hfi1_rcd_eoi_intr(9)
okay so this is the hfi1_rcd_eoi_intr(9) page from the Kernel API Manual, and weβre about to make interrupt cleanup make sense, bestie π
β¨ NAME β¨
hfi1_rcd_eoi_intr β End of Interrupt processing action π
π¦ SYNOPSIS π¦
void hfi1_rcd_eoi_intr (struct hfi1_ctxtdata *rcd );
π ARGUMENTS π
rcdβ Ptr tohfi1_ctxtdataof receive context π
πΈ DESCRIPTION πΈ
So the move here is: hold IRQs so we can safely clear the interrupt and recheck for a packet that may have arrived after the previous check and the interrupt clear. No cap, that recheck is the whole point π«Ά
If a packet arrived, force another interrupt. Periodt π₯
This routine can be called at the end of receive packet processing in interrupt service routines, interrupt service thread and softirqs β¨
π SEE ALSO π
Kernel file:
./drivers/infiniband/hw/hfi1/chip.c
And the whole friend group π―ββοΈ:
hfi1_addr_from_offset(9)read_csr(9)write_csr(9)get_csr_addr(9)update_xmit_counters(9)apply_link_downgrade_policy(9)is_rcv_avail_int(9)is_rcv_urgent_int(9)general_interrupt(9)hfi1_netdev_rx_napi(9)data_vls_operational(9)encode_rcv_header_entry_size(9)hfi1_validate_rcvhdrcnt(9)set_hdrq_regs(9)update_statusp(9)wait_logical_linkstate(9)read_mod_write(9)set_intr_bits(9)set_up_interrupts(9)hfi1_get_qp_map(9)init_qpmap_table(9)init_qos(9)hfi1_init_dd(9)create_pbc(9)
Thatβs the whole vibe check, bestie π«Ά the source/version footer lands at ./drivers/infiniband/hw/hfi1, and this edition is dated October 2026. Slay and happy interrupt processing π
β¨
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