diff mbox series

[PATCHv3,net-next,09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device

Message ID 905adccfe82888a8f0ca05fe6f2abd7e3a9649a0.1674835106.git.lucien.xin@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net: support ipv4 big tcp | 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: 4348 this patch: 4348
netdev/cc_maintainers warning 3 maintainers not CCed: liuhangbin@gmail.com idosch@nvidia.com petrm@nvidia.com
netdev/build_clang success Errors and warnings before: 1020 this patch: 1020
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 4558 this patch: 4558
netdev/checkpatch warning WARNING: line length of 90 exceeds 80 columns WARNING: please, no space before tabs
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Xin Long Jan. 27, 2023, 3:59 p.m. UTC 
This patch introduces gso_ipv4_max_size and gro_ipv4_max_size
per device and adds netlink attributes for them, so that IPV4
BIG TCP can be guarded by a separate tunable in the next patch.

To not break the old application using "gso/gro_max_size" for
IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size"
in netif_set_gso/gro_max_size() if the new size isn't greater
than GSO_LEGACY_MAX_SIZE, so that nothing will change even if
userspace doesn't realize the new netlink attributes.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 include/linux/netdevice.h    |  6 ++++++
 include/uapi/linux/if_link.h |  3 +++
 net/core/dev.c               |  4 ++++
 net/core/dev.h               | 18 ++++++++++++++++++
 net/core/rtnetlink.c         | 33 +++++++++++++++++++++++++++++++++
 5 files changed, 64 insertions(+)

Comments

Eric Dumazet Jan. 27, 2023, 5:48 p.m. UTC | #1 
On Fri, Jan 27, 2023 at 5:00 PM Xin Long <lucien.xin@gmail.com> wrote:
>
> This patch introduces gso_ipv4_max_size and gro_ipv4_max_size
> per device and adds netlink attributes for them, so that IPV4
> BIG TCP can be guarded by a separate tunable in the next patch.
>
> To not break the old application using "gso/gro_max_size" for
> IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size"
> in netif_set_gso/gro_max_size() if the new size isn't greater
> than GSO_LEGACY_MAX_SIZE, so that nothing will change even if
> userspace doesn't realize the new netlink attributes.
>
> Signed-off-by: Xin Long <lucien.xin@gmail.com>
> ---
>  include/linux/netdevice.h    |  6 ++++++
>  include/uapi/linux/if_link.h |  3 +++
>  net/core/dev.c               |  4 ++++
>  net/core/dev.h               | 18 ++++++++++++++++++
>  net/core/rtnetlink.c         | 33 +++++++++++++++++++++++++++++++++
>  5 files changed, 64 insertions(+)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 63b77cbc947e..ce075241ec47 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -2010,6 +2010,9 @@ enum netdev_ml_priv_type {
>   *                     SET_NETDEV_DEVLINK_PORT macro. This pointer is static
>   *                     during the time netdevice is registered.
>   *
> + *     @gso_ipv4_max_size:     Maximum size of IPv4 GSO packets.
> + *     @gro_ipv4_max_size:     Maximum size of IPv4 GRO packets.
> + *
>   *     FIXME: cleanup struct net_device such that network protocol info
>   *     moves out.
>   */
> @@ -2362,6 +2365,9 @@ struct net_device {
>         struct rtnl_hw_stats64  *offload_xstats_l3;
>
>         struct devlink_port     *devlink_port;
> +
> +       unsigned int            gso_ipv4_max_size;
> +       unsigned int            gro_ipv4_max_size;

This seems a pretty bad choice in terms of data locality.

Field order in "struct net_device" is very important for performance.

Please put gro_ipv4_max_size close to other related fields, so that we
do not need an extra cache line miss.

Same for gso_ipv4_max_size.

Use "pahole --hex" to study how "struct net_device" is currently partitioned.
It seems we have a hole after tso_max_segs, so this would be for
gso_ipv4_max_size


>  };
>  #define to_net_dev(d) container_of(d, struct net_device, dev)
>
>
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 63b77cbc947e..ce075241ec47 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2010,6 +2010,9 @@  enum netdev_ml_priv_type {
  *			SET_NETDEV_DEVLINK_PORT macro. This pointer is static
  *			during the time netdevice is registered.
  *
+ * 	@gso_ipv4_max_size:	Maximum size of IPv4 GSO packets.
+ * 	@gro_ipv4_max_size:	Maximum size of IPv4 GRO packets.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2362,6 +2365,9 @@  struct net_device {
 	struct rtnl_hw_stats64	*offload_xstats_l3;
 
 	struct devlink_port	*devlink_port;
+
+	unsigned int		gso_ipv4_max_size;
+	unsigned int		gro_ipv4_max_size;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1021a7e47a86..02b87e4c65be 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -374,6 +374,9 @@  enum {
 
 	IFLA_DEVLINK_PORT,
 
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+
 	__IFLA_MAX
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 9c60190fe352..45e955eadca4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3001,6 +3001,8 @@  void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
 	dev->tso_max_size = min(GSO_MAX_SIZE, size);
 	if (size < READ_ONCE(dev->gso_max_size))
 		netif_set_gso_max_size(dev, size);
+	if (size < READ_ONCE(dev->gso_ipv4_max_size))
+		netif_set_gso_ipv4_max_size(dev, size);
 }
 EXPORT_SYMBOL(netif_set_tso_max_size);
 
@@ -10610,6 +10612,8 @@  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_LEGACY_MAX_SIZE;
+	dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
+	dev->gro_ipv4_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/dev.h b/net/core/dev.h
index 814ed5b7b960..a065b7571441 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -100,6 +100,8 @@  static inline void netif_set_gso_max_size(struct net_device *dev,
 {
 	/* dev->gso_max_size is read locklessly from sk_setup_caps() */
 	WRITE_ONCE(dev->gso_max_size, size);
+	if (size <= GSO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gso_ipv4_max_size, size);
 }
 
 static inline void netif_set_gso_max_segs(struct net_device *dev,
@@ -114,6 +116,22 @@  static inline void netif_set_gro_max_size(struct net_device *dev,
 {
 	/* This pairs with the READ_ONCE() in skb_gro_receive() */
 	WRITE_ONCE(dev->gro_max_size, size);
+	if (size <= GRO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gro_ipv4_max_size, size);
+}
+
+static inline void netif_set_gso_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */
+	WRITE_ONCE(dev->gso_ipv4_max_size, size);
+}
+
+static inline void netif_set_gro_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* This pairs with the READ_ONCE() in skb_gro_receive() */
+	WRITE_ONCE(dev->gro_ipv4_max_size, size);
 }
 
 #endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 64289bc98887..b9f584955b77 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1074,6 +1074,8 @@  static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GSO_IPV4_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GRO_IPV4_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
@@ -1807,6 +1809,8 @@  static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
 	    nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
 	    nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
+	    nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) ||
+	    nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
 #ifdef CONFIG_RPS
@@ -1968,6 +1972,8 @@  static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_TSO_MAX_SIZE]	= { .type = NLA_REJECT },
 	[IFLA_TSO_MAX_SEGS]	= { .type = NLA_REJECT },
 	[IFLA_ALLMULTI]		= { .type = NLA_REJECT },
+	[IFLA_GSO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_GRO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2883,6 +2889,29 @@  static int do_setlink(const struct sk_buff *skb,
 		}
 	}
 
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
+		u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
+
+		if (max_size > dev->tso_max_size) {
+			err = -EINVAL;
+			goto errout;
+		}
+
+		if (dev->gso_ipv4_max_size ^ max_size) {
+			netif_set_gso_ipv4_max_size(dev, max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE]) {
+		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]);
+
+		if (dev->gro_ipv4_max_size ^ gro_max_size) {
+			netif_set_gro_ipv4_max_size(dev, gro_max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
 	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
 
@@ -3325,6 +3354,10 @@  struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS]));
 	if (tb[IFLA_GRO_MAX_SIZE])
 		netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE]));
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE])
+		netif_set_gso_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]));
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE])
+		netif_set_gro_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]));
 
 	return dev;
 }