get_user_pages_fast(9)

💖 NAME 💖

okay so bestie, this is get_user_pages_fast(9) from the Kernel API Manual — the function that pins user pages in memory, and it’s giving fast-path-first energy with a locky backup plan. 🦋✨

🦋 SYNOPSIS 🦋

int get_user_pages_fast (unsigned long start , int nr_pages , unsigned
       int gup_flags , struct page **pages );

✨ ARGUMENTS ✨

• start — the starting user address, aka where the page-pinning adventure begins.
• nr_pages — number of pages from start to pin; think “how many pages are we grabbing, bestie?”
• gup_flags — flags modifying pin behaviour, so they change how the pinning goes down.
• pages — array that receives pointers to the pages pinned. It should be at least nr_pages long — no skimping. 💅

🎀 DESCRIPTION 🎀

So the function attempts to pin user pages in memory without taking mm->mmap_lock. That’s the fast part, iykyk. 🔥

If that’s not successful, it falls back to taking the lock and calling get_user_pages. Lowkey reliable, highkey the backup plan. 😭

It returns number of pages pinned. Heads up though: this may be fewer than the number requested. If nr_pages is 0 or negative, it returns 0. If no pages were pinned, it returns -errno. Periodt. 👑

🌸 SEE ALSO 🌸

Kernel file ./mm/gup.c is over here doing its thing, and the full bestie list is:

• try_grab_folio(9)
• unpin_user_page(9)
• unpin_folio(9)
• folio_add_pin(9)
• unpin_user_pages_dirty_lock(9)
• unpin_user_page_range_dirty_lock(9)
• unpin_user_pages(9)
• unpin_user_folio(9)
• unpin_folios(9)
• try_grab_folio_fast(9)
• follow_page_mask(9)
• __get_user_pages(9)
• fixup_user_fault(9)
• populate_vma_page_range(9)
• fault_in_writeable(9)
• fault_in_subpage_writeable(9)
• fault_in_readable(9)
• get_dump_page(9)
• get_user_pages_remote(9)
• get_user_pages(9)
• get_user_pages_fast_only(9)
• pin_user_pages_fast(9)
• pin_user_pages_remote(9)
• pin_user_pages(9)
• memfd_pin_folios(9)
• folio_add_pins(9)

Big cute sign-off energy: source ./mm, date October 2026, and the get_user_pages_fast(9) manual page itself — slay 💅✨🫶