1 files changed, 125 insertions, 100 deletions

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 63a73e164d55..0e2132834bc7 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -48,6 +48,78 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
 	return dst_vma;
 }
 
+/*
+ * Install PTEs, to map dst_addr (within dst_vma) to page.
+ *
+ * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem
+ * and anon, and for both shared and private VMAs.
+ */
+int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
+			     struct vm_area_struct *dst_vma,
+			     unsigned long dst_addr, struct page *page,
+			     bool newly_allocated, bool wp_copy)
+{
+	int ret;
+	pte_t _dst_pte, *dst_pte;
+	bool writable = dst_vma->vm_flags & VM_WRITE;
+	bool vm_shared = dst_vma->vm_flags & VM_SHARED;
+	bool page_in_cache = page->mapping;
+	spinlock_t *ptl;
+	struct inode *inode;
+	pgoff_t offset, max_off;
+
+	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
+	if (page_in_cache && !vm_shared)
+		writable = false;
+	if (writable || !page_in_cache)
+		_dst_pte = pte_mkdirty(_dst_pte);
+	if (writable) {
+		if (wp_copy)
+			_dst_pte = pte_mkuffd_wp(_dst_pte);
+		else
+			_dst_pte = pte_mkwrite(_dst_pte);
+	}
+
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+
+	if (vma_is_shmem(dst_vma)) {
+		/* serialize against truncate with the page table lock */
+		inode = dst_vma->vm_file->f_inode;
+		offset = linear_page_index(dst_vma, dst_addr);
+		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+		ret = -EFAULT;
+		if (unlikely(offset >= max_off))
+			goto out_unlock;
+	}
+
+	ret = -EEXIST;
+	if (!pte_none(*dst_pte))
+		goto out_unlock;
+
+	if (page_in_cache)
+		page_add_file_rmap(page, false);
+	else
+		page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
+
+	/*
+	 * Must happen after rmap, as mm_counter() checks mapping (via
+	 * PageAnon()), which is set by __page_set_anon_rmap().
+	 */
+	inc_mm_counter(dst_mm, mm_counter(page));
+
+	if (newly_allocated)
+		lru_cache_add_inactive_or_unevictable(page, dst_vma);
+
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+	ret = 0;
+out_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+	return ret;
+}
+
 static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    pmd_t *dst_pmd,
 			    struct vm_area_struct *dst_vma,
@@ -56,13 +128,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    struct page **pagep,
 			    bool wp_copy)
 {
-	pte_t _dst_pte, *dst_pte;
-	spinlock_t *ptl;
 	void *page_kaddr;
 	int ret;
 	struct page *page;
-	pgoff_t offset, max_off;
-	struct inode *inode;
 
 	if (!*pagep) {
 		ret = -ENOMEM;
@@ -99,43 +167,12 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL))
 		goto out_release;
 
-	_dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
-	if (dst_vma->vm_flags & VM_WRITE) {
-		if (wp_copy)
-			_dst_pte = pte_mkuffd_wp(_dst_pte);
-		else
-			_dst_pte = pte_mkwrite(_dst_pte);
-	}
-
-	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
-	if (dst_vma->vm_file) {
-		/* the shmem MAP_PRIVATE case requires checking the i_size */
-		inode = dst_vma->vm_file->f_inode;
-		offset = linear_page_index(dst_vma, dst_addr);
-		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
-		ret = -EFAULT;
-		if (unlikely(offset >= max_off))
-			goto out_release_uncharge_unlock;
-	}
-	ret = -EEXIST;
-	if (!pte_none(*dst_pte))
-		goto out_release_uncharge_unlock;
-
-	inc_mm_counter(dst_mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
-	lru_cache_add_inactive_or_unevictable(page, dst_vma);
-
-	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
-
-	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(dst_vma, dst_addr, dst_pte);
-
-	pte_unmap_unlock(dst_pte, ptl);
-	ret = 0;
+	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
+				       page, true, wp_copy);
+	if (ret)
+		goto out_release;
 out:
 	return ret;
-out_release_uncharge_unlock:
-	pte_unmap_unlock(dst_pte, ptl);
 out_release:
 	put_page(page);
 	goto out;
@@ -176,6 +213,41 @@ out_unlock:
 	return ret;
 }
 
+/* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */
+static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
+				pmd_t *dst_pmd,
+				struct vm_area_struct *dst_vma,
+				unsigned long dst_addr,
+				bool wp_copy)
+{
+	struct inode *inode = file_inode(dst_vma->vm_file);
+	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
+	struct page *page;
+	int ret;
+
+	ret = shmem_getpage(inode, pgoff, &page, SGP_READ);
+	if (ret)
+		goto out;
+	if (!page) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
+				       page, false, wp_copy);
+	if (ret)
+		goto out_release;
+
+	unlock_page(page);
+	ret = 0;
+out:
+	return ret;
+out_release:
+	unlock_page(page);
+	put_page(page);
+	goto out;
+}
+
 static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
@@ -209,7 +281,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 					      unsigned long len,
 					      enum mcopy_atomic_mode mode)
 {
-	int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
 	ssize_t err;
 	pte_t *dst_pte;
@@ -308,7 +379,6 @@ retry:
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		i_mmap_unlock_read(mapping);
-		vm_alloc_shared = vm_shared;
 
 		cond_resched();
 
@@ -346,54 +416,8 @@ retry:
 out_unlock:
 	mmap_read_unlock(dst_mm);
 out:
-	if (page) {
-		/*
-		 * We encountered an error and are about to free a newly
-		 * allocated huge page.
-		 *
-		 * Reservation handling is very subtle, and is different for
-		 * private and shared mappings.  See the routine
-		 * restore_reserve_on_error for details.  Unfortunately, we
-		 * can not call restore_reserve_on_error now as it would
-		 * require holding mmap_lock.
-		 *
-		 * If a reservation for the page existed in the reservation
-		 * map of a private mapping, the map was modified to indicate
-		 * the reservation was consumed when the page was allocated.
-		 * We clear the HPageRestoreReserve flag now so that the global
-		 * reserve count will not be incremented in free_huge_page.
-		 * The reservation map will still indicate the reservation
-		 * was consumed and possibly prevent later page allocation.
-		 * This is better than leaking a global reservation.  If no
-		 * reservation existed, it is still safe to clear
-		 * HPageRestoreReserve as no adjustments to reservation counts
-		 * were made during allocation.
-		 *
-		 * The reservation map for shared mappings indicates which
-		 * pages have reservations.  When a huge page is allocated
-		 * for an address with a reservation, no change is made to
-		 * the reserve map.  In this case HPageRestoreReserve will be
-		 * set to indicate that the global reservation count should be
-		 * incremented when the page is freed.  This is the desired
-		 * behavior.  However, when a huge page is allocated for an
-		 * address without a reservation a reservation entry is added
-		 * to the reservation map, and HPageRestoreReserve will not be
-		 * set. When the page is freed, the global reserve count will
-		 * NOT be incremented and it will appear as though we have
-		 * leaked reserved page.  In this case, set HPageRestoreReserve
-		 * so that the global reserve count will be incremented to
-		 * match the reservation map entry which was created.
-		 *
-		 * Note that vm_alloc_shared is based on the flags of the vma
-		 * for which the page was originally allocated.  dst_vma could
-		 * be different or NULL on error.
-		 */
-		if (vm_alloc_shared)
-			SetHPageRestoreReserve(page);
-		else
-			ClearHPageRestoreReserve(page);
+	if (page)
 		put_page(page);
-	}
 	BUG_ON(copied < 0);
 	BUG_ON(err > 0);
 	BUG_ON(!copied && !err);
@@ -415,11 +439,16 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 						unsigned long dst_addr,
 						unsigned long src_addr,
 						struct page **page,
-						bool zeropage,
+						enum mcopy_atomic_mode mode,
 						bool wp_copy)
 {
 	ssize_t err;
 
+	if (mode == MCOPY_ATOMIC_CONTINUE) {
+		return mcontinue_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
+					    wp_copy);
+	}
+
 	/*
 	 * The normal page fault path for a shmem will invoke the
 	 * fault, fill the hole in the file and COW it right away. The
@@ -431,7 +460,7 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 	 * and not in the radix tree.
 	 */
 	if (!(dst_vma->vm_flags & VM_SHARED)) {
-		if (!zeropage)
+		if (mode == MCOPY_ATOMIC_NORMAL)
 			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
 					       dst_addr, src_addr, page,
 					       wp_copy);
@@ -440,13 +469,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 						 dst_vma, dst_addr);
 	} else {
 		VM_WARN_ON_ONCE(wp_copy);
-		if (!zeropage)
-			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
-						     dst_vma, dst_addr,
-						     src_addr, page);
-		else
-			err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd,
-						       dst_vma, dst_addr);
+		err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
+					     dst_addr, src_addr,
+					     mode != MCOPY_ATOMIC_NORMAL,
+					     page);
 	}
 
 	return err;
@@ -467,7 +493,6 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	long copied;
 	struct page *page;
 	bool wp_copy;
-	bool zeropage = (mcopy_mode == MCOPY_ATOMIC_ZEROPAGE);
 
 	/*
 	 * Sanitize the command parameters:
@@ -530,7 +555,7 @@ retry:
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
-	if (mcopy_mode == MCOPY_ATOMIC_CONTINUE)
+	if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE)
 		goto out_unlock;
 
 	/*
@@ -578,7 +603,7 @@ retry:
 		BUG_ON(pmd_trans_huge(*dst_pmd));
 
 		err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       src_addr, &page, zeropage, wp_copy);
+				       src_addr, &page, mcopy_mode, wp_copy);
 		cond_resched();
 
 		if (unlikely(err == -ENOENT)) {