rvt_dereg_clean_qp_cb(9)

🌸 NAME 🌸

Bestie, this is rvt_dereg_clean_qp_cb(9) from the Kernel API Manual — callback from iterator. That's the whole vibe: callback situation, very main character. 💅

✨ SYNOPSIS ✨

void rvt_dereg_clean_qp_cb (struct rvt_qp *qp , u64 v );

🎀 ARGUMENTS 🎀

• qp — the qp. Literally the qp. 💖
• v — the mregion (as u64). It's giving mregion-in-a-u64 realness. ✨

🦋 DESCRIPTION 🦋

Okay so this routine fields the callback for all QPs, and for QPs in the same PD as the MR it will call rvt_qp_mr_clean to potentially cleanup references. That's the assignment, and it ate. 🔥

It says potentially, bestie — that word is load-bearing. 💅

🌈 SEE ALSO 🌈

Kernel file ./drivers/infiniband/sw/rdmavt/mr.c — the whole squad lives there. 👑

• rvt_driver_mr_init(9)
• rvt_mr_exit(9)
• rvt_alloc_lkey(9)
• rvt_free_lkey(9)
• rvt_get_dma_mr(9)
• rvt_reg_user_mr(9)
• rvt_dereg_clean_qps(9)
• rvt_check_refs(9)
• rvt_mr_has_lkey(9)
• rvt_ss_has_lkey(9)
• rvt_dereg_mr(9)
• rvt_alloc_mr(9)
• rvt_set_page(9)
• rvt_map_mr_sg(9)
• rvt_fast_reg_mr(9)
• rvt_invalidate_rkey(9)
• rvt_sge_adjacent(9)
• rvt_lkey_ok(9)
• rvt_rkey_ok(9)

Signed off with so much love from the source/version ./drivers/infiniband/sw/rdmavt, dated October 2026, for rvt_dereg_clean_qp_cb(9). Periodt. 🫶💖