On Wed, Jan 25, 2023 at 1:42 AM Michal Hocko <mhocko@xxxxxxxx> wrote:
>
> On Wed 25-01-23 00:38:50, Suren Baghdasaryan wrote:
> > In cases when VMA flags are modified after VMA was isolated and mmap_lock
> > was downgraded, flags modifications would result in an assertion because
> > mmap write lock is not held.
> > Introduce mod_vm_flags_nolock to be used in such situation.
> > Pass a hint to untrack_pfn to conditionally use mod_vm_flags_nolock for
> > flags modification and to avoid assertion.
>
> The changelog nor the documentation of mod_vm_flags_nolock
> really explain when it is safe to use it. This is really important for
> future potential users.
True. I'll add clarification in the comments and in the changelog. Thanks!
>
> > Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
> > ---
> > arch/x86/mm/pat/memtype.c | 10 +++++++---
> > include/linux/mm.h | 12 +++++++++---
> > include/linux/pgtable.h | 5 +++--
> > mm/memory.c | 13 +++++++------
> > mm/memremap.c | 4 ++--
> > mm/mmap.c | 16 ++++++++++------
> > 6 files changed, 38 insertions(+), 22 deletions(-)
> >
> > diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
> > index ae9645c900fa..d8adc0b42cf2 100644
> > --- a/arch/x86/mm/pat/memtype.c
> > +++ b/arch/x86/mm/pat/memtype.c
> > @@ -1046,7 +1046,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
> > * can be for the entire vma (in which case pfn, size are zero).
> > */
> > void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
> > - unsigned long size)
> > + unsigned long size, bool mm_wr_locked)
> > {
> > resource_size_t paddr;
> > unsigned long prot;
> > @@ -1065,8 +1065,12 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
> > size = vma->vm_end - vma->vm_start;
> > }
> > free_pfn_range(paddr, size);
> > - if (vma)
> > - clear_vm_flags(vma, VM_PAT);
> > + if (vma) {
> > + if (mm_wr_locked)
> > + clear_vm_flags(vma, VM_PAT);
> > + else
> > + mod_vm_flags_nolock(vma, 0, VM_PAT);
> > + }
> > }
> >
> > /*
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 55335edd1373..48d49930c411 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -656,12 +656,18 @@ static inline void clear_vm_flags(struct vm_area_struct *vma,
> > vma->vm_flags &= ~flags;
> > }
> >
> > +static inline void mod_vm_flags_nolock(struct vm_area_struct *vma,
> > + unsigned long set, unsigned long clear)
> > +{
> > + vma->vm_flags |= set;
> > + vma->vm_flags &= ~clear;
> > +}
> > +
> > static inline void mod_vm_flags(struct vm_area_struct *vma,
> > unsigned long set, unsigned long clear)
> > {
> > mmap_assert_write_locked(vma->vm_mm);
> > - vma->vm_flags |= set;
> > - vma->vm_flags &= ~clear;
> > + mod_vm_flags_nolock(vma, set, clear);
> > }
> >
> > static inline void vma_set_anonymous(struct vm_area_struct *vma)
> > @@ -2087,7 +2093,7 @@ static inline void zap_vma_pages(struct vm_area_struct *vma)
> > }
> > void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
> > struct vm_area_struct *start_vma, unsigned long start,
> > - unsigned long end);
> > + unsigned long end, bool mm_wr_locked);
> >
> > struct mmu_notifier_range;
> >
> > diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> > index 5fd45454c073..c63cd44777ec 100644
> > --- a/include/linux/pgtable.h
> > +++ b/include/linux/pgtable.h
> > @@ -1185,7 +1185,8 @@ static inline int track_pfn_copy(struct vm_area_struct *vma)
> > * can be for the entire vma (in which case pfn, size are zero).
> > */
> > static inline void untrack_pfn(struct vm_area_struct *vma,
> > - unsigned long pfn, unsigned long size)
> > + unsigned long pfn, unsigned long size,
> > + bool mm_wr_locked)
> > {
> > }
> >
> > @@ -1203,7 +1204,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
> > pfn_t pfn);
> > extern int track_pfn_copy(struct vm_area_struct *vma);
> > extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
> > - unsigned long size);
> > + unsigned long size, bool mm_wr_locked);
> > extern void untrack_pfn_moved(struct vm_area_struct *vma);
> > #endif
> >
> > diff --git a/mm/memory.c b/mm/memory.c
> > index d6902065e558..5b11b50e2c4a 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -1613,7 +1613,7 @@ void unmap_page_range(struct mmu_gather *tlb,
> > static void unmap_single_vma(struct mmu_gather *tlb,
> > struct vm_area_struct *vma, unsigned long start_addr,
> > unsigned long end_addr,
> > - struct zap_details *details)
> > + struct zap_details *details, bool mm_wr_locked)
> > {
> > unsigned long start = max(vma->vm_start, start_addr);
> > unsigned long end;
> > @@ -1628,7 +1628,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
> > uprobe_munmap(vma, start, end);
> >
> > if (unlikely(vma->vm_flags & VM_PFNMAP))
> > - untrack_pfn(vma, 0, 0);
> > + untrack_pfn(vma, 0, 0, mm_wr_locked);
> >
> > if (start != end) {
> > if (unlikely(is_vm_hugetlb_page(vma))) {
> > @@ -1675,7 +1675,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
> > */
> > void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
> > struct vm_area_struct *vma, unsigned long start_addr,
> > - unsigned long end_addr)
> > + unsigned long end_addr, bool mm_wr_locked)
> > {
> > struct mmu_notifier_range range;
> > struct zap_details details = {
> > @@ -1689,7 +1689,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
> > start_addr, end_addr);
> > mmu_notifier_invalidate_range_start(&range);
> > do {
> > - unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
> > + unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
> > + mm_wr_locked);
> > } while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
> > mmu_notifier_invalidate_range_end(&range);
> > }
> > @@ -1723,7 +1724,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
> > * unmap 'address-end' not 'range.start-range.end' as range
> > * could have been expanded for hugetlb pmd sharing.
> > */
> > - unmap_single_vma(&tlb, vma, address, end, details);
> > + unmap_single_vma(&tlb, vma, address, end, details, false);
> > mmu_notifier_invalidate_range_end(&range);
> > tlb_finish_mmu(&tlb);
> > }
> > @@ -2492,7 +2493,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
> >
> > err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
> > if (err)
> > - untrack_pfn(vma, pfn, PAGE_ALIGN(size));
> > + untrack_pfn(vma, pfn, PAGE_ALIGN(size), true);
> > return err;
> > }
> > EXPORT_SYMBOL(remap_pfn_range);
> > diff --git a/mm/memremap.c b/mm/memremap.c
> > index 08cbf54fe037..2f88f43d4a01 100644
> > --- a/mm/memremap.c
> > +++ b/mm/memremap.c
> > @@ -129,7 +129,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
> > }
> > mem_hotplug_done();
> >
> > - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
> > + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
> > pgmap_array_delete(range);
> > }
> >
> > @@ -276,7 +276,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
> > if (!is_private)
> > kasan_remove_zero_shadow(__va(range->start), range_len(range));
> > err_kasan:
> > - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
> > + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
> > err_pfn_remap:
> > pgmap_array_delete(range);
> > return error;
> > diff --git a/mm/mmap.c b/mm/mmap.c
> > index 2c6e9072e6a8..69d440997648 100644
> > --- a/mm/mmap.c
> > +++ b/mm/mmap.c
> > @@ -78,7 +78,7 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
> > static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
> > struct vm_area_struct *vma, struct vm_area_struct *prev,
> > struct vm_area_struct *next, unsigned long start,
> > - unsigned long end);
> > + unsigned long end, bool mm_wr_locked);
> >
> > static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
> > {
> > @@ -2136,14 +2136,14 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
> > static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
> > struct vm_area_struct *vma, struct vm_area_struct *prev,
> > struct vm_area_struct *next,
> > - unsigned long start, unsigned long end)
> > + unsigned long start, unsigned long end, bool mm_wr_locked)
> > {
> > struct mmu_gather tlb;
> >
> > lru_add_drain();
> > tlb_gather_mmu(&tlb, mm);
> > update_hiwater_rss(mm);
> > - unmap_vmas(&tlb, mt, vma, start, end);
> > + unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked);
> > free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
> > next ? next->vm_start : USER_PGTABLES_CEILING);
> > tlb_finish_mmu(&tlb);
> > @@ -2391,7 +2391,11 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
> > mmap_write_downgrade(mm);
> > }
> >
> > - unmap_region(mm, &mt_detach, vma, prev, next, start, end);
> > + /*
> > + * We can free page tables without write-locking mmap_lock because VMAs
> > + * were isolated before we downgraded mmap_lock.
> > + */
> > + unmap_region(mm, &mt_detach, vma, prev, next, start, end, !downgrade);
> > /* Statistics and freeing VMAs */
> > mas_set(&mas_detach, start);
> > remove_mt(mm, &mas_detach);
> > @@ -2704,7 +2708,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
> >
> > /* Undo any partial mapping done by a device driver. */
> > unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start,
> > - vma->vm_end);
> > + vma->vm_end, true);
> > }
> > if (file && (vm_flags & VM_SHARED))
> > mapping_unmap_writable(file->f_mapping);
> > @@ -3031,7 +3035,7 @@ void exit_mmap(struct mm_struct *mm)
> > tlb_gather_mmu_fullmm(&tlb, mm);
> > /* update_hiwater_rss(mm) here? but nobody should be looking */
> > /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */
> > - unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX);
> > + unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, false);
> > mmap_read_unlock(mm);
> >
> > /*
> > --
> > 2.39.1
>
> --
> Michal Hocko
> SUSE Labs
