MCBP (INT)(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸŽ€ mcbp (int) πŸŽ€

okay so we're in the Kernel API Manual bestie, and this little cutie is called mcbp (int) πŸ’… it's a kernel parameter and honestly it's giving "small but powerful main character energy" ✨

🌸 what it does 🌸

It is used to enable mid command buffer preemption. 🫢

The values are literally:

  • 0 = disabled πŸ’€
  • 1 = enabled πŸ”₯
  • -1 auto (default) πŸ‘‘

so yes, default is -1, and yes, it's auto, she's mysterious like that 🧚 no cap.

it lives in the kernel file ./drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c β€” that's the address, bestie, don't lose it πŸŽ€

πŸ‘€ SEE ALSO πŸ‘€

okay the SEE ALSO list is long, like long long, but every single one of these is iconic in her own way, so we're listing them all, periodt πŸ’–

  • vramlimit (int)(9) πŸ¦‹
  • vis_vramlimit (int)(9) πŸ¦‹
  • gartsize (uint)(9) πŸ¦‹
  • gttsize (int)(9) πŸ¦‹
  • moverate (int)(9) πŸ¦‹
  • audio (int)(9) πŸ¦‹
  • disp_priority (int)(9) πŸ¦‹
  • hw_i2c (int)(9) πŸ¦‹
  • pcie_gen2 (int)(9) πŸ¦‹
  • msi (int)(9) πŸ¦‹
  • svm_default_granularity (uint)(9) πŸ¦‹
  • lockup_timeout (string)(9) πŸ¦‹
  • dpm (int)(9) πŸ¦‹
  • fw_load_type (int)(9) πŸ¦‹
  • aspm (int)(9) πŸ¦‹
  • runpm (int)(9) πŸ¦‹
  • ip_block_mask (uint)(9) πŸ¦‹
  • bapm (int)(9) πŸ¦‹
  • deep_color (int)(9) πŸ¦‹
  • vm_size (int)(9) πŸ¦‹
  • vm_fragment_size (int)(9) πŸ¦‹
  • vm_block_size (int)(9) πŸ¦‹
  • vm_fault_stop (int)(9) πŸ¦‹
  • vm_update_mode (int)(9) πŸ¦‹
  • exp_hw_support (int)(9) πŸ¦‹
  • dc (int)(9) πŸ¦‹
  • sched_jobs (int)(9) πŸ¦‹
  • sched_hw_submission (int)(9) πŸ¦‹
  • ppfeaturemask (hexint)(9) πŸ¦‹
  • forcelongtraining (uint)(9) πŸ¦‹
  • pcie_gen_cap (uint)(9) πŸ¦‹
  • pcie_lane_cap (uint)(9) πŸ¦‹
  • cg_mask (ullong)(9) πŸ¦‹
  • pg_mask (uint)(9) πŸ¦‹
  • sdma_phase_quantum (uint)(9) πŸ¦‹
  • disable_cu (charp)(9) πŸ¦‹
  • virtual_display (charp)(9) πŸ¦‹
  • lbpw (int)(9) πŸ¦‹
  • gpu_recovery (int)(9) πŸ¦‹
  • emu_mode (int)(9) πŸ¦‹
  • ras_enable (int)(9) πŸ¦‹
  • ras_mask (uint)(9) πŸ¦‹
  • timeout_fatal_disable (bool)(9) πŸ¦‹
  • timeout_period (uint)(9) πŸ¦‹
  • si_support (int)(9) πŸ¦‹
  • cik_support (int)(9) πŸ¦‹
  • smu_memory_pool_size (uint)(9) πŸ¦‹
  • async_gfx_ring (int)(9) πŸ¦‹
  • discovery (int)(9) πŸ¦‹
  • mes_log_enable (int)(9) πŸ¦‹
  • uni_mes (int)(9) πŸ¦‹
  • noretry (int)(9) πŸ¦‹
  • force_asic_type (int)(9) πŸ¦‹
  • use_xgmi_p2p (int)(9) πŸ¦‹
  • sched_policy (int)(9) πŸ¦‹
  • hws_max_conc_proc (int)(9) πŸ¦‹
  • cwsr_enable (int)(9) πŸ¦‹
  • max_num_of_queues_per_device (int)(9) πŸ¦‹
  • send_sigterm (int)(9) πŸ¦‹
  • halt_if_hws_hang (int)(9) πŸ¦‹
  • hws_gws_support(bool)(9) πŸ¦‹
  • queue_preemption_timeout_ms (int)(9) πŸ¦‹
  • debug_evictions(bool)(9) πŸ¦‹
  • no_system_mem_limit(bool)(9) πŸ¦‹
  • no_queue_eviction_on_vm_fault (int)(9) πŸ¦‹
  • mtype_local (int)(9) πŸ¦‹
  • pcie_p2p (bool)(9) πŸ¦‹
  • dcfeaturemask (uint)(9) πŸ¦‹
  • dcdebugmask (uint)(9) πŸ¦‹
  • abmlevel (uint)(9) πŸ¦‹
  • damageclips (int)(9) πŸ¦‹
  • tmz (int)(9) πŸ¦‹
  • freesync_video (uint)(9) πŸ¦‹
  • reset_method (int)(9) πŸ¦‹
  • bad_page_threshold (int) Bad page threshold is specifies the(9) πŸ¦‹
  • vcnfw_log (int)(9) πŸ¦‹
  • sg_display (int)(9) πŸ¦‹
  • umsch_mm (int)(9) πŸ¦‹
  • umsch_mm_fwlog (int)(9) πŸ¦‹
  • smu_pptable_id (int)(9) πŸ¦‹
  • partition_mode (int)(9) πŸ¦‹
  • enforce_isolation (int)(9) πŸ¦‹
  • modeset (int)(9) πŸ¦‹
  • seamless (int)(9) πŸ¦‹
  • debug_mask (uint)(9) πŸ¦‹
  • agp (int)(9) πŸ¦‹
  • wbrf (int)(9) πŸ¦‹
  • rebar (int)(9) πŸ¦‹
  • user_queue (int)(9) πŸ¦‹
  • ptl (int)(9) πŸ¦‹

and that's the whole vibe, bestie πŸ’œ this page is from the ./drivers/gpu/drm/amd/amdgpu source and it's dated October 2026 🌈 mwah, slay, go read your kernel params πŸŽ€βœ¨

πŸ“¦ where this page comes from