[RESEND PATCH v3 0/3] fsdax: Factor helper functions to simplify the code

[RESEND PATCH v3 0/3] fsdax: Factor helper functions to simplify the code

[Shiyang Ruan]

The page fault part of fsdax code is little complex. In order to add CoW
feature and make it easy to understand, I was suggested to factor some
helper functions to simplify the current dax code.

This is separated from the previous patchset called "V3 fsdax,xfs: Add
reflink&dedupe support for fsdax" as suggested[1].

[1]: https://lore.kernel.org/linux-xfs/20210402074936.GB7057@lst.de/


Changes from previous V3:
 - Rebased on v5.13
 - Add Darrick's Reviewed-by

Changes from V2:
 - fix the type of 'major' in patch 2
 - Rebased on v5.12-rc8

Changes from V1:
 - fix Ritesh's email address
 - simplify return logic in dax_fault_cow_page()

(Rebased on v5.13)
==


Shiyang Ruan (3):
  fsdax: Factor helpers to simplify dax fault code
  fsdax: Factor helper: dax_fault_actor()
  fsdax: Output address in dax_iomap_pfn() and rename it

 fs/dax.c | 443 +++++++++++++++++++++++++++++--------------------------
 1 file changed, 234 insertions(+), 209 deletions(-)

-- 
2.32.0

[RESEND PATCH v3 1/3] fsdax: Factor helpers to simplify dax fault code

[Shiyang Ruan]

The dax page fault code is too long and a bit difficult to read. And it
is hard to understand when we trying to add new features. Some of the
PTE/PMD codes have similar logic. So, factor them as helper functions to
simplify the code.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/dax.c | 153 ++++++++++++++++++++++++++++++-------------------------
 1 file changed, 84 insertions(+), 69 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 62352cbcf0f4..1fdd0b8dca0a 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1255,6 +1255,53 @@ static bool dax_fault_is_synchronous(unsigned long flags,
 		&& (iomap->flags & IOMAP_F_DIRTY);
 }
 
+/*
+ * If we are doing synchronous page fault and inode needs fsync, we can insert
+ * PTE/PMD into page tables only after that happens. Skip insertion for now and
+ * return the pfn so that caller can insert it after fsync is done.
+ */
+static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
+{
+	if (WARN_ON_ONCE(!pfnp))
+		return VM_FAULT_SIGBUS;
+
+	*pfnp = pfn;
+	return VM_FAULT_NEEDDSYNC;
+}
+
+static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
+		loff_t pos)
+{
+	int error = 0;
+	vm_fault_t ret;
+	unsigned long vaddr = vmf->address;
+	sector_t sector = dax_iomap_sector(iomap, pos);
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+	case IOMAP_UNWRITTEN:
+		clear_user_highpage(vmf->cow_page, vaddr);
+		break;
+	case IOMAP_MAPPED:
+		error = copy_cow_page_dax(iomap->bdev, iomap->dax_dev,
+						sector, vmf->cow_page, vaddr);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		error = -EIO;
+		break;
+	}
+
+	if (error)
+		return dax_fault_return(error);
+
+	__SetPageUptodate(vmf->cow_page);
+	ret = finish_fault(vmf);
+	if (!ret)
+		ret = VM_FAULT_DONE_COW;
+	return ret;
+}
+
 static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       int *iomap_errp, const struct iomap_ops *ops)
 {
@@ -1323,30 +1370,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	}
 
 	if (vmf->cow_page) {
-		sector_t sector = dax_iomap_sector(&iomap, pos);
-
-		switch (iomap.type) {
-		case IOMAP_HOLE:
-		case IOMAP_UNWRITTEN:
-			clear_user_highpage(vmf->cow_page, vaddr);
-			break;
-		case IOMAP_MAPPED:
-			error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev,
-						  sector, vmf->cow_page, vaddr);
-			break;
-		default:
-			WARN_ON_ONCE(1);
-			error = -EIO;
-			break;
-		}
-
-		if (error)
-			goto error_finish_iomap;
-
-		__SetPageUptodate(vmf->cow_page);
-		ret = finish_fault(vmf);
-		if (!ret)
-			ret = VM_FAULT_DONE_COW;
+		ret = dax_fault_cow_page(vmf, &iomap, pos);
 		goto finish_iomap;
 	}
 
@@ -1366,19 +1390,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
 						 0, write && !sync);
 
-		/*
-		 * If we are doing synchronous page fault and inode needs fsync,
-		 * we can insert PTE into page tables only after that happens.
-		 * Skip insertion for now and return the pfn so that caller can
-		 * insert it after fsync is done.
-		 */
 		if (sync) {
-			if (WARN_ON_ONCE(!pfnp)) {
-				error = -EIO;
-				goto error_finish_iomap;
-			}
-			*pfnp = pfn;
-			ret = VM_FAULT_NEEDDSYNC | major;
+			ret = dax_fault_synchronous_pfnp(pfnp, pfn);
 			goto finish_iomap;
 		}
 		trace_dax_insert_mapping(inode, vmf, entry);
@@ -1477,13 +1490,45 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	return VM_FAULT_FALLBACK;
 }
 
+static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
+		pgoff_t max_pgoff)
+{
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	/*
+	 * Make sure that the faulting address's PMD offset (color) matches
+	 * the PMD offset from the start of the file.  This is necessary so
+	 * that a PMD range in the page table overlaps exactly with a PMD
+	 * range in the page cache.
+	 */
+	if ((vmf->pgoff & PG_PMD_COLOUR) !=
+	    ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
+		return true;
+
+	/* Fall back to PTEs if we're going to COW */
+	if (write && !(vmf->vma->vm_flags & VM_SHARED))
+		return true;
+
+	/* If the PMD would extend outside the VMA */
+	if (pmd_addr < vmf->vma->vm_start)
+		return true;
+	if ((pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+		return true;
+
+	/* If the PMD would extend beyond the file size */
+	if ((xas->xa_index | PG_PMD_COLOUR) >= max_pgoff)
+		return true;
+
+	return false;
+}
+
 static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       const struct iomap_ops *ops)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
-	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool sync;
 	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
@@ -1506,33 +1551,12 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
 
-	/*
-	 * Make sure that the faulting address's PMD offset (color) matches
-	 * the PMD offset from the start of the file.  This is necessary so
-	 * that a PMD range in the page table overlaps exactly with a PMD
-	 * range in the page cache.
-	 */
-	if ((vmf->pgoff & PG_PMD_COLOUR) !=
-	    ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
-		goto fallback;
-
-	/* Fall back to PTEs if we're going to COW */
-	if (write && !(vma->vm_flags & VM_SHARED))
-		goto fallback;
-
-	/* If the PMD would extend outside the VMA */
-	if (pmd_addr < vma->vm_start)
-		goto fallback;
-	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
-		goto fallback;
-
 	if (xas.xa_index >= max_pgoff) {
 		result = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
-	/* If the PMD would extend beyond the file size */
-	if ((xas.xa_index | PG_PMD_COLOUR) >= max_pgoff)
+	if (dax_fault_check_fallback(vmf, &xas, max_pgoff))
 		goto fallback;
 
 	/*
@@ -1584,17 +1608,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
 						DAX_PMD, write && !sync);
 
-		/*
-		 * If we are doing synchronous page fault and inode needs fsync,
-		 * we can insert PMD into page tables only after that happens.
-		 * Skip insertion for now and return the pfn so that caller can
-		 * insert it after fsync is done.
-		 */
 		if (sync) {
-			if (WARN_ON_ONCE(!pfnp))
-				goto finish_iomap;
-			*pfnp = pfn;
-			result = VM_FAULT_NEEDDSYNC;
+			result = dax_fault_synchronous_pfnp(pfnp, pfn);
 			goto finish_iomap;
 		}
 
-- 
2.32.0

[RESEND PATCH v3 2/3] fsdax: Factor helper: dax_fault_actor()

[Shiyang Ruan]

The core logic in the two dax page fault functions is similar. So, move
the logic into a common helper function. Also, to facilitate the
addition of new features, such as CoW, switch-case is no longer used to
handle different iomap types.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/dax.c | 298 ++++++++++++++++++++++++++++---------------------------
 1 file changed, 150 insertions(+), 148 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 1fdd0b8dca0a..acc548875fd4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1065,6 +1065,66 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
+#ifdef CONFIG_FS_DAX_PMD
+static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
+		struct iomap *iomap, void **entry)
+{
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	struct inode *inode = mapping->host;
+	pgtable_t pgtable = NULL;
+	struct page *zero_page;
+	spinlock_t *ptl;
+	pmd_t pmd_entry;
+	pfn_t pfn;
+
+	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
+
+	if (unlikely(!zero_page))
+		goto fallback;
+
+	pfn = page_to_pfn_t(zero_page);
+	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
+			DAX_PMD | DAX_ZERO_PAGE, false);
+
+	if (arch_needs_pgtable_deposit()) {
+		pgtable = pte_alloc_one(vma->vm_mm);
+		if (!pgtable)
+			return VM_FAULT_OOM;
+	}
+
+	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+	if (!pmd_none(*(vmf->pmd))) {
+		spin_unlock(ptl);
+		goto fallback;
+	}
+
+	if (pgtable) {
+		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 = 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);
+	return VM_FAULT_NOPAGE;
+
+fallback:
+	if (pgtable)
+		pte_free(vma->vm_mm, pgtable);
+	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
+	return VM_FAULT_FALLBACK;
+}
+#else
+static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
+		struct iomap *iomap, void **entry)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif /* CONFIG_FS_DAX_PMD */
+
 s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
@@ -1302,6 +1362,64 @@ static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
 	return ret;
 }
 
+/**
+ * dax_fault_actor - Common actor to handle pfn insertion in PTE/PMD fault.
+ * @vmf:	vm fault instance
+ * @pfnp:	pfn to be returned
+ * @xas:	the dax mapping tree of a file
+ * @entry:	an unlocked dax entry to be inserted
+ * @pmd:	distinguish whether it is a pmd fault
+ * @flags:	iomap flags
+ * @iomap:	from iomap_begin()
+ * @srcmap:	from iomap_begin(), not equal to iomap if it is a CoW
+ */
+static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
+		struct xa_state *xas, void **entry, bool pmd,
+		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	size_t size = pmd ? PMD_SIZE : PAGE_SIZE;
+	loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	bool sync = dax_fault_is_synchronous(flags, vmf->vma, iomap);
+	unsigned long entry_flags = pmd ? DAX_PMD : 0;
+	int err = 0;
+	pfn_t pfn;
+
+	/* if we are reading UNWRITTEN and HOLE, return a hole. */
+	if (!write &&
+	    (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) {
+		if (!pmd)
+			return dax_load_hole(xas, mapping, entry, vmf);
+		else
+			return dax_pmd_load_hole(xas, vmf, iomap, entry);
+	}
+
+	if (iomap->type != IOMAP_MAPPED) {
+		WARN_ON_ONCE(1);
+		return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS;
+	}
+
+	err = dax_iomap_pfn(iomap, pos, size, &pfn);
+	if (err)
+		return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);
+
+	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags,
+				  write && !sync);
+
+	if (sync)
+		return dax_fault_synchronous_pfnp(pfnp, pfn);
+
+	/* insert PMD pfn */
+	if (pmd)
+		return vmf_insert_pfn_pmd(vmf, pfn, write);
+
+	/* insert PTE pfn */
+	if (write)
+		return vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
+	return vmf_insert_mixed(vmf->vma, vmf->address, pfn);
+}
+
 static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			       int *iomap_errp, const struct iomap_ops *ops)
 {
@@ -1309,17 +1427,14 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
 	struct inode *inode = mapping->host;
-	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	struct iomap iomap = { .type = IOMAP_HOLE };
 	struct iomap srcmap = { .type = IOMAP_HOLE };
 	unsigned flags = IOMAP_FAULT;
-	int error, major = 0;
+	int error;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool sync;
-	vm_fault_t ret = 0;
+	vm_fault_t ret = 0, major = 0;
 	void *entry;
-	pfn_t pfn;
 
 	trace_dax_pte_fault(inode, vmf, ret);
 	/*
@@ -1365,8 +1480,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		goto unlock_entry;
 	}
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;	/* fs corruption? */
-		goto error_finish_iomap;
+		ret = VM_FAULT_SIGBUS;	/* fs corruption? */
+		goto finish_iomap;
 	}
 
 	if (vmf->cow_page) {
@@ -1374,49 +1489,19 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		goto finish_iomap;
 	}
 
-	sync = dax_fault_is_synchronous(flags, vma, &iomap);
-
-	switch (iomap.type) {
-	case IOMAP_MAPPED:
-		if (iomap.flags & IOMAP_F_NEW) {
-			count_vm_event(PGMAJFAULT);
-			count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
-			major = VM_FAULT_MAJOR;
-		}
-		error = dax_iomap_pfn(&iomap, pos, PAGE_SIZE, &pfn);
-		if (error < 0)
-			goto error_finish_iomap;
-
-		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
-						 0, write && !sync);
-
-		if (sync) {
-			ret = dax_fault_synchronous_pfnp(pfnp, pfn);
-			goto finish_iomap;
-		}
-		trace_dax_insert_mapping(inode, vmf, entry);
-		if (write)
-			ret = vmf_insert_mixed_mkwrite(vma, vaddr, pfn);
-		else
-			ret = vmf_insert_mixed(vma, vaddr, pfn);
-
+	ret = dax_fault_actor(vmf, pfnp, &xas, &entry, false, flags,
+			      &iomap, &srcmap);
+	if (ret == VM_FAULT_SIGBUS)
 		goto finish_iomap;
-	case IOMAP_UNWRITTEN:
-	case IOMAP_HOLE:
-		if (!write) {
-			ret = dax_load_hole(&xas, mapping, &entry, vmf);
-			goto finish_iomap;
-		}
-		fallthrough;
-	default:
-		WARN_ON_ONCE(1);
-		error = -EIO;
-		break;
+
+	/* read/write MAPPED, CoW UNWRITTEN */
+	if (iomap.flags & IOMAP_F_NEW) {
+		count_vm_event(PGMAJFAULT);
+		count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
+		major = VM_FAULT_MAJOR;
 	}
 
- error_finish_iomap:
-	ret = dax_fault_return(error);
- finish_iomap:
+finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PAGE_SIZE;
 
@@ -1430,66 +1515,14 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		 */
 		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
+unlock_entry:
 	dax_unlock_entry(&xas, entry);
- out:
+out:
 	trace_dax_pte_fault_done(inode, vmf, ret);
 	return ret | major;
 }
 
 #ifdef CONFIG_FS_DAX_PMD
-static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
-		struct iomap *iomap, void **entry)
-{
-	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
-	unsigned long pmd_addr = vmf->address & PMD_MASK;
-	struct vm_area_struct *vma = vmf->vma;
-	struct inode *inode = mapping->host;
-	pgtable_t pgtable = NULL;
-	struct page *zero_page;
-	spinlock_t *ptl;
-	pmd_t pmd_entry;
-	pfn_t pfn;
-
-	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
-
-	if (unlikely(!zero_page))
-		goto fallback;
-
-	pfn = page_to_pfn_t(zero_page);
-	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
-			DAX_PMD | DAX_ZERO_PAGE, false);
-
-	if (arch_needs_pgtable_deposit()) {
-		pgtable = pte_alloc_one(vma->vm_mm);
-		if (!pgtable)
-			return VM_FAULT_OOM;
-	}
-
-	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
-	if (!pmd_none(*(vmf->pmd))) {
-		spin_unlock(ptl);
-		goto fallback;
-	}
-
-	if (pgtable) {
-		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 = 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);
-	return VM_FAULT_NOPAGE;
-
-fallback:
-	if (pgtable)
-		pte_free(vma->vm_mm, pgtable);
-	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
-	return VM_FAULT_FALLBACK;
-}
-
 static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
 		pgoff_t max_pgoff)
 {
@@ -1530,17 +1563,15 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool sync;
-	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
+	unsigned int flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
-	vm_fault_t result = VM_FAULT_FALLBACK;
+	vm_fault_t ret = VM_FAULT_FALLBACK;
 	struct iomap iomap = { .type = IOMAP_HOLE };
 	struct iomap srcmap = { .type = IOMAP_HOLE };
 	pgoff_t max_pgoff;
 	void *entry;
 	loff_t pos;
 	int error;
-	pfn_t pfn;
 
 	/*
 	 * Check whether offset isn't beyond end of file now. Caller is
@@ -1552,7 +1583,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
 
 	if (xas.xa_index >= max_pgoff) {
-		result = VM_FAULT_SIGBUS;
+		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
@@ -1567,7 +1598,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 */
 	entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
 	if (xa_is_internal(entry)) {
-		result = xa_to_internal(entry);
+		ret = xa_to_internal(entry);
 		goto fallback;
 	}
 
@@ -1579,7 +1610,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 */
 	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
 			!pmd_devmap(*vmf->pmd)) {
-		result = 0;
+		ret = 0;
 		goto unlock_entry;
 	}
 
@@ -1589,49 +1620,21 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * to look up our filesystem block.
 	 */
 	pos = (loff_t)xas.xa_index << PAGE_SHIFT;
-	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,
-			&srcmap);
+	error = ops->iomap_begin(inode, pos, PMD_SIZE, flags, &iomap, &srcmap);
 	if (error)
 		goto unlock_entry;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
-
-	switch (iomap.type) {
-	case IOMAP_MAPPED:
-		error = dax_iomap_pfn(&iomap, pos, PMD_SIZE, &pfn);
-		if (error < 0)
-			goto finish_iomap;
+	ret = dax_fault_actor(vmf, pfnp, &xas, &entry, true, flags,
+			      &iomap, &srcmap);
 
-		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
-						DAX_PMD, write && !sync);
-
-		if (sync) {
-			result = dax_fault_synchronous_pfnp(pfnp, pfn);
-			goto finish_iomap;
-		}
-
-		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
-		result = vmf_insert_pfn_pmd(vmf, pfn, write);
-		break;
-	case IOMAP_UNWRITTEN:
-	case IOMAP_HOLE:
-		if (WARN_ON_ONCE(write))
-			break;
-		result = dax_pmd_load_hole(&xas, vmf, &iomap, &entry);
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
-
- finish_iomap:
+finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
 
-		if (result == VM_FAULT_FALLBACK)
+		if (ret == VM_FAULT_FALLBACK)
 			copied = 0;
 		/*
 		 * The fault is done by now and there's no way back (other
@@ -1639,19 +1642,18 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		 * Just ignore error from ->iomap_end since we cannot do much
 		 * with it.
 		 */
-		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
-				&iomap);
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
+unlock_entry:
 	dax_unlock_entry(&xas, entry);
- fallback:
-	if (result == VM_FAULT_FALLBACK) {
+fallback:
+	if (ret == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
 out:
-	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
-	return result;
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, ret);
+	return ret;
 }
 #else
 static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
-- 
2.32.0

[RESEND PATCH v3 3/3] fsdax: Output address in dax_iomap_pfn() and rename it

[Shiyang Ruan]

Add address output in dax_iomap_pfn() in order to perform a memcpy() in
CoW case.  Since this function both output address and pfn, rename it to
dax_iomap_direct_access().

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/dax.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index acc548875fd4..f661227b49cd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1009,8 +1009,8 @@ static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
 }
 
-static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
-			 pfn_t *pfnp)
+static int dax_iomap_direct_access(struct iomap *iomap, loff_t pos, size_t size,
+		void **kaddr, pfn_t *pfnp)
 {
 	const sector_t sector = dax_iomap_sector(iomap, pos);
 	pgoff_t pgoff;
@@ -1022,11 +1022,13 @@ static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
 		return rc;
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
-				   NULL, pfnp);
+				   kaddr, pfnp);
 	if (length < 0) {
 		rc = length;
 		goto out;
 	}
+	if (!pfnp)
+		goto out_check_addr;
 	rc = -EINVAL;
 	if (PFN_PHYS(length) < size)
 		goto out;
@@ -1036,6 +1038,12 @@ static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
 	if (length > 1 && !pfn_t_devmap(*pfnp))
 		goto out;
 	rc = 0;
+
+out_check_addr:
+	if (!kaddr)
+		goto out;
+	if (!*kaddr)
+		rc = -EFAULT;
 out:
 	dax_read_unlock(id);
 	return rc;
@@ -1400,7 +1408,7 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 		return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS;
 	}
 
-	err = dax_iomap_pfn(iomap, pos, size, &pfn);
+	err = dax_iomap_direct_access(iomap, pos, size, NULL, &pfn);
 	if (err)
 		return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);
 
-- 
2.32.0