xsk_tx_metadata_request(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

✨ xsk_tx_metadata_request(9) ✨

okay so bestie, welcome to the kernel API manual (yes, the real one, xsk_tx_metadata_request(9)) β€” this page is short but it absolutely ate πŸ’…

🌸 NAME 🌸

xsk_tx_metadata_request β€” literally the function that evaluates AF_XDP TX metadata at submission and then calls the appropriate xsk_tx_metadata_ops operation. no cap, that's the whole gig πŸŽ€

πŸ¦‹ SYNOPSIS πŸ¦‹

void xsk_tx_metadata_request (const struct xsk_buff_pool *pool , struct
xsk_tx_metadata **pmeta , const struct xsk_tx_metadata_ops *ops , void
*priv );

πŸ’– ARGUMENTS πŸ’–

  • pool β€” pointer to the AF_XDP buffer pool. it's used to validate the metadata, so like… it's the vibe check for your metadata βœ…
  • pmeta β€” pointer to a pointer to the AF_XDP metadata area πŸ‘€ double pointer energy, she's iconic
  • ops β€” pointer to struct xsk_tx_metadata_ops
  • priv β€” pointer to the driver-private area πŸ™ˆ that's where the driver keeps its lil secrets

⭐ DESCRIPTION ⭐

so the networking device should call this function when it's preparing an AF_XDP egress packet. that's it. that's the assignment. main character behaviour honestly πŸ‘‘

ngl, the "should be called" here is real β€” the device is the one that's supposed to hit this up when it's getting an egress packet ready 🫢

🌈 SEE ALSO 🌈


and that's the whole page bestie, go forth and validate that metadata πŸ’œβœ¨πŸŽ€

sign-off fr fr: this one lives in ./include/net, dated October 2026 β€” shoutout to the kernel API manual for keeping us fed πŸ§šβ€β™€οΈπŸ“

πŸ“¦ where this page comes from