Commit e6116fc6 authored by Willem de Bruijn's avatar Willem de Bruijn Committed by Jakub Kicinski
Browse files

net: skb: free up one bit in tx_flags 

The linked series wants to add skb tx completion timestamps.
That needs a bit in skb_shared_info.tx_flags, but all are in use.

A per-skb bit is only needed for features that are configured on a
per packet basis. Per socket features can be read from sk->sk_tsflags.

Per packet tsflags can be set in sendmsg using cmsg, but only those in
SOF_TIMESTAMPING_TX_RECORD_MASK.

Per packet tsflags can also be set without cmsg by sandwiching a
send inbetween two setsockopts:

    val |= SOF_TIMESTAMPING_$FEATURE;
    setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));
    write(fd, buf, sz);
    val &= ~SOF_TIMESTAMPING_$FEATURE;
    setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));

Changing a datapath test from skb_shinfo(skb)->tx_flags to
skb->sk->sk_tsflags can change behavior in that case, as the tx_flags
is written before the second setsockopt updates sk_tsflags.

Therefore, only bits can be reclaimed that cannot be set by cmsg and
are also highly unlikely to be used to target individual packets
otherwise.

Free up the bit currently used for SKBTX_HW_TSTAMP_USE_CYCLES. This
selects between clock and free running counter source for HW TX
timestamps. It is probable that all packets of the same socket will
always use the same source.

Link: https://lore.kernel.org/netdev/cover.1739988644.git.pav@iki.fi/


Signed-off-by: default avatarWillem de Bruijn <willemb@google.com>
Reviewed-by: default avatarJason Xing <kerneljasonxing@gmail.com>
Reviewed-by: default avatarGerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250225023416.2088705-1-willemdebruijn.kernel@gmail.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 80c4a001

drivers/net/ethernet/engleder/tsnep_main.c

+2 −2
Original line number Diff line number Diff line
@@ -852,8 +852,8 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) 
			struct skb_shared_hwtstamps hwtstamps;

			u64 timestamp;



			if (skb_shinfo(entry->skb)->tx_flags &

			    SKBTX_HW_TSTAMP_USE_CYCLES)

			if (entry->skb->sk &&

			    READ_ONCE(entry->skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)

				timestamp =

					__le64_to_cpu(entry->desc_wb->counter);

			else

drivers/net/ethernet/intel/igc/igc_main.c

+2 −1
Original line number Diff line number Diff line
@@ -1668,7 +1668,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, 
		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {

			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;

			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;

			if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES)

			if (skb->sk &&

			    READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)

				tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1;

		} else {

			adapter->tx_hwtstamp_skipped++;

include/linux/skbuff.h

+2 −3
Original line number Diff line number Diff line
@@ -478,8 +478,8 @@ enum { 
	/* device driver is going to provide hardware time stamp */

	SKBTX_IN_PROGRESS = 1 << 2,



	/* generate hardware time stamp based on cycles if supported */

	SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3,

	/* reserved */

	SKBTX_RESERVED = 1 << 3,



	/* generate wifi status information (where possible) */

	SKBTX_WIFI_STATUS = 1 << 4,
@@ -500,7 +500,6 @@ enum { 
				 SKBTX_SCHED_TSTAMP | \

				 SKBTX_BPF)

#define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \

				 SKBTX_HW_TSTAMP_USE_CYCLES | \

				 SKBTX_ANY_SW_TSTAMP)



/* Definitions for flags in struct skb_shared_info */

net/socket.c

+1 −10
Original line number Diff line number Diff line
@@ -680,18 +680,9 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags) 
{

	u8 flags = *tx_flags;



	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {

	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)

		flags |= SKBTX_HW_TSTAMP_NOBPF;



		/* PTP hardware clocks can provide a free running cycle counter

		 * as a time base for virtual clocks. Tell driver to use the

		 * free running cycle counter for timestamp if socket is bound

		 * to virtual clock.

		 */

		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)

			flags |= SKBTX_HW_TSTAMP_USE_CYCLES;

	}



	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)

		flags |= SKBTX_SW_TSTAMP;