1 files changed, 41 insertions, 30 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 084d0ab316b7..29ffed27e5a9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -636,19 +636,21 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
- * @tx_ring:  tx ring to clean
- * @budget:   how many cleans we're allowed
+ * @vsi: the VSI we care about
+ * @tx_ring: Tx ring to clean
+ * @napi_budget: Used to determine if we are in netpoll
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  **/
-static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
+static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
+			      struct i40e_ring *tx_ring, int napi_budget)
 {
 	u16 i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
 	struct i40e_tx_desc *tx_head;
 	struct i40e_tx_desc *tx_desc;
-	unsigned int total_packets = 0;
-	unsigned int total_bytes = 0;
+	unsigned int total_bytes = 0, total_packets = 0;
+	unsigned int budget = vsi->work_limit;
 
 	tx_buf = &tx_ring->tx_bi[i];
 	tx_desc = I40E_TX_DESC(tx_ring, i);
@@ -678,7 +680,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		total_packets += tx_buf->gso_segs;
 
 		/* free the skb */
-		dev_consume_skb_any(tx_buf->skb);
+		napi_consume_skb(tx_buf->skb, napi_budget);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -749,7 +751,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 
 		if (budget &&
 		    ((j / (WB_STRIDE + 1)) == 0) && (j != 0) &&
-		    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+		    !test_bit(__I40E_DOWN, &vsi->state) &&
 		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
 			tx_ring->arm_wb = true;
 	}
@@ -767,7 +769,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
-		   !test_bit(__I40E_DOWN, &tx_ring->vsi->state)) {
+		   !test_bit(__I40E_DOWN, &vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
@@ -1701,7 +1703,9 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, const int budget)
 			 ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
 			 : 0;
 #ifdef I40E_FCOE
-		if (!i40e_fcoe_handle_offload(rx_ring, rx_desc, skb)) {
+		if (unlikely(
+		    i40e_rx_is_fcoe(rx_ptype) &&
+		    !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
 			dev_kfree_skb_any(skb);
 			continue;
 		}
@@ -1832,7 +1836,9 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			 ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1)
 			 : 0;
 #ifdef I40E_FCOE
-		if (!i40e_fcoe_handle_offload(rx_ring, rx_desc, skb)) {
+		if (unlikely(
+		    i40e_rx_is_fcoe(rx_ptype) &&
+		    !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
 			dev_kfree_skb_any(skb);
 			continue;
 		}
@@ -1975,9 +1981,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	i40e_for_each_ring(ring, q_vector->tx) {
-		clean_complete = clean_complete &&
-				 i40e_clean_tx_irq(ring, vsi->work_limit);
-		arm_wb = arm_wb || ring->arm_wb;
+		if (!i40e_clean_tx_irq(vsi, ring, budget)) {
+			clean_complete = false;
+			continue;
+		}
+		arm_wb |= ring->arm_wb;
 		ring->arm_wb = false;
 	}
 
@@ -1999,8 +2007,9 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 			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 = clean_complete && (budget_per_ring > cleaned);
+		/* if we clean as many as budgeted, we must not be done */
+		if (cleaned >= budget_per_ring)
+			clean_complete = false;
 	}
 
 	/* If work not completed, return budget and polling will return */
@@ -2247,15 +2256,13 @@ out:
 
 /**
  * i40e_tso - set up the tso context descriptor
- * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
  * @hdr_len:  ptr to the size of the packet header
  * @cd_type_cmd_tso_mss: Quad Word 1
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
  **/
-static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
+static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 {
 	u64 cd_cmd, cd_tso_len, cd_mss;
 	union {
@@ -2299,9 +2306,8 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			l4_offset = l4.hdr - skb->data;
 
 			/* remove payload length from outer checksum */
-			paylen = (__force u16)l4.udp->check;
-			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
-			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+			paylen = skb->len - l4_offset;
+			csum_replace_by_diff(&l4.udp->check, htonl(paylen));
 		}
 
 		/* reset pointers to inner headers */
@@ -2321,9 +2327,8 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	l4_offset = l4.hdr - skb->data;
 
 	/* remove payload length from inner checksum */
-	paylen = (__force u16)l4.tcp->check;
-	paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
-	l4.tcp->check = ~csum_fold((__force __wsum)paylen);
+	paylen = skb->len - l4_offset;
+	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
 
 	/* compute length of segmentation header */
 	*hdr_len = (l4.tcp->doff * 4) + l4_offset;
@@ -2405,7 +2410,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		unsigned char *hdr;
 	} l4;
 	unsigned char *exthdr;
-	u32 offset, cmd = 0, tunnel = 0;
+	u32 offset, cmd = 0;
 	__be16 frag_off;
 	u8 l4_proto = 0;
 
@@ -2419,6 +2424,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 	offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT;
 
 	if (skb->encapsulation) {
+		u32 tunnel = 0;
 		/* define outer network header type */
 		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 			tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ?
@@ -2717,6 +2723,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	tx_bi = first;
 
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+		unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED;
+
 		if (dma_mapping_error(tx_ring->dev, dma))
 			goto dma_error;
 
@@ -2724,12 +2732,14 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		dma_unmap_len_set(tx_bi, len, size);
 		dma_unmap_addr_set(tx_bi, dma, dma);
 
+		/* align size to end of page */
+		max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1);
 		tx_desc->buffer_addr = cpu_to_le64(dma);
 
 		while (unlikely(size > I40E_MAX_DATA_PER_TXD)) {
 			tx_desc->cmd_type_offset_bsz =
 				build_ctob(td_cmd, td_offset,
-					   I40E_MAX_DATA_PER_TXD, td_tag);
+					   max_data, td_tag);
 
 			tx_desc++;
 			i++;
@@ -2740,9 +2750,10 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 				i = 0;
 			}
 
-			dma += I40E_MAX_DATA_PER_TXD;
-			size -= I40E_MAX_DATA_PER_TXD;
+			dma += max_data;
+			size -= max_data;
 
+			max_data = I40E_MAX_DATA_PER_TXD_ALIGNED;
 			tx_desc->buffer_addr = cpu_to_le64(dma);
 		}
 
@@ -2892,7 +2903,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (i40e_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb))
 			goto out_drop;
-		count = TXD_USE_COUNT(skb->len);
+		count = i40e_txd_use_count(skb->len);
 		tx_ring->tx_stats.tx_linearize++;
 	}
 
@@ -2923,7 +2934,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(tx_ring, skb, &hdr_len, &cd_type_cmd_tso_mss);
+	tso = i40e_tso(skb, &hdr_len, &cd_type_cmd_tso_mss);
 
 	if (tso < 0)
 		goto out_drop;