idpf_chk_tso_segment(9)

๐Ÿ“ฆ version 7.3.1, in nixpkgs unstable

๐Ÿ’… idpf_chk_tso_segment(9) ๐Ÿ’…

okay so this is a page from the Kernel API Manual about idpf_chk_tso_segment(9) โ€” and bestie, it's lowkey the vibe check for TSO buffer counts. โœจ


๐ŸŒธ NAME ๐ŸŒธ

idpf_chk_tso_segment โ€” check that skb is not using too many buffers. No cap. ๐Ÿ’–

โœจ SYNOPSIS โœจ

bool idpf_chk_tso_segment (const struct sk_buff *skb , unsigned int
       max_bufs );

๐ŸŽ€ ARGUMENTS ๐ŸŽ€

  • skb โ€” the send buffer. That's the packet bestie we're checking. ๐Ÿฆ‹
  • max_bufs โ€” the maximum number of buffers. The limit, the boundary, the rules. ๐Ÿ’…

๐Ÿ”ฅ DESCRIPTION ๐Ÿ”ฅ

Okay so for TSO we need to count the TSO header and the segment payload separately. Because of that, we need to check cases where we have max_bufs-1 fragments or more, since we can potentially require max_bufs+1 DMA transactions: 1 for the TSO header, 1 for the segment payload in the first descriptor, and another max_buf-1 for the fragments. It's giving math, but make it packet math. ๐Ÿงฎโœจ

Returns true if the packet needs to be software segmented by core stack. Periodt. ๐Ÿ’ฏ

๐Ÿฆ‹ SEE ALSO ๐Ÿฆ‹

Kernel file: ./drivers/net/ethernet/intel/idpf/idpf_lib.c

The whole idpf bestie squad, all (9) pages, fr fr:

source/version vibes: ./drivers/net/ethernet/intel/idpf, October 2026, for idpf_chk_tso_segment(9) โ€” slay and goodnight! ๐ŸŽ€

๐Ÿ“ฆ where this page comes from