folio_split(9)

💖 folio_split(9) 💖

okay so this is from the Kernel API Manual bestie, and it's genuinely giving main character energy — we're splitting folios today 🔥

---

✨ NAME ✨

folio_split — split a folio at @split_at to a @new_order folio 🎀

---

🦋 SYNOPSIS 🦋

int folio_split (struct folio *folio , unsigned int new_order , struct
page *split_at , struct list_head *list );

like, yes, that's the whole signature, no cap 💅

---

🌸 ARGUMENTS 🌸

• folio — the folio you're splitting, bestie. this is the one.
• new_order — the order of the new folio ✨
• split_at — a page within the new folio. that's where the split happens, periodt.
• list — after-split folios get added to list if it's not null; otherwise they go to the LRU list. iykyk 🫶

---

💜 DESCRIPTION 💜

okay so real talk — it has the same prerequisites and returns as split_huge_page_to_list_to_order. not me just pointing you at that instead of explaining, but that's literally what the manpage says so 😭

So what does it actually do? It splits a folio at split_at into a new_order folio, and — this is the iconic part — it leaves the remaining subpages of the original folio as large as possible 👑

Let's do the example, because the example eats:

split an order-9 folio at its third order-3 subpages to an order-3 folio. There are 2^(9-3)=64 order-3 subpages in the order-9 folio. After the split, you get a group of folios with different orders, and the new folio containing split_at is marked in brackets:

[order-4, {order-3}, order-3, order-5, order-6, order-7, order-8]

see the {order-3} in there? that's the one. slay 💅

important bestie: after split, folio is left locked for the caller. don't forget to unlock it, i'm begging you 🙈

---

⭐ RETURN ⭐

• 0 — successful 🎉
• <0 — failed.

and here's the caveat, listen up: if -ENOMEM is returned, the folio might be split but not to new_order — so the caller needs to check. like, actually check. fr fr 💀

---

🌈 SEE ALSO 🌈

Kernel file ./mm/huge_memory.c, plus all these icons:

• vmf_insert_pfn_pmd(9)
• vmf_insert_pfn_pud(9)
• vmf_insert_folio_pud(9)
• touch_pmd(9)
• zap_huge_pmd(9)
• __split_unmapped_folio(9)
• folio_check_splittable(9)
• __folio_split(9)
• folio_split_unmapped(9)
• min_order_for_split(9)

---

anyway that's the whole page bestie, go split some folios responsibly 🧚

sign-off time: this little gem lives in ./mm and it's dated October 2026 — so yeah, it's from the future and it's still iconic 💖✨