diff mbox series

[net-next,08/14] gso: AccECN support

Message ID 20241018022051.39966-9-chia-yu.chang@nokia-bell-labs.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series AccECN protocol preparation patch series | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit fail Errors and warnings before: 44 this patch: 69
netdev/build_tools success Errors and warnings before: 0 (+0) this patch: 0 (+0)
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang fail Errors and warnings before: 90 this patch: 120
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn fail Errors and warnings before: 5017 this patch: 4722
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 82 this patch: 82
netdev/source_inline success Was 0 now: 0

Commit Message

Chia-Yu Chang (Nokia) Oct. 18, 2024, 2:20 a.m. UTC 
From: Ilpo Järvinen <ij@kernel.org>

Handling the CWR flag differs between RFC 3168 ECN and AccECN.
With RFC 3168 ECN aware TSO (NETIF_F_TSO_ECN) CWR flag is cleared
starting from 2nd segment which is incompatible how AccECN handles
the CWR flag. Such super-segments are indicated by SKB_GSO_TCP_ECN.
With AccECN, CWR flag (or more accurately, the ACE field that also
includes ECE & AE flags) changes only when new packet(s) with CE
mark arrives so the flag should not be changed within a super-skb.
The new skb/feature flags are necessary to prevent such TSO engines
corrupting AccECN ACE counters by clearing the CWR flag (if the
CWR handling feature cannot be turned off).

If NIC is completely unaware of RFC3168 ECN (doesn't support
NETIF_F_TSO_ECN) or its TSO engine can be set to not touch CWR flag
despite supporting also NETIF_F_TSO_ECN, TSO could be safely used
with AccECN on such NIC. This should be evaluated per NIC basis
(not done in this patch series for any NICs).

For the cases, where TSO cannot keep its hands off the CWR flag,
a GSO fallback is provided by this patch.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
 include/linux/netdev_features.h | 5 ++++-
 include/linux/netdevice.h       | 1 +
 include/linux/skbuff.h          | 2 ++
 net/ethtool/common.c            | 1 +
 net/ipv4/tcp_offload.c          | 6 +++++-
 5 files changed, 13 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 66e7d26b70a4..d26e9a22dfb5 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -34,6 +34,7 @@  enum {
 		= NETIF_F_GSO_SHIFT,
 	NETIF_F_GSO_ROBUST_BIT,		/* ... ->SKB_GSO_DODGY */
 	NETIF_F_TSO_ECN_BIT,		/* ... TCP ECN support */
+	NETIF_F_GSO_ACCECN_BIT,         /* TCP AccECN with TSO (no CWR clearing) */
 	NETIF_F_TSO_MANGLEID_BIT,	/* ... IPV4 ID mangling allowed */
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
@@ -128,6 +129,7 @@  enum {
 #define NETIF_F_SG		__NETIF_F(SG)
 #define NETIF_F_TSO6		__NETIF_F(TSO6)
 #define NETIF_F_TSO_ECN		__NETIF_F(TSO_ECN)
+#define NETIF_F_GSO_ACCECN	__NETIF_F(GSO_ACCECN)
 #define NETIF_F_TSO		__NETIF_F(TSO)
 #define NETIF_F_VLAN_CHALLENGED	__NETIF_F(VLAN_CHALLENGED)
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
@@ -210,7 +212,8 @@  static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | \
+				 NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \
 				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bdd7d6262112..92fb65090ee7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5067,6 +5067,7 @@  static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_ACCECN != (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 48f1e0fa2a13..530cb325fb86 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -694,6 +694,8 @@  enum {
 	SKB_GSO_UDP_L4 = 1 << 17,
 
 	SKB_GSO_FRAGLIST = 1 << 18,
+
+	SKB_GSO_TCP_ACCECN = 1 << 19,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 0d62363dbd9d..5c3ba2dfaa74 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -32,6 +32,7 @@  const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_TSO_BIT] =              "tx-tcp-segmentation",
 	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
 	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_GSO_ACCECN_BIT] =	 "tx-tcp-accecn-segmentation",
 	[NETIF_F_TSO_MANGLEID_BIT] =	 "tx-tcp-mangleid-segmentation",
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2308665b51c5..0b05f30e9e5f 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -139,6 +139,7 @@  struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	struct sk_buff *gso_skb = skb;
 	__sum16 newcheck;
 	bool ooo_okay, copy_destructor;
+	bool ecn_cwr_mask;
 	__wsum delta;
 
 	th = tcp_hdr(skb);
@@ -198,6 +199,8 @@  struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 
 	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 
+	ecn_cwr_mask = !!(skb_shinfo(gso_skb)->gso_type & SKB_GSO_TCP_ACCECN);
+
 	while (skb->next) {
 		th->fin = th->psh = 0;
 		th->check = newcheck;
@@ -217,7 +220,8 @@  struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		th = tcp_hdr(skb);
 
 		th->seq = htonl(seq);
-		th->cwr = 0;
+
+		th->cwr &= ecn_cwr_mask;
 	}
 
 	/* Following permits TCP Small Queues to work well with GSO :