@@ -39,6 +39,14 @@
#include <linux/mm_types.h>
#include <linux/sched.h>
#include <linux/page_table_check.h>
+#include <linux/kpkeys.h>
+
+#ifdef CONFIG_KPKEYS_HARDENED_PGTABLES
+KPKEYS_GUARD_COND(kpkeys_hardened_pgtables, KPKEYS_LVL_PGTABLES,
+ kpkeys_hardened_pgtables_enabled())
+#else
+KPKEYS_GUARD_NOOP(kpkeys_hardened_pgtables)
+#endif
static inline void emit_pte_barriers(void)
{
@@ -366,6 +374,7 @@ static inline pte_t pte_clear_uffd_wp(pte_t pte)
static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
{
+ guard(kpkeys_hardened_pgtables)();
WRITE_ONCE(*ptep, pte);
}
@@ -843,6 +852,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
}
#endif /* __PAGETABLE_PMD_FOLDED */
+ guard(kpkeys_hardened_pgtables)();
WRITE_ONCE(*pmdp, pmd);
if (pmd_valid(pmd))
@@ -909,6 +919,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
return;
}
+ guard(kpkeys_hardened_pgtables)();
WRITE_ONCE(*pudp, pud);
if (pud_valid(pud))
@@ -990,6 +1001,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
return;
}
+ guard(kpkeys_hardened_pgtables)();
WRITE_ONCE(*p4dp, p4d);
queue_pte_barriers();
}
@@ -1118,6 +1130,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
return;
}
+ guard(kpkeys_hardened_pgtables)();
WRITE_ONCE(*pgdp, pgd);
queue_pte_barriers();
}
@@ -1317,6 +1330,7 @@ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma,
{
pte_t old_pte, pte;
+ guard(kpkeys_hardened_pgtables)();
pte = __ptep_get(ptep);
do {
old_pte = pte;
@@ -1363,7 +1377,10 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
static inline pte_t ptep_get_and_clear_anysz(struct mm_struct *mm, pte_t *ptep,
unsigned long pgsize)
{
- pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
+ pte_t pte;
+
+ scoped_guard(kpkeys_hardened_pgtables)
+ pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
switch (pgsize) {
case PAGE_SIZE:
@@ -1434,6 +1451,7 @@ static inline void ___ptep_set_wrprotect(struct mm_struct *mm,
{
pte_t old_pte;
+ guard(kpkeys_hardened_pgtables)();
do {
old_pte = pte;
pte = pte_wrprotect(pte);
@@ -1467,6 +1485,7 @@ static inline void __clear_young_dirty_pte(struct vm_area_struct *vma,
{
pte_t old_pte;
+ guard(kpkeys_hardened_pgtables)();
do {
old_pte = pte;
@@ -1514,6 +1533,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
page_table_check_pmd_set(vma->vm_mm, pmdp, pmd);
+ guard(kpkeys_hardened_pgtables)();
return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
}
#endif
@@ -220,6 +220,8 @@ int __ptep_set_access_flags(struct vm_area_struct *vma,
if (pte_same(pte, entry))
return 0;
+ guard(kpkeys_hardened_pgtables)();
+
/* only preserve the access flags and write permission */
pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
When CONFIG_KPKEYS_HARDENED_PGTABLES is enabled, page tables (both user and kernel) are mapped with a privileged pkey in the linear mapping. As a result, they can only be written at an elevated kpkeys level. Introduce a kpkeys guard that sets POR_EL1 appropriately to allow writing to page tables, and use this guard wherever necessary. The scope is kept as small as possible, so that POR_EL1 is quickly reset to its default value. Where atomics are involved, the guard's scope encompasses the whole loop to avoid switching POR_EL1 unnecessarily. This patch is a no-op if CONFIG_KPKEYS_HARDENED_PGTABLES is disabled (default). Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com> --- arch/arm64/include/asm/pgtable.h | 22 +++++++++++++++++++++- arch/arm64/mm/fault.c | 2 ++ 2 files changed, 23 insertions(+), 1 deletion(-)