[PATCH net-next 3/8] rtnetlink: add IFLA_TX_EXTRA_HEADROOM

@@ -1098,6 +1098,16 @@ attribute-sets:
         name: pacing-offload
         type: u32
         doc: Enable EDT pacing offload (0 - disabled, 1 - enabled).
+      -
+        name: tx-extra-headroom
+        type: u32
+        doc: |
+          Additional headroom, in bytes, reserved on top of the driver's
+          requirement when the UDP, raw, AF_PACKET and AF_XDP copy mode transmit
+          paths allocate a packet for this device. TCP and forwarded packets are
+          not covered. Zero (the default) disables the extra reservation.
+        checks:
+          max: 512
   -
     name: prop-list-link-attrs
     subset-of: link-attrs

@@ -2471,6 +2481,7 @@ operations:
             - gso-ipv4-max-size
             - gro-ipv4-max-size
             - af-spec
+            - tx-extra-headroom
     -
       name: newlink-ntf
       doc: Notify that a link has been created

@@ -2567,6 +2578,7 @@ operations:
             - gso-ipv4-max-size
             - gro-ipv4-max-size
             - pacing-offload
+            - tx-extra-headroom
       dump:
         request:
           value: 18

@@ -441,6 +441,41 @@ from a notifier.
 
 Drivers **must not** generate nested notifications of the ops-locked types.
 
+TX headroom reservation
+=======================
+
+``needed_headroom`` is the driver's own additional header-space requirement.
+It is written by the driver, or by a stacked device inheriting the value of
+the device below it, and is reported read-only through ``IFLA_HEADROOM``.
+
+``tx_extra_headroom`` is a separate reservation configured by the
+administrator through the ``IFLA_TX_EXTRA_HEADROOM`` rtnetlink attribute, a
+byte count from 0 to 512 that defaults to 0. It can be supplied when a link
+is created or changed, is reported in link dumps and change notifications,
+and setting it back to 0 removes it.
+
+The extra reservation is only applied when the stack allocates a locally
+generated packet for transmission through the device. ``LL_ALLOC_SPACE()``
+adds ``tx_extra_headroom`` before ``LL_RESERVED_SPACE()`` aligns the sum to
+``HH_DATA_MOD``, and is used by the UDP, raw and AF_PACKET transmit paths.
+AF_XDP copy mode adds it through ``netdev_tx_alloc_headroom()``. Its purpose
+is to give programs attached at TC egress room to push additional headers
+without having to reallocate the packet first.
+
+The setting is deliberately not part of ``LL_RESERVED_SPACE()``, which
+remains the threshold for deciding whether an already existing packet must
+be expanded. Packets that reach the device with less than the extra
+reservation, such as forwarded packets or TCP segments, are therefore not
+reallocated because of it. Consumers must keep their usual headroom and
+clone checks.
+
+The setting is not inherited through stacked devices. Packets are allocated
+against the device selected by the route, so configure it on the VLAN,
+bond or bridge device the route points at rather than on the device
+beneath it. It survives link down/up and network namespace moves and is
+independent of any TC or BPF attachment. It does not change the MTU or
+the bytes on the wire.
+
 NETDEV_INTERNAL symbol namespace
 ================================
 

@@ -382,6 +382,7 @@ enum {
 	IFLA_HEADROOM,
 	IFLA_TAILROOM,
 	IFLA_PACING_OFFLOAD,
+	IFLA_TX_EXTRA_HEADROOM,
 	__IFLA_MAX
 };
 

@@ -1409,6 +1409,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4)  /* IFLA_PACING_OFFLOAD */
 	       + nla_total_size(2)  /* IFLA_HEADROOM */
 	       + nla_total_size(2)  /* IFLA_TAILROOM */
+	       + nla_total_size(4)  /* IFLA_TX_EXTRA_HEADROOM */
 	       + rtnl_dev_parent_size(dev)
 	       + 0;
 

@@ -2206,7 +2207,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u16(skb, IFLA_HEADROOM,
 			READ_ONCE(dev->needed_headroom)) ||
 	    nla_put_u16(skb, IFLA_TAILROOM,
-			READ_ONCE(dev->needed_tailroom)))
+			READ_ONCE(dev->needed_tailroom)) ||
+	    nla_put_u32(skb, IFLA_TX_EXTRA_HEADROOM,
+			READ_ONCE(dev->tx_extra_headroom)))
 		goto nla_put_failure;
 
 	if (rtnl_fill_proto_down(skb, dev))

@@ -2367,6 +2370,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_HEADROOM]		= { .type = NLA_REJECT },
 	[IFLA_TAILROOM]		= { .type = NLA_REJECT },
 	[IFLA_PACING_OFFLOAD]	= NLA_POLICY_MAX(NLA_U32, 1),
+	[IFLA_TX_EXTRA_HEADROOM] =
+		NLA_POLICY_MAX(NLA_U32, NETDEV_TX_EXTRA_HEADROOM_MAX),
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {

@@ -3374,6 +3379,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
+	if (tb[IFLA_TX_EXTRA_HEADROOM]) {
+		u32 val = nla_get_u32(tb[IFLA_TX_EXTRA_HEADROOM]);
+
+		if (dev->tx_extra_headroom != val) {
+			WRITE_ONCE(dev->tx_extra_headroom, val);
+			status |= DO_SETLINK_NOTIFY;
+		}
+	}
+
 	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
 

@@ -3865,6 +3879,9 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		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]));
+	if (tb[IFLA_TX_EXTRA_HEADROOM])
+		dev->tx_extra_headroom =
+			nla_get_u32(tb[IFLA_TX_EXTRA_HEADROOM]);
 
 	return dev;
 }