[PATCH v5 07/22] mm: Protect VMA modifications using VMA sequence count

From: Laurent Dufour
Date: Wed Oct 11 2017 - 09:53:28 EST


The VMA sequence count has been introduced to allow fast detection of
VMA modification when running a page fault handler without holding
the mmap_sem.

This patch provides protection against the VMA modification done in :
- madvise()
- mremap()
- mpol_rebind_policy()
- vma_replace_policy()
- change_prot_numa()
- mlock(), munlock()
- mprotect()
- mmap_region()
- collapse_huge_page()
- userfaultd registering services

In addition, VMA fields which will be read during the speculative fault
path needs to be written using WRITE_ONCE to prevent write to be split
and intermediate values to be pushed to other CPUs.

Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
---
fs/proc/task_mmu.c | 5 ++++-
fs/userfaultfd.c | 17 +++++++++++++----
mm/khugepaged.c | 3 +++
mm/madvise.c | 6 +++++-
mm/mempolicy.c | 51 ++++++++++++++++++++++++++++++++++-----------------
mm/mlock.c | 13 ++++++++-----
mm/mmap.c | 17 ++++++++++-------
mm/mprotect.c | 4 +++-
mm/mremap.c | 6 ++++++
9 files changed, 86 insertions(+), 36 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 0bf9e423aa99..4fc37f88437c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1155,8 +1155,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
goto out_mm;
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
- vma->vm_flags &= ~VM_SOFTDIRTY;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags,
+ vma->vm_flags & ~VM_SOFTDIRTY);
vma_set_page_prot(vma);
+ vm_write_end(vma);
}
downgrade_write(&mm->mmap_sem);
break;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 1c713fd5b3e6..426af4fd407c 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -640,8 +640,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)

octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+ vm_write_begin(vma);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+ WRITE_ONCE(vma->vm_flags,
+ vma->vm_flags & ~(VM_UFFD_WP | VM_UFFD_MISSING));
+ vm_write_end(vma);
return 0;
}

@@ -866,8 +869,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
vma = prev;
else
prev = vma;
- vma->vm_flags = new_flags;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+ vm_write_end(vma);
}
up_write(&mm->mmap_sem);
mmput(mm);
@@ -1425,8 +1430,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
+ vm_write_end(vma);

skip:
prev = vma;
@@ -1583,8 +1590,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+ vm_write_end(vma);

skip:
prev = vma;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index c01f177a1120..f723d42140db 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1005,6 +1005,7 @@ static void collapse_huge_page(struct mm_struct *mm,
if (mm_find_pmd(mm, address) != pmd)
goto out;

+ vm_write_begin(vma);
anon_vma_lock_write(vma->anon_vma);

pte = pte_offset_map(pmd, address);
@@ -1040,6 +1041,7 @@ static void collapse_huge_page(struct mm_struct *mm,
pmd_populate(mm, pmd, pmd_pgtable(_pmd));
spin_unlock(pmd_ptl);
anon_vma_unlock_write(vma->anon_vma);
+ vm_write_end(vma);
result = SCAN_FAIL;
goto out;
}
@@ -1074,6 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm,
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache_pmd(vma, address, pmd);
spin_unlock(pmd_ptl);
+ vm_write_end(vma);

*hpage = NULL;

diff --git a/mm/madvise.c b/mm/madvise.c
index acdd39fb1f5d..707e0657b33f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -183,7 +183,9 @@ static long madvise_behavior(struct vm_area_struct *vma,
/*
* vm_flags is protected by the mmap_sem held in write mode.
*/
- vma->vm_flags = new_flags;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, new_flags);
+ vm_write_end(vma);
out:
return error;
}
@@ -451,9 +453,11 @@ static void madvise_free_page_range(struct mmu_gather *tlb,
.private = tlb,
};

+ vm_write_begin(vma);
tlb_start_vma(tlb, vma);
walk_page_range(addr, end, &free_walk);
tlb_end_vma(tlb, vma);
+ vm_write_end(vma);
}

static int madvise_free_single_vma(struct vm_area_struct *vma,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a2af6d58a68f..72645928daa0 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -379,8 +379,11 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
struct vm_area_struct *vma;

down_write(&mm->mmap_sem);
- for (vma = mm->mmap; vma; vma = vma->vm_next)
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ vm_write_begin(vma);
mpol_rebind_policy(vma->vm_policy, new);
+ vm_write_end(vma);
+ }
up_write(&mm->mmap_sem);
}

@@ -578,9 +581,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
{
int nr_updated;

+ vm_write_begin(vma);
nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
if (nr_updated)
count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
+ vm_write_end(vma);

return nr_updated;
}
@@ -681,6 +686,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
if (IS_ERR(new))
return PTR_ERR(new);

+ vm_write_begin(vma);
if (vma->vm_ops && vma->vm_ops->set_policy) {
err = vma->vm_ops->set_policy(vma, new);
if (err)
@@ -688,11 +694,17 @@ static int vma_replace_policy(struct vm_area_struct *vma,
}

old = vma->vm_policy;
- vma->vm_policy = new; /* protected by mmap_sem */
+ /*
+ * The speculative page fault handler access this field without
+ * hodling the mmap_sem.
+ */
+ WRITE_ONCE(vma->vm_policy, new);
+ vm_write_end(vma);
mpol_put(old);

return 0;
err_out:
+ vm_write_end(vma);
mpol_put(new);
return err;
}
@@ -1562,23 +1574,28 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr)
{
- struct mempolicy *pol = NULL;
+ struct mempolicy *pol;

- if (vma) {
- if (vma->vm_ops && vma->vm_ops->get_policy) {
- pol = vma->vm_ops->get_policy(vma, addr);
- } else if (vma->vm_policy) {
- pol = vma->vm_policy;
+ if (!vma)
+ return NULL;

- /*
- * shmem_alloc_page() passes MPOL_F_SHARED policy with
- * a pseudo vma whose vma->vm_ops=NULL. Take a reference
- * count on these policies which will be dropped by
- * mpol_cond_put() later
- */
- if (mpol_needs_cond_ref(pol))
- mpol_get(pol);
- }
+ if (vma->vm_ops && vma->vm_ops->get_policy)
+ return vma->vm_ops->get_policy(vma, addr);
+
+ /*
+ * This could be called without holding the mmap_sem in the
+ * speculative page fault handler's path.
+ */
+ pol = READ_ONCE(vma->vm_policy);
+ if (pol) {
+ /*
+ * shmem_alloc_page() passes MPOL_F_SHARED policy with
+ * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+ * count on these policies which will be dropped by
+ * mpol_cond_put() later
+ */
+ if (mpol_needs_cond_ref(pol))
+ mpol_get(pol);
}

return pol;
diff --git a/mm/mlock.c b/mm/mlock.c
index 4d009350893f..83e49f99ad38 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -438,7 +438,9 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, vma->vm_flags & VM_LOCKED_CLEAR_MASK);
+ vm_write_end(vma);

while (start < end) {
struct page *page;
@@ -562,10 +564,11 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
* It's okay if try_to_unmap_one unmaps a page just after we
* set VM_LOCKED, populate_vma_page_range will bring it back.
*/
-
- if (lock)
- vma->vm_flags = newflags;
- else
+ if (lock) {
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, newflags);
+ vm_write_end(vma);
+ } else
munlock_vma_pages_range(vma, start, end);

out:
diff --git a/mm/mmap.c b/mm/mmap.c
index 0e90b469fd97..e28136cd3275 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -847,17 +847,18 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
}

if (start != vma->vm_start) {
- vma->vm_start = start;
+ WRITE_ONCE(vma->vm_start, start);
start_changed = true;
}
if (end != vma->vm_end) {
- vma->vm_end = end;
+ WRITE_ONCE(vma->vm_end, end);
end_changed = true;
}
- vma->vm_pgoff = pgoff;
+ WRITE_ONCE(vma->vm_pgoff, pgoff);
if (adjust_next) {
- next->vm_start += adjust_next << PAGE_SHIFT;
- next->vm_pgoff += adjust_next;
+ WRITE_ONCE(next->vm_start,
+ next->vm_start + (adjust_next << PAGE_SHIFT));
+ WRITE_ONCE(next->vm_pgoff, next->vm_pgoff + adjust_next);
}

if (root) {
@@ -1754,6 +1755,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
out:
perf_event_mmap(vma);

+ vm_write_begin(vma);
vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
@@ -1777,6 +1779,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
vma->vm_flags |= VM_SOFTDIRTY;

vma_set_page_prot(vma);
+ vm_write_end(vma);

return addr;

@@ -2405,8 +2408,8 @@ int expand_downwards(struct vm_area_struct *vma,
mm->locked_vm += grow;
vm_stat_account(mm, vma->vm_flags, grow);
anon_vma_interval_tree_pre_update_vma(vma);
- vma->vm_start = address;
- vma->vm_pgoff -= grow;
+ WRITE_ONCE(vma->vm_start, address);
+ WRITE_ONCE(vma->vm_pgoff, vma->vm_pgoff - grow);
anon_vma_interval_tree_post_update_vma(vma);
vma_gap_update(vma);
spin_unlock(&mm->page_table_lock);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6d3e2f082290..ce93c4f6af70 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -358,7 +358,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
* vm_flags and vm_page_prot are protected by the mmap_sem
* held in write mode.
*/
- vma->vm_flags = newflags;
+ vm_write_begin(vma);
+ WRITE_ONCE(vma->vm_flags, newflags);
dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
vma_set_page_prot(vma);

@@ -373,6 +374,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
(newflags & VM_WRITE)) {
populate_vma_page_range(vma, start, end, NULL);
}
+ vm_write_end(vma);

vm_stat_account(mm, oldflags, -nrpages);
vm_stat_account(mm, newflags, nrpages);
diff --git a/mm/mremap.c b/mm/mremap.c
index cfec004c4ff9..ca0b5cb6ed4d 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -301,6 +301,9 @@ static unsigned long move_vma(struct vm_area_struct *vma,
if (!new_vma)
return -ENOMEM;

+ vm_write_begin(vma);
+ vm_write_begin_nested(new_vma, SINGLE_DEPTH_NESTING);
+
moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
need_rmap_locks);
if (moved_len < old_len) {
@@ -317,6 +320,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
*/
move_page_tables(new_vma, new_addr, vma, old_addr, moved_len,
true);
+ vm_write_end(vma);
vma = new_vma;
old_len = new_len;
old_addr = new_addr;
@@ -325,7 +329,9 @@ static unsigned long move_vma(struct vm_area_struct *vma,
mremap_userfaultfd_prep(new_vma, uf);
arch_remap(mm, old_addr, old_addr + old_len,
new_addr, new_addr + new_len);
+ vm_write_end(vma);
}
+ vm_write_end(new_vma);

/* Conceal VM_ACCOUNT so old reservation is not undone */
if (vm_flags & VM_ACCOUNT) {
--
2.7.4