From: Fares Mehanna faresx@amazon.de
To make sure the kernel mm-local mapping is untouched by the user, we will seal the VMA before changing the protection to be used by the kernel.
This will guarantee that userspace can't unmap or alter this VMA while it is being used by the kernel.
After the kernel is done with the secret memory, it will unseal the VMA to be able to unmap and free it.
Unseal operation is not exposed to userspace.
Signed-off-by: Fares Mehanna faresx@amazon.de Signed-off-by: Roman Kagan rkagan@amazon.de --- mm/internal.h | 7 +++++ mm/mseal.c | 81 ++++++++++++++++++++++++++++++++------------------- 2 files changed, 58 insertions(+), 30 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h index b2c75b12014e..5278989610f5 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1453,6 +1453,8 @@ bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end); bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior); +/* mm's mmap write lock must be taken before seal/unseal operation */ +int do_mseal(unsigned long start, unsigned long end, bool seal); #else static inline int can_do_mseal(unsigned long flags) { @@ -1470,6 +1472,11 @@ static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, { return true; } + +static inline int do_mseal(unsigned long start, unsigned long end, bool seal) +{ + return -EINVAL; +} #endif
#ifdef CONFIG_SHRINKER_DEBUG diff --git a/mm/mseal.c b/mm/mseal.c index bf783bba8ed0..331745ac7064 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -26,6 +26,11 @@ static inline void set_vma_sealed(struct vm_area_struct *vma) vm_flags_set(vma, VM_SEALED); }
+static inline void clear_vma_sealed(struct vm_area_struct *vma) +{ + vm_flags_clear(vma, VM_SEALED); +} + /* * check if a vma is sealed for modification. * return true, if modification is allowed. @@ -109,7 +114,7 @@ bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long
static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, - unsigned long end, vm_flags_t newflags) + unsigned long end, vm_flags_t newflags, bool seal) { int ret = 0; vm_flags_t oldflags = vma->vm_flags; @@ -123,7 +128,10 @@ static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, goto out; }
- set_vma_sealed(vma); + if (seal) + set_vma_sealed(vma); + else + clear_vma_sealed(vma); out: *prev = vma; return ret; @@ -159,9 +167,9 @@ static int check_mm_seal(unsigned long start, unsigned long end) }
/* - * Apply sealing. + * Apply sealing / unsealing. */ -static int apply_mm_seal(unsigned long start, unsigned long end) +static int apply_mm_seal(unsigned long start, unsigned long end, bool seal) { unsigned long nstart; struct vm_area_struct *vma, *prev; @@ -183,11 +191,14 @@ static int apply_mm_seal(unsigned long start, unsigned long end) unsigned long tmp; vm_flags_t newflags;
- newflags = vma->vm_flags | VM_SEALED; + if (seal) + newflags = vma->vm_flags | VM_SEALED; + else + newflags = vma->vm_flags & ~(VM_SEALED); tmp = vma->vm_end; if (tmp > end) tmp = end; - error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags); + error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags, seal); if (error) return error; nstart = vma_iter_end(&vmi); @@ -196,6 +207,37 @@ static int apply_mm_seal(unsigned long start, unsigned long end) return 0; }
+int do_mseal(unsigned long start, unsigned long end, bool seal) +{ + int ret; + + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + /* + * First pass, this helps to avoid + * partial sealing in case of error in input address range, + * e.g. ENOMEM error. + */ + ret = check_mm_seal(start, end); + if (ret) + goto out; + + /* + * Second pass, this should success, unless there are errors + * from vma_modify_flags, e.g. merge/split error, or process + * reaching the max supported VMAs, however, those cases shall + * be rare. + */ + ret = apply_mm_seal(start, end, seal); + +out: + return ret; +} + /* * mseal(2) seals the VM's meta data from * selected syscalls. @@ -248,7 +290,7 @@ static int apply_mm_seal(unsigned long start, unsigned long end) * * unseal() is not supported. */ -static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +static int __do_mseal(unsigned long start, size_t len_in, unsigned long flags) { size_t len; int ret = 0; @@ -269,33 +311,12 @@ static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) return -EINVAL;
end = start + len; - if (end < start) - return -EINVAL; - - if (end == start) - return 0;
if (mmap_write_lock_killable(mm)) return -EINTR;
- /* - * First pass, this helps to avoid - * partial sealing in case of error in input address range, - * e.g. ENOMEM error. - */ - ret = check_mm_seal(start, end); - if (ret) - goto out; + ret = do_mseal(start, end, true);
- /* - * Second pass, this should success, unless there are errors - * from vma_modify_flags, e.g. merge/split error, or process - * reaching the max supported VMAs, however, those cases shall - * be rare. - */ - ret = apply_mm_seal(start, end); - -out: mmap_write_unlock(current->mm); return ret; } @@ -303,5 +324,5 @@ static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long, flags) { - return do_mseal(start, len, flags); + return __do_mseal(start, len, flags); }