Received-SPF: pass (google.com: domain of linux-kernel+bounces-137628-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
To: "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, Andrew Halaney <ahalaney@redhat.com>,
        Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
        Martin KaFai Lau <martin.lau@kernel.org>,
        Martin KaFai Lau <martin.lau@linux.dev>,
        Daniel Borkmann <daniel@iogearbox.net>, bpf <bpf@vger.kernel.org>
Cc: kernel@quicinc.com
Subject: [RFC PATCH bpf-next v1 3/3] net: Add additional bit to support userspace timestamp type
Date: Tue,  9 Apr 2024 14:05:47 -0700
Message-Id: <20240409210547.3815806-4-quic_abchauha@quicinc.com>
In-Reply-To: <20240409210547.3815806-1-quic_abchauha@quicinc.com>
References: <20240409210547.3815806-1-quic_abchauha@quicinc.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

tstamp_type can be real, mono or userspace timestamp.

This commit adds userspace timestamp and sets it if there is
valid transmit_time available in socket coming from userspace.

To make the design scalable for future needs this commit bring in
the change to extend the tstamp_type:1 to tstamp_type:2 to support
userspace timestamp.

Link: https://lore.kernel.org/netdev/bc037db4-58bb-4861-ac31-a361a93841d3@linux.dev/
Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
---
 include/linux/skbuff.h | 19 +++++++++++++++++--
 net/ipv4/ip_output.c   |  2 +-
 net/ipv4/raw.c         |  2 +-
 net/ipv6/ip6_output.c  |  2 +-
 net/ipv6/raw.c         |  2 +-
 net/packet/af_packet.c |  6 +++---
 6 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6160185f0fe0..2f91a8a2157a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -705,6 +705,9 @@ typedef unsigned char *sk_buff_data_t;
 enum skb_tstamp_type {
 	SKB_TSTAMP_TYPE_RX_REAL = 0,    /* A RX (receive) time in real */
 	SKB_TSTAMP_TYPE_TX_MONO = 1,    /* A TX (delivery) time in mono */
+	SKB_TSTAMP_TYPE_TX_USER = 2,    /* A TX (delivery) time and its clock
+									 * is in skb->sk->sk_clockid.
+									 */
 };
 
 /**
@@ -830,6 +833,9 @@ enum skb_tstamp_type {
  *		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.
@@ -960,7 +966,7 @@ struct sk_buff {
 	/* private: */
 	__u8			__mono_tc_offset[0];
 	/* public: */
-	__u8			tstamp_type:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */
+	__u8			tstamp_type:2;	/* See SKB_MONO_DELIVERY_TIME_MASK */
 #ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
@@ -4274,7 +4280,16 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
 					enum skb_tstamp_type tstamp_type)
 {
 	skb->tstamp = kt;
-	skb->tstamp_type = kt && tstamp_type;
+
+	if (skb->tstamp_type)
+		return;
+
+	if (kt && tstamp_type == SKB_TSTAMP_TYPE_TX_MONO)
+		skb->tstamp_type = SKB_TSTAMP_TYPE_TX_MONO;
+
+	if (kt && tstamp_type == SKB_TSTAMP_TYPE_TX_USER)
+		skb->tstamp_type = SKB_TSTAMP_TYPE_TX_USER;
+
 }
 
 DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 62e457f7c02c..9aea6e810f52 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1457,7 +1457,7 @@ 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_set_delivery_time(skb, cork->transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 	/*
 	 * 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 dcb11f22cbf2..d8f52bc06ed3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_time(skb, sockc->transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a9e819115622..2beb9fc8c0b1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1924,7 +1924,7 @@ 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_set_delivery_time(skb, cork->base.transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 0d896ca7b589..3a68ca80bf83 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_time(skb, sockc->transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 18f616f487ea..27ea972dfc56 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2056,7 +2056,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
-	skb->tstamp = sockc.transmit_time;
+	skb_set_delivery_time(skb, sockc.transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 
 	skb_setup_tx_timestamp(skb, sockc.tsflags);
 
@@ -2585,7 +2585,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = READ_ONCE(po->sk.sk_priority);
 	skb->mark = READ_ONCE(po->sk.sk_mark);
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_time(skb, sockc->transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 	skb_setup_tx_timestamp(skb, sockc->tsflags);
 	skb_zcopy_set_nouarg(skb, ph.raw);
 
@@ -3063,7 +3063,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc.mark;
-	skb->tstamp = sockc.transmit_time;
+	skb_set_delivery_time(skb, sockc.transmit_time, SKB_TSTAMP_TYPE_TX_USER);
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
-- 
2.25.1