hugetlbfs: close race between MADV_DONTNEED and page fault

Malloc libraries, like jemalloc and tcalloc, take decisions on when to
call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting
around to satisfy a page fault.  However, with hugetlbfs systems often
allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:

       CPU 1                            CPU 2

       MADV_DONTNEED
       unmap page
       shoot down TLB entry
                                       page fault
                                       fail to allocate a huge page
                                       killed with SIGBUS
       free page

Fix that race by pulling the locking from __unmap_hugepage_final_range
into helper functions called from zap_page_range_single.  This ensures
page faults stay locked out of the MADV_DONTNEED VMA until the huge pages
have actually been freed.

Link: https://lkml.kernel.org/r/20231006040020.3677377-4-riel@surriel.com
Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing")
Signed-off-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 30 insertions, 17 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d218ee2b6a99..1301ba7b2c9a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5306,9 +5306,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	return len + old_addr - old_end;
 }
 
-static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   struct page *ref_page, zap_flags_t zap_flags)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page, zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5437,16 +5437,25 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		tlb_flush_mmu_tlbonly(tlb);
 }
 
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
-			  struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page,
-			  zap_flags_t zap_flags)
+void __hugetlb_zap_begin(struct vm_area_struct *vma,
+			 unsigned long *start, unsigned long *end)
 {
+	if (!vma->vm_file)	/* hugetlbfs_file_mmap error */
+		return;
+
+	adjust_range_if_pmd_sharing_possible(vma, start, end);
 	hugetlb_vma_lock_write(vma);
-	i_mmap_lock_write(vma->vm_file->f_mapping);
+	if (vma->vm_file)
+		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);
+void __hugetlb_zap_end(struct vm_area_struct *vma,
+		       struct zap_details *details)
+{
+	zap_flags_t zap_flags = details ? details->zap_flags : 0;
+
+	if (!vma->vm_file)	/* hugetlbfs_file_mmap error */
+		return;
 
 	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
 		/*
@@ -5459,11 +5468,12 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 		 * someone else.
 		 */
 		__hugetlb_vma_unlock_write_free(vma);
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
 	} else {
-		i_mmap_unlock_write(vma->vm_file->f_mapping);
 		hugetlb_vma_unlock_write(vma);
 	}
+
+	if (vma->vm_file)
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/mm/memory.c b/mm/memory.c
index 6c264d2f969c..517221f01303 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1683,7 +1683,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			if (vma->vm_file) {
 				zap_flags_t zap_flags = details ?
 				    details->zap_flags : 0;
-				__unmap_hugepage_range_final(tlb, vma, start, end,
+				__unmap_hugepage_range(tlb, vma, start, end,
 							     NULL, zap_flags);
 			}
 		} else
@@ -1728,8 +1728,12 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+		unsigned long start = start_addr;
+		unsigned long end = end_addr;
+		hugetlb_zap_begin(vma, &start, &end);
+		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
+		hugetlb_zap_end(vma, &details);
 	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
 	mmu_notifier_invalidate_range_end(&range);
 }
@@ -1753,9 +1757,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
-	if (is_vm_hugetlb_page(vma))
-		adjust_range_if_pmd_sharing_possible(vma, &range.start,
-						     &range.end);
+	hugetlb_zap_begin(vma, &range.start, &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
@@ -1766,6 +1768,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
+	hugetlb_zap_end(vma, details);
 }
 
 /**