1 files changed, 120 insertions, 18 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 897b51e41d8f..f32d7125ad0f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -226,8 +226,8 @@ static inline void *unlock_slot(struct address_space *mapping, void **slot)
  *
  * Must be called with the i_pages lock held.
  */
-static void *get_unlocked_mapping_entry(struct address_space *mapping,
-					pgoff_t index, void ***slotp)
+static void *__get_unlocked_mapping_entry(struct address_space *mapping,
+		pgoff_t index, void ***slotp, bool (*wait_fn)(void))
 {
 	void *entry, **slot;
 	struct wait_exceptional_entry_queue ewait;
@@ -237,6 +237,8 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 	ewait.wait.func = wake_exceptional_entry_func;
 
 	for (;;) {
+		bool revalidate;
+
 		entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
 					  &slot);
 		if (!entry ||
@@ -251,14 +253,31 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 		prepare_to_wait_exclusive(wq, &ewait.wait,
 					  TASK_UNINTERRUPTIBLE);
 		xa_unlock_irq(&mapping->i_pages);
-		schedule();
+		revalidate = wait_fn();
 		finish_wait(wq, &ewait.wait);
 		xa_lock_irq(&mapping->i_pages);
+		if (revalidate)
+			return ERR_PTR(-EAGAIN);
 	}
 }
 
-static void dax_unlock_mapping_entry(struct address_space *mapping,
-				     pgoff_t index)
+static bool entry_wait(void)
+{
+	schedule();
+	/*
+	 * Never return an ERR_PTR() from
+	 * __get_unlocked_mapping_entry(), just keep looping.
+	 */
+	return false;
+}
+
+static void *get_unlocked_mapping_entry(struct address_space *mapping,
+		pgoff_t index, void ***slotp)
+{
+	return __get_unlocked_mapping_entry(mapping, index, slotp, entry_wait);
+}
+
+static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
 	void *entry, **slot;
 
@@ -277,7 +296,7 @@ static void dax_unlock_mapping_entry(struct address_space *mapping,
 static void put_locked_mapping_entry(struct address_space *mapping,
 		pgoff_t index)
 {
-	dax_unlock_mapping_entry(mapping, index);
+	unlock_mapping_entry(mapping, index);
 }
 
 /*
@@ -319,18 +338,27 @@ static unsigned long dax_radix_end_pfn(void *entry)
 	for (pfn = dax_radix_pfn(entry); \
 			pfn < dax_radix_end_pfn(entry); pfn++)
 
-static void dax_associate_entry(void *entry, struct address_space *mapping)
+/*
+ * TODO: for reflink+dax we need a way to associate a single page with
+ * multiple address_space instances at different linear_page_index()
+ * offsets.
+ */
+static void dax_associate_entry(void *entry, struct address_space *mapping,
+		struct vm_area_struct *vma, unsigned long address)
 {
-	unsigned long pfn;
+	unsigned long size = dax_entry_size(entry), pfn, index;
+	int i = 0;
 
 	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
 		return;
 
+	index = linear_page_index(vma, address & ~(size - 1));
 	for_each_mapped_pfn(entry, pfn) {
 		struct page *page = pfn_to_page(pfn);
 
 		WARN_ON_ONCE(page->mapping);
 		page->mapping = mapping;
+		page->index = index + i++;
 	}
 }
 
@@ -348,6 +376,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
 		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
 		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
 		page->mapping = NULL;
+		page->index = 0;
 	}
 }
 
@@ -364,6 +393,84 @@ static struct page *dax_busy_page(void *entry)
 	return NULL;
 }
 
+static bool entry_wait_revalidate(void)
+{
+	rcu_read_unlock();
+	schedule();
+	rcu_read_lock();
+
+	/*
+	 * Tell __get_unlocked_mapping_entry() to take a break, we need
+	 * to revalidate page->mapping after dropping locks
+	 */
+	return true;
+}
+
+bool dax_lock_mapping_entry(struct page *page)
+{
+	pgoff_t index;
+	struct inode *inode;
+	bool did_lock = false;
+	void *entry = NULL, **slot;
+	struct address_space *mapping;
+
+	rcu_read_lock();
+	for (;;) {
+		mapping = READ_ONCE(page->mapping);
+
+		if (!dax_mapping(mapping))
+			break;
+
+		/*
+		 * In the device-dax case there's no need to lock, a
+		 * struct dev_pagemap pin is sufficient to keep the
+		 * inode alive, and we assume we have dev_pagemap pin
+		 * otherwise we would not have a valid pfn_to_page()
+		 * translation.
+		 */
+		inode = mapping->host;
+		if (S_ISCHR(inode->i_mode)) {
+			did_lock = true;
+			break;
+		}
+
+		xa_lock_irq(&mapping->i_pages);
+		if (mapping != page->mapping) {
+			xa_unlock_irq(&mapping->i_pages);
+			continue;
+		}
+		index = page->index;
+
+		entry = __get_unlocked_mapping_entry(mapping, index, &slot,
+				entry_wait_revalidate);
+		if (!entry) {
+			xa_unlock_irq(&mapping->i_pages);
+			break;
+		} else if (IS_ERR(entry)) {
+			WARN_ON_ONCE(PTR_ERR(entry) != -EAGAIN);
+			continue;
+		}
+		lock_slot(mapping, slot);
+		did_lock = true;
+		xa_unlock_irq(&mapping->i_pages);
+		break;
+	}
+	rcu_read_unlock();
+
+	return did_lock;
+}
+
+void dax_unlock_mapping_entry(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+
+	if (S_ISCHR(inode->i_mode))
+		return;
+
+	unlock_mapping_entry(mapping, page->index);
+}
+
 /*
  * 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
@@ -655,7 +762,6 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
 {
 	void *vto, *kaddr;
 	pgoff_t pgoff;
-	pfn_t pfn;
 	long rc;
 	int id;
 
@@ -664,7 +770,7 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
 		return rc;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
+	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -709,7 +815,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	new_entry = dax_radix_locked_entry(pfn, flags);
 	if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
 		dax_disassociate_entry(entry, mapping, false);
-		dax_associate_entry(new_entry, mapping);
+		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
 	}
 
 	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
@@ -975,7 +1081,6 @@ static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
 {
 	const sector_t sector = dax_iomap_sector(iomap, pos);
 	pgoff_t pgoff;
-	void *kaddr;
 	int id, rc;
 	long length;
 
@@ -984,7 +1089,7 @@ 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),
-				   &kaddr, pfnp);
+				   NULL, pfnp);
 	if (length < 0) {
 		rc = length;
 		goto out;
@@ -1060,15 +1165,13 @@ int __dax_zero_page_range(struct block_device *bdev,
 		pgoff_t pgoff;
 		long rc, id;
 		void *kaddr;
-		pfn_t pfn;
 
 		rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
 		if (rc)
 			return rc;
 
 		id = dax_read_lock();
-		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr,
-				&pfn);
+		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
 		if (rc < 0) {
 			dax_read_unlock(id);
 			return rc;
@@ -1124,7 +1227,6 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		ssize_t map_len;
 		pgoff_t pgoff;
 		void *kaddr;
-		pfn_t pfn;
 
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;
@@ -1136,7 +1238,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			break;
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
-				&kaddr, &pfn);
+				&kaddr, NULL);
 		if (map_len < 0) {
 			ret = map_len;
 			break;