hugetlb: create hugetlb_unmap_file_folio to unmap single file folio

Create the new routine hugetlb_unmap_file_folio that will unmap a single
file folio.  This is refactored code from hugetlb_vmdelete_list.  It is
modified to do locking within the routine itself and check whether the
page is mapped within a specific vma before unmapping.

This refactoring will be put to use and expanded upon in a subsequent
patch adding vma specific locking.

Link: https://lkml.kernel.org/r/20220914221810.95771-8-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Prakash Sangappa <prakash.sangappa@oracle.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 7112a9a..3bb1772 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -371,6 +371,94 @@ static void hugetlb_delete_from_page_cache(struct page *page)
        delete_from_page_cache(page);
 }
 
+/*
+ * Called with i_mmap_rwsem held for inode based vma maps.  This makes
+ * sure vma (and vm_mm) will not go away.  We also hold the hugetlb fault
+ * mutex for the page in the mapping.  So, we can not race with page being
+ * faulted into the vma.
+ */
+static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
+                               unsigned long addr, struct page *page)
+{
+       pte_t *ptep, pte;
+
+       ptep = huge_pte_offset(vma->vm_mm, addr,
+                       huge_page_size(hstate_vma(vma)));
+
+       if (!ptep)
+               return false;
+
+       pte = huge_ptep_get(ptep);
+       if (huge_pte_none(pte) || !pte_present(pte))
+               return false;
+
+       if (pte_page(pte) == page)
+               return true;
+
+       return false;
+}
+
+/*
+ * Can vma_offset_start/vma_offset_end overflow on 32-bit arches?
+ * No, because the interval tree returns us only those vmas
+ * which overlap the truncated area starting at pgoff,
+ * and no vma on a 32-bit arch can span beyond the 4GB.
+ */
+static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start)
+{
+       if (vma->vm_pgoff < start)
+               return (start - vma->vm_pgoff) << PAGE_SHIFT;
+       else
+               return 0;
+}
+
+static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end)
+{
+       unsigned long t_end;
+
+       if (!end)
+               return vma->vm_end;
+
+       t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start;
+       if (t_end > vma->vm_end)
+               t_end = vma->vm_end;
+       return t_end;
+}
+
+/*
+ * Called with hugetlb fault mutex held.  Therefore, no more mappings to
+ * this folio can be created while executing the routine.
+ */
+static void hugetlb_unmap_file_folio(struct hstate *h,
+                                       struct address_space *mapping,
+                                       struct folio *folio, pgoff_t index)
+{
+       struct rb_root_cached *root = &mapping->i_mmap;
+       struct page *page = &folio->page;
+       struct vm_area_struct *vma;
+       unsigned long v_start;
+       unsigned long v_end;
+       pgoff_t start, end;
+
+       start = index * pages_per_huge_page(h);
+       end = (index + 1) * pages_per_huge_page(h);
+
+       i_mmap_lock_write(mapping);
+
+       vma_interval_tree_foreach(vma, root, start, end - 1) {
+               v_start = vma_offset_start(vma, start);
+               v_end = vma_offset_end(vma, end);
+
+               if (!hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page))
+                       continue;
+
+               unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
+                               NULL, ZAP_FLAG_DROP_MARKER);
+       }
+
+       i_mmap_unlock_write(mapping);
+}
+
 static void
 hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
                      zap_flags_t zap_flags)
@@ -383,30 +471,13 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
         * an inclusive "last".
         */
        vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) {
-               unsigned long v_offset;
+               unsigned long v_start;
                unsigned long v_end;
 
-               /*
-                * Can the expression below overflow on 32-bit arches?
-                * No, because the interval tree returns us only those vmas
-                * which overlap the truncated area starting at pgoff,
-                * and no vma on a 32-bit arch can span beyond the 4GB.
-                */
-               if (vma->vm_pgoff < start)
-                       v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
-               else
-                       v_offset = 0;
-
-               if (!end)
-                       v_end = vma->vm_end;
-               else {
-                       v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
-                                                       + vma->vm_start;
-                       if (v_end > vma->vm_end)
-                               v_end = vma->vm_end;
-               }
+               v_start = vma_offset_start(vma, start);
+               v_end = vma_offset_end(vma, end);
 
-               unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
+               unmap_hugepage_range(vma, vma->vm_start + v_start, v_end,
                                     NULL, zap_flags);
        }
 }
@@ -428,14 +499,8 @@ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode,
         * the fault mutex.  The mutex will prevent faults
         * until we finish removing the folio.
         */
-       if (unlikely(folio_mapped(folio))) {
-               i_mmap_lock_write(mapping);
-               hugetlb_vmdelete_list(&mapping->i_mmap,
-                       index * pages_per_huge_page(h),
-                       (index + 1) * pages_per_huge_page(h),
-                       ZAP_FLAG_DROP_MARKER);
-               i_mmap_unlock_write(mapping);
-       }
+       if (unlikely(folio_mapped(folio)))
+               hugetlb_unmap_file_folio(h, mapping, folio, index);
 
        folio_lock(folio);
        /*