* Pedro Falcato <pedro.falcato@xxxxxxxxx> [240807 17:13]:
> Replace can_modify_mm_madv() with a single vma variant, and associated
> checks in madvise.
>
> While we're at it, also invert the order of checks in:
> if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma))
>
> Checking if we can modify the vma itself (through vm_flags) is
> certainly cheaper than is_ro_anon() due to arch_vma_access_permitted()
> looking at e.g pkeys registers (with extra branches) in some
> architectures.
Doesn't this also allow for partial madvise success? If you pass a
range across vmas, then it will fail once it encounters an mseal'ed vma.
This change should probably be reflected in the change log.
>
> Signed-off-by: Pedro Falcato <pedro.falcato@xxxxxxxxx>
> ---
> mm/internal.h | 6 ++----
> mm/madvise.c | 13 +++----------
> mm/mseal.c | 17 ++++-------------
> 3 files changed, 9 insertions(+), 27 deletions(-)
>
> diff --git a/mm/internal.h b/mm/internal.h
> index 90f50f3c4cf..3f9a5c17626 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -1373,8 +1373,7 @@ static inline bool can_modify_vma(struct vm_area_struct *vma)
>
> 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);
> +bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior);
> #else
> static inline int can_do_mseal(unsigned long flags)
> {
> @@ -1387,8 +1386,7 @@ static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start,
> return true;
> }
>
> -static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
> - unsigned long end, int behavior)
> +static inline bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
> {
> return true;
> }
> diff --git a/mm/madvise.c b/mm/madvise.c
> index 89089d84f8d..4e64770be16 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -1031,6 +1031,9 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
> struct anon_vma_name *anon_name;
> unsigned long new_flags = vma->vm_flags;
>
> + if (unlikely(!can_modify_vma_madv(vma, behavior)))
> + return -EPERM;
> +
> switch (behavior) {
> case MADV_REMOVE:
> return madvise_remove(vma, prev, start, end);
> @@ -1448,15 +1451,6 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
> start = untagged_addr_remote(mm, start);
> end = start + len;
>
> - /*
> - * Check if the address range is sealed for do_madvise().
> - * can_modify_mm_madv assumes we have acquired the lock on MM.
> - */
> - if (unlikely(!can_modify_mm_madv(mm, start, end, behavior))) {
> - error = -EPERM;
> - goto out;
> - }
> -
Funny, this check stopped populate madvise operations. The new code
does not, which is probably better and fine.
> blk_start_plug(&plug);
> switch (behavior) {
> case MADV_POPULATE_READ:
> @@ -1470,7 +1464,6 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
> }
> blk_finish_plug(&plug);
>
> -out:
> if (write)
> mmap_write_unlock(mm);
> else
> diff --git a/mm/mseal.c b/mm/mseal.c
> index 4591ae8d29c..6559242dd05 100644
> --- a/mm/mseal.c
> +++ b/mm/mseal.c
> @@ -67,24 +67,15 @@ bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end)
> }
>
> /*
> - * Check if the vmas of a memory range are allowed to be modified by madvise.
> - * the memory ranger can have a gap (unallocated memory).
> - * return true, if it is allowed.
> + * Check if a vma is allowed to be modified by madvise.
> */
> -bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end,
> - int behavior)
> +bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
> {
> - struct vm_area_struct *vma;
> -
> - VMA_ITERATOR(vmi, mm, start);
> -
> if (!is_madv_discard(behavior))
> return true;
>
> - /* going through each vma to check. */
> - for_each_vma_range(vmi, vma, end)
> - if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma)))
> - return false;
> + if (unlikely(!can_modify_vma(vma) && is_ro_anon(vma)))
> + return false;
>
> /* Allow by default. */
> return true;
> --
> 2.46.0
>
