From 4f8ba33bbdfc475fdc1ac5de6a93f5de93203ed5 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Wed, 11 Jun 2025 22:47:45 +1200 Subject: [PATCH] mm: madvise: use per_vma lock for MADV_FREE MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit MADV_FREE is another option, besides MADV_DONTNEED, for dynamic memory freeing in user-space native or Java heap memory management. For example, jemalloc can be configured to use MADV_FREE, and recent versions of the Android Java heap have also increasingly adopted MADV_FREE. Supporting per-VMA locking for MADV_FREE thus appears increasingly necessary. We have replaced walk_page_range() with walk_page_range_vma(). Along with the proposed madvise_lock_mode by Lorenzo, the necessary infrastructure is now in place to begin exploring per-VMA locking support for MADV_FREE and potentially other madvise using walk_page_range_vma(). This patch adds support for the PGWALK_VMA_RDLOCK walk_lock mode in walk_page_range_vma(), and leverages madvise_lock_mode from madv_behavior to select the appropriate walk_lock—either mmap_lock or per-VMA lock—based on the context. Because we now dynamically update the walk_ops->walk_lock field, we must ensure this is thread-safe. The madvise_free_walk_ops is now defined as a stack variable instead of a global constant. Link: https://lkml.kernel.org/r/20250611104745.57405-1-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Acked-by: SeongJae Park Cc: "Liam R. Howlett" Cc: Vlastimil Babka Cc: Jann Horn Cc: Suren Baghdasaryan Cc: Lokesh Gidra Cc: Mike Rapoport Cc: Michal Hocko Cc: Tangquan Zheng Cc: Qi Zheng Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 2 ++ mm/madvise.c | 25 +++++++++++++++++++------ mm/pagewalk.c | 5 ++++- 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 8ac2f6d6d2a34..682472c154952 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -14,6 +14,8 @@ enum page_walk_lock { PGWALK_WRLOCK = 1, /* vma is expected to be already write-locked during the walk */ PGWALK_WRLOCK_VERIFY = 2, + /* vma is expected to be already read-locked during the walk */ + PGWALK_VMA_RDLOCK_VERIFY = 3, }; /** diff --git a/mm/madvise.c b/mm/madvise.c index 7d78d4b5fb184..d451438af999f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -777,10 +777,19 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, return 0; } -static const struct mm_walk_ops madvise_free_walk_ops = { - .pmd_entry = madvise_free_pte_range, - .walk_lock = PGWALK_RDLOCK, -}; +static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode) +{ + switch (mode) { + case MADVISE_VMA_READ_LOCK: + return PGWALK_VMA_RDLOCK_VERIFY; + case MADVISE_MMAP_READ_LOCK: + return PGWALK_RDLOCK; + default: + /* Other modes don't require fixing up the walk_lock */ + WARN_ON_ONCE(1); + return PGWALK_RDLOCK; + } +} static int madvise_free_single_vma(struct madvise_behavior *madv_behavior, struct vm_area_struct *vma, @@ -789,6 +798,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior, struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; struct mmu_gather *tlb = madv_behavior->tlb; + struct mm_walk_ops walk_ops = { + .pmd_entry = madvise_free_pte_range, + }; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) @@ -808,8 +820,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior, mmu_notifier_invalidate_range_start(&range); tlb_start_vma(tlb, vma); + walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode); walk_page_range_vma(vma, range.start, range.end, - &madvise_free_walk_ops, tlb); + &walk_ops, tlb); tlb_end_vma(tlb, vma); mmu_notifier_invalidate_range_end(&range); return 0; @@ -1658,7 +1671,6 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi case MADV_WILLNEED: case MADV_COLD: case MADV_PAGEOUT: - case MADV_FREE: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: @@ -1667,6 +1679,7 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi return MADVISE_MMAP_READ_LOCK; case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: + case MADV_FREE: return MADVISE_VMA_READ_LOCK; default: return MADVISE_MMAP_WRITE_LOCK; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ff5299eca687f..a214a2b40ab9f 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -422,7 +422,7 @@ static inline void process_mm_walk_lock(struct mm_struct *mm, { if (walk_lock == PGWALK_RDLOCK) mmap_assert_locked(mm); - else + else if (walk_lock != PGWALK_VMA_RDLOCK_VERIFY) mmap_assert_write_locked(mm); } @@ -437,6 +437,9 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma, case PGWALK_WRLOCK_VERIFY: vma_assert_write_locked(vma); break; + case PGWALK_VMA_RDLOCK_VERIFY: + vma_assert_locked(vma); + break; case PGWALK_RDLOCK: /* PGWALK_RDLOCK is handled by process_mm_walk_lock */ break; -- 2.47.2