xe_lrc_timestamp(9)
π xe_lrc_timestamp(9) β like, the current lrc timestamp, bestie
okay so this is a page from the Kernel API Manual (fancy, I know π) and it's all about xe_lrc_timestamp, which literally just hands you the current lrc timestamp. that's it. that's the vibe. β¨
πΈ SYNOPSIS πΈ
u64 xe_lrc_timestamp (struct xe_lrc *lrc );
yes she returns a u64 and yes she takes exactly one arg. iconic signature, no notes. π
π¦ ARGUMENTS π¦
lrcβ pointer to the lrc. that's the whole thing. just a pointer. to the lrc. π«Ά
π DESCRIPTION π
so the function returns the latest lrc timestamp. easy enough, right?
but here's the tea β β with support for active contexts/queues, the calculation may be slightly racy π so you gotta follow a read-again logic to make sure the context/queue is still active before you return the right timestamp. no cap, that's the important bit. don't skip the re-check, bestie, or you'll get a timestamp that's giving stale energy π
β RETURN β
the new lrc timestamp value. that's it. that's the return. slay. π
π₯ SEE ALSO π₯
- the kernel file
./drivers/gpu/drm/xe/xe_lrc.c xe_gt_lrc_hang_replay_size(9)xe_lrc_reg_size(9)xe_lrc_engine_state_size(9)xe_lrc_ctx_timestamp_ggtt_addr(9)xe_lrc_ctx_timestamp_udw_ggtt_addr(9)xe_lrc_ctx_timestamp(9)xe_lrc_queue_timestamp(9)xe_lrc_ctx_job_timestamp_ggtt_addr(9)xe_lrc_ctx_job_timestamp(9)xe_default_lrc_update_memirq_regs_with_address(9)xe_lrc_update_memirq_regs_with_address(9)xe_lrc_setup_wa_bb_with_scratch(9)xe_lrc_set_multi_queue_priority(9)xe_lrc_create(9)xe_lrc_destroy(9)xe_lrc_update_hwctx_regs_with_address(9)xe_lrc_alloc_seqno_fence(9)xe_lrc_free_seqno_fence(9)xe_lrc_init_seqno_fence(9)xe_lrc_engine_id(9)xe_lrc_update_timestamp(9)xe_lrc_ring_is_idle(9)
like, the whole lrc friend group showed up to the party π iykyk.
k bye bestie, go read your timestamps responsibly π
this masterpiece lives in ./drivers/gpu/drm/xe and it was stamped with love in October 2026 ποΈβ¨ mwah π
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