s390/mm: four page table levels vs. fork

commit 3446c13b268af86391d06611327006b059b8bab1 upstream.

The fork of a process with four page table levels is broken since
git commit 6252d702c5311ce9 "[S390] dynamic page tables."

All new mm contexts are created with three page table levels and
an asce limit of 4TB. If the parent has four levels dup_mmap will
add vmas to the new context which are outside of the asce limit.
The subsequent call to copy_page_range will walk the three level
page table structure of the new process with non-zero pgd and pud
indexes. This leads to memory clobbers as the pgd_index *and* the
pud_index is added to the mm->pgd pointer without a pgd_deref
in between.

The init_new_context() function is selecting the number of page
table levels for a new context. The function is used by mm_init()
which in turn is called by dup_mm() and mm_alloc(). These two are
used by fork() and exec(). The init_new_context() function can
distinguish the two cases by looking at mm->context.asce_limit,
for fork() the mm struct has been copied and the number of page
table levels may not change. For exec() the mm_alloc() function
set the new mm structure to zero, in this case a three-level page
table is created as the temporary stack space is located at
STACK_TOP_MAX = 4TB.

This fixes CVE-2016-2143.

Reported-by: Marcin Kościelnicki <koriakin@0x04.net>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16:
 - 31-bit s390 is still supported so keep the #ifdef CONFIG_64BIT conditions
 - PMDs are not accounted so don't call mm_inc_nr_pmds()
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 3815bfea1b2d23cc55ce8e1afaf2da371fc04bc6..d958de53d34a0ae2b25ca8a69f095f917570a2ec 100644 (file)
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,16 +15,22 @@
 static inline int init_new_context(struct task_struct *tsk,
                                   struct mm_struct *mm)
 {
+       spin_lock_init(&mm->context.list_lock);
+       INIT_LIST_HEAD(&mm->context.pgtable_list);
+       INIT_LIST_HEAD(&mm->context.gmap_list);
        cpumask_clear(&mm->context.cpu_attach_mask);
        atomic_set(&mm->context.attach_count, 0);
        mm->context.flush_mm = 0;
-       mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
-#ifdef CONFIG_64BIT
-       mm->context.asce_bits |= _ASCE_TYPE_REGION3;
-#endif
        mm->context.has_pgste = 0;
        mm->context.use_skey = 0;
-       mm->context.asce_limit = STACK_TOP_MAX;
+       if (mm->context.asce_limit == 0) {
+               /* context created by exec, set asce limit to 4TB */
+               mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
+#ifdef CONFIG_64BIT
+               mm->context.asce_bits |= _ASCE_TYPE_REGION3;
+#endif
+               mm->context.asce_limit = STACK_TOP_MAX;
+       }
        crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
        return 0;
 }
@@ -110,10 +116,6 @@ static inline void activate_mm(struct mm_struct *prev,
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
                                 struct mm_struct *mm)
 {
-#ifdef CONFIG_64BIT
-       if (oldmm->context.asce_limit < mm->context.asce_limit)
-               crst_table_downgrade(mm, oldmm->context.asce_limit);
-#endif
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)

diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 9e18a61d3df39c0c96f81032ae5f67ad427fa32c..9e0e1176a2221022164993ea7e474c5f5ae500ec 100644 (file)
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -124,12 +124,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-       spin_lock_init(&mm->context.list_lock);
-       INIT_LIST_HEAD(&mm->context.pgtable_list);
-       INIT_LIST_HEAD(&mm->context.gmap_list);
-       return (pgd_t *) crst_table_alloc(mm);
+       unsigned long *table = crst_table_alloc(mm);
+
+       if (!table)
+               return NULL;
+       if (mm->context.asce_limit == (1UL << 31)) {
+               /* Forking a compat process with 2 page table levels */
+               if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+                       crst_table_free(mm, table);
+                       return NULL;
+               }
+       }
+       return (pgd_t *) table;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+       if (mm->context.asce_limit == (1UL << 31))
+               pgtable_pmd_page_dtor(virt_to_page(pgd));
+       crst_table_free(mm, (unsigned long *) pgd);
 }
-#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
 
 static inline void pmd_populate(struct mm_struct *mm,
                                pmd_t *pmd, pgtable_t pte)