hugetlb: remove duplicate mmu notifications

The common hugetlb unmap routine __unmap_hugepage_range performs mmu
notification calls.  However, in the case where __unmap_hugepage_range is
called via __unmap_hugepage_range_final, mmu notification calls are
performed earlier in other calling routines.

Remove mmu notification calls from __unmap_hugepage_range.  Add
notification calls to the only other caller: unmap_hugepage_range.
unmap_hugepage_range is called for truncation and hole punch, so change
notification type from UNMAP to CLEAR as this is more appropriate.

Link: https://lkml.kernel.org/r/20221114235507.294320-4-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Suggested-by: Peter Xu <peterx@redhat.com>
Cc: Wei Chen <harperchen1110@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4f1338d..3fd4570 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5076,7 +5076,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
        struct page *page;
        struct hstate *h = hstate_vma(vma);
        unsigned long sz = huge_page_size(h);
-       struct mmu_notifier_range range;
        unsigned long last_addr_mask;
        bool force_flush = false;
 
@@ -5091,13 +5090,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
        tlb_change_page_size(tlb, sz);
        tlb_start_vma(tlb, vma);
 
-       /*
-        * If sharing possible, alert mmu notifiers of worst case.
-        */
-       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start,
-                               end);
-       adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
-       mmu_notifier_invalidate_range_start(&range);
        last_addr_mask = hugetlb_mask_last_page(h);
        address = start;
        for (; address < end; address += sz) {
@@ -5182,7 +5174,6 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
                if (ref_page)
                        break;
        }
-       mmu_notifier_invalidate_range_end(&range);
        tlb_end_vma(tlb, vma);
 
        /*
@@ -5210,6 +5201,7 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
        hugetlb_vma_lock_write(vma);
        i_mmap_lock_write(vma->vm_file->f_mapping);
 
+       /* mmu notification performed in caller */
        __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
 
        if (zap_flags & ZAP_FLAG_UNMAP) {       /* final unmap */
@@ -5234,10 +5226,18 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
                          unsigned long end, struct page *ref_page,
                          zap_flags_t zap_flags)
 {
+       struct mmu_notifier_range range;
        struct mmu_gather tlb;
 
+       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
+                               start, end);
+       adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
+       mmu_notifier_invalidate_range_start(&range);
        tlb_gather_mmu(&tlb, vma->vm_mm);
+
        __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags);
+
+       mmu_notifier_invalidate_range_end(&range);
        tlb_finish_mmu(&tlb);
 }