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 <[email protected]> --- arch/arm64/include/asm/pgtable.h | 22 +++++++++++++++++++++- arch/arm64/mm/fault.c | 2 ++ 2 files changed, 23 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b3e58735c49b..8c85e23223da 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -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) { @@ -363,6 +371,7 @@ 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); } @@ -830,6 +839,7 @@ 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)) @@ -890,6 +900,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud) return; } + guard(kpkeys_hardened_pgtables)(); WRITE_ONCE(*pudp, pud); if (pud_valid(pud)) @@ -971,6 +982,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) return; } + guard(kpkeys_hardened_pgtables)(); WRITE_ONCE(*p4dp, p4d); queue_pte_barriers(); } @@ -1099,6 +1111,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) return; } + guard(kpkeys_hardened_pgtables)(); WRITE_ONCE(*pgdp, pgd); queue_pte_barriers(); } @@ -1295,6 +1308,7 @@ 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; @@ -1343,7 +1357,10 @@ 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: @@ -1416,6 +1433,7 @@ 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); @@ -1449,6 +1467,7 @@ static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, { pte_t old_pte; + guard(kpkeys_hardened_pgtables)(); do { old_pte = pte; @@ -1496,6 +1515,7 @@ 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, address, pmdp, pmd); + guard(kpkeys_hardened_pgtables)(); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index be9dab2c7d6a..7e230499f7fe 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -214,6 +214,8 @@ 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; -- 2.51.2
