sdma_get_descq_cnt(9)
π sdma_get_descq_cnt β kernel API manual, bestie edition π
okay so real talk, you opened the manpage for sdma_get_descq_cnt and it's a kernel API manual situation β section 9, the whole vibe. come sit with me, this one's short and sweet and we're gonna slay it π
β¨ NAME β¨
sdma_get_descq_cnt β literally the function that gets called when the device gets probed. that's it, that's the whole name section π«Ά
πΈ SYNOPSIS πΈ
u16 sdma_get_descq_cnt (void );
look at her. returns a u16, takes nothing. iconic behavior honestly π
π¦ ARGUMENTS π¦
voidβ no arguments. zero. nada. she doesn't want anything from you, she's lowkey self-sufficient π
π DESCRIPTION π
so what does she actually do? she returns a validated descq count β¨ that's the whole flex.
rn she's currently only used in the verbs initialization, specifically to build the tx list β so like, that's her one job and she's doing it π
β οΈ heads up bestie: this will probably be deleted in favor of a more scalable approach to alloc tx's. so don't get too attached, she's giving limited-edition energy π
π₯ SEE ALSO π₯
the kernel file lives at ./drivers/infiniband/hw/hfi1/sdma.c and here's the whole friend group, no cap, all of them:
sdma_state_name(9)sdma_engine_get_vl(9)sdma_select_engine_vl(9)sdma_select_engine_sc(9)sdma_seqfile_dump_cpu_list(9)sdma_map_init(9)sdma_clean(9)sdma_init(9)sdma_all_running(9)sdma_start(9)sdma_exit(9)__sdma_txclean(9)sdma_engine_error(9)sdma_seqfile_dump_sde(9)sdma_send_txreq(9)sdma_send_txlist(9)sdma_ahg_alloc(9)sdma_ahg_free(9)_sdma_engine_progress_schedule(9)
and that's the page! π§ this one came from ./drivers/infiniband/hw/hfi1, dated October 2026, and it's sdma_get_descq_cnt(9) β go forth and build that tx list, bestie, you got this fr fr πβ
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