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
