[PATCH v3 20/35] mm: conditionally write-lock VMA in free_pgtables
From: Suren Baghdasaryan <surenb@google.com>
Date: 2023-02-16 05:20:18
Also in:
linux-mm, lkml
Subsystem:
memory management, memory management - core, memory mapping, the rest · Maintainers:
Andrew Morton, David Hildenbrand, Liam R. Howlett, Lorenzo Stoakes, Linus Torvalds
Normally free_pgtables needs to lock affected VMAs except for the case when VMAs were isolated under VMA write-lock. munmap() does just that, isolating while holding appropriate locks and then downgrading mmap_lock and dropping per-VMA locks before freeing page tables. Add a parameter to free_pgtables for such scenario. Signed-off-by: Suren Baghdasaryan <surenb@google.com> --- mm/internal.h | 2 +- mm/memory.c | 6 +++++- mm/mmap.c | 5 +++-- 3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index fc01fd092ea5..400c302fbf47 100644
--- a/mm/internal.h
+++ b/mm/internal.h@@ -105,7 +105,7 @@ void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long floor, - unsigned long ceiling); + unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details;
diff --git a/mm/memory.c b/mm/memory.c
index f456f3b5049c..8177c59ffd2d 100644
--- a/mm/memory.c
+++ b/mm/memory.c@@ -348,7 +348,7 @@ void free_pgd_range(struct mmu_gather *tlb, void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *vma, unsigned long floor, - unsigned long ceiling) + unsigned long ceiling, bool mm_wr_locked) { MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
@@ -366,6 +366,8 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ + if (mm_wr_locked) + vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma(vma);
@@ -380,6 +382,8 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, && !is_vm_hugetlb_page(next)) { vma = next; next = mas_find(&mas, ceiling - 1); + if (mm_wr_locked) + vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma(vma); }
diff --git a/mm/mmap.c b/mm/mmap.c
index aaa359a147b2..118b2246bba9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c@@ -2157,7 +2157,8 @@ static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, update_hiwater_rss(mm); unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked); free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, - next ? next->vm_start : USER_PGTABLES_CEILING); + next ? next->vm_start : USER_PGTABLES_CEILING, + mm_wr_locked); tlb_finish_mmu(&tlb); }
@@ -3069,7 +3070,7 @@ void exit_mmap(struct mm_struct *mm) mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, - USER_PGTABLES_CEILING); + USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); /*
--
2.39.1