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>

1 files changed, 33 insertions, 2 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 065ec022cbb0..47d25a5e1933 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -139,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *,
 			  zap_flags_t);
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+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);
@@ -246,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 
+extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
+				unsigned long *begin, unsigned long *end);
+extern void __hugetlb_zap_end(struct vm_area_struct *vma,
+			      struct zap_details *details);
+
+static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
+				     unsigned long *start, unsigned long *end)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_begin(vma, start, end);
+}
+
+static inline void hugetlb_zap_end(struct vm_area_struct *vma,
+				   struct zap_details *details)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_end(vma, details);
+}
+
 void hugetlb_vma_lock_read(struct vm_area_struct *vma);
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
 void hugetlb_vma_lock_write(struct vm_area_struct *vma);
@@ -297,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline void hugetlb_zap_begin(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
+
+static inline void hugetlb_zap_end(
+				struct vm_area_struct *vma,
+				struct zap_details *details)
+{
+}
+
 static inline struct page *hugetlb_follow_page_mask(
     struct vm_area_struct *vma, unsigned long address, unsigned int flags,
     unsigned int *page_mask)
@@ -442,7 +473,7 @@ static inline long hugetlb_change_protection(
 	return 0;
 }
 
-static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static inline 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)