1 files changed, 40 insertions, 25 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 423fc1607dfa..21b47402b3dc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1207,17 +1207,17 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = mapping->host;
 	pgtable_t pgtable = NULL;
-	struct page *zero_page;
+	struct folio *zero_folio;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
 	pfn_t pfn;
 
-	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
+	zero_folio = mm_get_huge_zero_folio(vmf->vma->vm_mm);
 
-	if (unlikely(!zero_page))
+	if (unlikely(!zero_folio))
 		goto fallback;
 
-	pfn = page_to_pfn_t(zero_page);
+	pfn = page_to_pfn_t(&zero_folio->page);
 	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn,
 				  DAX_PMD | DAX_ZERO_PAGE);
 
@@ -1237,17 +1237,17 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		mm_inc_nr_ptes(vma->vm_mm);
 	}
-	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
+	pmd_entry = mk_pmd(&zero_folio->page, vmf->vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
 	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
 	spin_unlock(ptl);
-	trace_dax_pmd_load_hole(inode, vmf, zero_page, *entry);
+	trace_dax_pmd_load_hole(inode, vmf, zero_folio, *entry);
 	return VM_FAULT_NOPAGE;
 
 fallback:
 	if (pgtable)
 		pte_free(vma->vm_mm, pgtable);
-	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
+	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_folio, *entry);
 	return VM_FAULT_FALLBACK;
 }
 #else
@@ -1262,35 +1262,46 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
-	loff_t pos = iter->pos;
-	loff_t length = iomap_length(iter);
+	loff_t copy_pos = iter->pos;
+	u64 copy_len = iomap_length(iter);
+	u32 mod;
 	int id = 0;
 	s64 ret = 0;
 	void *daddr = NULL, *saddr = NULL;
 
-	/* don't bother with blocks that are not shared to start with */
-	if (!(iomap->flags & IOMAP_F_SHARED))
-		return length;
+	if (!iomap_want_unshare_iter(iter))
+		return iomap_length(iter);
+
+	/*
+	 * Extend the file range to be aligned to fsblock/pagesize, because
+	 * we need to copy entire blocks, not just the byte range specified.
+	 * Invalidate the mapping because we're about to CoW.
+	 */
+	mod = offset_in_page(copy_pos);
+	if (mod) {
+		copy_len += mod;
+		copy_pos -= mod;
+	}
+
+	mod = offset_in_page(copy_pos + copy_len);
+	if (mod)
+		copy_len += PAGE_SIZE - mod;
+
+	invalidate_inode_pages2_range(iter->inode->i_mapping,
+				      copy_pos >> PAGE_SHIFT,
+				      (copy_pos + copy_len - 1) >> PAGE_SHIFT);
 
 	id = dax_read_lock();
-	ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
+	ret = dax_iomap_direct_access(iomap, copy_pos, copy_len, &daddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
-	/* zero the distance if srcmap is HOLE or UNWRITTEN */
-	if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
-		memset(daddr, 0, length);
-		dax_flush(iomap->dax_dev, daddr, length);
-		ret = length;
-		goto out_unlock;
-	}
-
-	ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
+	ret = dax_iomap_direct_access(srcmap, copy_pos, copy_len, &saddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
-	if (copy_mc_to_kernel(daddr, saddr, length) == 0)
-		ret = length;
+	if (copy_mc_to_kernel(daddr, saddr, copy_len) == 0)
+		ret = iomap_length(iter);
 	else
 		ret = -EIO;
 
@@ -1305,11 +1316,15 @@ int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 	struct iomap_iter iter = {
 		.inode		= inode,
 		.pos		= pos,
-		.len		= len,
 		.flags		= IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX,
 	};
+	loff_t size = i_size_read(inode);
 	int ret;
 
+	if (pos < 0 || pos >= size)
+		return 0;
+
+	iter.len = min(len, size - pos);
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = dax_unshare_iter(&iter);
 	return ret;