dma_fence_is...naled_locked(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… dma_fence_is_signaled_locked β€” Kernel API Manual ✨

okay bestie, welcome to the Kernel API Manual, this one's a dma_fence_is_signaled_locked(9) situation and honestly it's giving "tiny function, big responsibility" πŸŽ€

✨ NAME ✨

dma_fence_is_signaled_locked β€” returns an indication if the fence is signaled yet. that's it, that's the whole job πŸ’–

πŸ¦‹ SYNOPSIS πŸ¦‹

bool dma_fence_is_signaled_locked (struct dma_fence *fence );

🌸 ARGUMENTS 🌸

  • fence β€” the fence to check πŸ‘€ like, the actual one you're wondering about

πŸ’œ DESCRIPTION πŸ’œ

Returns true if the fence was already signaled, false if not. simple as that, no cap ✨

🚨 okay this part is important so listen up: since this function doesn't enable signaling, it is not guaranteed to ever return true if dma_fence_add_callback, dma_fence_wait or dma_fence_enable_sw_signaling haven't been called before. so if you skipped those and you're sitting there like "why is it always false 😭" β€” that's why, bestie, that's the vibe check failing on purpose πŸ’€

Also this function requires dma_fence.lock to be held. like, you literally have to be holding the lock, it's not optional, it's not a suggestion, holding it is the whole assignment πŸ”’πŸ‘‘

See also dma_fence_is_signaled β€” that's the unlocked cousin, iykyk 🫢

πŸ”₯ SEE ALSO πŸ”₯

Kernel file ./include/linux/dma-fence.h and the whole friend group:


and that's the whole page, periodt 🌈 this cutie lives in ./include/linux, dated October 2026, and it's dma_fence_is...naled_locked(9) signing off β€” mwah πŸ’‹πŸ§šβ€β™€οΈ

πŸ“¦ where this page comes from