diff options
| -rw-r--r-- | arch/x86/include/asm/pgtable.h | 8 | ||||
| -rw-r--r-- | arch/x86/mm/mmap.c | 21 | ||||
| -rw-r--r-- | include/asm-generic/pgtable.h | 12 | ||||
| -rw-r--r-- | mm/memory.c | 29 | ||||
| -rw-r--r-- | mm/mprotect.c | 49 |
5 files changed, 112 insertions, 7 deletions
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2ed1556d99b1..70e2248353cb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -942,6 +942,14 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) } #endif +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 307f60ecfc6d..9a055ea279eb 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -121,3 +121,24 @@ const char *arch_vma_name(struct vm_area_struct *vma) return "[mpx]"; return NULL; } + +/* + * Only allow root to set high MMIO mappings to PROT_NONE. + * This prevents an unpriv. user to set them to PROT_NONE and invert + * them, then pointing to valid memory for L1TF speculation. + * + * Note: for locked down kernels may want to disable the root override. + */ +bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return true; + if (!__pte_needs_invert(pgprot_val(prot))) + return true; + /* If it's real memory always allow */ + if (pfn_valid(pfn)) + return true; + if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN)) + return false; + return true; +} diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 25b793325b09..976f749099ef 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -805,4 +805,16 @@ static inline int pmd_free_pte_page(pmd_t *pmd) #define io_remap_pfn_range remap_pfn_range #endif +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/memory.c b/mm/memory.c index 78efb8c7ee20..d5bb1465d30c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1645,6 +1645,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, if (track_pfn_insert(vma, &pgprot, pfn)) return -EINVAL; + if (!pfn_modify_allowed(pfn, pgprot)) + return -EACCES; + ret = insert_pfn(vma, addr, pfn, pgprot); return ret; @@ -1663,6 +1666,9 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, if (track_pfn_insert(vma, &pgprot, pfn)) return -EINVAL; + if (!pfn_modify_allowed(pfn, pgprot)) + return -EACCES; + /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* @@ -1691,6 +1697,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; spinlock_t *ptl; + int err = 0; pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) @@ -1698,12 +1705,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); + if (!pfn_modify_allowed(pfn, prot)) { + err = -EACCES; + break; + } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); - return 0; + return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, @@ -1712,6 +1723,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, { pmd_t *pmd; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); @@ -1720,9 +1732,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); - if (remap_pte_range(mm, pmd, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (pmd++, addr = next, addr != end); return 0; } @@ -1733,6 +1746,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, { pud_t *pud; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, pgd, addr); @@ -1740,9 +1754,10 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, return -ENOMEM; do { next = pud_addr_end(addr, end); - if (remap_pmd_range(mm, pud, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (pud++, addr = next, addr != end); return 0; } diff --git a/mm/mprotect.c b/mm/mprotect.c index c0b4b2a49462..a277f3412a5d 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -255,6 +255,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, return pages; } +static int prot_none_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_test(unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return 0; +} + +static int prot_none_walk(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long newflags) +{ + pgprot_t new_pgprot = vm_get_page_prot(newflags); + struct mm_walk prot_none_walk = { + .pte_entry = prot_none_pte_entry, + .hugetlb_entry = prot_none_hugetlb_entry, + .test_walk = prot_none_test, + .mm = current->mm, + .private = &new_pgprot, + }; + + return walk_page_range(start, end, &prot_none_walk); +} + int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags) @@ -273,6 +309,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, } /* + * Do PROT_NONE PFN permission checks here when we can still + * bail out without undoing a lot of state. This is a rather + * uncommon case, so doesn't need to be very optimized. + */ + if (arch_has_pfn_modify_check() && + (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) { + error = prot_none_walk(vma, start, end, newflags); + if (error) + return error; + } + + /* * If we make a private mapping writable we increase our commit; * but (without finer accounting) cannot reduce our commit if we * make it unwritable again. hugetlb mapping were accounted for |