Re: [PATCH net-next 07/15] ipv6: add GRO_IPV6_MAX_SIZE
From: Paolo Abeni <pabeni@redhat.com>
Date: 2022-02-03 10:45:06
On Wed, 2022-02-02 at 17:51 -0800, Eric Dumazet wrote:
quoted hunk ↗ jump to hunk
From: "Signed-off-by: Coco Li" <redacted> Enable GRO to have IPv6 specific limit for max packet size. This patch introduces new dev->gro_ipv6_max_size that is modifiable through ip link. ip link set dev eth0 gro_ipv6_max_size 185000 Note that this value is only considered if bigger than gro_max_size, and for non encapsulated TCP/ipv6 packets. Signed-off-by: Coco Li <redacted> Signed-off-by: Eric Dumazet <edumazet@google.com> --- include/linux/netdevice.h | 10 ++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 1 + net/core/gro.c | 20 ++++++++++++++++++-- net/core/rtnetlink.c | 15 +++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + 6 files changed, 46 insertions(+), 2 deletions(-)diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2a563869ba44f7d48095d36b1395e3fbd8cfff87..a3a61cffd953add6f272a53f551a49a47d200c68 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h@@ -1944,6 +1944,8 @@ enum netdev_ml_priv_type { * keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) + * @gro_ipv6_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO), for IPv6 * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch.@@ -2137,6 +2139,7 @@ struct net_device { int napi_defer_hard_irqs; #define GRO_MAX_SIZE 65536 unsigned int gro_max_size; + unsigned int gro_ipv6_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data;@@ -4840,6 +4843,13 @@ static inline void netif_set_gso_ipv6_max_size(struct net_device *dev, WRITE_ONCE(dev->gso_ipv6_max_size, size); } +static inline void netif_set_gro_ipv6_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_ipv6_max_size, size); +} + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len)diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 024b3bd0467e1360917001dba6bcfd1f30391894..48fe85bed4a629df0dd7cc0ee3a5139370e2c94d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h@@ -350,6 +350,7 @@ enum { IFLA_GRO_MAX_SIZE, IFLA_TSO_IPV6_MAX_SIZE, IFLA_GSO_IPV6_MAX_SIZE, + IFLA_GRO_IPV6_MAX_SIZE, __IFLA_MAX };diff --git a/net/core/dev.c b/net/core/dev.c index 53c947e6fdb7c47e6cc92fd4e38b71e9b90d921c..e7df5c3f53d6e96d01ff06d081cef77d0c6d9d29 100644 --- a/net/core/dev.c +++ b/net/core/dev.c@@ -10190,6 +10190,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gro_max_size = GRO_MAX_SIZE; dev->tso_ipv6_max_size = GSO_MAX_SIZE; dev->gso_ipv6_max_size = GSO_MAX_SIZE; + dev->gro_ipv6_max_size = GRO_MAX_SIZE; dev->upper_level = 1; dev->lower_level = 1;diff --git a/net/core/gro.c b/net/core/gro.c index a11b286d149593827f1990fb8d06b0295fa72189..005a05468418f0373264e8019384e2daa13176eb 100644 --- a/net/core/gro.c +++ b/net/core/gro.c@@ -136,11 +136,27 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int new_truesize; struct sk_buff *lp; + if (unlikely(NAPI_GRO_CB(skb)->flush)) + return -E2BIG; + /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ gro_max_size = READ_ONCE(p->dev->gro_max_size); - if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) - return -E2BIG; + if (unlikely(p->len + len >= gro_max_size)) { + /* pairs with WRITE_ONCE() in netif_set_gro_ipv6_max_size() */ + unsigned int gro6_max_size = READ_ONCE(p->dev->gro_ipv6_max_size); + + if (gro6_max_size > gro_max_size && + p->protocol == htons(ETH_P_IPV6) && + skb_headroom(p) >= sizeof(struct hop_jumbo_hdr) && + ipv6_hdr(p)->nexthdr == IPPROTO_TCP && + !p->encapsulation) + gro_max_size = gro6_max_size; + + if (p->len + len >= gro_max_size) + return -E2BIG; + } + lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp);
If I read correctly, a big GRO packet could be forwarded and/or redirected to an egress device not supporting LSOv2 or with a lower tso_ipv6_max_size. Don't we need to update netif_needs_gso() to take care of such scenario? AFAICS we are not enforcing gso_max_size, so I'm wondering if that is really a problem?!? Thanks! Paolo