pfnmap_track(9)

pfnmap_track(9) 🎀

okay so bestie, welcome to the Kernel API Manual page for pfnmap_track(9) — this is the one that gets a pfn range tracked by a hardware implementation, and it's giving very specific memory-cache energy. no cap, let's go 💅

✨ NAME ✨

pfnmap_track — track a pfn range 🎯

💅 SYNOPSIS 💅

int pfnmap_track (unsigned long pfn , unsigned long size , pgprot_t *prot );

🫶 ARGUMENTS 🫶

• pfn — the start of the pfn range 🌸
• size — the size of the pfn range in bytes 📏
• prot — the pgprot to track 🧠

✨ DESCRIPTION ✨

okay so here's the tea: you're requesting the pfn range to be 'tracked' by a hardware implementation, and setting up the cachemode in prot similar to pfnmap_setup_cachemode.

this allows for fine-grained control of memory cache behaviour at page level granularity — literally page-level cache vibes. tracking memory this way is persisted across VMA splits (VMA merging does not apply for VM_PFNMAP). 🦋

currently, there is only one implementation for this — x86 Page Attribute Table (PAT). see Documentation/arch/x86/pat.rst for more details 👑

it returns 0 on success and -EINVAL on error 💀.

🌈 SEE ALSO 🌈

Kernel file ./include/linux/pgtable.h is the whole group chat: lazy_mmu_mode_enable(9), lazy_mmu_mode_disable(9), __task_lazy_mmu_mode_pause(9), lazy_mmu_mode_pause(9), __task_lazy_mmu_mode_resume(9), lazy_mmu_mode_resume(9), pte_batch_hint(9), set_ptes(9), clear_young_dirty_ptes(9), get_and_clear_full_ptes(9), get_and_clear_ptes(9), clear_full_ptes(9), clear_ptes(9), clear_nonpresent_ptes(9), ptep_try_set(9), flush_tlb_before_set(9), wrprotect_ptes(9), clear_flush_young_ptes(9), test_and_clear_young_ptes(9), modify_prot_start_ptes(9), modify_prot_commit_ptes(9), pfnmap_setup_cachemode(9), pfnmap_untrack(9), pfnmap_setup_cachemode_pfn(9) 🫶

byeee 💖 source/version: ./include/linux, date: October 2026 — mwah, ily, go track those pfn ranges 🫶