[PATCH v12 0/6] THP aware uprobe

[Song Liu]

This set makes uprobe aware of THPs.

Currently, when uprobe is attached to text on THP, the page is split by
FOLL_SPLIT. As a result, uprobe eliminates the performance benefit of THP.

This set makes uprobe THP-aware. Instead of FOLL_SPLIT, we introduces
FOLL_SPLIT_PMD, which only split PMD for uprobe.

After all uprobes within the THP are removed, the PTE-mapped pages are
regrouped as huge PMD.

This set (plus a few THP patches) is also available at

   https://github.com/liu-song-6/linux/tree/uprobe-thp


Changes v11.4 => v12
1. Combine the first 4 patches with the rest 2 patches again in the same
   set.
2. Improve checks for the page in collapse_pte_mapped_thp() (Oleg).
3. Fixed build error w/o CONFIG_SHMEM.

v11.1 to v11.4 are only the last two patches.

Changes v11.3 => v11.4:
1. Simplify locking for pte_mapped_thp (Oleg).
2. Improve checks for the page in collapse_pte_mapped_thp() (Oleg).
3. Move HPAGE_PMD_MASK to collapse_pte_mapped_thp() (kbuild test robot).

Changes v11.2 => v11.3:
1. Update vma/pmd check in collapse_pte_mapped_thp() (Oleg).
2. Add Acked-by from Kirill

Changes v11.1 => v11.2:
1. Call collapse_pte_mapped_thp() directly from uprobe_write_opcode();
2. Add VM_BUG_ON() for addr alignment in khugepaged_add_pte_mapped_thp()
   and collapse_pte_mapped_thp().

Changes v9 => v10:
1. 2/4 incorporate suggestion by Oleg Nesterov.
2. Reword change log of 4/4.

Changes v8 => v9:
1. To replace with orig_page, only unmap old_page. Let the orig_page fault
   in (Oleg Nesterov).

Changes v7 => v8:
1. check PageUptodate() for orig_page (Oleg Nesterov).

Changes v6 => v7:
1. Include Acked-by from Kirill A. Shutemov for the first 4 patches;
2. Keep only the first 4 patches (while I working on improving the last 2).

Changes v5 => v6:
1. Enable khugepaged to collapse pmd for pte-mapped THP
   (Kirill A. Shutemov).
2. uprobe asks khuagepaged to collaspe pmd. (Kirill A. Shutemov)

Note: Theast two patches in v6 the set apply _after_ v7 of set "Enable THP
      for text section of non-shmem files"

Changes v4 => v5:
1. Propagate pte_alloc() error out of follow_pmd_mask().

Changes since v3:
1. Simplify FOLL_SPLIT_PMD case in follow_pmd_mask(), (Kirill A. Shutemov)
2. Fix try_collapse_huge_pmd() to match change in follow_pmd_mask().

Changes since v2:
1. For FOLL_SPLIT_PMD, populated the page table in follow_pmd_mask().
2. Simplify logic in uprobe_write_opcode. (Oleg Nesterov)
3. Fix page refcount handling with FOLL_SPLIT_PMD.
4. Much more testing, together with THP on ext4 and btrfs (sending in
   separate set).
5. Rebased.

Changes since v1:
1. introduces FOLL_SPLIT_PMD, instead of modifying split_huge_pmd*();
2. reuse pages_identical() from ksm.c;
3. rewrite most of try_collapse_huge_pmd().

Song Liu (6):
  mm: move memcmp_pages() and pages_identical()
  uprobe: use original page when all uprobes are removed
  mm, thp: introduce FOLL_SPLIT_PMD
  uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT
  khugepaged: enable collapse pmd for pte-mapped THP
  uprobe: collapse THP pmd after removing all uprobes

 include/linux/khugepaged.h |  12 ++++
 include/linux/mm.h         |   8 +++
 kernel/events/uprobes.c    |  81 ++++++++++++++++-----
 mm/gup.c                   |   8 ++-
 mm/khugepaged.c            | 140 ++++++++++++++++++++++++++++++++++++-
 mm/ksm.c                   |  18 -----
 mm/util.c                  |  13 ++++
 7 files changed, 240 insertions(+), 40 deletions(-)

--
2.17.1