When serving a page fault, maybe_mkwrite() makes a PTE writable if its vma
has VM_WRITE.
A shadow stack vma has VM_SHADOW_STACK. Its PTEs have _PAGE_DIRTY, but not
_PAGE_WRITE. In fork(), _PAGE_DIRTY is cleared to cause copy-on-write,
and in the page fault handler, _PAGE_DIRTY is restored and the shadow stack
page is writable again.
Introduce an x86 version of maybe_mkwrite(), which sets proper PTE bits
according to VM flags.
Apply the same changes to maybe_pmd_mkwrite().
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
v24:
- Instead of doing arch_maybe_mkwrite(), overwrite maybe*_mkwrite() with x86
versions.
- Change VM_SHSTK to VM_SHADOW_STACK.
arch/x86/include/asm/pgtable.h | 8 ++++++++
arch/x86/mm/pgtable.c | 20 ++++++++++++++++++++
include/linux/mm.h | 2 ++
mm/huge_memory.c | 2 ++
4 files changed, 32 insertions(+)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 46d9394b884f..51cdf14488b7 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1686,6 +1686,14 @@ static inline bool arch_faults_on_old_pte(void)
return false;
}
+#define maybe_mkwrite maybe_mkwrite
+extern pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define maybe_pmd_mkwrite maybe_pmd_mkwrite
+extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f6a9e2e36642..e778dbbef3d8 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -610,6 +610,26 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
}
#endif
+pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_flags & VM_WRITE))
+ pte = pte_mkwrite(pte);
+ else if (likely(vma->vm_flags & VM_SHADOW_STACK))
+ pte = pte_mkwrite_shstk(pte);
+ return pte;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_flags & VM_WRITE))
+ pmd = pmd_mkwrite(pmd);
+ else if (likely(vma->vm_flags & VM_SHADOW_STACK))
+ pmd = pmd_mkwrite_shstk(pmd);
+ return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
/**
* reserve_top_address - reserves a hole in the top of kernel address space
* @reserve - size of hole to reserve
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 08282eb2f195..6ac9b3e9a865 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -993,12 +993,14 @@ void free_compound_page(struct page *page);
* pte_mkwrite. But get_user_pages can cause write faults for mappings
* that do not have writing enabled, when used by access_process_vm.
*/
+#ifndef maybe_mkwrite
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pte = pte_mkwrite(pte);
return pte;
}
+#endif
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ae907a9c2050..8203bd6ae4bd 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -478,12 +478,14 @@ static int __init setup_transparent_hugepage(char *str)
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
+#ifndef maybe_pmd_mkwrite
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pmd = pmd_mkwrite(pmd);
return pmd;
}
+#endif
#ifdef CONFIG_MEMCG
static inline struct deferred_split *get_deferred_split_queue(struct page *page)
--
2.21.0
