cik_fence_gfx_ring_emit(9)
π cik_fence_gfx_ring_emit(9) β or, "how to drop a fence on the gfx ring", bestie edition π
okay so real talk, this one lives in the Kernel API Manual (section 9, kernel-flavoured, iykyk) and it's genuinely one little function with a big job. let's get into it β¨
πΈ NAME πΈ
cik_fence_gfx_ring_emit β emit a fence on the gfx ring. that's it, that's the whole vibe. it puts a fence out into the world π
β¨ SYNOPSIS β¨
void cik_fence_gfx_ring_emit (struct radeon_device *rdev , struct
radeon_fence *fence );
returns void, takes two pointers, zero drama. she's lowkey elegant π¦
π«Ά ARGUMENTS π«Ά
rdevβ aradeon_devicepointer. the whole device, the main character πfenceβ aradeon_fenceobject. the fence in question, the moment itself π
π₯ DESCRIPTION π₯
so what does she actually do? she emits a fence sequence number on the gfx ring, and then flushes the GPU caches. both. no cap, that's the whole job description and she ate πβ¨
like β fence goes out, caches get flushed, everyone moves on. iconic behaviour, honestly π
β SEE ALSO β
the source of truth, right here:
- Kernel file
./drivers/gpu/drm/radeon/cik.c
and the whole extended friend group, because this function does NOT exist in a vacuum bestie π:
cik_get_allowed_info_register(9)cik_get_xclk(9)cik_mm_rdoorbell(9)cik_mm_wdoorbell(9)cik_srbm_select(9)ci_mc_load_microcode(9)cik_init_microcode(9)cik_tiling_mode_table_init(9)cik_select_se_sh(9)cik_create_bitmask(9)cik_get_rb_disabled(9)cik_setup_rb(9)cik_gpu_init(9)cik_scratch_init(9)cik_ring_test(9)cik_hdp_flush_cp_ring_emit(9)cik_fence_compute_ring_emit(9)cik_semaphore_ring_emit(9)cik_copy_cpdma(9)cik_ring_ib_execute(9)cik_ib_test(9)cik_cp_gfx_enable(9)cik_cp_gfx_load_microcode(9)cik_cp_gfx_start(9)cik_cp_gfx_fini(9)cik_cp_gfx_resume(9)cik_cp_compute_enable(9)cik_cp_compute_load_microcode(9)cik_cp_compute_start(9)cik_cp_compute_fini(9)cik_cp_compute_resume(9)cik_gpu_check_soft_reset(9)cik_gpu_soft_reset(9)cik_asic_reset(9)cik_gfx_is_lockup(9)cik_mc_program(9)cik_mc_init(9)cik_pcie_gart_tlb_flush(9)cik_pcie_gart_enable(9)cik_pcie_gart_disable(9)cik_pcie_gart_fini(9)cik_ib_parse(9)cik_vm_init(9)cik_vm_fini(9)cik_vm_decode_fault(9)cik_rlc_stop(9)cik_rlc_start(9)cik_rlc_resume(9)cik_enable_interrupts(9)cik_disable_interrupts(9)cik_disable_interrupt_state(9)cik_irq_init(9)cik_irq_set(9)cik_irq_ack(9)cik_irq_disable(9)cik_irq_suspend(9)cik_irq_fini(9)cik_get_ih_wptr(9)cik_irq_process(9)cik_startup(9)cik_resume(9)cik_suspend(9)cik_init(9)cik_fini(9)dce8_line_buffer_adjust(9)cik_get_number_of_dram_channels(9)dce8_dram_bandwidth(9)dce8_dram_bandwidth_for_display(9)dce8_data_return_bandwidth(9)dce8_dmif_request_bandwidth(9)dce8_available_bandwidth(9)dce8_average_bandwidth(9)dce8_latency_watermark(9)dce8_average_bandwidth_vs_dram_bandwidth_for_display(9)dce8_average_bandwidth_vs_available_bandwidth(9)dce8_check_latency_hiding(9)dce8_program_watermarks(9)dce8_bandwidth_update(9)cik_get_gpu_clock_counter(9)
ok and one little footnote before you go β this page is served up from./drivers/gpu/drm/radeon, dated October 2026, and the man page itself signs off ascik_fence_gfx_ring_emit(9). that's the whole footer bestie, mwah ππ§
go forth and emit your fences, you're doing amazing π«ΆπΈ
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