diff mbox series

[bpf-next,v8,05/12] net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING

Message ID 20250204183024.87508-6-kerneljasonxing@gmail.com (mailing list archive)
State New
Delegated to: BPF
Headers show
Series net-timestamp: bpf extension to equip applications transparently | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-11 success Logs for aarch64-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-18 success Logs for s390x-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-19 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-gcc / veristat-kernel / x86_64-gcc veristat_kernel
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-gcc / veristat-meta / x86_64-gcc veristat_meta
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-17 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-17 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-43 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-44 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-45 success Logs for x86_64-llvm-18 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-46 success Logs for x86_64-llvm-18 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-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: 42 this patch: 42
netdev/build_tools success Errors and warnings before: 26 (+1) this patch: 26 (+1)
netdev/cc_maintainers warning 1 maintainers not CCed: ncardwell@google.com
netdev/build_clang success Errors and warnings before: 7660 this patch: 7660
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: 4969 this patch: 4969
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 185 this patch: 185
netdev/source_inline success Was 0 now: 0

Commit Message

Jason Xing Feb. 4, 2025, 6:30 p.m. UTC 
No functional changes here, only add skb_enable_app_tstamp() to test
if the orig_skb matches the usage of application SO_TIMESTAMPING
or its bpf extension. And it's good to support two modes in
parallel later in this series.

Also, this patch deliberately distinguish the software and
hardware SCM_TSTAMP_SND timestamp by passing 'sw' parameter in order
to avoid such a case where hardware may go wrong and pass a NULL
hwstamps, which is even though unlikely to happen. If it really
happens, bpf prog will finally consider it as a software timestamp.
It will be hardly recognized. Let's make the timestamping part
more robust.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
---
 include/linux/skbuff.h | 13 +++++++------
 net/core/dev.c         |  2 +-
 net/core/skbuff.c      | 32 ++++++++++++++++++++++++++++++--
 net/ipv4/tcp_input.c   |  3 ++-
 4 files changed, 40 insertions(+), 10 deletions(-)

Comments

Jakub Kicinski Feb. 5, 2025, 1:47 a.m. UTC | #1 
On Wed,  5 Feb 2025 02:30:17 +0800 Jason Xing wrote:
> @@ -4565,7 +4566,7 @@ static inline void skb_tx_timestamp(struct sk_buff *skb)
>  {
>  	skb_clone_tx_timestamp(skb);
>  	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
> -		skb_tstamp_tx(skb, NULL);
> +		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SND);
>  }

Please move skb_tx_timestamp() to net/core/timestamping.c
You can make skb_clone_tx_timestamp() static, this is its only caller.
This way on balance we won't be adding any non-inlined calls,
and we don't have to drag the linux/errqueue.h include into skbuff.h
Jakub Kicinski Feb. 5, 2025, 1:50 a.m. UTC | #2 
On Wed,  5 Feb 2025 02:30:17 +0800 Jason Xing wrote:
>  void __skb_tstamp_tx(struct sk_buff *orig_skb,
>  		     const struct sk_buff *ack_skb,
>  		     struct skb_shared_hwtstamps *hwtstamps,
> -		     struct sock *sk, int tstype)
> +		     struct sock *sk, bool sw, int tstype)
>  {
>  	struct sk_buff *skb;
>  	bool tsonly, opt_stats = false;
> @@ -5551,6 +5576,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
>  	if (!sk)
>  		return;
>  
> +	if (!skb_enable_app_tstamp(orig_skb, tstype, sw))

maybe keep the order of @tstype vs @sw consistent?
Jason Xing Feb. 5, 2025, 2:40 a.m. UTC | #3 
On Wed, Feb 5, 2025 at 9:47 AM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Wed,  5 Feb 2025 02:30:17 +0800 Jason Xing wrote:
> > @@ -4565,7 +4566,7 @@ static inline void skb_tx_timestamp(struct sk_buff *skb)
> >  {
> >       skb_clone_tx_timestamp(skb);
> >       if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
> > -             skb_tstamp_tx(skb, NULL);
> > +             __skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SND);
> >  }
>
> Please move skb_tx_timestamp() to net/core/timestamping.c
> You can make skb_clone_tx_timestamp() static, this is its only caller.

I just tested it and it works after reading your message.

I wonder if we need a separate cleanup after this series about moving
this kind of functions into net/core/timestamping.c, say,
__skb_tstamp_tx()?

Thanks,
Jason

> This way on balance we won't be adding any non-inlined calls,
> and we don't have to drag the linux/errqueue.h include into skbuff.h
Jakub Kicinski Feb. 5, 2025, 3:14 a.m. UTC | #4 
On Wed, 5 Feb 2025 10:40:42 +0800 Jason Xing wrote:
> I wonder if we need a separate cleanup after this series about moving
> this kind of functions into net/core/timestamping.c, say,
> __skb_tstamp_tx()?

IMHO no need to go too far, just move the one function as part of this
series. The only motivation is to avoid adding includes to
linux/skbuff.h since skbuff.h is included in something like 8k objects.
Jason Xing Feb. 5, 2025, 3:23 a.m. UTC | #5 
On Wed, Feb 5, 2025 at 11:14 AM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Wed, 5 Feb 2025 10:40:42 +0800 Jason Xing wrote:
> > I wonder if we need a separate cleanup after this series about moving
> > this kind of functions into net/core/timestamping.c, say,
> > __skb_tstamp_tx()?
>
> IMHO no need to go too far, just move the one function as part of this
> series. The only motivation is to avoid adding includes to
> linux/skbuff.h since skbuff.h is included in something like 8k objects.

Thanks for clarifying. Will do it in the re-spin.

Thanks,
Jason
Willem de Bruijn Feb. 5, 2025, 3:34 p.m. UTC | #6 
Jason Xing wrote:
> No functional changes here, only add skb_enable_app_tstamp() to test
> if the orig_skb matches the usage of application SO_TIMESTAMPING
> or its bpf extension. And it's good to support two modes in
> parallel later in this series.
> 
> Also, this patch deliberately distinguish the software and
> hardware SCM_TSTAMP_SND timestamp by passing 'sw' parameter in order
> to avoid such a case where hardware may go wrong and pass a NULL
> hwstamps, which is even though unlikely to happen. If it really
> happens, bpf prog will finally consider it as a software timestamp.
> It will be hardly recognized. Let's make the timestamping part
> more robust.

Disagree. Don't add a crutch that has not shown to be necessary for
all this time.

Just infer hw from hwtstamps != NULL.
 
> Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
> ---
>  include/linux/skbuff.h | 13 +++++++------
>  net/core/dev.c         |  2 +-
>  net/core/skbuff.c      | 32 ++++++++++++++++++++++++++++++--
>  net/ipv4/tcp_input.c   |  3 ++-
>  4 files changed, 40 insertions(+), 10 deletions(-)
> 
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index bb2b751d274a..dfc419281cc9 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -39,6 +39,7 @@
>  #include <net/net_debug.h>
>  #include <net/dropreason-core.h>
>  #include <net/netmem.h>
> +#include <uapi/linux/errqueue.h>
>  
>  /**
>   * DOC: skb checksums
> @@ -4533,18 +4534,18 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
>  
>  void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb,
>  		     struct skb_shared_hwtstamps *hwtstamps,
> -		     struct sock *sk, int tstype);
> +		     struct sock *sk, bool sw, int tstype);
>  
>  /**
> - * skb_tstamp_tx - queue clone of skb with send time stamps
> + * skb_tstamp_tx - queue clone of skb with send HARDWARE timestamps

Unfortunately this cannot be modified to skb_tstamp_tx_hw, as that
would require updating way too many callers.

>   * @orig_skb:	the original outgoing packet
>   * @hwtstamps:	hardware time stamps, may be NULL if not available
>   *
>   * If the skb has a socket associated, then this function clones the
>   * skb (thus sharing the actual data and optional structures), stores
> - * the optional hardware time stamping information (if non NULL) or
> - * generates a software time stamp (otherwise), then queues the clone
> - * to the error queue of the socket.  Errors are silently ignored.
> + * the optional hardware time stamping information (if non NULL) then
> + * queues the clone to the error queue of the socket.  Errors are
> + * silently ignored.
>   */
>  void skb_tstamp_tx(struct sk_buff *orig_skb,
>  		   struct skb_shared_hwtstamps *hwtstamps);
> @@ -4565,7 +4566,7 @@ static inline void skb_tx_timestamp(struct sk_buff *skb)
>  {
>  	skb_clone_tx_timestamp(skb);
>  	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
> -		skb_tstamp_tx(skb, NULL);
> +		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SND);

If a separate version for software timestamps were needed, I'd suggest
adding a skb_tstamp_tx_sw() wrapper. But see first comment.

>  }
>  
>  /**
> diff --git a/net/core/dev.c b/net/core/dev.c
> index afa2282f2604..d77b8389753e 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -4501,7 +4501,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
>  	skb_assert_len(skb);
>  
>  	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
> -		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
> +		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SCHED);
>  
>  	/* Disable soft irqs for various locks below. Also
>  	 * stops preemption for RCU.
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index a441613a1e6c..6042961dfc02 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -5539,10 +5539,35 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
>  }
>  EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
>  
> +static bool skb_enable_app_tstamp(struct sk_buff *skb, int tstype, bool sw)

app is a bit vague. I suggest

skb_tstamp_tx_report_so_timestamping

and

skb_tstamp_tx_report_bpf_timestamping

> +{
> +	int flag;
> +
> +	switch (tstype) {
> +	case SCM_TSTAMP_SCHED:
> +		flag = SKBTX_SCHED_TSTAMP;
> +		break;

Please just have a one line statements in the case directly:

    case SCM_TSTAMP_SCHED:
        return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
    case SCM_TSTAMP_SND:
        return skb_shinfo(skb)->tx_flags & (sw ? SKBTX_SW_TSTAMP :
                                                 SKBTX_HW_TSTAMP);
    case SCM_TSTAMP_ACK:
        return TCP_SKB_CB(skb)->txstamp_ack;

> +	case SCM_TSTAMP_SND:
> +		flag = sw ? SKBTX_SW_TSTAMP : SKBTX_HW_TSTAMP;
> +		break;
> +	case SCM_TSTAMP_ACK:
> +		if (TCP_SKB_CB(skb)->txstamp_ack)
> +			return true;
> +		fallthrough;
> +	default:
> +		return false;
> +	}
> +
> +	if (skb_shinfo(skb)->tx_flags & flag)
> +		return true;
> +
> +	return false;
> +}
> +
>  void __skb_tstamp_tx(struct sk_buff *orig_skb,
>  		     const struct sk_buff *ack_skb,
>  		     struct skb_shared_hwtstamps *hwtstamps,
> -		     struct sock *sk, int tstype)
> +		     struct sock *sk, bool sw, int tstype)
>  {
>  	struct sk_buff *skb;
>  	bool tsonly, opt_stats = false;
> @@ -5551,6 +5576,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
>  	if (!sk)
>  		return;
>  
> +	if (!skb_enable_app_tstamp(orig_skb, tstype, sw))
> +		return;
> +
>  	tsflags = READ_ONCE(sk->sk_tsflags);
>  	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
>  	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
> @@ -5599,7 +5627,7 @@ EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
>  void skb_tstamp_tx(struct sk_buff *orig_skb,
>  		   struct skb_shared_hwtstamps *hwtstamps)
>  {
> -	return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk,
> +	return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, false,
>  			       SCM_TSTAMP_SND);
>  }
>  EXPORT_SYMBOL_GPL(skb_tstamp_tx);
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index 77185479ed5e..62252702929d 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -3330,7 +3330,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
>  	if (!before(shinfo->tskey, prior_snd_una) &&
>  	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
>  		tcp_skb_tsorted_save(skb) {
> -			__skb_tstamp_tx(skb, ack_skb, NULL, sk, SCM_TSTAMP_ACK);
> +			__skb_tstamp_tx(skb, ack_skb, NULL, sk, true,
> +					SCM_TSTAMP_ACK);
>  		} tcp_skb_tsorted_restore(skb);
>  	}
>  }
> -- 
> 2.43.5
>
Jason Xing Feb. 5, 2025, 3:52 p.m. UTC | #7 
On Wed, Feb 5, 2025 at 11:34 PM Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
>
> Jason Xing wrote:
> > No functional changes here, only add skb_enable_app_tstamp() to test
> > if the orig_skb matches the usage of application SO_TIMESTAMPING
> > or its bpf extension. And it's good to support two modes in
> > parallel later in this series.
> >
> > Also, this patch deliberately distinguish the software and
> > hardware SCM_TSTAMP_SND timestamp by passing 'sw' parameter in order
> > to avoid such a case where hardware may go wrong and pass a NULL
> > hwstamps, which is even though unlikely to happen. If it really
> > happens, bpf prog will finally consider it as a software timestamp.
> > It will be hardly recognized. Let's make the timestamping part
> > more robust.
>
> Disagree. Don't add a crutch that has not shown to be necessary for
> all this time.
>
> Just infer hw from hwtstamps != NULL.
>
> > Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
> > ---
> >  include/linux/skbuff.h | 13 +++++++------
> >  net/core/dev.c         |  2 +-
> >  net/core/skbuff.c      | 32 ++++++++++++++++++++++++++++++--
> >  net/ipv4/tcp_input.c   |  3 ++-
> >  4 files changed, 40 insertions(+), 10 deletions(-)
> >
> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> > index bb2b751d274a..dfc419281cc9 100644
> > --- a/include/linux/skbuff.h
> > +++ b/include/linux/skbuff.h
> > @@ -39,6 +39,7 @@
> >  #include <net/net_debug.h>
> >  #include <net/dropreason-core.h>
> >  #include <net/netmem.h>
> > +#include <uapi/linux/errqueue.h>
> >
> >  /**
> >   * DOC: skb checksums
> > @@ -4533,18 +4534,18 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
> >
> >  void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb,
> >                    struct skb_shared_hwtstamps *hwtstamps,
> > -                  struct sock *sk, int tstype);
> > +                  struct sock *sk, bool sw, int tstype);
> >
> >  /**
> > - * skb_tstamp_tx - queue clone of skb with send time stamps
> > + * skb_tstamp_tx - queue clone of skb with send HARDWARE timestamps
>
> Unfortunately this cannot be modified to skb_tstamp_tx_hw, as that
> would require updating way too many callers.
>
> >   * @orig_skb:        the original outgoing packet
> >   * @hwtstamps:       hardware time stamps, may be NULL if not available
> >   *
> >   * If the skb has a socket associated, then this function clones the
> >   * skb (thus sharing the actual data and optional structures), stores
> > - * the optional hardware time stamping information (if non NULL) or
> > - * generates a software time stamp (otherwise), then queues the clone
> > - * to the error queue of the socket.  Errors are silently ignored.
> > + * the optional hardware time stamping information (if non NULL) then
> > + * queues the clone to the error queue of the socket.  Errors are
> > + * silently ignored.
> >   */
> >  void skb_tstamp_tx(struct sk_buff *orig_skb,
> >                  struct skb_shared_hwtstamps *hwtstamps);
> > @@ -4565,7 +4566,7 @@ static inline void skb_tx_timestamp(struct sk_buff *skb)
> >  {
> >       skb_clone_tx_timestamp(skb);
> >       if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
> > -             skb_tstamp_tx(skb, NULL);
> > +             __skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SND);
>
> If a separate version for software timestamps were needed, I'd suggest
> adding a skb_tstamp_tx_sw() wrapper. But see first comment.
>
> >  }
> >
> >  /**
> > diff --git a/net/core/dev.c b/net/core/dev.c
> > index afa2282f2604..d77b8389753e 100644
> > --- a/net/core/dev.c
> > +++ b/net/core/dev.c
> > @@ -4501,7 +4501,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
> >       skb_assert_len(skb);
> >
> >       if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
> > -             __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
> > +             __skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SCHED);
> >
> >       /* Disable soft irqs for various locks below. Also
> >        * stops preemption for RCU.
> > diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> > index a441613a1e6c..6042961dfc02 100644
> > --- a/net/core/skbuff.c
> > +++ b/net/core/skbuff.c
> > @@ -5539,10 +5539,35 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
> >  }
> >  EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
> >
> > +static bool skb_enable_app_tstamp(struct sk_buff *skb, int tstype, bool sw)
>
> app is a bit vague. I suggest
>
> skb_tstamp_tx_report_so_timestamping
>
> and
>
> skb_tstamp_tx_report_bpf_timestamping

Good name. I like them.

>
> > +{
> > +     int flag;
> > +
> > +     switch (tstype) {
> > +     case SCM_TSTAMP_SCHED:
> > +             flag = SKBTX_SCHED_TSTAMP;
> > +             break;
>
> Please just have a one line statements in the case directly:
>
>     case SCM_TSTAMP_SCHED:
>         return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
>     case SCM_TSTAMP_SND:
>         return skb_shinfo(skb)->tx_flags & (sw ? SKBTX_SW_TSTAMP :
>                                                  SKBTX_HW_TSTAMP);
>     case SCM_TSTAMP_ACK:
>         return TCP_SKB_CB(skb)->txstamp_ack;
>

Thanks for the re-arrangement!

> > +     case SCM_TSTAMP_SND:
> > +             flag = sw ? SKBTX_SW_TSTAMP : SKBTX_HW_TSTAMP;
> > +             break;
> > +     case SCM_TSTAMP_ACK:
> > +             if (TCP_SKB_CB(skb)->txstamp_ack)
> > +                     return true;
> > +             fallthrough;
> > +     default:
> > +             return false;
> > +     }
> > +
> > +     if (skb_shinfo(skb)->tx_flags & flag)
> > +             return true;
> > +
> > +     return false;
> > +}
> > +
> >  void __skb_tstamp_tx(struct sk_buff *orig_skb,
> >                    const struct sk_buff *ack_skb,
> >                    struct skb_shared_hwtstamps *hwtstamps,
> > -                  struct sock *sk, int tstype)
> > +                  struct sock *sk, bool sw, int tstype)
> >  {
> >       struct sk_buff *skb;
> >       bool tsonly, opt_stats = false;
> > @@ -5551,6 +5576,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
> >       if (!sk)
> >               return;
> >
> > +     if (!skb_enable_app_tstamp(orig_skb, tstype, sw))
> > +             return;
> > +
> >       tsflags = READ_ONCE(sk->sk_tsflags);
> >       if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
> >           skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
> > @@ -5599,7 +5627,7 @@ EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
> >  void skb_tstamp_tx(struct sk_buff *orig_skb,
> >                  struct skb_shared_hwtstamps *hwtstamps)
> >  {
> > -     return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk,
> > +     return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, false,
> >                              SCM_TSTAMP_SND);
> >  }
> >  EXPORT_SYMBOL_GPL(skb_tstamp_tx);
> > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> > index 77185479ed5e..62252702929d 100644
> > --- a/net/ipv4/tcp_input.c
> > +++ b/net/ipv4/tcp_input.c
> > @@ -3330,7 +3330,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
> >       if (!before(shinfo->tskey, prior_snd_una) &&
> >           before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
> >               tcp_skb_tsorted_save(skb) {
> > -                     __skb_tstamp_tx(skb, ack_skb, NULL, sk, SCM_TSTAMP_ACK);
> > +                     __skb_tstamp_tx(skb, ack_skb, NULL, sk, true,
> > +                                     SCM_TSTAMP_ACK);
> >               } tcp_skb_tsorted_restore(skb);
> >       }
> >  }
> > --
> > 2.43.5
> >
>
>
diff mbox series

Patch

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb2b751d274a..dfc419281cc9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -39,6 +39,7 @@ 
 #include <net/net_debug.h>
 #include <net/dropreason-core.h>
 #include <net/netmem.h>
+#include <uapi/linux/errqueue.h>
 
 /**
  * DOC: skb checksums
@@ -4533,18 +4534,18 @@  void skb_complete_tx_timestamp(struct sk_buff *skb,
 
 void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
-		     struct sock *sk, int tstype);
+		     struct sock *sk, bool sw, int tstype);
 
 /**
- * skb_tstamp_tx - queue clone of skb with send time stamps
+ * skb_tstamp_tx - queue clone of skb with send HARDWARE timestamps
  * @orig_skb:	the original outgoing packet
  * @hwtstamps:	hardware time stamps, may be NULL if not available
  *
  * If the skb has a socket associated, then this function clones the
  * skb (thus sharing the actual data and optional structures), stores
- * the optional hardware time stamping information (if non NULL) or
- * generates a software time stamp (otherwise), then queues the clone
- * to the error queue of the socket.  Errors are silently ignored.
+ * the optional hardware time stamping information (if non NULL) then
+ * queues the clone to the error queue of the socket.  Errors are
+ * silently ignored.
  */
 void skb_tstamp_tx(struct sk_buff *orig_skb,
 		   struct skb_shared_hwtstamps *hwtstamps);
@@ -4565,7 +4566,7 @@  static inline void skb_tx_timestamp(struct sk_buff *skb)
 {
 	skb_clone_tx_timestamp(skb);
 	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
-		skb_tstamp_tx(skb, NULL);
+		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SND);
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index afa2282f2604..d77b8389753e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4501,7 +4501,7 @@  int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_assert_len(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
-		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
+		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, true, SCM_TSTAMP_SCHED);
 
 	/* Disable soft irqs for various locks below. Also
 	 * stops preemption for RCU.
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a441613a1e6c..6042961dfc02 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5539,10 +5539,35 @@  void skb_complete_tx_timestamp(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
+static bool skb_enable_app_tstamp(struct sk_buff *skb, int tstype, bool sw)
+{
+	int flag;
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		flag = SKBTX_SCHED_TSTAMP;
+		break;
+	case SCM_TSTAMP_SND:
+		flag = sw ? SKBTX_SW_TSTAMP : SKBTX_HW_TSTAMP;
+		break;
+	case SCM_TSTAMP_ACK:
+		if (TCP_SKB_CB(skb)->txstamp_ack)
+			return true;
+		fallthrough;
+	default:
+		return false;
+	}
+
+	if (skb_shinfo(skb)->tx_flags & flag)
+		return true;
+
+	return false;
+}
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     const struct sk_buff *ack_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
-		     struct sock *sk, int tstype)
+		     struct sock *sk, bool sw, int tstype)
 {
 	struct sk_buff *skb;
 	bool tsonly, opt_stats = false;
@@ -5551,6 +5576,9 @@  void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!sk)
 		return;
 
+	if (!skb_enable_app_tstamp(orig_skb, tstype, sw))
+		return;
+
 	tsflags = READ_ONCE(sk->sk_tsflags);
 	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
 	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
@@ -5599,7 +5627,7 @@  EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
 void skb_tstamp_tx(struct sk_buff *orig_skb,
 		   struct skb_shared_hwtstamps *hwtstamps)
 {
-	return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk,
+	return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, false,
 			       SCM_TSTAMP_SND);
 }
 EXPORT_SYMBOL_GPL(skb_tstamp_tx);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 77185479ed5e..62252702929d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3330,7 +3330,8 @@  static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 	if (!before(shinfo->tskey, prior_snd_una) &&
 	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
 		tcp_skb_tsorted_save(skb) {
-			__skb_tstamp_tx(skb, ack_skb, NULL, sk, SCM_TSTAMP_ACK);
+			__skb_tstamp_tx(skb, ack_skb, NULL, sk, true,
+					SCM_TSTAMP_ACK);
 		} tcp_skb_tsorted_restore(skb);
 	}
 }