net: Re-use and set mono_delivery_time bit for userspace tstamp packets

Bridge driver today has no support to forward the userspace timestamp
packets and ends up resetting the timestamp. ETF qdisc checks the
packet coming from userspace and encounters to be 0 thereby dropping
time sensitive packets. These changes will allow userspace timestamps
packets to be forwarded from the bridge to NIC drivers.

Setting the same bit (mono_delivery_time) to avoid dropping of
userspace tstamp packets in the forwarding path.

Existing functionality of mono_delivery_time remains unaltered here,
instead just extended with userspace tstamp support for bridge
forwarding path.

Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240301201348.2815102-1-quic_abchauha@quicinc.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d577e0bee18d21e6d568939326be5e92ad263335..3013355b63f5f29acfcb0331bfd1c3308aba034d 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -822,9 +822,9 @@ typedef unsigned char *sk_buff_data_t;
  *     @decrypted: Decrypted SKB
  *     @slow_gro: state present at GRO time, slower prepare step required
  *     @mono_delivery_time: When set, skb->tstamp has the
- *             delivery_time in mono clock base (i.e. EDT).  Otherwise, the
- *             skb->tstamp has the (rcv) timestamp at ingress and
- *             delivery_time at egress.
+ *             delivery_time in mono clock base (i.e., EDT) or a clock base chosen
+ *             by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at
+ *             ingress.
  *     @napi_id: id of the NAPI struct this skb came from
  *     @sender_cpu: (aka @napi_id) source CPU in XPS
  *     @alloc_cpu: CPU which did the skb allocation.

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1fe794967211e249016df00dc3c2ae230d71dcff..33f93dc730a3359b2a43e3cab447b94bc63597e0 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1458,6 +1458,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
        skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
        skb->mark = cork->mark;
        skb->tstamp = cork->transmit_time;
+       skb->mono_delivery_time = !!skb->tstamp;
        /*
         * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
         * on dst refcount

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index a82fd102df05a7aedb601f4bd59d408089e65eae..494a6284bd7ee346a4fca7a161477e6dc5ed5021 100644 (file)
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -353,6 +353,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
        skb->priority = READ_ONCE(sk->sk_priority);
        skb->mark = sockc->mark;
        skb->tstamp = sockc->transmit_time;
+       skb->mono_delivery_time = !!skb->tstamp;
        skb_dst_set(skb, &rt->dst);
        *rtp = NULL;
 

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b9dd3a66e4236fbf67af75c5f98c921b38c18bf6..02eeca5492cd4d894b4acc8ec89bf004e81c0ccb 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
        skb->priority = READ_ONCE(sk->sk_priority);
        skb->mark = cork->base.mark;
        skb->tstamp = cork->base.transmit_time;
-
+       skb->mono_delivery_time = !!skb->tstamp;
        ip6_cork_steal_dst(skb, cork);
        IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
        if (proto == IPPROTO_ICMPV6) {

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 76e6eb3b643d0f98597aae5483fd519ebeeac0f5..779274055abf99530048ad4738c2263e97c94cce 100644 (file)
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -615,7 +615,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
        skb->priority = READ_ONCE(sk->sk_priority);
        skb->mark = sockc->mark;
        skb->tstamp = sockc->transmit_time;
-
+       skb->mono_delivery_time = !!skb->tstamp;
        skb_put(skb, length);
        skb_reset_network_header(skb);
        iph = ipv6_hdr(skb);

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c9bbc2686690776fc2611ae68814c22fc73c708f..0db31ca4982daea787fc3cb15c28e501de1f95bb 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2057,7 +2057,7 @@ retry:
        skb->priority = READ_ONCE(sk->sk_priority);
        skb->mark = READ_ONCE(sk->sk_mark);
        skb->tstamp = sockc.transmit_time;
-
+       skb->mono_delivery_time = !!skb->tstamp;
        skb_setup_tx_timestamp(skb, sockc.tsflags);
 
        if (unlikely(extra_len == 4))
@@ -2586,6 +2586,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
        skb->priority = READ_ONCE(po->sk.sk_priority);
        skb->mark = READ_ONCE(po->sk.sk_mark);
        skb->tstamp = sockc->transmit_time;
+       skb->mono_delivery_time = !!skb->tstamp;
        skb_setup_tx_timestamp(skb, sockc->tsflags);
        skb_zcopy_set_nouarg(skb, ph.raw);
 
@@ -3064,6 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
        skb->priority = READ_ONCE(sk->sk_priority);
        skb->mark = sockc.mark;
        skb->tstamp = sockc.transmit_time;
+       skb->mono_delivery_time = !!skb->tstamp;
 
        if (unlikely(extra_len == 4))
                skb->no_fcs = 1;