[PATCH v5 0/5] Readahead tweaks for larger folios

[Ryan Roberts]

Hi All,

This series adds some tweaks to readahead so that it does a better job of
ramping up folio sizes as readahead extends further into the file. And it
additionally special-cases executable mappings to allow the arch to request a
preferred folio size for text.

Originally the series focussed on the latter part only (large folios for text).
See [3]. But after discussion with Matthew Wilcox, v4 switched to additionally
fix some of the unintended behaviours in how a folio size is selected in general
before special-casing for text. As a result patches 1-4 make folio size
selection behave more sanely, then patch 5 introduces large folios for text.
Patch 5 depends on patch 1, but does not depend on patches 2-4.

---

I've run a number of benchmarks and observed no regressions. mm selftests also
shows no regressions vs mm-unstable. Selected benchmark results are presented in
the commit log for the final patch.

Most patches have R-b/A-b now so would be good to get into linux-next for some
soak testing when possible.

Applies on top of today's mm-unstable (a32230de8810).

Changes since v4 [4]
====================

- Added R-b/A-b (thanks all!)
- Patch 1:
  - Removed ra->size fallback check in page_cache_ra_order() (Pankaj)
- Patch 2:
  - Modify ra end alignment to handle non-power-of-2 optimal ra sizes (Jan)
- Patch 4:
  - Only reset order to 0 if fallback is due to not supporting large folios
    (Jan)
- Patch 5:
  - Ignore VM_RAND_READ for VM_EXEC mappings in favour of following the new
    VM_EXEC code path since code is always random (Will)

Changes since v3 [3]
====================

 - Added patchs 1-4 to do better job of ramping up folio order
 - In patch 5:
   - Confine readahead blocks to vma boundaries (per Kalesh)
   - Rename arch_exec_folio_order() to exec_folio_order() (per Matthew)
   - exec_folio_order() now returns unsigned int and defaults to order-0
     (per Matthew)
   - readahead size is honoured (including when disabled)

Changes since v2 [2]
====================

 - Rename arch_wants_exec_folio_order() to arch_exec_folio_order() (per Andrew)
 - Fixed some typos (per Andrew)

Changes since v1 [1]
====================

 - Remove "void" from arch_wants_exec_folio_order() macro args list

[1] https://lore.kernel.org/linux-mm/20240111154106.3692206-1-ryan.roberts@xxxxxxx/
[2] https://lore.kernel.org/all/20240215154059.2863126-1-ryan.roberts@xxxxxxx/
[3] https://lore.kernel.org/linux-mm/20250327160700.1147155-1-ryan.roberts@xxxxxxx/
[4] https://lore.kernel.org/linux-mm/20250430145920.3748738-1-ryan.roberts@xxxxxxx/

Thanks,
Ryan

Ryan Roberts (5):
  mm/readahead: Honour new_order in page_cache_ra_order()
  mm/readahead: Terminate async readahead on natural boundary
  mm/readahead: Make space in struct file_ra_state
  mm/readahead: Store folio order in struct file_ra_state
  mm/filemap: Allow arch to request folio size for exec memory

 arch/arm64/include/asm/pgtable.h |  8 +++++
 include/linux/fs.h               |  4 ++-
 include/linux/pgtable.h          | 11 ++++++
 mm/filemap.c                     | 62 ++++++++++++++++++++++++--------
 mm/internal.h                    |  3 +-
 mm/readahead.c                   | 36 ++++++++++---------
 6 files changed, 89 insertions(+), 35 deletions(-)

--
2.43.0