| Message ID | 20240704182718.2653918-11-Liam.Howlett@oracle.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Avoid MAP_FIXED gap exposure | expand |
On Thu, Jul 04, 2024 at 02:27:12PM GMT, Liam R. Howlett wrote: > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > Instead of moving (or leaving) the vma iterator pointing at the previous > vma, leave it pointing at the insert location. Pointing the vma > iterator at the insert location allows for a cleaner walk of the vma > tree for MAP_FIXED and the no expansion cases. I mean, it's funny I litearlly just asked why it was being left pointing at prev and I guess this answers that basically :) > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > --- > mm/mmap.c | 28 ++++++++++++++-------------- > 1 file changed, 14 insertions(+), 14 deletions(-) > > diff --git a/mm/mmap.c b/mm/mmap.c > index f5b33de4e717..ecf55d32e804 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > vms_complete_munmap_vmas(&vms, &mas_detach); > next = vms.next; > prev = vms.prev; > - vma_prev(&vmi); > vma = NULL; > } else { > next = vma_next(&vmi); > prev = vma_prev(&vmi); > + if (prev) > + vma_iter_next_range(&vmi); > } > > /* > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > vm_flags |= VM_ACCOUNT; > } > > - if (vm_flags & VM_SPECIAL) { > - if (prev) > - vma_iter_next_range(&vmi); > + if (vm_flags & VM_SPECIAL) > goto cannot_expand; > - } > > /* Attempt to expand an old mapping */ > /* Check next */ > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > merge_start = prev->vm_start; > vma = prev; > vm_pgoff = prev->vm_pgoff; > - } else if (prev) { > - vma_iter_next_range(&vmi); > + vma_prev(&vmi); Why not vma_iter_prev_range()? > } > > - /* Actually expand, if possible */ > - if (vma && > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > - khugepaged_enter_vma(vma, vm_flags); > - goto expanded; > + if (vma) { > + /* Actually expand, if possible */ > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > + khugepaged_enter_vma(vma, vm_flags); > + goto expanded; > + } > + > + /* If the expand fails, then reposition the vma iterator */ > + if (unlikely(vma == prev)) > + vma_iter_set(&vmi, addr); > } > > - if (vma == prev) > - vma_iter_set(&vmi, addr); > cannot_expand: > > /* > -- > 2.43.0 > Looks good to me, Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
* Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [240705 16:18]: > On Thu, Jul 04, 2024 at 02:27:12PM GMT, Liam R. Howlett wrote: > > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > > > Instead of moving (or leaving) the vma iterator pointing at the previous > > vma, leave it pointing at the insert location. Pointing the vma > > iterator at the insert location allows for a cleaner walk of the vma > > tree for MAP_FIXED and the no expansion cases. > > I mean, it's funny I litearlly just asked why it was being left pointing at > prev and I guess this answers that basically :) > > > > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > > --- > > mm/mmap.c | 28 ++++++++++++++-------------- > > 1 file changed, 14 insertions(+), 14 deletions(-) > > > > diff --git a/mm/mmap.c b/mm/mmap.c > > index f5b33de4e717..ecf55d32e804 100644 > > --- a/mm/mmap.c > > +++ b/mm/mmap.c > > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > vms_complete_munmap_vmas(&vms, &mas_detach); > > next = vms.next; > > prev = vms.prev; > > - vma_prev(&vmi); > > vma = NULL; > > } else { > > next = vma_next(&vmi); > > prev = vma_prev(&vmi); > > + if (prev) > > + vma_iter_next_range(&vmi); > > } > > > > /* > > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > vm_flags |= VM_ACCOUNT; > > } > > > > - if (vm_flags & VM_SPECIAL) { > > - if (prev) > > - vma_iter_next_range(&vmi); > > + if (vm_flags & VM_SPECIAL) > > goto cannot_expand; > > - } > > > > /* Attempt to expand an old mapping */ > > /* Check next */ > > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > merge_start = prev->vm_start; > > vma = prev; > > vm_pgoff = prev->vm_pgoff; > > - } else if (prev) { > > - vma_iter_next_range(&vmi); > > + vma_prev(&vmi); > > Why not vma_iter_prev_range()? In any situation where we arrive at prev being able to merge with the current, the prev->end == addr and we are already pointing at the gap with addr. So vma_iter_prev_range() and vma_prev() will do the same thing here. I thought a lot about this (and created a small test application since it is so difficult to test vma merging right now..). If we do not clear the gap, it is possible we will be pointing at the first vma in the range, and not addr at all when we call vms_gather_munmap_vmas(), but the loop at the end of the gather function ensures the vmi is at the correct address (vms->start is in the range). So the result is that we consistently point to the correct location and so these two calls will do the same thing. > > > } > > > > - /* Actually expand, if possible */ > > - if (vma && > > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > - khugepaged_enter_vma(vma, vm_flags); > > - goto expanded; > > + if (vma) { > > + /* Actually expand, if possible */ > > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > + khugepaged_enter_vma(vma, vm_flags); > > + goto expanded; > > + } > > + > > + /* If the expand fails, then reposition the vma iterator */ > > + if (unlikely(vma == prev)) > > + vma_iter_set(&vmi, addr); > > } > > > > - if (vma == prev) > > - vma_iter_set(&vmi, addr); > > cannot_expand: > > > > /* > > -- > > 2.43.0 > > > Looks good to me, > > Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Thanks!
On Fri, Jul 05, 2024 at 04:56:34PM GMT, Liam R. Howlett wrote: > * Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [240705 16:18]: > > On Thu, Jul 04, 2024 at 02:27:12PM GMT, Liam R. Howlett wrote: > > > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > > > > > Instead of moving (or leaving) the vma iterator pointing at the previous > > > vma, leave it pointing at the insert location. Pointing the vma > > > iterator at the insert location allows for a cleaner walk of the vma > > > tree for MAP_FIXED and the no expansion cases. > > > > I mean, it's funny I litearlly just asked why it was being left pointing at > > prev and I guess this answers that basically :) > > > > > > > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > > > --- > > > mm/mmap.c | 28 ++++++++++++++-------------- > > > 1 file changed, 14 insertions(+), 14 deletions(-) > > > > > > diff --git a/mm/mmap.c b/mm/mmap.c > > > index f5b33de4e717..ecf55d32e804 100644 > > > --- a/mm/mmap.c > > > +++ b/mm/mmap.c > > > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > vms_complete_munmap_vmas(&vms, &mas_detach); > > > next = vms.next; > > > prev = vms.prev; > > > - vma_prev(&vmi); > > > vma = NULL; > > > } else { > > > next = vma_next(&vmi); > > > prev = vma_prev(&vmi); > > > + if (prev) > > > + vma_iter_next_range(&vmi); > > > } > > > > > > /* > > > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > vm_flags |= VM_ACCOUNT; > > > } > > > > > > - if (vm_flags & VM_SPECIAL) { > > > - if (prev) > > > - vma_iter_next_range(&vmi); > > > + if (vm_flags & VM_SPECIAL) > > > goto cannot_expand; > > > - } > > > > > > /* Attempt to expand an old mapping */ > > > /* Check next */ > > > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > merge_start = prev->vm_start; > > > vma = prev; > > > vm_pgoff = prev->vm_pgoff; > > > - } else if (prev) { > > > - vma_iter_next_range(&vmi); > > > + vma_prev(&vmi); > > > > Why not vma_iter_prev_range()? > > In any situation where we arrive at prev being able to merge with the > current, the prev->end == addr and we are already pointing at the gap > with addr. So vma_iter_prev_range() and vma_prev() will do the same > thing here. > > I thought a lot about this (and created a small test application since > it is so difficult to test vma merging right now..). If we do not clear > the gap, it is possible we will be pointing at the first vma in the > range, and not addr at all when we call vms_gather_munmap_vmas(), but > the loop at the end of the gather function ensures the vmi is at the > correct address (vms->start is in the range). So the result is that we > consistently point to the correct location and so these two calls will > do the same thing. Might it be worth a comment here? > > > > > > } > > > > > > - /* Actually expand, if possible */ > > > - if (vma && > > > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > > - khugepaged_enter_vma(vma, vm_flags); > > > - goto expanded; > > > + if (vma) { > > > + /* Actually expand, if possible */ > > > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > > + khugepaged_enter_vma(vma, vm_flags); > > > + goto expanded; > > > + } > > > + > > > + /* If the expand fails, then reposition the vma iterator */ > > > + if (unlikely(vma == prev)) > > > + vma_iter_set(&vmi, addr); > > > } > > > > > > - if (vma == prev) > > > - vma_iter_set(&vmi, addr); > > > cannot_expand: > > > > > > /* > > > -- > > > 2.43.0 > > > > > Looks good to me, > > > > Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> > > Thanks!
* Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [240708 07:08]: > On Fri, Jul 05, 2024 at 04:56:34PM GMT, Liam R. Howlett wrote: > > * Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [240705 16:18]: > > > On Thu, Jul 04, 2024 at 02:27:12PM GMT, Liam R. Howlett wrote: > > > > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > > > > > > > Instead of moving (or leaving) the vma iterator pointing at the previous > > > > vma, leave it pointing at the insert location. Pointing the vma > > > > iterator at the insert location allows for a cleaner walk of the vma > > > > tree for MAP_FIXED and the no expansion cases. > > > > > > I mean, it's funny I litearlly just asked why it was being left pointing at > > > prev and I guess this answers that basically :) > > > > > > > > > > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > > > > --- > > > > mm/mmap.c | 28 ++++++++++++++-------------- > > > > 1 file changed, 14 insertions(+), 14 deletions(-) > > > > > > > > diff --git a/mm/mmap.c b/mm/mmap.c > > > > index f5b33de4e717..ecf55d32e804 100644 > > > > --- a/mm/mmap.c > > > > +++ b/mm/mmap.c > > > > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > > vms_complete_munmap_vmas(&vms, &mas_detach); > > > > next = vms.next; > > > > prev = vms.prev; > > > > - vma_prev(&vmi); > > > > vma = NULL; > > > > } else { > > > > next = vma_next(&vmi); > > > > prev = vma_prev(&vmi); > > > > + if (prev) > > > > + vma_iter_next_range(&vmi); > > > > } > > > > > > > > /* > > > > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > > vm_flags |= VM_ACCOUNT; > > > > } > > > > > > > > - if (vm_flags & VM_SPECIAL) { > > > > - if (prev) > > > > - vma_iter_next_range(&vmi); > > > > + if (vm_flags & VM_SPECIAL) > > > > goto cannot_expand; > > > > - } > > > > > > > > /* Attempt to expand an old mapping */ > > > > /* Check next */ > > > > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > > > merge_start = prev->vm_start; > > > > vma = prev; > > > > vm_pgoff = prev->vm_pgoff; > > > > - } else if (prev) { > > > > - vma_iter_next_range(&vmi); > > > > + vma_prev(&vmi); > > > > > > Why not vma_iter_prev_range()? > > > > In any situation where we arrive at prev being able to merge with the > > current, the prev->end == addr and we are already pointing at the gap > > with addr. So vma_iter_prev_range() and vma_prev() will do the same > > thing here. > > > > I thought a lot about this (and created a small test application since > > it is so difficult to test vma merging right now..). If we do not clear > > the gap, it is possible we will be pointing at the first vma in the > > range, and not addr at all when we call vms_gather_munmap_vmas(), but > > the loop at the end of the gather function ensures the vmi is at the > > correct address (vms->start is in the range). So the result is that we > > consistently point to the correct location and so these two calls will > > do the same thing. > > Might it be worth a comment here? Okay, I'll add something. > > > > > > > > > > } > > > > > > > > - /* Actually expand, if possible */ > > > > - if (vma && > > > > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > > > - khugepaged_enter_vma(vma, vm_flags); > > > > - goto expanded; > > > > + if (vma) { > > > > + /* Actually expand, if possible */ > > > > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > > > + khugepaged_enter_vma(vma, vm_flags); > > > > + goto expanded; > > > > + } > > > > + > > > > + /* If the expand fails, then reposition the vma iterator */ > > > > + if (unlikely(vma == prev)) > > > > + vma_iter_set(&vmi, addr); > > > > } > > > > > > > > - if (vma == prev) > > > > - vma_iter_set(&vmi, addr); > > > > cannot_expand: > > > > > > > > /* > > > > -- > > > > 2.43.0 > > > > > > > Looks good to me, > > > > > > Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> > > > > Thanks!
On Thu, Jul 4, 2024 at 11:27 AM Liam R. Howlett <Liam.Howlett@oracle.com> wrote: > > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > Instead of moving (or leaving) the vma iterator pointing at the previous > vma, leave it pointing at the insert location. Pointing the vma > iterator at the insert location allows for a cleaner walk of the vma > tree for MAP_FIXED and the no expansion cases. > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > --- > mm/mmap.c | 28 ++++++++++++++-------------- > 1 file changed, 14 insertions(+), 14 deletions(-) > > diff --git a/mm/mmap.c b/mm/mmap.c > index f5b33de4e717..ecf55d32e804 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > vms_complete_munmap_vmas(&vms, &mas_detach); > next = vms.next; > prev = vms.prev; > - vma_prev(&vmi); > vma = NULL; > } else { > next = vma_next(&vmi); > prev = vma_prev(&vmi); > + if (prev) > + vma_iter_next_range(&vmi); > } > > /* > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > vm_flags |= VM_ACCOUNT; > } > > - if (vm_flags & VM_SPECIAL) { > - if (prev) > - vma_iter_next_range(&vmi); > + if (vm_flags & VM_SPECIAL) > goto cannot_expand; > - } > > /* Attempt to expand an old mapping */ > /* Check next */ > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > merge_start = prev->vm_start; > vma = prev; > vm_pgoff = prev->vm_pgoff; > - } else if (prev) { > - vma_iter_next_range(&vmi); > + vma_prev(&vmi); > } > > - /* Actually expand, if possible */ > - if (vma && > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > - khugepaged_enter_vma(vma, vm_flags); > - goto expanded; > + if (vma) { > + /* Actually expand, if possible */ > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > + khugepaged_enter_vma(vma, vm_flags); > + goto expanded; > + } > + > + /* If the expand fails, then reposition the vma iterator */ > + if (unlikely(vma == prev)) > + vma_iter_set(&vmi, addr); > } > > - if (vma == prev) > - vma_iter_set(&vmi, addr); Before this change we would reposition vmi if vma == prev == NULL. After this change we don't do that. Is this situation possible and if so, will vmi be correct? > cannot_expand: > > /* > -- > 2.43.0 >
* Suren Baghdasaryan <surenb@google.com> [240710 12:48]: > On Thu, Jul 4, 2024 at 11:27 AM Liam R. Howlett <Liam.Howlett@oracle.com> wrote: > > > > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com> > > > > Instead of moving (or leaving) the vma iterator pointing at the previous > > vma, leave it pointing at the insert location. Pointing the vma > > iterator at the insert location allows for a cleaner walk of the vma > > tree for MAP_FIXED and the no expansion cases. > > > > Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> > > --- > > mm/mmap.c | 28 ++++++++++++++-------------- > > 1 file changed, 14 insertions(+), 14 deletions(-) > > > > diff --git a/mm/mmap.c b/mm/mmap.c > > index f5b33de4e717..ecf55d32e804 100644 > > --- a/mm/mmap.c > > +++ b/mm/mmap.c > > @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > vms_complete_munmap_vmas(&vms, &mas_detach); > > next = vms.next; > > prev = vms.prev; > > - vma_prev(&vmi); > > vma = NULL; > > } else { > > next = vma_next(&vmi); > > prev = vma_prev(&vmi); > > + if (prev) > > + vma_iter_next_range(&vmi); > > } > > > > /* > > @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > vm_flags |= VM_ACCOUNT; > > } > > > > - if (vm_flags & VM_SPECIAL) { > > - if (prev) > > - vma_iter_next_range(&vmi); > > + if (vm_flags & VM_SPECIAL) > > goto cannot_expand; > > - } > > > > /* Attempt to expand an old mapping */ > > /* Check next */ > > @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > > merge_start = prev->vm_start; > > vma = prev; > > vm_pgoff = prev->vm_pgoff; > > - } else if (prev) { > > - vma_iter_next_range(&vmi); > > + vma_prev(&vmi); > > } > > > > - /* Actually expand, if possible */ > > - if (vma && > > - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > - khugepaged_enter_vma(vma, vm_flags); > > - goto expanded; > > + if (vma) { > > + /* Actually expand, if possible */ > > + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { > > + khugepaged_enter_vma(vma, vm_flags); > > + goto expanded; > > + } > > + > > + /* If the expand fails, then reposition the vma iterator */ > > + if (unlikely(vma == prev)) > > + vma_iter_set(&vmi, addr); > > } > > > > - if (vma == prev) > > - vma_iter_set(&vmi, addr); > > Before this change we would reposition vmi if vma == prev == NULL. > After this change we don't do that. Is this situation possible and if > so, will vmi be correct? vma == NULL can happen if it is a MAP_FIXED or we cannot expand (no prev/next that match the checks for expanding). If there is no prev, then we can have a case where vma == prev == NULL. So the situation can be reached. In the MAP_FIXED situation, the vms_complete_munmap_vmas() call will return with the iterator pointing at the range of addr, so this is fine. In the other case, we cannot move the vma iterator to prev since there isn't one and the vma iterator is left pointing at the first range in the tree (0 to .. whatever) that includes the addr. So yes it is possible and yes it is correctly positioned. Thanks, Liam
diff --git a/mm/mmap.c b/mm/mmap.c index f5b33de4e717..ecf55d32e804 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2963,11 +2963,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vms_complete_munmap_vmas(&vms, &mas_detach); next = vms.next; prev = vms.prev; - vma_prev(&vmi); vma = NULL; } else { next = vma_next(&vmi); prev = vma_prev(&vmi); + if (prev) + vma_iter_next_range(&vmi); } /* @@ -2980,11 +2981,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vm_flags |= VM_ACCOUNT; } - if (vm_flags & VM_SPECIAL) { - if (prev) - vma_iter_next_range(&vmi); + if (vm_flags & VM_SPECIAL) goto cannot_expand; - } /* Attempt to expand an old mapping */ /* Check next */ @@ -3005,19 +3003,21 @@ unsigned long mmap_region(struct file *file, unsigned long addr, merge_start = prev->vm_start; vma = prev; vm_pgoff = prev->vm_pgoff; - } else if (prev) { - vma_iter_next_range(&vmi); + vma_prev(&vmi); } - /* Actually expand, if possible */ - if (vma && - !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { - khugepaged_enter_vma(vma, vm_flags); - goto expanded; + if (vma) { + /* Actually expand, if possible */ + if (!vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { + khugepaged_enter_vma(vma, vm_flags); + goto expanded; + } + + /* If the expand fails, then reposition the vma iterator */ + if (unlikely(vma == prev)) + vma_iter_set(&vmi, addr); } - if (vma == prev) - vma_iter_set(&vmi, addr); cannot_expand: /*