[RFC,26/30] hugetlb/userfaultfd: Handle uffd-wp special pte in hugetlb pf handler
diff mbox series

Message ID 20210115170907.24498-27-peterx@redhat.com
State New, archived
Headers show
Series
  • userfaultfd-wp: Support shmem and hugetlbfs
Related show

Commit Message

Peter Xu Jan. 15, 2021, 5:09 p.m. UTC
Teach the hugetlb page fault code to understand uffd-wp special pte.  For
example, when seeing such a pte we need to convert any write fault into a read
one (which is fake - we'll retry the write later if so).  Meanwhile, for
handle_userfault() we'll need to make sure we must wait for the special swap
pte too just like a none pte.

Note that we also need to teach UFFDIO_COPY about this special pte across the
code path so that we can safely install a new page at this special pte as long
as we know it's a stall entry.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 fs/userfaultfd.c |  5 ++++-
 mm/hugetlb.c     | 35 ++++++++++++++++++++++++++++-------
 mm/userfaultfd.c |  3 ++-
 3 files changed, 34 insertions(+), 9 deletions(-)

Patch
diff mbox series

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 3190dff39d6c..3264ec46242b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -248,8 +248,11 @@  static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
 	 * changes under us.
+	 *
+	 * Regarding uffd-wp special case, please refer to comments in
+	 * userfaultfd_must_wait().
 	 */
-	if (huge_pte_none(pte))
+	if (huge_pte_none(pte) || pte_swp_uffd_wp_special(pte))
 		ret = true;
 	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
 		ret = true;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a971513cdff6..9b9f71ec30e1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4253,7 +4253,8 @@  int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			struct vm_area_struct *vma,
 			struct address_space *mapping, pgoff_t idx,
-			unsigned long address, pte_t *ptep, unsigned int flags)
+			unsigned long address, pte_t *ptep,
+			pte_t old_pte, unsigned int flags)
 {
 	struct hstate *h = hstate_vma(vma);
 	vm_fault_t ret = VM_FAULT_SIGBUS;
@@ -4297,6 +4298,7 @@  static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				.vma = vma,
 				.address = haddr,
 				.flags = flags,
+				.orig_pte = old_pte,
 				/*
 				 * Hard to debug if it ends up being
 				 * used by a callee that assumes
@@ -4394,7 +4396,7 @@  static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 
 	ptl = huge_pte_lock(h, mm, ptep);
 	ret = 0;
-	if (!huge_pte_none(huge_ptep_get(ptep)))
+	if (!pte_same(huge_ptep_get(ptep), old_pte))
 		goto backout;
 
 	if (anon_rmap) {
@@ -4404,6 +4406,11 @@  static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		page_dup_rmap(page, true);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
+	if (unlikely(flags & FAULT_FLAG_UFFD_WP)) {
+		WARN_ON_ONCE(flags & FAULT_FLAG_WRITE);
+		/* We should have the write bit cleared already, but be safe */
+		new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte));
+	}
 	set_huge_pte_at(mm, haddr, ptep, new_pte);
 
 	hugetlb_count_add(pages_per_huge_page(h), mm);
@@ -4485,9 +4492,16 @@  vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
 			migration_entry_wait_huge(vma, mm, ptep);
 			return 0;
-		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
+		} else if (unlikely(is_swap_special_pte(entry))) {
+			/* Must be a uffd-wp special swap pte */
+			WARN_ON_ONCE(!pte_swp_uffd_wp_special(entry));
+			flags |= FAULT_FLAG_UFFD_WP;
+			/* Emulate a read fault */
+			flags &= ~FAULT_FLAG_WRITE;
+		}
 	}
 
 	/*
@@ -4519,8 +4533,13 @@  vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
-	if (huge_pte_none(entry)) {
-		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
+	/*
+	 * FAULT_FLAG_UFFD_WP should be handled merely the same as pte none
+	 * because it's basically a none pte with a special marker
+	 */
+	if (huge_pte_none(entry) || pte_swp_uffd_wp_special(entry)) {
+		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
+				      entry, flags);
 		goto out_mutex;
 	}
 
@@ -4651,7 +4670,7 @@  int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
 	struct hstate *h = hstate_vma(dst_vma);
-	pte_t _dst_pte;
+	pte_t _dst_pte, cur_pte;
 	spinlock_t *ptl;
 	int ret;
 	struct page *page;
@@ -4725,8 +4744,10 @@  int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (idx >= size)
 		goto out_release_unlock;
 
+	cur_pte = huge_ptep_get(dst_pte);
 	ret = -EEXIST;
-	if (!huge_pte_none(huge_ptep_get(dst_pte)))
+	/* Please refer to shmem_mfill_atomic_pte() for uffd-wp special case */
+	if (!huge_pte_none(cur_pte) && !pte_swp_uffd_wp_special(cur_pte))
 		goto out_release_unlock;
 
 	if (vm_shared) {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 3d49b888e3e8..1dff5b9a2c26 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -300,7 +300,8 @@  static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 
 		err = -EEXIST;
 		dst_pteval = huge_ptep_get(dst_pte);
-		if (!huge_pte_none(dst_pteval)) {
+		if (!huge_pte_none(dst_pteval) &&
+		    !pte_swp_uffd_wp_special(dst_pteval)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);
 			goto out_unlock;