xe_sriov_pac...write_single(9)
π xe_sriov_pac...write_single(9) π
okay bestie, so this is a page straight out of the Kernel API Manual for xe_sriov_pac...write_single(9) β and yes the title is truncated with ... in the header, that's just how the man page renders it, we don't question the man page's choices π
β¨ NAME β¨
xe_sriov_packet_write_single β writes migration data into a single packet. one packet. that's it. that's the whole job π
πΈ SYNOPSIS πΈ
ssize_t xe_sriov_packet_write_single (struct xe_device *xe , unsigned
int vfid , const char __user *buf , size_t len );
ngl the line wrapping in the original is doing the absolute most, but we keep it exactly like that because facts are facts, periodt π«Ά
π¦ ARGUMENTS π¦
xeβ thexe_device. your main character struct, the whole reason we're here πvfidβ the VF identifier. which virtual function we're talking to, iykyk β¨bufβ start address of the userspace buffer. where the data lives on the user side πlenβ the requested write size from userspace. how much they're asking us to write, bestie πΈ
β RETURN β
the number of bytes that have been successfully written π and -errno on failure π
so likeβ¦ check your return value, okay? positive = slay, negative = something went sideways π
π SEE ALSO π
- Kernel file
./drivers/gpu/drm/xe/xe_sriov_packet.cβ the actual source, go read it, it's giving lore π xe_sriov_packet_alloc(9)xe_sriov_packet_free(9)xe_sriov_packet_init(9)xe_sriov_packet_init_from_hdr(9)xe_sriov_packet_read_single(9)β the read twin, the sibling energy is real πxe_sriov_packet_process_descriptor(9)xe_sriov_packet_save_init(9)
okay that's the whole page, no notes π
this all lives over in ./drivers/gpu/drm/xe, and the version stamp says October 2026 β so like, a little future-coded, we love that for us π¦β¨ bye bestie, go write some packets π«Άπ
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms