features field was correctly being set to the same value as the
netdev features field. However, this was being done before the features
were actually being set up, leaving the vlan_features empty.

Also, after a reset, vlan_features will be incorrectly assigned the
previous netdev feature flags, which can contain VLAN feature bits. This
makes the VLAN code angry and will cause a stack dump.

To fix these issues, set up the netdev features first, then mask out the
VLAN feature bits when assigning vlan_features.

Change-ID: Ib0548869dc83cf6a841cb8697dd94c12359ba4d2
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 5e13363..9e754d0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2123,7 +2123,10 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 
 	if (adapter->vf_res->vf_offload_flags
 	    & I40E_VIRTCHNL_VF_OFFLOAD_VLAN) {
-		netdev->vlan_features = netdev->features;
+		netdev->vlan_features = netdev->features &
+					~(NETIF_F_HW_VLAN_CTAG_TX |
+					  NETIF_F_HW_VLAN_CTAG_RX |
+					  NETIF_F_HW_VLAN_CTAG_FILTER);
 		netdev->features |= NETIF_F_HW_VLAN_CTAG_TX |
 				    NETIF_F_HW_VLAN_CTAG_RX |
 				    NETIF_F_HW_VLAN_CTAG_FILTER;
-- 
2.4.3

[net-next 14/17] i40e: Recognize 1000Base_T_Optical phy type when link is up

[Jeff Kirsher]

From: Catherine Sullivan <catherine.sullivan@intel.com>

1000Base_T_Optical got added to the function that figures out what
is supported when link is down but not when link is up. Add it in there
too so that we display the correct information.

Change-ID: I85ebcdfa7c02d898c44c673b1500552a53c8042e
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 822649f..e2c2178 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -307,6 +307,12 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
 			ecmd->advertising |= ADVERTISED_1000baseT_Full;
 		break;
+	case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
+		ecmd->supported = SUPPORTED_Autoneg |
+				  SUPPORTED_1000baseT_Full;
+		ecmd->advertising = ADVERTISED_Autoneg |
+				    ADVERTISED_1000baseT_Full;
+		break;
 	case I40E_PHY_TYPE_100BASE_TX:
 		ecmd->supported = SUPPORTED_Autoneg |
 				  SUPPORTED_100baseT_Full;
-- 
2.4.3

[net-next 15/17] i40evf: relax and stagger init timing a bit

[Jeff Kirsher]

From: Mitch Williams <mitch.a.williams@intel.com>

On some devices, in some systems, in some configurations, the VFs would
fail to initialize the first time you loaded the driver.

To correct this, increase the delay time for the init task slightly, and
wait longer before giving up.

If we enable VFs and load the VF driver in the same kernel as the PF
driver, we can totally overwhelm the PF driver with AQ requests because
all of the instances try to initialize at the same time.

To help alleviate this, stagger the initial scheduling of the init task
using the PCIe function as a multiplier. We mask off the function to
only three bits so no instance has to wait too long.

With these two changes, initializing 128 VFs on a single device goes
from four minutes to just a few seconds.

Change-ID: If3d8720c1c4e838ab36d8781d9ec295a62380936
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf.h      | 2 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index c74f614..22841c6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -87,7 +87,7 @@ struct i40e_vsi {
 #define I40EVF_MAX_RXBUFFER   16384  /* largest size for single descriptor */
 #define I40EVF_MAX_AQ_BUF_SIZE    4096
 #define I40EVF_AQ_LEN             32
-#define I40EVF_AQ_MAX_ERR         10 /* times to try before resetting AQ */
+#define I40EVF_AQ_MAX_ERR         20 /* times to try before resetting AQ */
 
 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 9e754d0..b943d93 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2344,7 +2344,7 @@ static void i40evf_init_task(struct work_struct *work)
 	}
 	return;
 restart:
-	schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(20));
+	schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30));
 	return;
 
 err_register:
@@ -2361,7 +2361,7 @@ err:
 		adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
 		return; /* do not reschedule */
 	}
-	schedule_delayed_work(&adapter->init_task, HZ / 2);
+	schedule_delayed_work(&adapter->init_task, HZ);
 }
 
 /**
-- 
2.4.3

[net-next 16/17] i40e: increase AQ work limit

[Jeff Kirsher]

From: Mitch Williams <mitch.a.williams@intel.com>

With 64 VFs, we can easily overwhelm the AQ on the PF if we have too low
a limit on the number of AQ requests. This leads to ARQ overflow errors,
and occasionally VFs that fail to initialize.

Since we really only hit this condition on initial VF driver load, the
requests that we process are lightweight, so this extra work doesn't
cause problems for the PF driver.

Change-ID: I620221520d8af987df6ace9ba938ffaf22107681
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ad48f52..7a58b1f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -93,7 +93,7 @@
 #endif /* I40E_FCOE */
 #define I40E_MAX_AQ_BUF_SIZE          4096
 #define I40E_AQ_LEN                   256
-#define I40E_AQ_WORK_LIMIT            32
+#define I40E_AQ_WORK_LIMIT            66 /* max number of VFs + a little */
 #define I40E_MAX_USER_PRIORITY        8
 #define I40E_DEFAULT_MSG_ENABLE       4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT   10
-- 
2.4.3

[net-next 17/17] i40e/i40evf: Bump i40e to 1.3.34 and i40evf to 1.3.21

[Jeff Kirsher]

From: Catherine Sullivan <catherine.sullivan@intel.com>

Bump.

Change-ID: I7ec818a507554648675b9b245ced9e6b6bd9ed4e
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c     | 2 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 722b0a1..87a5d09 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 28
+#define DRV_VERSION_BUILD 34
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index b943d93..2575473 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf";
 static const char i40evf_driver_string[] =
 	"Intel(R) XL710/X710 Virtual Function Network Driver";
 
-#define DRV_VERSION "1.3.19"
+#define DRV_VERSION "1.3.21"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2015 Intel Corporation.";
-- 
2.4.3

Re: [net-next 00/17][pull request] Intel Wired LAN Driver Updates 2015-10-15

[David Miller]

From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Thu, 15 Oct 2015 14:43:07 -0700

> This series contains updates to e1000, e1000e, igb, igbvf, ixgbe, ixgbevf,
> i40e, i40evf and fm10k.

Please fix the missing space issue pointed out by Sergei and resend this
pull request, thanks.