[PATCH v4 21/26] hugetlb/userfaultfd: Handle uffd-wp special pte in hugetlb pf handler

[Peter Xu <peterx@redhat.com>]

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     | 26 ++++++++++++++++++++------
 mm/userfaultfd.c |  5 ++++-
 3 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e1c1cbc7bcc8..644df737fbb2 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -245,8 +245,11 @@ 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 6a66b598245e..15e5de480cf0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4786,7 +4786,8 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
 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;
@@ -4910,7 +4911,7 @@ 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) {
@@ -4920,6 +4921,12 @@ 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 this pte was previously wr-protected, keep it wr-protected even
+	 * if populated.
+	 */
+	if (unlikely(pte_swp_uffd_wp_special(old_pte)))
+		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);
@@ -5035,8 +5042,13 @@ 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);
+	/*
+	 * uffd-wp-special 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;
 	}
 
@@ -5170,7 +5182,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
 	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
-	pte_t _dst_pte;
+	pte_t _dst_pte, cur_pte;
 	spinlock_t *ptl;
 	int ret = -ENOMEM;
 	struct page *page;
@@ -5287,8 +5299,10 @@ 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 7ba721aca1c5..a8038903effd 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -363,6 +363,8 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 	}
 
 	while (src_addr < src_start + len) {
+		pte_t pteval;
+
 		BUG_ON(dst_addr >= dst_start + len);
 
 		/*
@@ -385,8 +387,9 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 			goto out_unlock;
 		}
 
+		pteval = huge_ptep_get(dst_pte);
 		if (mode != MCOPY_ATOMIC_CONTINUE &&
-		    !huge_pte_none(huge_ptep_get(dst_pte))) {
+		    !huge_pte_none(pteval) && !pte_swp_uffd_wp_special(pteval)) {
 			err = -EEXIST;
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);
-- 
2.31.1