Merge branch 'for-4.18/dax' into libnvdimm-for-next

drivers/dax/super.c

@@ -86,6 +86,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 {
 	struct block_device *bdev = sb->s_bdev;
 	struct dax_device *dax_dev;
+	bool dax_enabled = false;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
@@ -134,14 +135,21 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 		 * on being able to do (page_address(pfn_to_page())).
 		 */
 		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
+		dax_enabled = true;
 	} else if (pfn_t_devmap(pfn)) {
-		/* pass */;
-	} else {
+		struct dev_pagemap *pgmap;
+
+		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
+		if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX)
+			dax_enabled = true;
+		put_dev_pagemap(pgmap);
+	}
+
+	if (!dax_enabled) {
 		pr_debug("VFS (%s): error: dax support not enabled\n",
 				sb->s_id);
 		return -EOPNOTSUPP;
 	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);

drivers/nvdimm/pfn_devs.c

@@ -561,8 +561,6 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	res->start += start_pad;
 	res->end -= end_trunc;
 
-	pgmap->type = MEMORY_DEVICE_HOST;
-
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < SZ_8K)
 			return -EINVAL;

drivers/nvdimm/pmem.c

@@ -289,6 +289,27 @@ static void pmem_release_disk(void *__pmem)
 	put_disk(pmem->disk);
 }
 
+static void pmem_release_pgmap_ops(void *__pgmap)
+{
+	dev_pagemap_put_ops();
+}
+
+static void fsdax_pagefree(struct page *page, void *data)
+{
+	wake_up_var(&page->_refcount);
+}
+
+static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
+{
+	dev_pagemap_get_ops();
+	if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
+		return -ENOMEM;
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+	pgmap->page_free = fsdax_pagefree;
+
+	return 0;
+}
+
 static int pmem_attach_disk(struct device *dev,
 		struct nd_namespace_common *ndns)
 {
@@ -347,6 +368,8 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->pfn_flags = PFN_DEV;
 	pmem->pgmap.ref = &q->q_usage_counter;
 	if (is_nd_pfn(dev)) {
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -358,6 +381,8 @@ static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
 		pmem->pgmap.altmap_valid = false;
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));

fs/Kconfig

@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)
 	select FS_IOMAP
 	select DAX
 	help

fs/dax.c

@@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
 	}
 }
 
+static struct page *dax_busy_page(void *entry)
+{
+	unsigned long pfn;
+
+	for_each_mapped_pfn(entry, pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		if (page_ref_count(page) > 1)
+			return page;
+	}
+	return NULL;
+}
+
 /*
  * Find radix tree entry at given index. If it points to an exceptional entry,
  * return it with the radix tree entry locked. If the radix tree doesn't
@@ -492,6 +505,90 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
 	return entry;
 }
 
+/**
+ * dax_layout_busy_page - find first pinned page in @mapping
+ * @mapping: address space to scan for a page with ref count > 1
+ *
+ * DAX requires ZONE_DEVICE mapped pages. These pages are never
+ * 'onlined' to the page allocator so they are considered idle when
+ * page->count == 1. A filesystem uses this interface to determine if
+ * any page in the mapping is busy, i.e. for DMA, or other
+ * get_user_pages() usages.
+ *
+ * It is expected that the filesystem is holding locks to block the
+ * establishment of new mappings in this address_space. I.e. it expects
+ * to be able to run unmap_mapping_range() and subsequently not race
+ * mapping_mapped() becoming true.
+ */
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	pgoff_t	indices[PAGEVEC_SIZE];
+	struct page *page = NULL;
+	struct pagevec pvec;
+	pgoff_t	index, end;
+	unsigned i;
+
+	/*
+	 * In the 'limited' case get_user_pages() for dax is disabled.
+	 */
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+		return NULL;
+
+	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+		return NULL;
+
+	pagevec_init(&pvec);
+	index = 0;
+	end = -1;
+
+	/*
+	 * If we race get_user_pages_fast() here either we'll see the
+	 * elevated page count in the pagevec_lookup and wait, or
+	 * get_user_pages_fast() will see that the page it took a reference
+	 * against is no longer mapped in the page tables and bail to the
+	 * get_user_pages() slow path.  The slow path is protected by
+	 * pte_lock() and pmd_lock(). New references are not taken without
+	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * pte or pmd without holding the respective lock, so we are
+	 * guaranteed to either see new references or prevent new
+	 * references from being established.
+	 */
+	unmap_mapping_range(mapping, 0, 0, 1);
+
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE),
+				indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *pvec_ent = pvec.pages[i];
+			void *entry;
+
+			index = indices[i];
+			if (index >= end)
+				break;
+
+			if (!radix_tree_exceptional_entry(pvec_ent))
+				continue;
+
+			xa_lock_irq(&mapping->i_pages);
+			entry = get_unlocked_mapping_entry(mapping, index, NULL);
+			if (entry)
+				page = dax_busy_page(entry);
+			put_unlocked_mapping_entry(mapping, index, entry);
+			xa_unlock_irq(&mapping->i_pages);
+			if (page)
+				break;
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		index++;
+
+		if (page)
+			break;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page);
+
 static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 					  pgoff_t index, bool trunc)
 {
@@ -912,7 +1009,6 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 	unsigned long vaddr = vmf->address;
 	int ret = VM_FAULT_NOPAGE;
 	struct page *zero_page;
-	void *entry2;
 	pfn_t pfn;
 
 	zero_page = ZERO_PAGE(0);
@@ -922,13 +1018,8 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 	}
 
 	pfn = page_to_pfn_t(zero_page);
-	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(entry2)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out;
-	}
-
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
+			false);
 	vm_insert_mixed(vmf->vma, vaddr, pfn);
 out:
 	trace_dax_load_hole(inode, vmf, ret);
@@ -1240,10 +1331,6 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						 0, write && !sync);
-		if (IS_ERR(entry)) {
-			error = PTR_ERR(entry);
-			goto error_finish_iomap;
-		}
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
@@ -1327,8 +1414,6 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(ret))
-		goto fallback;
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1450,8 +1535,6 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						RADIX_DAX_PMD, write && !sync);
-		if (IS_ERR(entry))
-			goto finish_iomap;
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,

fs/xfs/xfs_file.c

@@ -312,7 +312,7 @@ xfs_file_aio_write_checks(
 	if (error <= 0)
 		return error;
 
-	error = xfs_break_layouts(inode, iolock);
+	error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
 	if (error)
 		return error;
 
@@ -718,6 +718,69 @@ xfs_file_write_iter(
 	return ret;
 }
 
+static void
+xfs_wait_dax_page(
+	struct inode		*inode,
+	bool			*did_unlock)
+{
+	struct xfs_inode        *ip = XFS_I(inode);
+
+	*did_unlock = true;
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+	schedule();
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+}
+
+static int
+xfs_break_dax_layouts(
+	struct inode		*inode,
+	uint			iolock,
+	bool			*did_unlock)
+{
+	struct page		*page;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+
+	page = dax_layout_busy_page(inode->i_mapping);
+	if (!page)
+		return 0;
+
+	return ___wait_var_event(&page->_refcount,
+			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+			0, 0, xfs_wait_dax_page(inode, did_unlock));
+}
+
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock,
+	enum layout_break_reason reason)
+{
+	bool			retry;
+	int			error;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	do {
+		retry = false;
+		switch (reason) {
+		case BREAK_UNMAP:
+			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			if (error || retry)
+				break;
+			/* fall through */
+		case BREAK_WRITE:
+			error = xfs_break_leased_layouts(inode, iolock, &retry);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			error = -EINVAL;
+		}
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 #define	XFS_FALLOC_FL_SUPPORTED						\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
@@ -734,7 +797,7 @@ xfs_file_fallocate(
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	enum xfs_prealloc_flags	flags = 0;
-	uint			iolock = XFS_IOLOCK_EXCL;
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	loff_t			new_size = 0;
 	bool			do_file_insert = false;
 
@@ -744,13 +807,10 @@ xfs_file_fallocate(
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
 	if (error)
 		goto out_unlock;
 
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	iolock |= XFS_MMAPLOCK_EXCL;
-
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)

fs/xfs/xfs_inode.h

@@ -378,6 +378,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
 #define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) \
 					>> XFS_ILOCK_SHIFT)
 
+/*
+ * Layouts are broken in the BREAK_WRITE case to ensure that
+ * layout-holders do not collide with local writes. Additionally,
+ * layouts are broken in the BREAK_UNMAP case to make sure the
+ * layout-holder has a consistent view of the file's extent map. While
+ * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
+ * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
+ * go idle.
+ */
+enum layout_break_reason {
+        BREAK_WRITE,
+        BREAK_UNMAP,
+};
+
 /*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
@@ -443,6 +457,8 @@ enum xfs_prealloc_flags {
 
 int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 				  enum xfs_prealloc_flags flags);
+int	xfs_break_layouts(struct inode *inode, uint *iolock,
+		enum layout_break_reason reason);
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);