net: make dev_xdp_sb_prog_count() see programs attached through a link
Subsystems (3)
Jakub Kicinski
maintainerPATCH 1/1 net: make dev_xdp_sb_prog_count() see programs attached through a link
ethtool refuses to enable tcp-data-split on a device running a single-buffer XDP program (which can't deal with the payload landing in a separate buffer). dev_xdp_sb_prog_count() only looks at xdp_state[].prog though, ignoring bpf_link integration. Get the prog pointer from dev_xdp_prog(), which will consult both.
bpf_xdp_link_update() needs a bit of a touch-up, too, since ethtool calls dev_xdp_sb_prog_count() with just the instance lock (for ops-locked devices) - we now have to make sure the link updates happen under that lock.
Spotted by AI while reviewing the XDP propagation series, verified and tested on netdevsim with a C test along these lines:
link = bpf_program__attach_xdp(prog, ifindex);
system("ethtool -G eth0 tcp-data-split on")---
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
CC: [email protected]
--- net/core/dev.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
net/core/dev.c +7 -4
@@ -10367,13 +10367,15 @@ EXPORT_SYMBOL_GPL(dev_xdp_prog_count);u8 dev_xdp_sb_prog_count (struct net_device *dev) { +struct bpf_prog *prog;u8 count =0 ;int i; -for (i =0 ; i < __MAX_XDP_MODE; i++) -if (dev->xdp_state[i].prog && - !dev->xdp_state[i].prog->aux->xdp_has_frags) +for (i =0 ; i < __MAX_XDP_MODE; i++) { + prog =dev_xdp_prog (dev, i); +if (prog && !prog->aux->xdp_has_frags) count++; + }return count; }
@@ -10753,11 +10755,12 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, bpf_op =dev_xdp_bpf_op (xdp_link->dev, mode); err =dev_xdp_install (xdp_link->dev, mode, bpf_op,NULL , xdp_link->flags, new_prog); +if (!err) + old_prog =xchg (&link->prog, new_prog);netdev_unlock_ops (xdp_link->dev);if (err) goto out_unlock; - old_prog =xchg (&link->prog, new_prog);bpf_prog_put (old_prog); out_unlock:
Signature · 1 line
2.55.0
Quoted 11 lines · Jakub Kicinski
ethtool refuses to enable tcp-data-split on a device running a single-buffer XDP program (which can't deal with the payload landing in a separate buffer).
dev_xdp_sb_prog_count()only looks at xdp_state[].prog though, ignoringbpf_linkintegration. Get the prog pointer fromdev_xdp_prog(), which will consult both.
bpf_xdp_link_update()needs a bit of a touch-up, too, since ethtool callsdev_xdp_sb_prog_count()with just the instance lock (for ops-locked devices) - we now have to make sure the link updates happen under that lock.
Quoted 8 lines
Spotted by AI while reviewing the XDP propagation series, verified and tested on netdevsim with a C test along these lines:
link = bpf_program__attach_xdp(prog, ifindex); system("ethtool -G eth0 tcp-data-split on")Fixes 197258f0ef68 ("net: ethtool: add hds_config member in ethtool_netdev_state")Signed-off-by Jakub Kicinski <[email protected]>
This patch was applied to netdev/net.git (main) by Jakub Kicinski <[email protected]>:
Hello:
This patch was applied to netdev/net.git (main)
by Jakub Kicinski <[email protected]>:
Quoted 6 lines · On Wed, 30 Sep 2026 18:25:59 -0700 you wrote:
ethtool refuses to enable tcp-data-split on a device running a single-buffer XDP program (which can't deal with the payload landing in a separate buffer).
dev_xdp_sb_prog_count()only looks at xdp_state[].prog though, ignoringbpf_linkintegration. Get the prog pointer fromdev_xdp_prog(), which will consult both.
Quoted 6 lines
bpf_xdp_link_update()needs a bit of a touch-up, too, since ethtool callsdev_xdp_sb_prog_count()with just the instance lock (for ops-locked devices) - we now have to make sure the link updates happen under that lock.[...]
Here is the summary with links:
- [net] net: make dev_xdp_sb_prog_count() see programs attached through a link
https://git.kernel.org/netdev/net/c/d333c8bca6dc
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html