remap_file_pages.rst 1.6 KB

123456789101112131415161718192021222324252627282930313233
  1. .. _remap_file_pages:
  2. ==============================
  3. remap_file_pages() system call
  4. ==============================
  5. The remap_file_pages() system call is used to create a nonlinear mapping,
  6. that is, a mapping in which the pages of the file are mapped into a
  7. nonsequential order in memory. The advantage of using remap_file_pages()
  8. over using repeated calls to mmap(2) is that the former approach does not
  9. require the kernel to create additional VMA (Virtual Memory Area) data
  10. structures.
  11. Supporting of nonlinear mapping requires significant amount of non-trivial
  12. code in kernel virtual memory subsystem including hot paths. Also to get
  13. nonlinear mapping work kernel need a way to distinguish normal page table
  14. entries from entries with file offset (pte_file). Kernel reserves flag in
  15. PTE for this purpose. PTE flags are scarce resource especially on some CPU
  16. architectures. It would be nice to free up the flag for other usage.
  17. Fortunately, there are not many users of remap_file_pages() in the wild.
  18. It's only known that one enterprise RDBMS implementation uses the syscall
  19. on 32-bit systems to map files bigger than can linearly fit into 32-bit
  20. virtual address space. This use-case is not critical anymore since 64-bit
  21. systems are widely available.
  22. The syscall is deprecated and replaced it with an emulation now. The
  23. emulation creates new VMAs instead of nonlinear mappings. It's going to
  24. work slower for rare users of remap_file_pages() but ABI is preserved.
  25. One side effect of emulation (apart from performance) is that user can hit
  26. vm.max_map_count limit more easily due to additional VMAs. See comment for
  27. DEFAULT_MAX_MAP_COUNT for more details on the limit.