From c73d2e8462d0bb1d47b0e8f6a33d97ab9a154824 Mon Sep 17 00:00:00 2001
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
Date: Wed, 14 Sep 2016 16:24:31 -0700
Subject: [PATCH 01/17] i40e: Fix client interaction

This patch fixes a problem in the client interface that
was causing random stack traces in RDMA driver load and
unload tests.  This patch fixes the problem by checking
for an existing client before trying to open it.  Without
this patch, there is a timing related null pointer deref.

Change-ID: Ib73d30671a27f6f9770dd53b3e5292b88d6b62da
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_client.c | 29 +++++++++----------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 250db0b244b7..6ffac03d5015 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -565,7 +565,7 @@ void i40e_client_subtask(struct i40e_pf *pf)
 			if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
 				continue;
 		} else {
-			dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n",
+			dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n",
 				 client->name);
 		}
 
@@ -582,24 +582,21 @@ void i40e_client_subtask(struct i40e_pf *pf)
 			dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
 				 client->name, pf->hw.pf_id,
 				 pf->hw.bus.device, pf->hw.bus.func);
-		}
-
-		mutex_lock(&i40e_client_instance_mutex);
-		/* Send an Open request to the client */
-		atomic_inc(&cdev->ref_cnt);
-		if (client->ops && client->ops->open)
-			ret = client->ops->open(&cdev->lan_info, client);
-		atomic_dec(&cdev->ref_cnt);
-		if (!ret) {
+			mutex_lock(&i40e_client_instance_mutex);
+			atomic_inc(&cdev->ref_cnt);
+			if (client->ops && client->ops->open)
+				ret = client->ops->open(&cdev->lan_info,
+							client);
+			atomic_dec(&cdev->ref_cnt);
+			if (ret < 0) {
+				mutex_unlock(&i40e_client_instance_mutex);
+				i40e_client_del_instance(pf, client);
+				atomic_dec(&client->ref_cnt);
+				continue;
+			}
 			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
-		} else {
-			/* remove client instance */
 			mutex_unlock(&i40e_client_instance_mutex);
-			i40e_client_del_instance(pf, client);
-			atomic_dec(&client->ref_cnt);
-			continue;
 		}
-		mutex_unlock(&i40e_client_instance_mutex);
 	}
 	mutex_unlock(&i40e_client_mutex);
 }

From ed245406da1409437f9d2c4e7c69112fb255964c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Wed, 14 Sep 2016 16:24:32 -0700
Subject: [PATCH 02/17] i40e: Rewrite Flow Director busy wait loop

We can reorder the busy wait loop at the start of the Flow Director
transmit function to reduce the overall code size while still retaining the
same functionality.  As such I am taking advantage of the opportunity to do
so.

Change-ID: I34c403ca001953c6ac9816e65d5305e73d869026
Signed-off-by: Alexander Duyck <alexander.h.duyck@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_txrx.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6287bf63c43c..af36c44c4844 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -122,7 +122,6 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data,
 	struct device *dev;
 	dma_addr_t dma;
 	u32 td_cmd = 0;
-	u16 delay = 0;
 	u16 i;
 
 	/* find existing FDIR VSI */
@@ -137,15 +136,11 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data,
 	dev = tx_ring->dev;
 
 	/* we need two descriptors to add/del a filter and we can wait */
-	do {
-		if (I40E_DESC_UNUSED(tx_ring) > 1)
-			break;
+	for (i = I40E_FD_CLEAN_DELAY; I40E_DESC_UNUSED(tx_ring) < 2; i--) {
+		if (!i)
+			return -EAGAIN;
 		msleep_interruptible(1);
-		delay++;
-	} while (delay < I40E_FD_CLEAN_DELAY);
-
-	if (!(I40E_DESC_UNUSED(tx_ring) > 1))
-		return -EAGAIN;
+	}
 
 	dma = dma_map_single(dev, raw_packet,
 			     I40E_FDIR_MAX_RAW_PACKET_SIZE, DMA_TO_DEVICE);

From 7ed3573223dd6bf36b1bd35c8e5e3d0cd4f6f690 Mon Sep 17 00:00:00 2001
From: Filip Sadowski <filip.sadowski@intel.com>
Date: Wed, 14 Sep 2016 16:24:33 -0700
Subject: [PATCH 03/17] i40e: Bit test mask correction

Incorrect bit mask was used for testing "get link status" response.
Instead of I40E_AQ_LSE_ENABLE (which is actually 0x03) it most probably
should be I40E_AQ_LSE_IS_ENABLED (which is defined as 0x01).

Change-ID: Ia199142906720507f847de3a33a25c61a9781b2f
Signed-off-by: Filip Sadowski <filip.sadowski@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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 2154a34c1dd8..fe8100bb1027 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1849,7 +1849,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	else
 		hw_link_info->crc_enable = false;
 
-	if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_ENABLE))
+	if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_IS_ENABLED))
 		hw_link_info->lse_enable = true;
 	else
 		hw_link_info->lse_enable = false;

From dc7621205a93a00a898c193cf985c4c1a65a47d6 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Wed, 14 Sep 2016 16:24:34 -0700
Subject: [PATCH 04/17] i40e: Remove unused function i40e_vsi_lookup

The function is not used so there is no need to carry it forward.  I have
plans to add a slightly different function that can be inlined to handle
the same kind of functionality.

Change-ID: Ie2dfcb189dc75e5fbc156bac23003e3b4210ae0f
Signed-off-by: Alexander Duyck <alexander.h.duyck@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 --
 drivers/net/ethernet/intel/i40e/i40e_client.c | 31 -------------------
 2 files changed, 33 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 2030d7c1dc94..34c7a5d395f7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -728,8 +728,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
 struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 				u16 uplink, u32 param1);
 int i40e_vsi_release(struct i40e_vsi *vsi);
-struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, enum i40e_vsi_type type,
-				 struct i40e_vsi *start_vsi);
 #ifdef I40E_FCOE
 void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 			      struct i40e_vsi_context *ctxt,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 6ffac03d5015..417ac1646bc6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -405,37 +405,6 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
 	return capable;
 }
 
-/**
- * i40e_vsi_lookup - finds a matching VSI from the PF list starting at start_vsi
- * @pf: board private structure
- * @type: vsi type
- * @start_vsi: a VSI pointer from where to start the search
- *
- * Returns non NULL on success or NULL for failure
- **/
-struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf,
-				 enum i40e_vsi_type type,
-				 struct i40e_vsi *start_vsi)
-{
-	struct i40e_vsi *vsi;
-	int i = 0;
-
-	if (start_vsi) {
-		for (i = 0; i < pf->num_alloc_vsi; i++) {
-			vsi = pf->vsi[i];
-			if (vsi == start_vsi)
-				break;
-		}
-	}
-	for (; i < pf->num_alloc_vsi; i++) {
-		vsi = pf->vsi[i];
-		if (vsi && vsi->type == type)
-			return vsi;
-	}
-
-	return NULL;
-}
-
 /**
  * i40e_client_add_instance - add a client instance struct to the instance list
  * @pf: pointer to the board struct

From e1da71ca88170d1a6232951294b44dc0c824e464 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Wed, 14 Sep 2016 16:24:35 -0700
Subject: [PATCH 05/17] i40e: Drop code for unsupported flow types

We cannot currently support SCTP in the hardware, and IPV4_FLOW is not used
anywhere by the software so we can go through and drop the functionality
related to these two flow types.

In addition we cannot support masking based on the protocol value so if the
user is expecting a value other than TCP or UDP we should simply return an
error rather then trying to allocate a filter for a rule that will only
partially match what the user requested.

Change-ID: I10d52bb97d8104d76255fe244551814ff9531a63
Signed-off-by: Alexander Duyck <alexander.h.duyck@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_txrx.c | 31 ++++-----------------
 1 file changed, 5 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index af36c44c4844..7d160c9497b7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -330,22 +330,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	return err ? -EOPNOTSUPP : 0;
 }
 
-/**
- * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
- * a specific flow spec
- * @vsi: pointer to the targeted VSI
- * @fd_data: the flow director data required for the FDir descriptor
- * @add: true adds a filter, false removes it
- *
- * Returns 0 if the filters were successfully added or removed
- **/
-static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
-				    struct i40e_fdir_filter *fd_data,
-				    bool add)
-{
-	return -EOPNOTSUPP;
-}
-
 #define I40E_IP_DUMMY_PACKET_LEN 34
 /**
  * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for
@@ -428,12 +412,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 	case UDP_V4_FLOW:
 		ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 		break;
-	case SCTP_V4_FLOW:
-		ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
-		break;
-	case IPV4_FLOW:
-		ret = i40e_add_del_fdir_ipv4(vsi, input, add);
-		break;
 	case IP_USER_FLOW:
 		switch (input->ip4_proto) {
 		case IPPROTO_TCP:
@@ -442,15 +420,16 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 		case IPPROTO_UDP:
 			ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 			break;
-		case IPPROTO_SCTP:
-			ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
-			break;
-		default:
+		case IPPROTO_IP:
 			ret = i40e_add_del_fdir_ipv4(vsi, input, add);
 			break;
+		default:
+			/* We cannot support masking based on protocol */
+			goto unsupported_flow;
 		}
 		break;
 	default:
+unsupported_flow:
 		dev_info(&pf->pdev->dev, "Could not specify spec type %d\n",
 			 input->flow_type);
 		ret = -EINVAL;

From 7be96322a57a3612ea7640e6ff56030a7350fd7f Mon Sep 17 00:00:00 2001
From: Mitch Williams <mitch.a.williams@intel.com>
Date: Wed, 14 Sep 2016 16:24:36 -0700
Subject: [PATCH 06/17] i40e: reopen client after reset

Allow the client interface to reopen existing clients if they were
closed. This allows clients to recover from reset, which is essential
for supporting VF RDMA. In one instance, the driver was not clearing the
open bit when the client was closed. Add the code to clear this bit so
that the state is accurate and the driver will not attempt to reopen
already-open clients. Remove the ref_cnt variable; it was just getting
in the way and was not being used consistently.

Change-ID: Ic71af4553b096963ac0c56a997f887c9a4ed162d
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_client.c | 47 +++++++------------
 drivers/net/ethernet/intel/i40e/i40e_client.h |  2 -
 2 files changed, 17 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 417ac1646bc6..7fe72abc0b4a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -287,6 +287,7 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
 			}
 			cdev->client->ops->close(&cdev->lan_info, cdev->client,
 						 reset);
+			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
 			i40e_client_release_qvlist(&cdev->lan_info);
 		}
 	}
@@ -544,28 +545,27 @@ void i40e_client_subtask(struct i40e_pf *pf)
 			continue;
 
 		if (!existing) {
-			/* Also up the ref_cnt for no. of instances of this
-			 * client.
-			 */
-			atomic_inc(&client->ref_cnt);
 			dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
 				 client->name, pf->hw.pf_id,
 				 pf->hw.bus.device, pf->hw.bus.func);
-			mutex_lock(&i40e_client_instance_mutex);
-			atomic_inc(&cdev->ref_cnt);
+		}
+
+		mutex_lock(&i40e_client_instance_mutex);
+		if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+			      &cdev->state)) {
+			/* Send an Open request to the client */
 			if (client->ops && client->ops->open)
 				ret = client->ops->open(&cdev->lan_info,
 							client);
-			atomic_dec(&cdev->ref_cnt);
-			if (ret < 0) {
-				mutex_unlock(&i40e_client_instance_mutex);
+			if (!ret) {
+				set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+					&cdev->state);
+			} else {
+				/* remove client instance */
 				i40e_client_del_instance(pf, client);
-				atomic_dec(&client->ref_cnt);
-				continue;
 			}
-			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
-			mutex_unlock(&i40e_client_instance_mutex);
 		}
+		mutex_unlock(&i40e_client_instance_mutex);
 	}
 	mutex_unlock(&i40e_client_mutex);
 }
@@ -660,10 +660,6 @@ static int i40e_client_release(struct i40e_client *client)
 			continue;
 		pf = (struct i40e_pf *)cdev->lan_info.pf;
 		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
-			if (atomic_read(&cdev->ref_cnt) > 0) {
-				ret = I40E_ERR_NOT_READY;
-				goto out;
-			}
 			if (client->ops && client->ops->close)
 				client->ops->close(&cdev->lan_info, client,
 						   false);
@@ -676,11 +672,9 @@ static int i40e_client_release(struct i40e_client *client)
 		}
 		/* delete the client instance from the list */
 		list_move(&cdev->list, &cdevs_tmp);
-		atomic_dec(&client->ref_cnt);
 		dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n",
 			 client->name);
 	}
-out:
 	mutex_unlock(&i40e_client_instance_mutex);
 
 	/* free the client device and release its vsi */
@@ -1006,17 +1000,10 @@ int i40e_unregister_client(struct i40e_client *client)
 		ret = -ENODEV;
 		goto out;
 	}
-	if (atomic_read(&client->ref_cnt) == 0) {
-		clear_bit(__I40E_CLIENT_REGISTERED, &client->state);
-		list_del(&client->list);
-		pr_info("i40e: Unregistered client %s with return code %d\n",
-			client->name, ret);
-	} else {
-		ret = I40E_ERR_NOT_READY;
-		pr_err("i40e: Client %s failed unregister - client has open instances\n",
-		       client->name);
-	}
-
+	clear_bit(__I40E_CLIENT_REGISTERED, &client->state);
+	list_del(&client->list);
+	pr_info("i40e: Unregistered client %s with return code %d\n",
+		client->name, ret);
 out:
 	mutex_unlock(&i40e_client_mutex);
 	return ret;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h
index 38a6c36a6a0e..528bd79b05fe 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.h
@@ -203,8 +203,6 @@ struct i40e_client_instance {
 	struct i40e_info lan_info;
 	struct i40e_client *client;
 	unsigned long  state;
-	/* A count of all the in-progress calls to the client */
-	atomic_t ref_cnt;
 };
 
 struct i40e_client {

From 6d6fd1be2a1052cbe5b04c3678b30925a9344ac7 Mon Sep 17 00:00:00 2001
From: Preethi Banala <preethi.banala@intel.com>
Date: Wed, 14 Sep 2016 16:24:37 -0700
Subject: [PATCH 07/17] i40e: group base mode VF offload flags

Group together the minimum set of offload capabilities that are always
supported by VF in base mode. This define would be used by PF to make
sure VF in base mode gets minimum of base capabilities .

Change-ID: Id5e8f22ba169c8f0a38d22fc36b2cb531c02582c
Signed-off-by: Preethi Banala <preethi.banala@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.h   | 4 ++++
 drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
index f861d3109d1a..974ba2baf6ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
@@ -165,6 +165,10 @@ struct i40e_virtchnl_vsi_resource {
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF		0X00080000
 #define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00100000
 
+#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
+				    I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
+				    I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
+
 struct i40e_virtchnl_vf_resource {
 	u16 num_vsis;
 	u16 num_queue_pairs;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
index bd691ad86673..fc374f833aa9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
@@ -162,6 +162,10 @@ struct i40e_virtchnl_vsi_resource {
 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF		0X00080000
 #define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM	0X00100000
 
+#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
+				    I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
+				    I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
+
 struct i40e_virtchnl_vf_resource {
 	u16 num_vsis;
 	u16 num_queue_pairs;

From 96db776a368263bcce9f7eb12e878b0aef1a1974 Mon Sep 17 00:00:00 2001
From: Alan Brady <alan.brady@intel.com>
Date: Wed, 14 Sep 2016 16:24:38 -0700
Subject: [PATCH 08/17] i40e/i40evf: fix interrupt affinity bug

There exists a bug in which a 'perfect storm' can occur and cause
interrupts to fail to be correctly affinitized. This causes unexpected
behavior and has a substantial impact on performance when it happens.

The bug occurs if there is heavy traffic, any number of CPUs that have
an i40e interrupt are pegged at 100%, and the interrupt afffinity for
those CPUs is changed.  Instead of moving to the new CPU, the interrupt
continues to be polled while there is heavy traffic.

The bug is most readily realized as the driver is first brought up and
all interrupts start on CPU0. If there is heavy traffic and the
interrupt starts polling before the interrupt is affinitized, the
interrupt will be stuck on CPU0 until traffic stops. The bug, however,
can also be wrought out more simply by affinitizing all the interrupts
to a single CPU and then attempting to move any of those interrupts off
while there is heavy traffic.

This patch fixes the bug by registering for update notifications from
the kernel when the interrupt affinity changes. When that fires, we
cache the intended affinity mask. Then, while polling, if the cpu is
pegged at 100% and we failed to clean the rings, we check to make sure
we have the correct affinity and stop polling if we're firing on the
wrong CPU.  When the kernel successfully moves the interrupt, it will
start polling on the correct CPU. The performance impact is minimal
since the only time this section gets executed is when performance is
already compromised by the CPU.

Change-ID: I4410a880159b9dba1f8297aa72bef36dca34e830
Signed-off-by: Alan Brady <alan.brady@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 +
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 64 +++++++++++++----
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 36 +++++++---
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 31 ++++++--
 drivers/net/ethernet/intel/i40evf/i40evf.h    |  3 +-
 .../net/ethernet/intel/i40evf/i40evf_main.c   | 71 +++++++++++++------
 6 files changed, 159 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 34c7a5d395f7..01cce5bab861 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -607,6 +607,8 @@ struct i40e_q_vector {
 	unsigned long hung_detected; /* Set/Reset for hung_detection logic */
 
 	cpumask_t affinity_mask;
+	struct irq_affinity_notify affinity_notify;
+
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 83edbe8e3618..9382ba80b70c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3316,6 +3316,33 @@ static irqreturn_t i40e_msix_clean_rings(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/**
+ * i40e_irq_affinity_notify - Callback for affinity changes
+ * @notify: context as to what irq was changed
+ * @mask: the new affinity mask
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * so that we may register to receive changes to the irq affinity masks.
+ **/
+static void i40e_irq_affinity_notify(struct irq_affinity_notify *notify,
+				     const cpumask_t *mask)
+{
+	struct i40e_q_vector *q_vector =
+		container_of(notify, struct i40e_q_vector, affinity_notify);
+
+	q_vector->affinity_mask = *mask;
+}
+
+/**
+ * i40e_irq_affinity_release - Callback for affinity notifier release
+ * @ref: internal core kernel usage
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * to inform the current notification subscriber that they will no longer
+ * receive notifications.
+ **/
+static void i40e_irq_affinity_release(struct kref *ref) {}
+
 /**
  * i40e_vsi_request_irq_msix - Initialize MSI-X interrupts
  * @vsi: the VSI being configured
@@ -3331,10 +3358,13 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 	int rx_int_idx = 0;
 	int tx_int_idx = 0;
 	int vector, err;
+	int irq_num;
 
 	for (vector = 0; vector < q_vectors; vector++) {
 		struct i40e_q_vector *q_vector = vsi->q_vectors[vector];
 
+		irq_num = pf->msix_entries[base + vector].vector;
+
 		if (q_vector->tx.ring && q_vector->rx.ring) {
 			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
 				 "%s-%s-%d", basename, "TxRx", rx_int_idx++);
@@ -3349,7 +3379,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 			/* skip this unused q_vector */
 			continue;
 		}
-		err = request_irq(pf->msix_entries[base + vector].vector,
+		err = request_irq(irq_num,
 				  vsi->irq_handler,
 				  0,
 				  q_vector->name,
@@ -3359,9 +3389,13 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 				 "MSIX request_irq failed, error: %d\n", err);
 			goto free_queue_irqs;
 		}
+
+		/* register for affinity change notifications */
+		q_vector->affinity_notify.notify = i40e_irq_affinity_notify;
+		q_vector->affinity_notify.release = i40e_irq_affinity_release;
+		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
 		/* assign the mask for this irq */
-		irq_set_affinity_hint(pf->msix_entries[base + vector].vector,
-				      &q_vector->affinity_mask);
+		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	vsi->irqs_ready = true;
@@ -3370,10 +3404,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 free_queue_irqs:
 	while (vector) {
 		vector--;
-		irq_set_affinity_hint(pf->msix_entries[base + vector].vector,
-				      NULL);
-		free_irq(pf->msix_entries[base + vector].vector,
-			 &(vsi->q_vectors[vector]));
+		irq_num = pf->msix_entries[base + vector].vector;
+		irq_set_affinity_notifier(irq_num, NULL);
+		irq_set_affinity_hint(irq_num, NULL);
+		free_irq(irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
 }
@@ -4012,19 +4046,23 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 
 		vsi->irqs_ready = false;
 		for (i = 0; i < vsi->num_q_vectors; i++) {
-			u16 vector = i + base;
+			int irq_num;
+			u16 vector;
+
+			vector = i + base;
+			irq_num = pf->msix_entries[vector].vector;
 
 			/* free only the irqs that were actually requested */
 			if (!vsi->q_vectors[i] ||
 			    !vsi->q_vectors[i]->num_ringpairs)
 				continue;
 
+			/* clear the affinity notifier in the IRQ descriptor */
+			irq_set_affinity_notifier(irq_num, NULL);
 			/* clear the affinity_mask in the IRQ descriptor */
-			irq_set_affinity_hint(pf->msix_entries[vector].vector,
-					      NULL);
-			synchronize_irq(pf->msix_entries[vector].vector);
-			free_irq(pf->msix_entries[vector].vector,
-				 vsi->q_vectors[i]);
+			irq_set_affinity_hint(irq_num, NULL);
+			synchronize_irq(irq_num);
+			free_irq(irq_num, vsi->q_vectors[i]);
 
 			/* Tear down the interrupt queue link list
 			 *
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 7d160c9497b7..48e65335373f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1999,12 +1999,25 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
+		const cpumask_t *aff_mask = &q_vector->affinity_mask;
+		int cpu_id = smp_processor_id();
+
+		/* It is possible that the interrupt affinity has changed but,
+		 * if the cpu is pegged at 100%, polling will never exit while
+		 * traffic continues and the interrupt will be stuck on this
+		 * cpu.  We check to make sure affinity is correct before we
+		 * continue to poll, otherwise we must stop polling so the
+		 * interrupt can move to the correct cpu.
+		 */
+		if (likely(cpumask_test_cpu(cpu_id, aff_mask) ||
+			   !(vsi->back->flags & I40E_FLAG_MSIX_ENABLED))) {
 tx_only:
-		if (arm_wb) {
-			q_vector->tx.ring[0].tx_stats.tx_force_wb++;
-			i40e_enable_wb_on_itr(vsi, q_vector);
+			if (arm_wb) {
+				q_vector->tx.ring[0].tx_stats.tx_force_wb++;
+				i40e_enable_wb_on_itr(vsi, q_vector);
+			}
+			return budget;
 		}
-		return budget;
 	}
 
 	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
@@ -2012,11 +2025,18 @@ tx_only:
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete_done(napi, work_done);
-	if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
-		i40e_update_enable_itr(vsi, q_vector);
-	} else { /* Legacy mode */
+
+	/* If we're prematurely stopping polling to fix the interrupt
+	 * affinity we want to make sure polling starts back up so we
+	 * issue a call to i40e_force_wb which triggers a SW interrupt.
+	 */
+	if (!clean_complete)
+		i40e_force_wb(vsi, q_vector);
+	else if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED))
 		i40e_irq_dynamic_enable_icr0(vsi->back, false);
-	}
+	else
+		i40e_update_enable_itr(vsi, q_vector);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 75f2a2cdd738..dd8ad6b989db 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1461,12 +1461,24 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
+		const cpumask_t *aff_mask = &q_vector->affinity_mask;
+		int cpu_id = smp_processor_id();
+
+		/* It is possible that the interrupt affinity has changed but,
+		 * if the cpu is pegged at 100%, polling will never exit while
+		 * traffic continues and the interrupt will be stuck on this
+		 * cpu.  We check to make sure affinity is correct before we
+		 * continue to poll, otherwise we must stop polling so the
+		 * interrupt can move to the correct cpu.
+		 */
+		if (likely(cpumask_test_cpu(cpu_id, aff_mask))) {
 tx_only:
-		if (arm_wb) {
-			q_vector->tx.ring[0].tx_stats.tx_force_wb++;
-			i40e_enable_wb_on_itr(vsi, q_vector);
+			if (arm_wb) {
+				q_vector->tx.ring[0].tx_stats.tx_force_wb++;
+				i40e_enable_wb_on_itr(vsi, q_vector);
+			}
+			return budget;
 		}
-		return budget;
 	}
 
 	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
@@ -1474,7 +1486,16 @@ tx_only:
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete_done(napi, work_done);
-	i40e_update_enable_itr(vsi, q_vector);
+
+	/* If we're prematurely stopping polling to fix the interrupt
+	 * affinity we want to make sure polling starts back up so we
+	 * issue a call to i40evf_force_wb which triggers a SW interrupt.
+	 */
+	if (!clean_complete)
+		i40evf_force_wb(vsi, q_vector);
+	else
+		i40e_update_enable_itr(vsi, q_vector);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index c5fd724313c7..fffe4cf2c20b 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -107,7 +107,8 @@ struct i40e_q_vector {
 	int v_idx;	/* vector index in list */
 	char name[IFNAMSIZ + 9];
 	bool arm_wb_state;
-	cpumask_var_t affinity_mask;
+	cpumask_t affinity_mask;
+	struct irq_affinity_notify affinity_notify;
 };
 
 /* Helper macros to switch between ints/sec and what the register uses.
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 777eb29e4ff7..e95e87381962 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -495,6 +495,33 @@ static void i40evf_netpoll(struct net_device *netdev)
 }
 
 #endif
+/**
+ * i40evf_irq_affinity_notify - Callback for affinity changes
+ * @notify: context as to what irq was changed
+ * @mask: the new affinity mask
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * so that we may register to receive changes to the irq affinity masks.
+ **/
+static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify,
+				       const cpumask_t *mask)
+{
+	struct i40e_q_vector *q_vector =
+		container_of(notify, struct i40e_q_vector, affinity_notify);
+
+	q_vector->affinity_mask = *mask;
+}
+
+/**
+ * i40evf_irq_affinity_release - Callback for affinity notifier release
+ * @ref: internal core kernel usage
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * to inform the current notification subscriber that they will no longer
+ * receive notifications.
+ **/
+static void i40evf_irq_affinity_release(struct kref *ref) {}
+
 /**
  * i40evf_request_traffic_irqs - Initialize MSI-X interrupts
  * @adapter: board private structure
@@ -507,6 +534,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 {
 	int vector, err, q_vectors;
 	int rx_int_idx = 0, tx_int_idx = 0;
+	int irq_num;
 
 	i40evf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -514,6 +542,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 
 	for (vector = 0; vector < q_vectors; vector++) {
 		struct i40e_q_vector *q_vector = &adapter->q_vectors[vector];
+		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
 
 		if (q_vector->tx.ring && q_vector->rx.ring) {
 			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
@@ -532,21 +561,23 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 			/* skip this unused q_vector */
 			continue;
 		}
-		err = request_irq(
-			adapter->msix_entries[vector + NONQ_VECS].vector,
-			i40evf_msix_clean_rings,
-			0,
-			q_vector->name,
-			q_vector);
+		err = request_irq(irq_num,
+				  i40evf_msix_clean_rings,
+				  0,
+				  q_vector->name,
+				  q_vector);
 		if (err) {
 			dev_info(&adapter->pdev->dev,
 				 "Request_irq failed, error: %d\n", err);
 			goto free_queue_irqs;
 		}
+		/* register for affinity change notifications */
+		q_vector->affinity_notify.notify = i40evf_irq_affinity_notify;
+		q_vector->affinity_notify.release =
+						   i40evf_irq_affinity_release;
+		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
 		/* assign the mask for this irq */
-		irq_set_affinity_hint(
-			adapter->msix_entries[vector + NONQ_VECS].vector,
-			q_vector->affinity_mask);
+		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	return 0;
@@ -554,11 +585,10 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 free_queue_irqs:
 	while (vector) {
 		vector--;
-		irq_set_affinity_hint(
-			adapter->msix_entries[vector + NONQ_VECS].vector,
-			NULL);
-		free_irq(adapter->msix_entries[vector + NONQ_VECS].vector,
-			 &adapter->q_vectors[vector]);
+		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
+		irq_set_affinity_notifier(irq_num, NULL);
+		irq_set_affinity_hint(irq_num, NULL);
+		free_irq(irq_num, &adapter->q_vectors[vector]);
 	}
 	return err;
 }
@@ -599,16 +629,15 @@ static int i40evf_request_misc_irq(struct i40evf_adapter *adapter)
  **/
 static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter)
 {
-	int i;
-	int q_vectors;
+	int vector, irq_num, q_vectors;
 
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
-	for (i = 0; i < q_vectors; i++) {
-		irq_set_affinity_hint(adapter->msix_entries[i+1].vector,
-				      NULL);
-		free_irq(adapter->msix_entries[i+1].vector,
-			 &adapter->q_vectors[i]);
+	for (vector = 0; vector < q_vectors; vector++) {
+		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
+		irq_set_affinity_notifier(irq_num, NULL);
+		irq_set_affinity_hint(irq_num, NULL);
+		free_irq(irq_num, &adapter->q_vectors[vector]);
 	}
 }
 

From 4adbb642eaf53dfe2ea0a4170d8df95d115c12ac Mon Sep 17 00:00:00 2001
From: Bimmy Pujari <bimmy.pujari@intel.com>
Date: Wed, 14 Sep 2016 16:24:39 -0700
Subject: [PATCH 09/17] i40e/i40evf: Changed version from 1.6.16 to 1.6.19

Signed-off-by: Bimmy Pujari <bimmy.pujari@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 9382ba80b70c..c25247fa3814 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -41,7 +41,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 16
+#define DRV_VERSION_BUILD 19
 #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 e95e87381962..3e51ff2f48f8 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -38,7 +38,7 @@ static const char i40evf_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 16
+#define DRV_VERSION_BUILD 19
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \

From fe180a5e275adc7430ada9e4881dcca5ea1a8037 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 26 Sep 2016 20:17:01 -0700
Subject: [PATCH 10/17] i40e: Make struct i40e_stats const

Move some data to text

$ size drivers/net/ethernet/intel/i40e/i40e_ethtool.o*
   text	   data	    bss	    dec	    hex	filename
  25012	      0	     32	  25044	   61d4	drivers/net/ethernet/intel/i40e/i40e_ethtool.o.new
  22868	   2120	     32	  25020	   61bc	drivers/net/ethernet/intel/i40e/i40e_ethtool.o.old

Signed-off-by: Joe Perches <joe@perches.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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 92bc8846f1ba..3a1f91efcae2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -104,7 +104,7 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = {
  * The PF_STATs are appended to the netdev stats only when ethtool -S
  * is queried on the base PF netdev, not on the VMDq or FCoE netdev.
  */
-static struct i40e_stats i40e_gstrings_stats[] = {
+static const struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_bytes", stats.eth.rx_bytes),
 	I40E_PF_STAT("tx_bytes", stats.eth.tx_bytes),
 	I40E_PF_STAT("rx_unicast", stats.eth.rx_unicast),

From 128150576f85b2745d849aba43980683a6267e50 Mon Sep 17 00:00:00 2001
From: Lihong Yang <lihong.yang@intel.com>
Date: Tue, 27 Sep 2016 11:28:48 -0700
Subject: [PATCH 11/17] i40e: fix confusing dmesg info for ethtool -L option

Ethtool -L option with the combined parameter is for changing the number of
multi-purpose channels of the specified network device. The pre-set maximum
for the combined channels is cpu dependent. Currently, for an i40e device,
when the user sets a value between 64 and the maximum that the cpu can
support for the combined parameter, the i40e driver displays the confusing
info in dmesg to only show 64 as the RSS count regardless of what the
accepted user input is as long as it is larger than 64.

This patch fixes the message in the i40e driver when the user uses
ethtool -L to change the number of the combined channels to consistently
display the user requested value if it is valid and accepted by ethtool.

Change-ID: Ia80a68bc844b779a49e0f76e7d3dcc915032d9af
Signed-off-by: Lihong Yang <lihong.yang@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 | 4 ++--
 1 file 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 c25247fa3814..a4bae0a4e8ad 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8400,8 +8400,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 
 		i40e_pf_config_rss(pf);
 	}
-	dev_info(&pf->pdev->dev, "RSS count/HW max RSS count:  %d/%d\n",
-		 pf->alloc_rss_size, pf->rss_size_max);
+	dev_info(&pf->pdev->dev, "User requested queue count/HW max RSS count:  %d/%d\n",
+		 vsi->req_queue_pairs, pf->rss_size_max);
 	return pf->alloc_rss_size;
 }
 

From 99dad8b34c687cb8c4975fbabced76db35f88c14 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 27 Sep 2016 11:28:50 -0700
Subject: [PATCH 12/17] i40e: Drop redundant Rx descriptor processing code

This patch cleans up several pieces of redundant code in the Rx clean-up
paths.

The first bit is that hdr_addr and the status_err_len portions of the Rx
descriptor represent the same value.  As such there is no point in setting
them to 0 before setting them to 0.  I'm dropping the second spot where we
are updating the value to 0 so that we only have 1 write for this value
instead of 2.

The second piece is the checking for the DD bit in the packet.  We only
need to check for a non-zero value for the status_err_len because if the
device is done with the descriptor it will have written something back and
the DD is just one piece of it.  In addition I have moved the reading of
the Rx descriptor bits related to rx_ptype down so that they are actually
below the dma_rmb() call so that we are guaranteed that we don't have any
funky 64b on 32b calls causing any ordering issues.

Change-ID: I256e44a025d3c64a7224aaaec37c852bfcb1871b
Signed-off-by: Alexander Duyck <alexander.h.duyck@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_txrx.c   | 18 ++++++------------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 18 ++++++------------
 2 files changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 48e65335373f..daade4fe80d6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1220,7 +1220,6 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		 * because each write-back erases this info.
 		 */
 		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
-		rx_desc->read.hdr_addr = 0;
 
 		rx_desc++;
 		bi++;
@@ -1741,7 +1740,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < budget)) {
 		union i40e_rx_desc *rx_desc;
 		struct sk_buff *skb;
-		u32 rx_status;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1755,21 +1753,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 
 		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
-			   I40E_RXD_QW1_PTYPE_SHIFT;
-		rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
-			    I40E_RXD_QW1_STATUS_SHIFT;
-
-		if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
-			break;
-
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
 		 * hardware wrote DD then it will be non-zero
 		 */
-		if (!rx_desc->wb.qword1.status_error_len)
+		if (!i40e_test_staterr(rx_desc,
+				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -1803,6 +1793,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
+			   I40E_RXD_QW1_PTYPE_SHIFT;
+
 		/* populate checksum, VLAN, and protocol */
 		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index dd8ad6b989db..e2d362238fd7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -705,7 +705,6 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		 * because each write-back erases this info.
 		 */
 		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
-		rx_desc->read.hdr_addr = 0;
 
 		rx_desc++;
 		bi++;
@@ -1209,7 +1208,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < budget)) {
 		union i40e_rx_desc *rx_desc;
 		struct sk_buff *skb;
-		u32 rx_status;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1223,21 +1221,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 
 		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
-			   I40E_RXD_QW1_PTYPE_SHIFT;
-		rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
-			    I40E_RXD_QW1_STATUS_SHIFT;
-
-		if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
-			break;
-
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
 		 * hardware wrote DD then it will be non-zero
 		 */
-		if (!rx_desc->wb.qword1.status_error_len)
+		if (!i40e_test_staterr(rx_desc,
+				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -1271,6 +1261,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
+			   I40E_RXD_QW1_PTYPE_SHIFT;
+
 		/* populate checksum, VLAN, and protocol */
 		i40evf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 

From ab425cb7ffdb024a45b0b3bcbf58d52ead3c347c Mon Sep 17 00:00:00 2001
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
Date: Tue, 27 Sep 2016 11:28:52 -0700
Subject: [PATCH 13/17] i40e: Fix for long link down notification time

This patch fixes a problem where it could take a very
long time (>100 msec) to print the link down notification.
This problem is fixed by changing how often we update link
info from fw, when link is down. Without this patch, it can
take over 100msec to notify user link is down.

Change-ID: Ib876eb30834c7080792becd13ee093b9cbb35d78
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@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 | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index fe8100bb1027..a47594603d69 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -2494,7 +2494,10 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw)
 	if (status)
 		return status;
 
-	if (hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) {
+	/* extra checking needed to ensure link info to user is timely */
+	if ((hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) &&
+	    ((hw->phy.link_info.link_info & I40E_AQ_LINK_UP) ||
+	     !(hw->phy.link_info_old.link_info & I40E_AQ_LINK_UP))) {
 		status = i40e_aq_get_phy_capabilities(hw, false, false,
 						      &abilities, NULL);
 		if (status)

From 53cb6e9e8949b13f63db0bc96f8fcc249763acfb Mon Sep 17 00:00:00 2001
From: Filip Sadowski <filip.sadowski@intel.com>
Date: Tue, 27 Sep 2016 11:28:53 -0700
Subject: [PATCH 14/17] i40e: Removal of workaround for simple MAC address
 filter deletion

This is code refactoring. This patch removes the workaround which deleted
a default MAC filter added by the firmware when the interface was brought
up. This filter caused frames to pass disregarding the VLAN tagging.
It used to be automatically applied after reset in pre-SRA FW versions.
This workaround is not needed in production NICs and hence can be removed.

Change-ID: I129fe1aae1f17b5a224c9b29a996d916aa1be1ec
Signed-off-by: Filip Sadowski <filip.sadowski@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 | 41 ---------------------
 1 file changed, 41 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a4bae0a4e8ad..2e787ffb47ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1286,39 +1286,6 @@ int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 	return -ENOENT;
 }
 
-/**
- * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM
- * @vsi: the PF Main VSI - inappropriate for any other VSI
- * @macaddr: the MAC address
- *
- * Remove whatever filter the firmware set up so the driver can manage
- * its own filtering intelligently.
- **/
-static void i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr)
-{
-	struct i40e_aqc_remove_macvlan_element_data element;
-	struct i40e_pf *pf = vsi->back;
-
-	/* Only appropriate for the PF main VSI */
-	if (vsi->type != I40E_VSI_MAIN)
-		return;
-
-	memset(&element, 0, sizeof(element));
-	ether_addr_copy(element.mac_addr, macaddr);
-	element.vlan_tag = 0;
-	/* Ignore error returns, some firmware does it this way... */
-	element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
-	i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
-
-	memset(&element, 0, sizeof(element));
-	ether_addr_copy(element.mac_addr, macaddr);
-	element.vlan_tag = 0;
-	/* ...and some firmware does it this way. */
-	element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH |
-			I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
-	i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
-}
-
 /**
  * i40e_add_filter - Add a mac/vlan filter to the VSI
  * @vsi: the VSI to be searched
@@ -9218,12 +9185,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
 		ether_addr_copy(mac_addr, hw->mac.perm_addr);
-		/* The following steps are necessary to prevent reception
-		 * of tagged packets - some older NVM configurations load a
-		 * default a MAC-VLAN filter that accepts any tagged packet
-		 * which must be replaced by a normal filter.
-		 */
-		i40e_rm_default_mac_filter(vsi, mac_addr);
 		spin_lock_bh(&vsi->mac_filter_list_lock);
 		i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true);
 		spin_unlock_bh(&vsi->mac_filter_list_lock);
@@ -9741,8 +9702,6 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 	pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
 	pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
 	i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
-	if (vsi->type == I40E_VSI_MAIN)
-		i40e_rm_default_mac_filter(vsi, pf->hw.mac.perm_addr);
 
 	/* assign it some queues */
 	ret = i40e_alloc_rings(vsi);

From cf465fe750412335b7a3c75263bd795aecef4fef Mon Sep 17 00:00:00 2001
From: Bimmy Pujari <bimmy.pujari@intel.com>
Date: Tue, 27 Sep 2016 11:28:54 -0700
Subject: [PATCH 15/17] i40e/i40evf: Changed version from 1.6.19 to 1.6.21

Signed-off-by: Bimmy Pujari <bimmy.pujari@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 2e787ffb47ce..00c322d3cbab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -41,7 +41,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 19
+#define DRV_VERSION_BUILD 21
 #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 3e51ff2f48f8..bcb1cafdf28a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -38,7 +38,7 @@ static const char i40evf_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 19
+#define DRV_VERSION_BUILD 21
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \

From c17ef430b9fd5f58074f5cdc0128d06a5ae92304 Mon Sep 17 00:00:00 2001
From: David Ertman <david.m.ertman@intel.com>
Date: Fri, 30 Sep 2016 01:36:21 -0700
Subject: [PATCH 16/17] i40e: Fix bit logic error in failure case

Patch a036244c0686 "i40e: Fix kernel panic on enable/disable LLDP"
introduced an error in bit logic.

Originally this bit manipulation was meant to clear two bits to indicate
that DCB was not enabled or capable. An "&" was incorrectly used instead
of an "|" bit operator to combine the two bitmasks into one.  This also
created a static checker error since the resultant code was a no-op.

This patch fixes the error by using the correct bit-wise operator.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.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 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 00c322d3cbab..0c2328dab8f7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10970,7 +10970,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_init_pf_dcb(pf);
 	if (err) {
 		dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err);
-		pf->flags &= ~(I40E_FLAG_DCB_CAPABLE & I40E_FLAG_DCB_ENABLED);
+		pf->flags &= ~(I40E_FLAG_DCB_CAPABLE | I40E_FLAG_DCB_ENABLED);
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */

From 5d4ca23e58f2db7c14b76070f31295244b6edb7b Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 30 Sep 2016 08:21:46 -0400
Subject: [PATCH 17/17] i40e: Clean up handling of msglevel flags and debug
 parameter

So the i40e driver had a really convoluted configuration for how to handle
the debug flags contained in msg_level.  Part of the issue is that the
driver has its own 32 bit mask that it was using to track a separate set of
debug features.  From what I can tell it was trying to use the upper 4 bits
to determine if the value was meant to represent a bit-mask or the numeric
value provided by debug level.

What this patch does is clean this up by compressing those 4 bits into bit
31, as a result we just have to perform a check against the value being
negative to determine if we are looking at a debug level (positive), or a
debug mask (negative).  The debug level will populate the msg_level, and
the debug mask will populate the debug_mask in the hardware struct.

I added similar logic for ethtool.  If the value being provided has bit 31
set we assume the value being provided is a debug mask, otherwise we assume
it is a msg_enable mask.  For displaying we only provide the msg_enable,
and if debug_mask is in use we will print it to the dmesg log.

Lastly I removed the debugfs interface.  It is redundant with what we
already have in ethtool and really doesn't belong anyway.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_debugfs.c    | 19 ---------------
 .../net/ethernet/intel/i40e/i40e_ethtool.c    |  7 +++++-
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 23 +++++++------------
 3 files changed, 14 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 0c1875b5b16d..0354632fe2f8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1210,24 +1210,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			dev_info(&pf->pdev->dev,
 				 "dump debug fwdata <cluster_id> <table_id> <index>\n");
 		}
-
-	} else if (strncmp(cmd_buf, "msg_enable", 10) == 0) {
-		u32 level;
-		cnt = sscanf(&cmd_buf[10], "%i", &level);
-		if (cnt) {
-			if (I40E_DEBUG_USER & level) {
-				pf->hw.debug_mask = level;
-				dev_info(&pf->pdev->dev,
-					 "set hw.debug_mask = 0x%08x\n",
-					 pf->hw.debug_mask);
-			}
-			pf->msg_enable = level;
-			dev_info(&pf->pdev->dev, "set msg_enable = 0x%08x\n",
-				 pf->msg_enable);
-		} else {
-			dev_info(&pf->pdev->dev, "msg_enable = 0x%08x\n",
-				 pf->msg_enable);
-		}
 	} else if (strncmp(cmd_buf, "pfr", 3) == 0) {
 		dev_info(&pf->pdev->dev, "debugfs: forcing PFR\n");
 		i40e_do_reset_safe(pf, BIT(__I40E_PF_RESET_REQUESTED));
@@ -1644,7 +1626,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		dev_info(&pf->pdev->dev, "  dump desc aq\n");
 		dev_info(&pf->pdev->dev, "  dump reset stats\n");
 		dev_info(&pf->pdev->dev, "  dump debug fwdata <cluster_id> <table_id> <index>\n");
-		dev_info(&pf->pdev->dev, "  msg_enable [level]\n");
 		dev_info(&pf->pdev->dev, "  read <reg>\n");
 		dev_info(&pf->pdev->dev, "  write <reg> <value>\n");
 		dev_info(&pf->pdev->dev, "  clear_stats vsi [seid]\n");
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 3a1f91efcae2..fb4fb524eab2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -978,6 +978,10 @@ static u32 i40e_get_msglevel(struct net_device *netdev)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
+	u32 debug_mask = pf->hw.debug_mask;
+
+	if (debug_mask)
+		netdev_info(netdev, "i40e debug_mask: 0x%08X\n", debug_mask);
 
 	return pf->msg_enable;
 }
@@ -989,7 +993,8 @@ static void i40e_set_msglevel(struct net_device *netdev, u32 data)
 
 	if (I40E_DEBUG_USER & data)
 		pf->hw.debug_mask = data;
-	pf->msg_enable = data;
+	else
+		pf->msg_enable = data;
 }
 
 static int i40e_get_regs_len(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0c2328dab8f7..7fa535f57820 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -93,8 +93,8 @@ MODULE_DEVICE_TABLE(pci, i40e_pci_tbl);
 
 #define I40E_MAX_VF_COUNT 128
 static int debug = -1;
-module_param(debug, int, 0);
-MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+module_param(debug, uint, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX)");
 
 MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
@@ -8511,15 +8511,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	int err = 0;
 	int size;
 
-	pf->msg_enable = netif_msg_init(I40E_DEFAULT_MSG_ENABLE,
-				(NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK));
-	if (debug != -1 && debug != I40E_DEFAULT_MSG_ENABLE) {
-		if (I40E_DEBUG_USER & debug)
-			pf->hw.debug_mask = debug;
-		pf->msg_enable = netif_msg_init((debug & ~I40E_DEBUG_USER),
-						I40E_DEFAULT_MSG_ENABLE);
-	}
-
 	/* Set default capability flags */
 	pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
 		    I40E_FLAG_MSI_ENABLED     |
@@ -10825,10 +10816,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	mutex_init(&hw->aq.asq_mutex);
 	mutex_init(&hw->aq.arq_mutex);
 
-	if (debug != -1) {
-		pf->msg_enable = pf->hw.debug_mask;
-		pf->msg_enable = debug;
-	}
+	pf->msg_enable = netif_msg_init(debug,
+					NETIF_MSG_DRV |
+					NETIF_MSG_PROBE |
+					NETIF_MSG_LINK);
+	if (debug < -1)
+		pf->hw.debug_mask = debug;
 
 	/* do a special CORER for clearing PXE mode once at init */
 	if (hw->revision_id == 0 &&