diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 591599829e2a6659e355d5ca7e2da1e9474e6007..5945caccf003ef96e91574ded30ef1fa86359185 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -405,7 +405,8 @@ static void remove_huge_page(struct page *page)
}
static void
-hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
+hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
+ zap_flags_t zap_flags)
{
struct vm_area_struct *vma;
@@ -439,7 +440,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
}
unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
- NULL);
+ NULL, zap_flags);
}
}
@@ -517,7 +518,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
mutex_lock(&hugetlb_fault_mutex_table[hash]);
hugetlb_vmdelete_list(&mapping->i_mmap,
index * pages_per_huge_page(h),
- (index + 1) * pages_per_huge_page(h));
+ (index + 1) * pages_per_huge_page(h),
+ ZAP_FLAG_DROP_MARKER);
i_mmap_unlock_write(mapping);
}
@@ -583,7 +585,8 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
i_mmap_lock_write(mapping);
i_size_write(inode, offset);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
- hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
+ hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
+ ZAP_FLAG_DROP_MARKER);
i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, offset, LLONG_MAX);
}
@@ -616,8 +619,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap,
- hole_start >> PAGE_SHIFT,
- hole_end >> PAGE_SHIFT);
+ hole_start >> PAGE_SHIFT,
+ hole_end >> PAGE_SHIFT, 0);
i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, hole_start, hole_end);
inode_unlock(inode);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index f1143f1fb4443bedf4615b1406843f7f87b45e40..19cec415f54685191f8e809de3928ff6462d832a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -143,11 +143,12 @@ long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
unsigned long *, unsigned long *, long, unsigned int,
int *);
void unmap_hugepage_range(struct vm_area_struct *,
- unsigned long, unsigned long, struct page *);
+ unsigned long, unsigned long, struct page *,
+ zap_flags_t);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
- struct page *ref_page);
+ struct page *ref_page, zap_flags_t zap_flags);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(char *buf, int len, int nid);
void hugetlb_show_meminfo(void);
@@ -406,7 +407,8 @@ static inline unsigned long hugetlb_change_protection(
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
- unsigned long end, struct page *ref_page)
+ unsigned long end, struct page *ref_page,
+ zap_flags_t zap_flags)
{
BUG();
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 61786259e52a617f4d506908437f28cc56489cbe..de32c038338751bbc155793dff7a65e369d5a996 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3428,8 +3428,6 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
}
#endif
-typedef unsigned int __bitwise zap_flags_t;
-
/*
* Whether to drop the pte markers, for example, the uffd-wp information for
* file-backed memory. This should only be specified when we will completely
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index dd382270ae409f1fa0a61b5a8aea0e2c13f6d5d9..b34ff2cdbc4face79515b1881188c3e89f36034f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -863,4 +863,6 @@ enum fault_flag {
FAULT_FLAG_ORIG_PTE_VALID = 1 << 11,
};
+typedef unsigned int __bitwise zap_flags_t;
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ec9774ed84c018ae67994d9e62e485682a476559..99281aecbd289a3495822c8e38288c7e9c7a8e34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4973,7 +4973,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
- struct page *ref_page)
+ struct page *ref_page, zap_flags_t zap_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
@@ -5029,7 +5029,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
* unmapped and its refcount is dropped, so just clear pte here.
*/
if (unlikely(!pte_present(pte))) {
- huge_pte_clear(mm, address, ptep, sz);
+ /*
+ * If the pte was wr-protected by uffd-wp in any of the
+ * swap forms, meanwhile the caller does not want to
+ * drop the uffd-wp bit in this zap, then replace the
+ * pte with a marker.
+ */
+ if (pte_swp_uffd_wp_any(pte) &&
+ !(zap_flags & ZAP_FLAG_DROP_MARKER))
+ set_huge_pte_at(mm, address, ptep,
+ make_pte_marker(PTE_MARKER_UFFD_WP));
+ else
+ huge_pte_clear(mm, address, ptep, sz);
spin_unlock(ptl);
continue;
}
@@ -5057,7 +5068,11 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
if (huge_pte_dirty(pte))
set_page_dirty(page);
-
+ /* Leave a uffd-wp pte marker if needed */
+ if (huge_pte_uffd_wp(pte) &&
+ !(zap_flags & ZAP_FLAG_DROP_MARKER))
+ set_huge_pte_at(mm, address, ptep,
+ make_pte_marker(PTE_MARKER_UFFD_WP));
hugetlb_count_sub(pages_per_huge_page(h), mm);
page_remove_rmap(page, vma, true);
@@ -5091,9 +5106,10 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
- unsigned long end, struct page *ref_page)
+ unsigned long end, struct page *ref_page,
+ zap_flags_t zap_flags)
{
- __unmap_hugepage_range(tlb, vma, start, end, ref_page);
+ __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
/*
* Clear this flag so that x86's huge_pmd_share page_table_shareable
@@ -5109,12 +5125,13 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
}
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, struct page *ref_page)
+ unsigned long end, struct page *ref_page,
+ zap_flags_t zap_flags)
{
struct mmu_gather tlb;
tlb_gather_mmu(&tlb, vma->vm_mm);
- __unmap_hugepage_range(&tlb, vma, start, end, ref_page);
+ __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags);
tlb_finish_mmu(&tlb);
}
@@ -5169,7 +5186,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
*/
if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
unmap_hugepage_range(iter_vma, address,
- address + huge_page_size(h), page);
+ address + huge_page_size(h), page, 0);
}
i_mmap_unlock_write(mapping);
}
diff --git a/mm/memory.c b/mm/memory.c
index 8827157cf3928d76894c49035c95557a8888e4c8..82adda885605c83c80dc450fdaaf70f5c5d58ba9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1675,8 +1675,11 @@ static void unmap_single_vma(struct mmu_gather *tlb,
* safe to do nothing in this case.
*/
if (vma->vm_file) {
+ zap_flags_t zap_flags = details ?
+ details->zap_flags : 0;
i_mmap_lock_write(vma->vm_file->f_mapping);
- __unmap_hugepage_range_final(tlb, vma, start, end, NULL);
+ __unmap_hugepage_range_final(tlb, vma, start, end,
+ NULL, zap_flags);
i_mmap_unlock_write(vma->vm_file->f_mapping);
}
} else