[next-queue v2 0/4] ixgbe: Enable tso and checksum offload with ipsec

[next-queue v2 0/4] ixgbe: Enable tso and checksum offload with ipsec

[Shannon Nelson]

This patchset fixes up the bits for supporting TSO and checksum
offload in conjunction with IPsec offload.  This brings the
throughput of a simple iperf test back up to nearly line rate.

v2: fixes in patch 4 from Alex's comments

Shannon Nelson (4):
  ixgbe: no need for ipsec csum feature check
  ixgbe: remove unneeded ipsec test in Tx path
  ixgbe: no need for esp trailer if gso
  ixgbe: enable tso with ipsec offload

 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 45 +++++++++++++++-----------
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c  | 30 ++++++++---------
 2 files changed, 42 insertions(+), 33 deletions(-)

-- 
2.7.4

[next-queue v2 1/4] ixgbe: no need for ipsec csum feature check

[Shannon Nelson]

With the patch
commit f8aa2696b4af ("esp: check the NETIF_F_HW_ESP_TX_CSUM bit before segmenting")
we no longer need to protect ourself from checksum
offload requests on IPsec packets, so we can remove
the check in our .ndo_features_check callback.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 8536942..153cd9e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9908,12 +9908,6 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID))
 		features &= ~NETIF_F_TSO;
 
-#ifdef CONFIG_XFRM_OFFLOAD
-	/* IPsec offload doesn't get along well with others *yet* */
-	if (skb->sp)
-		features &= ~(NETIF_F_TSO | NETIF_F_HW_CSUM);
-#endif
-
 	return features;
 }
 
-- 
2.7.4

[next-queue v2 2/4] ixgbe: remove unneeded ipsec test in TX path

[Shannon Nelson]

Since the ipsec data fields will be zero anyway in the non-ipsec
case, we can remove the conditional jump.

Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 153cd9e..a54f3d8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7864,10 +7864,8 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring,
 	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
-	if (first->tx_flags & IXGBE_TX_FLAGS_IPSEC) {
-		fceof_saidx |= itd->sa_idx;
-		type_tucmd |= itd->flags | itd->trailer_len;
-	}
+	fceof_saidx |= itd->sa_idx;
+	type_tucmd |= itd->flags | itd->trailer_len;
 
 	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, 0);
 }
-- 
2.7.4

[next-queue v2 3/4] ixgbe: no need for esp trailer if gso

[Shannon Nelson]

There is no need to calculate the trailer length if we're doing
a GSO/TSO, as there is no trailer added to the packet data.
Also, don't bother clearing the flags field as it was already
cleared earlier.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 37 +++++++++++++++-----------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index f225452..5ddea43 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -774,11 +774,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 
 	first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CC;
 
-	itd->flags = 0;
 	if (xs->id.proto == IPPROTO_ESP) {
-		struct sk_buff *skb = first->skb;
-		int ret, authlen, trailerlen;
-		u8 padlen;
 
 		itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP |
 			      IXGBE_ADVTXD_TUCMD_L4T_TCP;
@@ -790,19 +786,28 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 		 * padlen bytes of padding.  This ends up not the same
 		 * as the static value found in xs->props.trailer_len (21).
 		 *
-		 * The "correct" way to get the auth length would be to use
-		 *    authlen = crypto_aead_authsize(xs->data);
-		 * but since we know we only have one size to worry about
-		 * we can let the compiler use the constant and save us a
-		 * few CPU cycles.
+		 * ... but if we're doing GSO, don't bother as the stack
+		 * doesn't add a trailer for those.
 		 */
-		authlen = IXGBE_IPSEC_AUTH_BITS / 8;
-
-		ret = skb_copy_bits(skb, skb->len - (authlen + 2), &padlen, 1);
-		if (unlikely(ret))
-			return 0;
-		trailerlen = authlen + 2 + padlen;
-		itd->trailer_len = trailerlen;
+		if (!skb_is_gso(first->skb)) {
+			/* The "correct" way to get the auth length would be
+			 * to use
+			 *    authlen = crypto_aead_authsize(xs->data);
+			 * but since we know we only have one size to worry
+			 * about * we can let the compiler use the constant
+			 * and save us a few CPU cycles.
+			 */
+			const int authlen = IXGBE_IPSEC_AUTH_BITS / 8;
+			struct sk_buff *skb = first->skb;
+			u8 padlen;
+			int ret;
+
+			ret = skb_copy_bits(skb, skb->len - (authlen + 2),
+					    &padlen, 1);
+			if (unlikely(ret))
+				return 0;
+			itd->trailer_len = authlen + 2 + padlen;
+		}
 	}
 	if (tsa->encrypt)
 		itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN;
-- 
2.7.4

[next-queue v2 4/4] ixgbe: enable tso with ipsec offload

[Shannon Nelson]

Fix things up to support TSO offload in conjunction
with IPsec hw offload.  This raises throughput with
IPsec offload on to nearly line rate.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
---
v2 updates from Alex's comments:
 - changed feature add from variable to #define
 - fixed a reverse christmas tree miss
 - GSO_PARTIAL'd the ipv4 header checksum
 - dropped an extra blank line


 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c |  9 +++++++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c  | 26 ++++++++++++++++++--------
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 5ddea43..68af127 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -929,8 +929,13 @@ void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
 	ixgbe_ipsec_clear_hw_tables(adapter);
 
 	adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops;
-	adapter->netdev->features |= NETIF_F_HW_ESP;
-	adapter->netdev->hw_enc_features |= NETIF_F_HW_ESP;
+
+#define IXGBE_ESP_FEATURES	(NETIF_F_HW_ESP | \
+				 NETIF_F_HW_ESP_TX_CSUM | \
+				 NETIF_F_GSO_ESP)
+
+	adapter->netdev->features |= IXGBE_ESP_FEATURES;
+	adapter->netdev->hw_enc_features |= IXGBE_ESP_FEATURES;
 
 	return;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a54f3d8..b947435 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7721,7 +7721,8 @@ static void ixgbe_service_task(struct work_struct *work)
 
 static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 		     struct ixgbe_tx_buffer *first,
-		     u8 *hdr_len)
+		     u8 *hdr_len,
+		     struct ixgbe_ipsec_tx_data *itd)
 {
 	u32 vlan_macip_lens, type_tucmd, mss_l4len_idx;
 	struct sk_buff *skb = first->skb;
@@ -7735,6 +7736,7 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 		unsigned char *hdr;
 	} l4;
 	u32 paylen, l4_offset;
+	u32 fceof_saidx = 0;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -7760,13 +7762,15 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 	if (ip.v4->version == 4) {
 		unsigned char *csum_start = skb_checksum_start(skb);
 		unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4);
+		int len = csum_start - trans_start;
 
 		/* IP header will have to cancel out any data that
-		 * is not a part of the outer IP header
+		 * is not a part of the outer IP header, so set to
+		 * a reverse csum if needed, else init check to 0.
 		 */
-		ip.v4->check = csum_fold(csum_partial(trans_start,
-						      csum_start - trans_start,
-						      0));
+		ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ?
+					   csum_fold(csum_partial(trans_start,
+								  len, 0)) : 0;
 		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
 
 		ip.v4->tot_len = 0;
@@ -7797,12 +7801,15 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring,
 	mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
 
+	fceof_saidx |= itd->sa_idx;
+	type_tucmd |= itd->flags | itd->trailer_len;
+
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
 	vlan_macip_lens = l4.hdr - ip.hdr;
 	vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
-	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, 0, type_tucmd,
+	ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd,
 			  mss_l4len_idx);
 
 	return 1;
@@ -8493,7 +8500,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 	if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
-	tso = ixgbe_tso(tx_ring, first, &hdr_len);
+	tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
 	if (tso < 0)
 		goto out_drop;
 	else if (!tso)
@@ -9902,8 +9909,11 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 
 	/* We can only support IPV4 TSO in tunnels if we can mangle the
 	 * inner IP ID field, so strip TSO if MANGLEID is not supported.
+	 * IPsec offoad sets skb->encapsulation but still can handle
+	 * the TSO, so it's the exception.
 	 */
-	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID))
+	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID) &&
+	    !skb->sp)
 		features &= ~NETIF_F_TSO;
 
 	return features;
-- 
2.7.4