diff mbox series

[net-next,v2,11/12] net-timestamp: add bpf framework for rx timestamps

Message ID 20241012040651.95616-12-kerneljasonxing@gmail.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series net-timestamp: bpf extension to equip applications transparently | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 204 this patch: 204
netdev/build_tools success Errors and warnings before: 159 (+0) this patch: 159 (+0)
netdev/cc_maintainers warning 1 maintainers not CCed: horms@kernel.org
netdev/build_clang success Errors and warnings before: 250 this patch: 250
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
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: 6942 this patch: 6942
netdev/checkpatch warning CHECK: spaces preferred around that '<<' (ctx:VxV) WARNING: line length of 81 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 11 this patch: 11
netdev/source_inline success Was 0 now: 0

Commit Message

Jason Xing Oct. 12, 2024, 4:06 a.m. UTC 
From: Jason Xing <kernelxing@tencent.com>

Prepare for later changes in this series. Here I use u32 for
bpf_sock_ops_cb_flags for better extension and introduce a new
rx bpf flag to control separately.

Main change is let userside set through bpf_setsockopt() for
SO_TIMESTAMPING feature.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
 include/linux/tcp.h            |  2 +-
 include/net/tcp.h              |  2 +-
 include/uapi/linux/bpf.h       |  5 ++++-
 net/core/filter.c              |  6 +++++-
 net/ipv4/tcp.c                 | 13 ++++++++++++-
 tools/include/uapi/linux/bpf.h |  5 ++++-
 6 files changed, 27 insertions(+), 6 deletions(-)

Comments

Willem de Bruijn Oct. 15, 2024, 1:44 a.m. UTC | #1 
Jason Xing wrote:
> From: Jason Xing <kernelxing@tencent.com>
> 
> Prepare for later changes in this series. Here I use u32 for
> bpf_sock_ops_cb_flags for better extension and introduce a new
> rx bpf flag to control separately.
> 
> Main change is let userside set through bpf_setsockopt() for
> SO_TIMESTAMPING feature.
> 
> Signed-off-by: Jason Xing <kernelxing@tencent.com>
> ---
>  include/linux/tcp.h            |  2 +-
>  include/net/tcp.h              |  2 +-
>  include/uapi/linux/bpf.h       |  5 ++++-
>  net/core/filter.c              |  6 +++++-
>  net/ipv4/tcp.c                 | 13 ++++++++++++-
>  tools/include/uapi/linux/bpf.h |  5 ++++-
>  6 files changed, 27 insertions(+), 6 deletions(-)
> 
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index 6a5e08b937b3..e21fd3035962 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -446,7 +446,7 @@ struct tcp_sock {
>  
>  /* Sock_ops bpf program related variables */
>  #ifdef CONFIG_BPF
> -	u8	bpf_sock_ops_cb_flags;  /* Control calling BPF programs
> +	u32	bpf_sock_ops_cb_flags;  /* Control calling BPF programs
>  					 * values defined in uapi/linux/tcp.h
>  					 */
>  	u8	bpf_chg_cc_inprogress:1; /* In the middle of
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 739a9fb83d0c..728db7107074 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -423,7 +423,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val);
>  int tcp_set_window_clamp(struct sock *sk, int val);
>  void tcp_update_recv_tstamps(struct sk_buff *skb,
>  			     struct scm_timestamping_internal *tss);
> -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
>  			struct scm_timestamping_internal *tss);
>  void tcp_data_ready(struct sock *sk);
>  #ifdef CONFIG_MMU
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 1b478ec18ac2..d2754f155cf7 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -6903,8 +6903,11 @@ enum {
>  	/* Call bpf when the kernel is generating tx timestamps.
>  	 */
>  	BPF_SOCK_OPS_TX_TIMESTAMPING_OPT_CB_FLAG = (1<<7),
> +	/* Call bpf when the kernel is generating rx timestamps.
> +	 */
> +	BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG = (1<<8),
>  /* Mask of all currently supported cb flags */
> -	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xFF,
> +	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x1FF,
>  };
>  
>  /* List of known BPF sock_ops operators.
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 3b4afaa273d9..36b357b76f4a 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5216,14 +5216,18 @@ static int bpf_sock_set_timestamping(struct sock *sk,
>  		return -EINVAL;
>  
>  	if (!(flags & (SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
> -	      SOF_TIMESTAMPING_TX_ACK)))
> +	      SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_RX_SOFTWARE)))
>  		return -EINVAL;
>  
>  	ret = sock_set_tskey(sk, flags, BPFPROG_TS_REQUESTOR);
>  	if (ret)
>  		return ret;
>  
> +	if (flags & SOF_TIMESTAMPING_RX_SOFTWARE)
> +		sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
> +
>  	WRITE_ONCE(sk->sk_tsflags[BPFPROG_TS_REQUESTOR], flags);
> +
>  	static_branch_enable(&bpf_tstamp_control);
>  
>  	return 0;
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index d37e231b2737..0891b41bc745 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -2260,14 +2260,25 @@ static int tcp_zerocopy_receive(struct sock *sk,
>  }
>  #endif
>  
> +static void tcp_bpf_recv_timestamp(struct sock *sk, struct scm_timestamping_internal *tss)
> +{
> +	struct tcp_sock *tp = tcp_sk(sk);
> +
> +	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG))
> +		return;
> +}
> +
>  /* Similar to __sock_recv_timestamp, but does not require an skb */
> -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
>  			struct scm_timestamping_internal *tss)
>  {
>  	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
>  	u32 tsflags = READ_ONCE(sk->sk_tsflags[SOCKETOPT_TS_REQUESTOR]);
>  	bool has_timestamping = false;
>  
> +	if (static_branch_unlikely(&bpf_tstamp_control))
> +		tcp_bpf_recv_timestamp(sk, tss);
> +
>  	if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
>  		if (sock_flag(sk, SOCK_RCVTSTAMP)) {
>  			if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {

tcp_recv_timestamp is called from tcp_recvmsg only conditionally:

        if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
                if (cmsg_flags & TCP_CMSG_TS)
                        tcp_recv_timestamp(msg, sk, &tss);

How do you get this triggered for your BPF program?

And also check the other caller, tcp_zc_finalize_rx_tstamp.
Jason Xing Oct. 15, 2024, 2:18 a.m. UTC | #2 
On Tue, Oct 15, 2024 at 9:44 AM Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
>
> Jason Xing wrote:
> > From: Jason Xing <kernelxing@tencent.com>
> >
> > Prepare for later changes in this series. Here I use u32 for
> > bpf_sock_ops_cb_flags for better extension and introduce a new
> > rx bpf flag to control separately.
> >
> > Main change is let userside set through bpf_setsockopt() for
> > SO_TIMESTAMPING feature.
> >
> > Signed-off-by: Jason Xing <kernelxing@tencent.com>
> > ---
> >  include/linux/tcp.h            |  2 +-
> >  include/net/tcp.h              |  2 +-
> >  include/uapi/linux/bpf.h       |  5 ++++-
> >  net/core/filter.c              |  6 +++++-
> >  net/ipv4/tcp.c                 | 13 ++++++++++++-
> >  tools/include/uapi/linux/bpf.h |  5 ++++-
> >  6 files changed, 27 insertions(+), 6 deletions(-)
> >
> > diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> > index 6a5e08b937b3..e21fd3035962 100644
> > --- a/include/linux/tcp.h
> > +++ b/include/linux/tcp.h
> > @@ -446,7 +446,7 @@ struct tcp_sock {
> >
> >  /* Sock_ops bpf program related variables */
> >  #ifdef CONFIG_BPF
> > -     u8      bpf_sock_ops_cb_flags;  /* Control calling BPF programs
> > +     u32     bpf_sock_ops_cb_flags;  /* Control calling BPF programs
> >                                        * values defined in uapi/linux/tcp.h
> >                                        */
> >       u8      bpf_chg_cc_inprogress:1; /* In the middle of
> > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > index 739a9fb83d0c..728db7107074 100644
> > --- a/include/net/tcp.h
> > +++ b/include/net/tcp.h
> > @@ -423,7 +423,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val);
> >  int tcp_set_window_clamp(struct sock *sk, int val);
> >  void tcp_update_recv_tstamps(struct sk_buff *skb,
> >                            struct scm_timestamping_internal *tss);
> > -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> > +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
> >                       struct scm_timestamping_internal *tss);
> >  void tcp_data_ready(struct sock *sk);
> >  #ifdef CONFIG_MMU
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index 1b478ec18ac2..d2754f155cf7 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -6903,8 +6903,11 @@ enum {
> >       /* Call bpf when the kernel is generating tx timestamps.
> >        */
> >       BPF_SOCK_OPS_TX_TIMESTAMPING_OPT_CB_FLAG = (1<<7),
> > +     /* Call bpf when the kernel is generating rx timestamps.
> > +      */
> > +     BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG = (1<<8),
> >  /* Mask of all currently supported cb flags */
> > -     BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xFF,
> > +     BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x1FF,
> >  };
> >
> >  /* List of known BPF sock_ops operators.
> > diff --git a/net/core/filter.c b/net/core/filter.c
> > index 3b4afaa273d9..36b357b76f4a 100644
> > --- a/net/core/filter.c
> > +++ b/net/core/filter.c
> > @@ -5216,14 +5216,18 @@ static int bpf_sock_set_timestamping(struct sock *sk,
> >               return -EINVAL;
> >
> >       if (!(flags & (SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
> > -           SOF_TIMESTAMPING_TX_ACK)))
> > +           SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_RX_SOFTWARE)))
> >               return -EINVAL;
> >
> >       ret = sock_set_tskey(sk, flags, BPFPROG_TS_REQUESTOR);
> >       if (ret)
> >               return ret;
> >
> > +     if (flags & SOF_TIMESTAMPING_RX_SOFTWARE)
> > +             sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
> > +
> >       WRITE_ONCE(sk->sk_tsflags[BPFPROG_TS_REQUESTOR], flags);
> > +
> >       static_branch_enable(&bpf_tstamp_control);
> >
> >       return 0;
> > diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> > index d37e231b2737..0891b41bc745 100644
> > --- a/net/ipv4/tcp.c
> > +++ b/net/ipv4/tcp.c
> > @@ -2260,14 +2260,25 @@ static int tcp_zerocopy_receive(struct sock *sk,
> >  }
> >  #endif
> >
> > +static void tcp_bpf_recv_timestamp(struct sock *sk, struct scm_timestamping_internal *tss)
> > +{
> > +     struct tcp_sock *tp = tcp_sk(sk);
> > +
> > +     if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG))
> > +             return;
> > +}
> > +
> >  /* Similar to __sock_recv_timestamp, but does not require an skb */
> > -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> > +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
> >                       struct scm_timestamping_internal *tss)
> >  {
> >       int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
> >       u32 tsflags = READ_ONCE(sk->sk_tsflags[SOCKETOPT_TS_REQUESTOR]);
> >       bool has_timestamping = false;
> >
> > +     if (static_branch_unlikely(&bpf_tstamp_control))
> > +             tcp_bpf_recv_timestamp(sk, tss);
> > +
> >       if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
> >               if (sock_flag(sk, SOCK_RCVTSTAMP)) {
> >                       if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
>
> tcp_recv_timestamp is called from tcp_recvmsg only conditionally:
>
>         if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
>                 if (cmsg_flags & TCP_CMSG_TS)
>                         tcp_recv_timestamp(msg, sk, &tss);
>
> How do you get this triggered for your BPF program?

When users use BPF SO_TIMESTAMPING to print rx timestamp, it will use
bpf_setsockopt() to call sock_enable_timestamp() (see this patch), so
the skb will carry a timestamp. In tcp_recvmsg_locked(), cmsg_flags
will be initialized, so tcp_recv_timestamp() will get called.

>
> And also check the other caller, tcp_zc_finalize_rx_tstamp.

Got it, thanks for pointing it out.
diff mbox series

Patch

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 6a5e08b937b3..e21fd3035962 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -446,7 +446,7 @@  struct tcp_sock {
 
 /* Sock_ops bpf program related variables */
 #ifdef CONFIG_BPF
-	u8	bpf_sock_ops_cb_flags;  /* Control calling BPF programs
+	u32	bpf_sock_ops_cb_flags;  /* Control calling BPF programs
 					 * values defined in uapi/linux/tcp.h
 					 */
 	u8	bpf_chg_cc_inprogress:1; /* In the middle of
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 739a9fb83d0c..728db7107074 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -423,7 +423,7 @@  int tcp_set_rcvlowat(struct sock *sk, int val);
 int tcp_set_window_clamp(struct sock *sk, int val);
 void tcp_update_recv_tstamps(struct sk_buff *skb,
 			     struct scm_timestamping_internal *tss);
-void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			struct scm_timestamping_internal *tss);
 void tcp_data_ready(struct sock *sk);
 #ifdef CONFIG_MMU
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1b478ec18ac2..d2754f155cf7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6903,8 +6903,11 @@  enum {
 	/* Call bpf when the kernel is generating tx timestamps.
 	 */
 	BPF_SOCK_OPS_TX_TIMESTAMPING_OPT_CB_FLAG = (1<<7),
+	/* Call bpf when the kernel is generating rx timestamps.
+	 */
+	BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG = (1<<8),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xFF,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x1FF,
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 3b4afaa273d9..36b357b76f4a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5216,14 +5216,18 @@  static int bpf_sock_set_timestamping(struct sock *sk,
 		return -EINVAL;
 
 	if (!(flags & (SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
-	      SOF_TIMESTAMPING_TX_ACK)))
+	      SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_RX_SOFTWARE)))
 		return -EINVAL;
 
 	ret = sock_set_tskey(sk, flags, BPFPROG_TS_REQUESTOR);
 	if (ret)
 		return ret;
 
+	if (flags & SOF_TIMESTAMPING_RX_SOFTWARE)
+		sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
+
 	WRITE_ONCE(sk->sk_tsflags[BPFPROG_TS_REQUESTOR], flags);
+
 	static_branch_enable(&bpf_tstamp_control);
 
 	return 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d37e231b2737..0891b41bc745 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2260,14 +2260,25 @@  static int tcp_zerocopy_receive(struct sock *sk,
 }
 #endif
 
+static void tcp_bpf_recv_timestamp(struct sock *sk, struct scm_timestamping_internal *tss)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG))
+		return;
+}
+
 /* Similar to __sock_recv_timestamp, but does not require an skb */
-void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			struct scm_timestamping_internal *tss)
 {
 	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
 	u32 tsflags = READ_ONCE(sk->sk_tsflags[SOCKETOPT_TS_REQUESTOR]);
 	bool has_timestamping = false;
 
+	if (static_branch_unlikely(&bpf_tstamp_control))
+		tcp_bpf_recv_timestamp(sk, tss);
+
 	if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
 		if (sock_flag(sk, SOCK_RCVTSTAMP)) {
 			if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index fc9b94de19f2..331e3e6f1ed5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6902,8 +6902,11 @@  enum {
 	/* Call bpf when the kernel is generating tx timestamps.
 	 */
 	BPF_SOCK_OPS_TX_TIMESTAMPING_OPT_CB_FLAG = (1<<7),
+	/* Call bpf when the kernel is generating rx timestamps.
+	 */
+	BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG = (1<<8),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xFF,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x1FF,
 };
 
 /* List of known BPF sock_ops operators.