Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2017-10-09

This series contains updates to i40e and i40evf only.

Jake fixes missed flag conversion from u64 to u32.  Fixes a deafult ITR
value issue where the driver defaults to an ITR value of half the
expected value (in terms of minimum microseconds between interrupts).  So
fix this by changing the default values to be calculated using the
ITR_REG_TO_USEC() macro which indicates that we are converting from the
register units into microseconds. Updates the drivers to bump the tail in
increments of 8 and double the number of descriptors we will bundle into
one tail bump when receiving.  With the recent kernel support for
enabling XPS and QoS at the same time, we no longer need to worry about
the number of traffic classes when enabling XPS.

Lihong converts the use of hash_for_each() to hash_for_each_safe() to
safely remove a hash entry.  Adds a check for the return value for
find_first_bit() in the case that it returns the size passed to search.

Alan fixes a bug in which filters are erroneously removed if they are
removed and then added again.  So make sure that when adding a filter, if
we find it already existed in our list, make sure it is not marked to be
removed.

Jayaprakash adds the retrying of PHY reads when the I2C is busy for a
maximum period of 500ms.

Rami fixes code comment typo.

Stefano Brivio simplifies the code by removing the use of a local
return code variable and simply return the results of the read function.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

12 files changed, 107 insertions, 81 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 18c453a3e728..8139b4ee1dc3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -424,7 +424,7 @@ struct i40e_pf {
 #define I40E_HW_PORT_ID_VALID			BIT(17)
 #define I40E_HW_RESTART_AUTONEG			BIT(18)
 
-	u64 flags;
+	u32 flags;
 #define I40E_FLAG_RX_CSUM_ENABLED		BIT(0)
 #define I40E_FLAG_MSI_ENABLED			BIT(1)
 #define I40E_FLAG_MSIX_ENABLED			BIT(2)
@@ -949,9 +949,6 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
-	/* definitely clear the PBA here, as this function is meant to
-	 * clean out all previous interrupts AND enable the interrupt
-	 */
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
@@ -960,7 +957,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 }
 
 void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf);
 int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
 int i40e_open(struct net_device *netdev);
 int i40e_close(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 60542beda7ad..53aad378d49c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1567,30 +1567,46 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 	struct i40e_aq_desc desc;
 	i40e_status status;
 	u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp);
+	u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0;
 
 	if (!abilities)
 		return I40E_ERR_PARAM;
 
-	i40e_fill_default_direct_cmd_desc(&desc,
-					  i40e_aqc_opc_get_phy_abilities);
+	do {
+		i40e_fill_default_direct_cmd_desc(&desc,
+					       i40e_aqc_opc_get_phy_abilities);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	if (abilities_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		if (abilities_size > I40E_AQ_LARGE_BUF)
+			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
-	if (qualified_modules)
-		desc.params.external.param0 |=
+		if (qualified_modules)
+			desc.params.external.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES);
 
-	if (report_init)
-		desc.params.external.param0 |=
+		if (report_init)
+			desc.params.external.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES);
 
-	status = i40e_asq_send_command(hw, &desc, abilities, abilities_size,
-				       cmd_details);
+		status = i40e_asq_send_command(hw, &desc, abilities,
+					       abilities_size, cmd_details);
 
-	if (hw->aq.asq_last_status == I40E_AQ_RC_EIO)
-		status = I40E_ERR_UNKNOWN_PHY;
+		if (status)
+			break;
+
+		if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) {
+			status = I40E_ERR_UNKNOWN_PHY;
+			break;
+		} else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) {
+			usleep_range(1000, 2000);
+			total_delay++;
+			status = I40E_ERR_TIMEOUT;
+		}
+	} while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) &&
+		 (total_delay < max_delay));
+
+	if (status)
+		return status;
 
 	if (report_init) {
 		if (hw->mac.type ==  I40E_MAC_XL710 &&
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 60b11fdeca2d..4de52001a2b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2879,23 +2879,18 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
  **/
 static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 {
-	struct i40e_vsi *vsi = ring->vsi;
 	int cpu;
 
 	if (!ring->q_vector || !ring->netdev)
 		return;
 
-	if ((vsi->tc_config.numtc <= 1) &&
-	    !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) {
-		cpu = cpumask_local_spread(ring->q_vector->v_idx, -1);
-		netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu),
-				    ring->queue_index);
-	}
+	/* We only initialize XPS once, so as not to overwrite user settings */
+	if (test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state))
+		return;
 
-	/* schedule our worker thread which will take care of
-	 * applying the new filter changes
-	 */
-	i40e_service_event_schedule(vsi->back);
+	cpu = cpumask_local_spread(ring->q_vector->v_idx, -1);
+	netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu),
+			    ring->queue_index);
 }
 
 /**
@@ -3030,7 +3025,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (hw->revision_id == 0)
 		rx_ctx.lrxqthresh = 0;
 	else
-		rx_ctx.lrxqthresh = 2;
+		rx_ctx.lrxqthresh = 1;
 	rx_ctx.crcstrip = 1;
 	rx_ctx.l2tsel = 1;
 	/* this controls whether VLAN is stripped from inner headers */
@@ -3403,15 +3398,14 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf)
 /**
  * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0
  * @pf: board private structure
- * @clearpba: true when all pending interrupt events should be cleared
  **/
-void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba)
+void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTL0_INTENA_MASK   |
-	      (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) |
+	      I40E_PFINT_DYN_CTL0_CLEARPBA_MASK |
 	      (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT);
 
 	wr32(hw, I40E_PFINT_DYN_CTL0, val);
@@ -3597,7 +3591,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
 		for (i = 0; i < vsi->num_q_vectors; i++)
 			i40e_irq_dynamic_enable(vsi, i);
 	} else {
-		i40e_irq_dynamic_enable_icr0(pf, true);
+		i40e_irq_dynamic_enable_icr0(pf);
 	}
 
 	i40e_flush(&pf->hw);
@@ -3746,7 +3740,7 @@ enable_intr:
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
 	if (!test_bit(__I40E_DOWN, pf->state)) {
 		i40e_service_event_schedule(pf);
-		i40e_irq_dynamic_enable_icr0(pf, false);
+		i40e_irq_dynamic_enable_icr0(pf);
 	}
 
 	return ret;
@@ -7694,7 +7688,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 
 /**
  * i40e_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi
- * @type: VSI pointer
+ * @vsi: VSI pointer
  * @alloc_qvectors: a bool to specify if q_vectors need to be allocated.
  *
  * On error: returns error code (negative)
@@ -8455,7 +8449,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
 
 	i40e_flush(hw);
 
-	i40e_irq_dynamic_enable_icr0(pf, true);
+	i40e_irq_dynamic_enable_icr0(pf);
 
 	return err;
 }
@@ -8983,8 +8977,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    I40E_FLAG_MSIX_ENABLED;
 
 	/* Set default ITR */
-	pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF;
-	pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF;
+	pf->rx_itr_default = I40E_ITR_RX_DEF;
+	pf->tx_itr_default = I40E_ITR_TX_DEF;
 
 	/* Depending on PF configurations, it is possible that the RSS
 	 * maximum might end up larger than the available queues
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 57505b1df98d..151d9cfb6ea4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -311,13 +311,10 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset,
 static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw,
 					u16 offset, u16 *data)
 {
-	i40e_status ret_code = 0;
-
 	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
-		ret_code = i40e_read_nvm_word_aq(hw, offset, data);
-	else
-		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
-	return ret_code;
+		return i40e_read_nvm_word_aq(hw, offset, data);
+
+	return i40e_read_nvm_word_srctl(hw, offset, data);
 }
 
 /**
@@ -331,7 +328,7 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw,
 i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 			       u16 *data)
 {
-	i40e_status ret_code = 0;
+	i40e_status ret_code;
 
 	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 	if (ret_code)
@@ -446,13 +443,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw,
 					  u16 offset, u16 *words,
 					  u16 *data)
 {
-	i40e_status ret_code = 0;
-
 	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE)
-		ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data);
-	else
-		ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data);
-	return ret_code;
+		return i40e_read_nvm_buffer_aq(hw, offset, words, data);
+
+	return i40e_read_nvm_buffer_srctl(hw, offset, words, data);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 3bd176606c09..a23306f04e00 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1372,6 +1372,15 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 	union i40e_rx_desc *rx_desc;
 	struct i40e_rx_buffer *bi;
 
+	/* Hardware only fetches new descriptors in cache lines of 8,
+	 * essentially ignoring the lower 3 bits of the tail register. We want
+	 * to ensure our tail writes are aligned to avoid unnecessary work. We
+	 * can't simply round down the cleaned count, since we might fail to
+	 * allocate some buffers. What we really want is to ensure that
+	 * next_to_used + cleaned_count produces an aligned value.
+	 */
+	cleaned_count -= (ntu + cleaned_count) & 0x7;
+
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
 		return false;
@@ -2202,9 +2211,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-	      /* Don't clear PBA because that can cause lost interrupts that
-	       * came in while we were cleaning/polling
-	       */
+	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
 	      (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
 	      (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
 
@@ -2241,7 +2248,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 
 	/* If we don't have MSIX, then we only need to re-enable icr0 */
 	if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) {
-		i40e_irq_dynamic_enable_icr0(vsi->back, false);
+		i40e_irq_dynamic_enable_icr0(vsi->back);
 		return;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index a4e3e665a1a1..ff57ae451524 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -38,8 +38,10 @@
 #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_20K
-#define I40E_ITR_TX_DEF            I40E_ITR_20K
+#define I40E_ITR_RX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
+#define I40E_ITR_TX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
@@ -206,7 +208,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 }
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40E_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+#define I40E_RX_BUFFER_WRITE	32	/* Must be power of 2 */
 #define I40E_RX_INCREMENT(r, i) \
 	do {					\
 		(i)++;				\
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 4b32b1d38a66..0410fcbdbb94 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -46,6 +46,9 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
+/* Max timeout in ms for the phy to respond */
+#define I40E_MAX_PHY_TIMEOUT		500
+
 /* Switch from ms to the 1usec global time (this is the GTIME resolution) */
 #define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 04568137e029..0c4fa225c7be 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -273,7 +273,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 	struct i40e_hw *hw = &pf->hw;
 	u16 vsi_queue_id, pf_queue_id;
 	enum i40e_queue_type qtype;
-	u16 next_q, vector_id;
+	u16 next_q, vector_id, size;
 	u32 reg, reg_idx;
 	u16 itr_idx = 0;
 
@@ -303,9 +303,11 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 				     vsi_queue_id + 1));
 	}
 
-	next_q = find_first_bit(&linklistmap,
-				(I40E_MAX_VSI_QP *
-				 I40E_VIRTCHNL_SUPPORTED_QTYPES));
+	size = I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES;
+	next_q = find_first_bit(&linklistmap, size);
+	if (unlikely(next_q == size))
+		goto irq_list_done;
+
 	vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES;
 	qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES;
 	pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
@@ -313,7 +315,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 
 	wr32(hw, reg_idx, reg);
 
-	while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+	while (next_q < size) {
 		switch (qtype) {
 		case I40E_QUEUE_TYPE_RX:
 			reg_idx = I40E_QINT_RQCTL(pf_queue_id);
@@ -327,12 +329,8 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id,
 			break;
 		}
 
-		next_q = find_next_bit(&linklistmap,
-				       (I40E_MAX_VSI_QP *
-					I40E_VIRTCHNL_SUPPORTED_QTYPES),
-				       next_q + 1);
-		if (next_q <
-		    (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) {
+		next_q = find_next_bit(&linklistmap, size, next_q + 1);
+		if (next_q < size) {
 			vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES;
 			qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES;
 			pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id,
@@ -639,7 +637,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 	rx_ctx.dsize = 1;
 
 	/* default values */
-	rx_ctx.lrxqthresh = 2;
+	rx_ctx.lrxqthresh = 1;
 	rx_ctx.crcstrip = 1;
 	rx_ctx.prefena = 1;
 	rx_ctx.l2tsel = 1;
@@ -1358,7 +1356,7 @@ err_alloc:
 		i40e_free_vfs(pf);
 err_iov:
 	/* Re-enable interrupt 0. */
-	i40e_irq_dynamic_enable_icr0(pf, false);
+	i40e_irq_dynamic_enable_icr0(pf);
 	return ret;
 }
 
@@ -2883,6 +2881,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	struct i40e_mac_filter *f;
 	struct i40e_vf *vf;
 	int ret = 0;
+	struct hlist_node *h;
 	int bkt;
 
 	/* validate the request */
@@ -2921,7 +2920,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	/* Delete all the filters for this VSI - we're going to kill it
 	 * anyway.
 	 */
-	hash_for_each(vsi->mac_filter_hash, bkt, f, hlist)
+	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
 		__i40e_del_filter(vsi, f);
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 37e1de886d48..6806ada11490 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -711,6 +711,15 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 	union i40e_rx_desc *rx_desc;
 	struct i40e_rx_buffer *bi;
 
+	/* Hardware only fetches new descriptors in cache lines of 8,
+	 * essentially ignoring the lower 3 bits of the tail register. We want
+	 * to ensure our tail writes are aligned to avoid unnecessary work. We
+	 * can't simply round down the cleaned count, since we might fail to
+	 * allocate some buffers. What we really want is to ensure that
+	 * next_to_used + cleaned_count produces an aligned value.
+	 */
+	cleaned_count -= (ntu + cleaned_count) & 0x7;
+
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
 		return false;
@@ -1409,9 +1418,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr)
 	u32 val;
 
 	val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-	      /* Don't clear PBA because that can cause lost interrupts that
-	       * came in while we were cleaning/polling
-	       */
+	      I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
 	      (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
 	      (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index d8ca802a71a9..8d26c85d12e1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -38,8 +38,10 @@
 #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_20K
-#define I40E_ITR_TX_DEF            I40E_ITR_20K
+#define I40E_ITR_RX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
+#define I40E_ITR_TX_DEF            (ITR_REG_TO_USEC(I40E_ITR_20K) | \
+				    I40E_ITR_DYNAMIC)
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
@@ -189,7 +191,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
 }
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
-#define I40E_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+#define I40E_RX_BUFFER_WRITE	32	/* Must be power of 2 */
 #define I40E_RX_INCREMENT(r, i) \
 	do {					\
 		(i)++;				\
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 9364b67fff9c..213b773dfad6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -46,6 +46,9 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
+/* Max timeout in ms for the phy to respond */
+#define I40E_MAX_PHY_TIMEOUT		500
+
 /* Switch from ms to the 1usec global time (this is the GTIME resolution) */
 #define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1d2fc898b664..5bcbd46e2f6c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -880,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
 		adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+	} else {
+		f->remove = false;
 	}
 
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
@@ -1221,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->netdev = adapter->netdev;
 		tx_ring->dev = &adapter->pdev->dev;
 		tx_ring->count = adapter->tx_desc_count;
-		tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF);
+		tx_ring->tx_itr_setting = I40E_ITR_TX_DEF;
 		if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
 
@@ -1230,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		rx_ring->netdev = adapter->netdev;
 		rx_ring->dev = &adapter->pdev->dev;
 		rx_ring->count = adapter->rx_desc_count;
-		rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF);
+		rx_ring->rx_itr_setting = I40E_ITR_RX_DEF;
 	}
 
 	adapter->num_active_queues = num_active_queues;