diff options
| author | Barry Song <v-songbaohua@oppo.com> | 2025-06-11 22:47:45 +1200 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2025-07-09 22:42:07 -0700 |
| commit | 4f8ba33bbdfc475fdc1ac5de6a93f5de93203ed5 (patch) | |
| tree | 13b53a24d3a652abd7eafeb39c3ca9188e71590b /mm/madvise.c | |
| parent | f822a9a81a31311d67f260aea96005540b18ab07 (diff) | |
| download | tip-4f8ba33bbdfc475fdc1ac5de6a93f5de93203ed5.tar.gz | |
mm: madvise: use per_vma lock for MADV_FREE
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 <v-songbaohua@oppo.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/madvise.c')
| -rw-r--r-- | mm/madvise.c | 25 |
1 files changed, 19 insertions, 6 deletions
diff --git a/mm/madvise.c b/mm/madvise.c index 7d78d4b5fb1848..d451438af999f3 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; |