[LTS 9.4] hugetlb: CVE-2025-38084, CVE-2025-38085, CVE-2024-57883

include/linux/hugetlb.h

@@ -255,6 +255,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 
 bool is_hugetlb_entry_migration(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
+void hugetlb_split(struct vm_area_struct *vma, unsigned long addr);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
@@ -464,6 +465,8 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
 
 static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { }
 
+static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {}
+
 #endif /* !CONFIG_HUGETLB_PAGE */
 /*
  * hugepages at page global directory. If arch support
@@ -1229,7 +1232,7 @@ static inline __init void hugetlb_cma_reserve(int order)
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 static inline bool hugetlb_pmd_shared(pte_t *pte)
 {
-	return page_count(virt_to_page(pte)) > 1;
+	return atomic_read(&virt_to_page(pte)->pt_share_count);
 }
 #else
 static inline bool hugetlb_pmd_shared(pte_t *pte)

include/linux/mm.h

@@ -2539,6 +2539,9 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
 	if (!pmd_ptlock_init(page))
 		return false;
 	__SetPageTable(page);
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+	atomic_set(&page->pt_share_count, 0);
+#endif
 	inc_lruvec_page_state(page, NR_PAGETABLE);
 	return true;
 }

include/linux/mm_types.h

@@ -173,6 +173,9 @@ struct page {
 			union {
 				struct mm_struct *pt_mm; /* x86 pgds only */
 				atomic_t pt_frag_refcount; /* powerpc */
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+				RH_KABI_BROKEN_INSERT(atomic_t pt_share_count)
+#endif
 			};
 #if ALLOC_SPLIT_PTLOCKS
 			spinlock_t *ptl;

mm/hugetlb.c

@@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta);
 static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
 static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, bool take_locks);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -4834,6 +4836,39 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+void hugetlb_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	/*
+	 * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+	 * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+	 * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+	 * This function is called in the middle of a VMA split operation, with
+	 * MM, VMA and rmap all write-locked to prevent concurrent page table
+	 * walks (except hardware and gup_fast()).
+	 */
+	mmap_assert_write_locked(vma->vm_mm);
+	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
+
+	if (addr & ~PUD_MASK) {
+		unsigned long floor = addr & PUD_MASK;
+		unsigned long ceil = floor + PUD_SIZE;
+
+		if (floor >= vma->vm_start && ceil <= vma->vm_end) {
+			/*
+			 * Locking:
+			 * Use take_locks=false here.
+			 * The file rmap lock is already held.
+			 * The hugetlb VMA lock can't be taken when we already
+			 * hold the file rmap lock, and we don't need it because
+			 * its purpose is to synchronize against concurrent page
+			 * table walks, which are not possible thanks to the
+			 * locks held by our caller.
+			 */
+			hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false);
+		}
+	}
+}
+
 static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
 {
 	return huge_page_size(hstate_vma(vma));
@@ -4978,18 +5013,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/*
-		 * If the pagetables are shared don't copy or take references.
-		 *
-		 * dst_pte == src_pte is the common case of src/dest sharing.
-		 * However, src could have 'unshared' and dst shares with
-		 * another vma. So page_count of ptep page is checked instead
-		 * to reliably determine whether pte is shared.
-		 */
-		if (page_count(virt_to_page(dst_pte)) > 1) {
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+		/* If the pagetables are shared, there is nothing to do */
+		if (atomic_read(&virt_to_page(dst_pte)->pt_share_count)) {
 			addr |= last_addr_mask;
 			continue;
 		}
+#endif
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
@@ -5330,17 +5360,10 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	tlb_end_vma(tlb, vma);
 
 	/*
-	 * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
-	 * could defer the flush until now, since by holding i_mmap_rwsem we
-	 * guaranteed that the last refernece would not be dropped. But we must
-	 * do the flushing before we return, as otherwise i_mmap_rwsem will be
-	 * dropped and the last reference to the shared PMDs page might be
-	 * dropped as well.
-	 *
-	 * In theory we could defer the freeing of the PMD pages as well, but
-	 * huge_pmd_unshare() relies on the exact page_count for the PMD page to
-	 * detect sharing, so we cannot defer the release of the page either.
-	 * Instead, do flush now.
+	 * There is nothing protecting a previously-shared page table that we
+	 * unshared through huge_pmd_unshare() from getting freed after we
+	 * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare()
+	 * succeeded, flush the range corresponding to the pud.
 	 */
 	if (force_flush)
 		tlb_flush_mmu_tlbonly(tlb);
@@ -6726,11 +6749,10 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 	}
 	/*
-	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
-	 * may have cleared our pud entry and done put_page on the page table:
-	 * once we release i_mmap_rwsem, another task can do the final put_page
-	 * and that page table be reused and filled with junk.  If we actually
-	 * did unshare a page of pmds, flush the range corresponding to the pud.
+	 * There is nothing protecting a previously-shared page table that we
+	 * unshared through huge_pmd_unshare() from getting freed after we
+	 * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare()
+	 * succeeded, flush the range corresponding to the pud.
 	 */
 	if (shared_pmd)
 		flush_hugetlb_tlb_range(vma, range.start, range.end);
@@ -7058,7 +7080,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 			spte = hugetlb_walk(svma, saddr,
 					    vma_mmu_pagesize(svma));
 			if (spte) {
-				get_page(virt_to_page(spte));
+				atomic_inc(&virt_to_page(spte)->pt_share_count);
 				break;
 			}
 		}
@@ -7073,7 +7095,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
 		mm_inc_nr_pmds(mm);
 	} else {
-		put_page(virt_to_page(spte));
+		atomic_dec(&virt_to_page(spte)->pt_share_count);
 	}
 	spin_unlock(ptl);
 out:
@@ -7085,10 +7107,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 /*
  * unmap huge page backed by shared pte.
  *
- * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
- * indicated by page_count > 1, unmap is achieved by clearing pud and
- * decrementing the ref count. If count == 1, the pte page is not shared.
- *
  * Called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
@@ -7097,18 +7115,27 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep)
 {
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 	pgd_t *pgd = pgd_offset(mm, addr);
 	p4d_t *p4d = p4d_offset(pgd, addr);
 	pud_t *pud = pud_offset(p4d, addr);
 
 	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	hugetlb_vma_assert_locked(vma);
-	BUG_ON(page_count(virt_to_page(ptep)) == 0);
-	if (page_count(virt_to_page(ptep)) == 1)
+	if (sz != PMD_SIZE)
+		return 0;
+	if (!atomic_read(&virt_to_page(ptep)->pt_share_count))
 		return 0;
 
 	pud_clear(pud);
-	put_page(virt_to_page(ptep));
+	/*
+	 * Once our caller drops the rmap lock, some other process might be
+	 * using this page table as a normal, non-hugetlb page table.
+	 * Wait for pending gup_fast() in other threads to finish before letting
+	 * that happen.
+	 */
+	tlb_remove_table_sync_one();
+	atomic_dec(&virt_to_page(ptep)->pt_share_count);
 	mm_dec_nr_pmds(mm);
 	return 1;
 }
@@ -7340,25 +7367,27 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 }
 
 /*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
+ * If @take_locks is false, the caller must ensure that no concurrent page table
+ * access can happen (except for gup_fast() and hardware page walks).
+ * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like
+ * concurrent page fault handling) and the file rmap lock.
  */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+				   unsigned long start,
+				   unsigned long end,
+				   bool take_locks)
 {
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_notifier_range range;
-	unsigned long address, start, end;
+	unsigned long address;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		return;
 
-	start = ALIGN(vma->vm_start, PUD_SIZE);
-	end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
 	if (start >= end)
 		return;
 
@@ -7370,8 +7399,12 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
 				start, end);
 	mmu_notifier_invalidate_range_start(&range);
-	hugetlb_vma_lock_write(vma);
-	i_mmap_lock_write(vma->vm_file->f_mapping);
+	if (take_locks) {
+		hugetlb_vma_lock_write(vma);
+		i_mmap_lock_write(vma->vm_file->f_mapping);
+	} else {
+		i_mmap_assert_write_locked(vma->vm_file->f_mapping);
+	}
 	for (address = start; address < end; address += PUD_SIZE) {
 		ptep = hugetlb_walk(vma, address, sz);
 		if (!ptep)
@@ -7381,15 +7414,28 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 		spin_unlock(ptl);
 	}
 	flush_hugetlb_tlb_range(vma, start, end);
-	i_mmap_unlock_write(vma->vm_file->f_mapping);
-	hugetlb_vma_unlock_write(vma);
+	if (take_locks) {
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_unlock_write(vma);
+	}
 	/*
 	 * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see
 	 * Documentation/mm/mmu_notifier.rst.
 	 */
 	mmu_notifier_invalidate_range_end(&range);
 }
 
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+	hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
+			ALIGN_DOWN(vma->vm_end, PUD_SIZE),
+			/* take_locks = */ true);
+}
+
 #ifdef CONFIG_CMA
 static bool cma_reserve_called __initdata;
 

mm/mmap.c

@@ -815,7 +815,15 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 again:
+	/*
+	 * Get rid of huge pages and shared page tables straddling the split
+	 * boundary.
+	 */
 	vma_adjust_trans_huge(orig_vma, start, end, adjust_next);
+	if (is_vm_hugetlb_page(orig_vma)) {
+		hugetlb_split(orig_vma, start);
+		hugetlb_split(orig_vma, end);
+	}
 
 	if (file) {
 		mapping = file->f_mapping;

mm/rmap.c

@@ -1556,14 +1556,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 					flush_tlb_range(vma,
 						range.start, range.end);
 					/*
-					 * The ref count of the PMD page was
-					 * dropped which is part of the way map
-					 * counting is done for shared PMDs.
-					 * Return 'true' here.  When there is
-					 * no other sharing, huge_pmd_unshare
-					 * returns false and we will unmap the
-					 * actual page and drop map count
-					 * to zero.
+					 * The PMD table was unmapped,
+					 * consequently unmapping the folio.
 					 */
 					page_vma_mapped_walk_done(&pvmw);
 					break;
@@ -1926,14 +1920,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 						range.start, range.end);
 
 					/*
-					 * The ref count of the PMD page was
-					 * dropped which is part of the way map
-					 * counting is done for shared PMDs.
-					 * Return 'true' here.  When there is
-					 * no other sharing, huge_pmd_unshare
-					 * returns false and we will unmap the
-					 * actual page and drop map count
-					 * to zero.
+					 * The PMD table was unmapped,
+					 * consequently unmapping the folio.
 					 */
 					page_vma_mapped_walk_done(&pvmw);
 					break;