svc_rdma_reply_done(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

✨ svc_rdma_reply_done(9) ✨

okay bestie, welcome to the Kernel API Manual πŸ’– this one's a lil function called svc_rdma_reply_done and honestly? it's giving "i do one thing and i do it correctly." periodt.


🌸 NAME 🌸

svc_rdma_reply_done β€” the Reply chunk Write completion handler 🫢

⭐ SYNOPSIS ⭐

void svc_rdma_reply_done (struct ib_cq *cq , struct ib_wc *wc );

like, that's it. that's the whole signature. no cap. πŸ”₯

πŸŽ€ ARGUMENTS πŸŽ€

  • cq β€” the controlling Completion Queue πŸ‘‘ she's the boss of this whole operation
  • wc β€” the Work Completion report πŸ¦‹ the receipts, basically

πŸ’… DESCRIPTION πŸ’…

so here's the tea β˜• and it's a short one: pages under I/O are released by a subsequent Send completion.

that's the entire plot, bestie. the I/O pages don't get freed here β€” they get freed later, when that Send completion comes through. lowkey iconic how the whole function is one sentence of vibes. 😭

ngl this is one of those pages where the description is doing the absolute least, but we respect it β€” every single word of it is load-bearing πŸ’œ

🌈 SEE ALSO 🌈

okay this list is long long, so buckle up 🧚✨

twenty-two references and a kernel file, we ate that πŸ’…πŸ“


this lil page lives in ./net/sunrpc/xprtrdma, dated October 2026, and it's page svc_rdma_reply_done(9) of the manual β€” mwah, bye bestie, go read a Send completion next πŸ’–βœ¨πŸŽ€

πŸ“¦ where this page comes from