diff mbox series

[net-next,07/15] ipv6: add GRO_IPV6_MAX_SIZE

Message ID 20220203015140.3022854-8-eric.dumazet@gmail.com (mailing list archive)
State Changes Requested
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
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: 4834 this patch: 4834
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 823 this patch: 823
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: 4987 this patch: 4987
netdev/checkpatch warning CHECK: Alignment should match open parenthesis WARNING: From:/Signed-off-by: email name mismatch: 'From: "Signed-off-by: Coco Li" <lixiaoyan@google.com>' != 'Signed-off-by: Coco Li <lixiaoyan@google.com>' WARNING: line length of 82 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet Feb. 3, 2022, 1:51 a.m. UTC 
From: "Signed-off-by: Coco Li" <lixiaoyan@google.com>

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 <lixiaoyan@google.com>
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(-)

Comments

Eric Dumazet Feb. 3, 2022, 2:18 a.m. UTC | #1 
On Wed, Feb 2, 2022 at 5:52 PM Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
> From: "Signed-off-by: Coco Li" <lixiaoyan@google.com>

Small glitch here, it should be:

From: Coco Li <lixiaoyan@google.com>

Fixed in my tree :)

>
> 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 <lixiaoyan@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> ---
Paolo Abeni Feb. 3, 2022, 10:44 a.m. UTC | #2 
On Wed, 2022-02-02 at 17:51 -0800, Eric Dumazet wrote:
> From: "Signed-off-by: Coco Li" <lixiaoyan@google.com>
> 
> 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 <lixiaoyan@google.com>
> 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
diff mbox series

Patch

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);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0a0b26261f6d9e4e40bf9cfbda31a29c1f2e3aaa..cb552d99682ab8498613f79df9bd6fbaad8c2d59 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1029,6 +1029,7 @@  static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_IPV6_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_GSO_IPV6_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GRO_IPV6_MAX_SIZE */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
@@ -1734,6 +1735,7 @@  static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_IPV6_MAX_SIZE, dev->tso_ipv6_max_size) ||
 	    nla_put_u32(skb, IFLA_GSO_IPV6_MAX_SIZE, dev->gso_ipv6_max_size) ||
+	    nla_put_u32(skb, IFLA_GRO_IPV6_MAX_SIZE, dev->gro_ipv6_max_size) ||
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
@@ -1889,6 +1891,7 @@  static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_GRO_MAX_SIZE]	= { .type = NLA_U32 },
 	[IFLA_TSO_IPV6_MAX_SIZE]	= { .type = NLA_U32 },
 	[IFLA_GSO_IPV6_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_GRO_IPV6_MAX_SIZE]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2784,6 +2787,15 @@  static int do_setlink(const struct sk_buff *skb,
 		}
 	}
 
+	if (tb[IFLA_GRO_IPV6_MAX_SIZE]) {
+		u32 max_size = nla_get_u32(tb[IFLA_GRO_IPV6_MAX_SIZE]);
+
+		if (dev->gro_ipv6_max_size ^ max_size) {
+			netif_set_gro_ipv6_max_size(dev, max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
 	if (tb[IFLA_GSO_MAX_SEGS]) {
 		u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
 
@@ -3262,6 +3274,9 @@  struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	if (tb[IFLA_GSO_IPV6_MAX_SIZE])
 		netif_set_gso_ipv6_max_size(dev,
 			nla_get_u32(tb[IFLA_GSO_IPV6_MAX_SIZE]));
+	if (tb[IFLA_GRO_IPV6_MAX_SIZE])
+		netif_set_gro_ipv6_max_size(dev,
+			nla_get_u32(tb[IFLA_GRO_IPV6_MAX_SIZE]));
 
 	return dev;
 }
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 024b3bd0467e1360917001dba6bcfd1f30391894..48fe85bed4a629df0dd7cc0ee3a5139370e2c94d 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/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
 };