diff mbox series

[v6,net-next,08/13] net: allow gro_max_size to exceed 65536

Message ID 20220510033219.2639364-9-eric.dumazet@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series tcp: BIG TCP implementation | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 4693 this patch: 4693
netdev/cc_maintainers warning 6 maintainers not CCed: saeedm@nvidia.com leon@kernel.org yoshfuji@linux-ipv6.org linux-rdma@vger.kernel.org petrm@nvidia.com dsahern@kernel.org
netdev/build_clang success Errors and warnings before: 1059 this patch: 1059
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 4844 this patch: 4844
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 64 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet May 10, 2022, 3:32 a.m. UTC 
From: Alexander Duyck <alexanderduyck@fb.com>

Allow the gro_max_size to exceed a value larger than 65536.

There weren't really any external limitations that prevented this other
than the fact that IPv4 only supports a 16 bit length field. Since we have
the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to
exceed this value and for IPv4 and non-TCP flows we can cap things at 65536
via a constant rather than relying on gro_max_size.

[edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 include/linux/netdevice.h                       | 6 +++++-
 include/net/ipv6.h                              | 2 +-
 net/core/dev.c                                  | 2 +-
 net/core/gro.c                                  | 8 ++++++++
 net/core/rtnetlink.c                            | 8 --------
 6 files changed, 16 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 838870bc6dbd6e3a3d8c9443ff4675a0e411006b..24de37b79f5a917b304c011fcebcd09748ee5c6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2038,7 +2038,7 @@  mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 {
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 
-	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_MAX_SIZE;
+	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
 }
 
 static void
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 673c444aae874428b117df45dffcaf702ac72a47..69743188f639c5afd20f06a5e301edca00aedaef 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2151,7 +2151,11 @@  struct net_device {
 	struct bpf_prog __rcu	*xdp_prog;
 	unsigned long		gro_flush_timeout;
 	int			napi_defer_hard_irqs;
-#define GRO_MAX_SIZE		65536
+#define GRO_LEGACY_MAX_SIZE	65536u
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b6df0314aa02dd1c4094620145ccb24da7195b2b..5b38bf1a586b9da55f43db30d140d364a70f6c11 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -477,7 +477,7 @@  static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
 	const struct hop_jumbo_hdr *jhdr;
 	const struct ipv6hdr *nhdr;
 
-	if (likely(skb->len <= GRO_MAX_SIZE))
+	if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
 		return 0;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
diff --git a/net/core/dev.c b/net/core/dev.c
index 68b76b45a5ac5f2ea705bd3db5d1732b79034609..4be3695846520af18a687cdcaa70c5f327ba94e8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10605,7 +10605,7 @@  struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
-	dev->gro_max_size = GRO_MAX_SIZE;
+	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;
diff --git a/net/core/gro.c b/net/core/gro.c
index 78110edf5d4b36d2fa6f8a2676096efe0112aa0e..b4190eb084672fb4f2be8b437eccb4e8507ff63f 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -167,6 +167,14 @@  int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
+	if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
+		if (p->protocol != htons(ETH_P_IPV6) ||
+		    skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
+		    ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+		    p->encapsulation)
+			return -E2BIG;
+	}
+
 	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 823db8999a2c1d5959042393783492dbecf1352c..5d7d7fe1e63a972bbcbd5eed1404b2643c74cfcb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2347,14 +2347,6 @@  static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	if (tb[IFLA_GRO_MAX_SIZE]) {
-		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
-
-		if (gro_max_size > GRO_MAX_SIZE) {
-			NL_SET_ERR_MSG(extack, "too big gro_max_size");
-			return -EINVAL;
-		}
-	}
 	return 0;
 }