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

Tony Nguyen says:

====================
40GbE Intel Wired LAN Driver Updates 2021-02-08

This series contains updates to i40e driver only.

Cristian makes improvements to driver XDP path. Avoids writing
next-to-clean pointer on every update, removes redundant updates of
cleaned_count and buffer info, creates a helper function to consolidate
XDP actions and simplifies some of the behavior.

Eryk adds messages to inform the user when MTU is larger than supported
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -12448,9 +12448,10 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb,
  * i40e_xdp_setup - add/remove an XDP program
  * @vsi: VSI to changed
  * @prog: XDP program
+ * @extack: netlink extended ack
  **/
-static int i40e_xdp_setup(struct i40e_vsi *vsi,
-			  struct bpf_prog *prog)
+static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
+			  struct netlink_ext_ack *extack)
 {
 	int frame_size = vsi->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	struct i40e_pf *pf = vsi->back;
@@ -12459,8 +12460,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	int i;
 
 	/* Don't allow frames that span over multiple buffers */
-	if (frame_size > vsi->rx_buf_len)
+	if (frame_size > vsi->rx_buf_len) {
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP");
 		return -EINVAL;
+	}
 
 	if (!i40e_enabled_xdp_vsi(vsi) && !prog)
 		return 0;
@@ -12769,7 +12772,7 @@ static int i40e_xdp(struct net_device *dev,
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return i40e_xdp_setup(vsi, xdp->prog);
+		return i40e_xdp_setup(vsi, xdp->prog, xdp->extack);
 	case XDP_SETUP_XSK_POOL:
 		return i40e_xsk_pool_setup(vsi, xdp->xsk.pool,
 					   xdp->xsk.queue_id);

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -250,27 +250,68 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 			       xdp->data_end - xdp->data_hard_start,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
-		return NULL;
+		goto out;
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
+out:
 	xsk_buff_free(xdp);
 	return skb;
 }
 
-/**
- * i40e_inc_ntc: Advance the next_to_clean index
- * @rx_ring: Rx ring
- **/
-static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
+				      struct xdp_buff *xdp_buff,
+				      union i40e_rx_desc *rx_desc,
+				      unsigned int *rx_packets,
+				      unsigned int *rx_bytes,
+				      unsigned int size,
+				      unsigned int xdp_res)
 {
-	u32 ntc = rx_ring->next_to_clean + 1;
+	struct sk_buff *skb;
+
+	*rx_packets = 1;
+	*rx_bytes = size;
+
+	if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX)
+		return;
+
+	if (xdp_res == I40E_XDP_CONSUMED) {
+		xsk_buff_free(xdp_buff);
+		return;
+	}
+
+	if (xdp_res == I40E_XDP_PASS) {
+		/* NB! We are not checking for errors using
+		 * i40e_test_staterr with
+		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
+		 * SBP is *not* set in PRT_SBPVSI (default not set).
+		 */
+		skb = i40e_construct_skb_zc(rx_ring, xdp_buff);
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			*rx_packets = 0;
+			*rx_bytes = 0;
+			return;
+		}
 
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
+		if (eth_skb_pad(skb)) {
+			*rx_packets = 0;
+			*rx_bytes = 0;
+			return;
+		}
+
+		*rx_bytes = skb->len;
+		i40e_process_skb_fields(rx_ring, rx_desc, skb);
+		napi_gro_receive(&rx_ring->q_vector->napi, skb);
+		return;
+	}
+
+	/* Should never get here, as all valid cases have been handled already.
+	 */
+	WARN_ON_ONCE(1);
 }
 
 /**
@@ -284,17 +325,20 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+	u16 next_to_clean = rx_ring->next_to_clean;
+	u16 count_mask = rx_ring->count - 1;
 	unsigned int xdp_res, xdp_xmit = 0;
 	bool failure = false;
-	struct sk_buff *skb;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union i40e_rx_desc *rx_desc;
-		struct xdp_buff **bi;
+		unsigned int rx_packets;
+		unsigned int rx_bytes;
+		struct xdp_buff *bi;
 		unsigned int size;
 		u64 qword;
 
-		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = I40E_RX_DESC(rx_ring, next_to_clean);
 		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
@@ -307,11 +351,9 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 			i40e_clean_programming_status(rx_ring,
 						      rx_desc->raw.qword[0],
 						      qword);
-			bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-			xsk_buff_free(*bi);
-			*bi = NULL;
-			cleaned_count++;
-			i40e_inc_ntc(rx_ring);
+			bi = *i40e_rx_bi(rx_ring, next_to_clean);
+			xsk_buff_free(bi);
+			next_to_clean = (next_to_clean + 1) & count_mask;
 			continue;
 		}
 
@@ -320,53 +362,22 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-		(*bi)->data_end = (*bi)->data + size;
-		xsk_buff_dma_sync_for_cpu(*bi, rx_ring->xsk_pool);
-
-		xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
-		if (xdp_res) {
-			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR))
-				xdp_xmit |= xdp_res;
-			else
-				xsk_buff_free(*bi);
-
-			*bi = NULL;
-			total_rx_bytes += size;
-			total_rx_packets++;
-
-			cleaned_count++;
-			i40e_inc_ntc(rx_ring);
-			continue;
-		}
-
-		/* XDP_PASS path */
-
-		/* NB! We are not checking for errors using
-		 * i40e_test_staterr with
-		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
-		 * SBP is *not* set in PRT_SBPVSI (default not set).
-		 */
-		skb = i40e_construct_skb_zc(rx_ring, *bi);
-		if (!skb) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			break;
-		}
-
-		*bi = NULL;
-		cleaned_count++;
-		i40e_inc_ntc(rx_ring);
-
-		if (eth_skb_pad(skb))
-			continue;
-
-		total_rx_bytes += skb->len;
-		total_rx_packets++;
-
-		i40e_process_skb_fields(rx_ring, rx_desc, skb);
-		napi_gro_receive(&rx_ring->q_vector->napi, skb);
+		bi = *i40e_rx_bi(rx_ring, next_to_clean);
+		bi->data_end = bi->data + size;
+		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
+
+		xdp_res = i40e_run_xdp_zc(rx_ring, bi);
+		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
+					  &rx_bytes, size, xdp_res);
+		total_rx_packets += rx_packets;
+		total_rx_bytes += rx_bytes;
+		xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR);
+		next_to_clean = (next_to_clean + 1) & count_mask;
 	}
 
+	rx_ring->next_to_clean = next_to_clean;
+	cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask;
+
 	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
 		failure = !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
 
@@ -374,7 +385,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
 	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
-		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+		if (failure || next_to_clean == rx_ring->next_to_use)
 			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
 		else
 			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
@@ -604,16 +615,14 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 
 void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i++) {
-		struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, i);
+	u16 count_mask = rx_ring->count - 1;
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-		if (!rx_bi)
-			continue;
+	for ( ; ntc != ntu; ntc = (ntc + 1)  & count_mask) {
+		struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, ntc);
 
 		xsk_buff_free(rx_bi);
-		rx_bi = NULL;
 	}
 }