| Message ID | 20230801220733.1987762-7-surenb@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | make vma locking more obvious | expand |
* Suren Baghdasaryan <surenb@google.com> [230801 18:07]: > vma_prepare() is currently the central place where vmas are being locked > before vma_complete() applies changes to them. While this is convenient, > it also obscures vma locking and makes it hard to follow the locking rules. > Move vma locking out of vma_prepare() and take vma locks explicitly at the > locations where vmas are being modified. > > Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org> > Signed-off-by: Suren Baghdasaryan <surenb@google.com> > Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> > --- > mm/mmap.c | 26 ++++++++++++++++---------- > 1 file changed, 16 insertions(+), 10 deletions(-) > > diff --git a/mm/mmap.c b/mm/mmap.c > index 850a39dee075..e59d83cb1d7a 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -476,16 +476,6 @@ static inline void init_vma_prep(struct vma_prepare *vp, > */ > static inline void vma_prepare(struct vma_prepare *vp) > { > - vma_start_write(vp->vma); > - if (vp->adj_next) > - vma_start_write(vp->adj_next); > - if (vp->insert) > - vma_start_write(vp->insert); > - if (vp->remove) > - vma_start_write(vp->remove); > - if (vp->remove2) > - vma_start_write(vp->remove2); > - > if (vp->file) { > uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); > > @@ -650,6 +640,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, > bool remove_next = false; > struct vma_prepare vp; > > + vma_start_write(vma); This lock made me think about the lock in dup_anon_vma().. the only reason we need to dup the anon vma is because the VMA _will_ be modified.. So if we are to remove next the dup_anon_vma() call may lock vma again. This happens multiple times through this patch set. If we lock both dst and src VMAs before calling dup_anon_vma, then I think it will become more clear in the code below which VMAs are locked. We could remove the lock in the dup_anon_vma() (and replace with an assert?), and drop the vma locking of "vma". I think this would address the confusion of the locking below that I experienced and avoid calling the vma_start_write() multiple times for the same vma. I mean, having the vma_start_write(vma) obscures which VMA is locked as well. > if (next && (vma != next) && (end == next->vm_end)) { > int ret; > > @@ -657,6 +648,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, > ret = dup_anon_vma(vma, next); > if (ret) > return ret; > + vma_start_write(next); > } > > init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); > @@ -708,6 +700,8 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, > if (vma_iter_prealloc(vmi)) > return -ENOMEM; > > + vma_start_write(vma); > + > init_vma_prep(&vp, vma); > vma_prepare(&vp); > vma_adjust_trans_huge(vma, start, end, 0); > @@ -946,10 +940,12 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > /* Can we merge both the predecessor and the successor? */ > if (merge_prev && merge_next && > is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { > + vma_start_write(next); > remove = next; /* case 1 */ > vma_end = next->vm_end; > err = dup_anon_vma(prev, next); > if (curr) { /* case 6 */ > + vma_start_write(curr); > remove = curr; > remove2 = next; > if (!next->anon_vma) > @@ -958,6 +954,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > } else if (merge_prev) { /* case 2 */ > if (curr) { > err = dup_anon_vma(prev, curr); > + vma_start_write(curr); > if (end == curr->vm_end) { /* case 7 */ > remove = curr; > } else { /* case 5 */ > @@ -969,6 +966,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > res = next; > if (prev && addr < prev->vm_end) { /* case 4 */ > vma_end = addr; > + vma_start_write(next); > adjust = next; > adj_start = -(prev->vm_end - addr); > err = dup_anon_vma(next, prev); > @@ -983,6 +981,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > vma_pgoff = next->vm_pgoff - pglen; > if (curr) { /* case 8 */ > vma_pgoff = curr->vm_pgoff; > + vma_start_write(curr); > remove = curr; > err = dup_anon_vma(next, curr); > } > @@ -996,6 +995,8 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > if (vma_iter_prealloc(vmi)) > return NULL; > > + vma_start_write(vma); > + > init_multi_vma_prep(&vp, vma, adjust, remove, remove2); > VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && > vp.anon_vma != adjust->anon_vma); > @@ -2373,6 +2374,9 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, > if (new->vm_ops && new->vm_ops->open) > new->vm_ops->open(new); > > + vma_start_write(vma); > + vma_start_write(new); > + > init_vma_prep(&vp, vma); > vp.insert = new; > vma_prepare(&vp); > @@ -3078,6 +3082,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, > if (vma_iter_prealloc(vmi)) > goto unacct_fail; > > + vma_start_write(vma); > + > init_vma_prep(&vp, vma); > vma_prepare(&vp); > vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); > -- > 2.41.0.585.gd2178a4bd4-goog >
On Wed, Aug 2, 2023 at 9:59 AM Liam R. Howlett <Liam.Howlett@oracle.com> wrote: > > * Suren Baghdasaryan <surenb@google.com> [230801 18:07]: > > vma_prepare() is currently the central place where vmas are being locked > > before vma_complete() applies changes to them. While this is convenient, > > it also obscures vma locking and makes it hard to follow the locking rules. > > Move vma locking out of vma_prepare() and take vma locks explicitly at the > > locations where vmas are being modified. > > > > Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org> > > Signed-off-by: Suren Baghdasaryan <surenb@google.com> > > Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> > > --- > > mm/mmap.c | 26 ++++++++++++++++---------- > > 1 file changed, 16 insertions(+), 10 deletions(-) > > > > diff --git a/mm/mmap.c b/mm/mmap.c > > index 850a39dee075..e59d83cb1d7a 100644 > > --- a/mm/mmap.c > > +++ b/mm/mmap.c > > @@ -476,16 +476,6 @@ static inline void init_vma_prep(struct vma_prepare *vp, > > */ > > static inline void vma_prepare(struct vma_prepare *vp) > > { > > - vma_start_write(vp->vma); > > - if (vp->adj_next) > > - vma_start_write(vp->adj_next); > > - if (vp->insert) > > - vma_start_write(vp->insert); > > - if (vp->remove) > > - vma_start_write(vp->remove); > > - if (vp->remove2) > > - vma_start_write(vp->remove2); > > - > > if (vp->file) { > > uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); > > > > @@ -650,6 +640,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, > > bool remove_next = false; > > struct vma_prepare vp; > > > > + vma_start_write(vma); > > This lock made me think about the lock in dup_anon_vma().. the only > reason we need to dup the anon vma is because the VMA _will_ be > modified.. So if we are to remove next the dup_anon_vma() call may lock > vma again. This happens multiple times through this patch set. > > If we lock both dst and src VMAs before calling dup_anon_vma, then I > think it will become more clear in the code below which VMAs are locked. > We could remove the lock in the dup_anon_vma() (and replace with an > assert?), and drop the vma locking of "vma". > > I think this would address the confusion of the locking below that I > experienced and avoid calling the vma_start_write() multiple times for > the same vma. I mean, having the vma_start_write(vma) obscures which > VMA is locked as well. Agree, it would result in an easier to understand locking code. I'll move the lock outside of dup_anon_vma() and will replace it with an assert. Thanks! > > > > if (next && (vma != next) && (end == next->vm_end)) { > > int ret; > > > > @@ -657,6 +648,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, > > ret = dup_anon_vma(vma, next); > > if (ret) > > return ret; > > + vma_start_write(next); > > } > > > > init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); > > @@ -708,6 +700,8 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, > > if (vma_iter_prealloc(vmi)) > > return -ENOMEM; > > > > + vma_start_write(vma); > > + > > init_vma_prep(&vp, vma); > > vma_prepare(&vp); > > vma_adjust_trans_huge(vma, start, end, 0); > > @@ -946,10 +940,12 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > > /* Can we merge both the predecessor and the successor? */ > > if (merge_prev && merge_next && > > is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { > > + vma_start_write(next); > > remove = next; /* case 1 */ > > vma_end = next->vm_end; > > err = dup_anon_vma(prev, next); > > if (curr) { /* case 6 */ > > + vma_start_write(curr); > > remove = curr; > > remove2 = next; > > if (!next->anon_vma) > > @@ -958,6 +954,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > > } else if (merge_prev) { /* case 2 */ > > if (curr) { > > err = dup_anon_vma(prev, curr); > > + vma_start_write(curr); > > if (end == curr->vm_end) { /* case 7 */ > > remove = curr; > > } else { /* case 5 */ > > @@ -969,6 +966,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > > res = next; > > if (prev && addr < prev->vm_end) { /* case 4 */ > > vma_end = addr; > > + vma_start_write(next); > > adjust = next; > > adj_start = -(prev->vm_end - addr); > > err = dup_anon_vma(next, prev); > > @@ -983,6 +981,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > > vma_pgoff = next->vm_pgoff - pglen; > > if (curr) { /* case 8 */ > > vma_pgoff = curr->vm_pgoff; > > + vma_start_write(curr); > > remove = curr; > > err = dup_anon_vma(next, curr); > > } > > @@ -996,6 +995,8 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, > > if (vma_iter_prealloc(vmi)) > > return NULL; > > > > + vma_start_write(vma); > > + > > init_multi_vma_prep(&vp, vma, adjust, remove, remove2); > > VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && > > vp.anon_vma != adjust->anon_vma); > > @@ -2373,6 +2374,9 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, > > if (new->vm_ops && new->vm_ops->open) > > new->vm_ops->open(new); > > > > + vma_start_write(vma); > > + vma_start_write(new); > > + > > init_vma_prep(&vp, vma); > > vp.insert = new; > > vma_prepare(&vp); > > @@ -3078,6 +3082,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, > > if (vma_iter_prealloc(vmi)) > > goto unacct_fail; > > > > + vma_start_write(vma); > > + > > init_vma_prep(&vp, vma); > > vma_prepare(&vp); > > vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); > > -- > > 2.41.0.585.gd2178a4bd4-goog > >
diff --git a/mm/mmap.c b/mm/mmap.c index 850a39dee075..e59d83cb1d7a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -476,16 +476,6 @@ static inline void init_vma_prep(struct vma_prepare *vp, */ static inline void vma_prepare(struct vma_prepare *vp) { - vma_start_write(vp->vma); - if (vp->adj_next) - vma_start_write(vp->adj_next); - if (vp->insert) - vma_start_write(vp->insert); - if (vp->remove) - vma_start_write(vp->remove); - if (vp->remove2) - vma_start_write(vp->remove2); - if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); @@ -650,6 +640,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, bool remove_next = false; struct vma_prepare vp; + vma_start_write(vma); if (next && (vma != next) && (end == next->vm_end)) { int ret; @@ -657,6 +648,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, ret = dup_anon_vma(vma, next); if (ret) return ret; + vma_start_write(next); } init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); @@ -708,6 +700,8 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, if (vma_iter_prealloc(vmi)) return -ENOMEM; + vma_start_write(vma); + init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); @@ -946,10 +940,12 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { + vma_start_write(next); remove = next; /* case 1 */ vma_end = next->vm_end; err = dup_anon_vma(prev, next); if (curr) { /* case 6 */ + vma_start_write(curr); remove = curr; remove2 = next; if (!next->anon_vma) @@ -958,6 +954,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, } else if (merge_prev) { /* case 2 */ if (curr) { err = dup_anon_vma(prev, curr); + vma_start_write(curr); if (end == curr->vm_end) { /* case 7 */ remove = curr; } else { /* case 5 */ @@ -969,6 +966,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, res = next; if (prev && addr < prev->vm_end) { /* case 4 */ vma_end = addr; + vma_start_write(next); adjust = next; adj_start = -(prev->vm_end - addr); err = dup_anon_vma(next, prev); @@ -983,6 +981,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_pgoff = next->vm_pgoff - pglen; if (curr) { /* case 8 */ vma_pgoff = curr->vm_pgoff; + vma_start_write(curr); remove = curr; err = dup_anon_vma(next, curr); } @@ -996,6 +995,8 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vma_iter_prealloc(vmi)) return NULL; + vma_start_write(vma); + init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); @@ -2373,6 +2374,9 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); + vma_start_write(vma); + vma_start_write(new); + init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); @@ -3078,6 +3082,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, if (vma_iter_prealloc(vmi)) goto unacct_fail; + vma_start_write(vma); + init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0);