lookup_sign...y_partial_id(9)
π lookup_signaled_event_by_partial_id β from the Kernel API Manual, bestie
okay so this is a Kernel API Manual page and it's genuinely so useful, stay with me π«Ά
β¨ NAME β¨
lookup_signaled_event_by_partial_id β literally looks up a signaled event from a partial ID. that's the whole vibe π
πΈ SYNOPSIS πΈ
struct kfd_event * lookup_signaled_event_by_partial_id (struct
kfd_process *p , uint32_t id , uint32_t bits , bool
signal_mailbox_updated );
π ARGUMENTS π
pβ pointer tostruct kfd_process, the main character of this whole situation πidβ the ID we're out here looking up πbitsβ how many bits inidare actually valid, no capsignal_mailbox_updatedβ a flag that says whether the FW updates the signal mailbox entry, iykyk π¦
π DESCRIPTION π
so the way this works is: it finds the first signaled event that has a matching partial ID. slay. β¨
but if there's, like, no matching signaled event? it returns NULL. π and in that case the caller should assume the partial ID is invalid and go do an exhaustive search of all signaled events β like a full grid search, bestie, no shortcuts.
and here's the spicy part πΆοΈ: if multiple events with the same partial ID signal at the same time, they get found one interrupt at a time, and not necessarily in the same order the interrupts actually happened. it's giving chaos but it's fine. as long as the number of interrupts is correct, all signaled events will be seen by the driver. periodt. π
π₯ SEE ALSO π₯
- Kernel file
./drivers/gpu/drm/amd/amdkfd/kfd_events.cβ go read it, it ate π
and that's the page!! brought to you by ./drivers/gpu/drm/amd/amdkfd, dated October 2026 β mwah, go touch some kernel code bestie π§π
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