Merge branch '10GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next

-queue

Tony Nguyen says:

====================
10GbE Intel Wired LAN Driver Updates 2022-01-31

Alexander Lobakin says:

This is an interpolation of [0] to other Intel Ethernet drivers
(and is (re)based on its code).
The main aim is to keep XDP metadata not only in case with
build_skb(), but also when we do napi_alloc_skb() + memcpy().

All Intel drivers suffers from the same here:
 - metadata gets lost on XDP_PASS in legacy-rx;
 - excessive headroom allocation on XSK Rx to skbs;
 - metadata gets lost on XSK Rx to skbs.

Those get especially actual in XDP Hints upcoming.
I couldn't have addressed the first one for all Intel drivers due to
that they don't reserve any headroom for now in legacy-rx mode even
with XDP enabled. This is hugely wrong, but requires quite a bunch
of work and a separate series. Luckily, ice doesn't suffer from
that.
igc has 1 and 3 already fixed in [0].

[0] https://lore.kernel.org/netdev/163700856423.565980.10162564921347693758.stgit@firesoul
====================

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

5 files changed, 54 insertions, 33 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 945b1bb9c6f4..67e9844e2076 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -241,21 +241,25 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 					     struct xdp_buff *xdp)
 {
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
 	struct sk_buff *skb;
 
+	net_prefetch(xdp->data_meta);
+
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       xdp->data_end - xdp->data_hard_start,
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		goto out;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
-	if (metasize)
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
 		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
 out:
 	xsk_buff_free(xdp);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 3e38695f1c9d..c2258bee8ecb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -983,15 +983,17 @@ static struct sk_buff *
 ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 		  struct xdp_buff *xdp)
 {
+	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int size = xdp->data_end - xdp->data;
 	unsigned int headlen;
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	net_prefetch(xdp->data);
+	net_prefetch(xdp->data_meta);
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       ICE_RX_HDR_SIZE + metasize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
@@ -1003,8 +1005,13 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 		headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
-							 sizeof(long)));
+	memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta,
+	       ALIGN(headlen + metasize, sizeof(long)));
+
+	if (metasize) {
+		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
 	/* if we exhaust the linear part then add what is left as a frag */
 	size -= headlen;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 2388837d6d6c..feb874bde171 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -428,20 +428,24 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
 static struct sk_buff *
 ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
 	struct sk_buff *skb;
 
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
+	net_prefetch(xdp->data_meta);
+
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
-	if (metasize)
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
 		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
 	xsk_buff_free(xdp);
 	return skb;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 6b51baadee3d..b965fb809d84 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2446,19 +2446,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 					    struct xdp_buff *xdp)
 {
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int totalsize = metasize + datasize;
 	struct sk_buff *skb;
 
-	skb = __napi_alloc_skb(&ring->q_vector->napi,
-			       xdp->data_end - xdp->data_hard_start,
+	net_prefetch(xdp->data_meta);
+
+	skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
-	memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize);
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
 	if (metasize) {
 		skb_metadata_set(skb, metasize);
 		__skb_pull(skb, metasize);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index b3fd8e5cd85b..ee28929b9c5f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -207,26 +207,28 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
 }
 
 static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
-					      struct ixgbe_rx_buffer *bi)
+					      const struct xdp_buff *xdp)
 {
-	unsigned int metasize = bi->xdp->data - bi->xdp->data_meta;
-	unsigned int datasize = bi->xdp->data_end - bi->xdp->data;
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
+	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
 
+	net_prefetch(xdp->data_meta);
+
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       bi->xdp->data_end - bi->xdp->data_hard_start,
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize);
-	if (metasize)
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
 		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
-	xsk_buff_free(bi->xdp);
-	bi->xdp = NULL;
 	return skb;
 }
 
@@ -317,12 +319,15 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		}
 
 		/* XDP_PASS path */
-		skb = ixgbe_construct_skb_zc(rx_ring, bi);
+		skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp);
 		if (!skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			break;
 		}
 
+		xsk_buff_free(bi->xdp);
+		bi->xdp = NULL;
+
 		cleaned_count++;
 		ixgbe_inc_ntc(rx_ring);