1 files changed, 280 insertions, 89 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 7fd4cd9a51f2..af5045b0f476 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -71,6 +71,11 @@ static unsigned long dax_to_pfn(void *entry)
 	return xa_to_value(entry) >> DAX_SHIFT;
 }
 
+static struct folio *dax_to_folio(void *entry)
+{
+	return page_folio(pfn_to_page(dax_to_pfn(entry)));
+}
+
 static void *dax_make_entry(pfn_t pfn, unsigned long flags)
 {
 	return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
@@ -206,7 +211,7 @@ static void dax_wake_entry(struct xa_state *xas, void *entry,
  *
  * Must be called with the i_pages lock held.
  */
-static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
+static void *get_next_unlocked_entry(struct xa_state *xas, unsigned int order)
 {
 	void *entry;
 	struct wait_exceptional_entry_queue ewait;
@@ -236,6 +241,37 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
 }
 
 /*
+ * Wait for the given entry to become unlocked. Caller must hold the i_pages
+ * lock and call either put_unlocked_entry() if it did not lock the entry or
+ * dax_unlock_entry() if it did. Returns an unlocked entry if still present.
+ */
+static void *wait_entry_unlocked_exclusive(struct xa_state *xas, void *entry)
+{
+	struct wait_exceptional_entry_queue ewait;
+	wait_queue_head_t *wq;
+
+	init_wait(&ewait.wait);
+	ewait.wait.func = wake_exceptional_entry_func;
+
+	while (unlikely(dax_is_locked(entry))) {
+		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
+		prepare_to_wait_exclusive(wq, &ewait.wait,
+					TASK_UNINTERRUPTIBLE);
+		xas_pause(xas);
+		xas_unlock_irq(xas);
+		schedule();
+		finish_wait(wq, &ewait.wait);
+		xas_lock_irq(xas);
+		entry = xas_load(xas);
+	}
+
+	if (xa_is_internal(entry))
+		return NULL;
+
+	return entry;
+}
+
+/*
  * The only thing keeping the address space around is the i_pages lock
  * (it's cycled in clear_inode() after removing the entries from i_pages)
  * After we call xas_unlock_irq(), we cannot touch xas->xa.
@@ -250,7 +286,7 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry)
 
 	wq = dax_entry_waitqueue(xas, entry, &ewait.key);
 	/*
-	 * Unlike get_unlocked_entry() there is no guarantee that this
+	 * Unlike get_next_unlocked_entry() there is no guarantee that this
 	 * path ever successfully retrieves an unlocked entry before an
 	 * inode dies. Perform a non-exclusive wait in case this path
 	 * never successfully performs its own wake up.
@@ -307,109 +343,156 @@ static unsigned long dax_entry_size(void *entry)
 		return PAGE_SIZE;
 }
 
-static unsigned long dax_end_pfn(void *entry)
+/*
+ * A DAX folio is considered shared if it has no mapping set and ->share (which
+ * shares the ->index field) is non-zero. Note this may return false even if the
+ * page is shared between multiple files but has not yet actually been mapped
+ * into multiple address spaces.
+ */
+static inline bool dax_folio_is_shared(struct folio *folio)
 {
-	return dax_to_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
+	return !folio->mapping && folio->share;
 }
 
 /*
- * Iterate through all mapped pfns represented by an entry, i.e. skip
- * 'empty' and 'zero' entries.
+ * When it is called by dax_insert_entry(), the shared flag will indicate
+ * whether this entry is shared by multiple files. If the page has not
+ * previously been associated with any mappings the ->mapping and ->index
+ * fields will be set. If it has already been associated with a mapping
+ * the mapping will be cleared and the share count set. It's then up to
+ * reverse map users like memory_failure() to call back into the filesystem to
+ * recover ->mapping and ->index information. For example by implementing
+ * dax_holder_operations.
  */
-#define for_each_mapped_pfn(entry, pfn) \
-	for (pfn = dax_to_pfn(entry); \
-			pfn < dax_end_pfn(entry); pfn++)
-
-static inline bool dax_page_is_shared(struct page *page)
+static void dax_folio_make_shared(struct folio *folio)
 {
-	return page->mapping == PAGE_MAPPING_DAX_SHARED;
+	/*
+	 * folio is not currently shared so mark it as shared by clearing
+	 * folio->mapping.
+	 */
+	folio->mapping = NULL;
+
+	/*
+	 * folio has previously been mapped into one address space so set the
+	 * share count.
+	 */
+	folio->share = 1;
 }
 
-/*
- * Set the page->mapping with PAGE_MAPPING_DAX_SHARED flag, increase the
- * refcount.
- */
-static inline void dax_page_share_get(struct page *page)
+static inline unsigned long dax_folio_put(struct folio *folio)
 {
-	if (page->mapping != PAGE_MAPPING_DAX_SHARED) {
+	unsigned long ref;
+	int order, i;
+
+	if (!dax_folio_is_shared(folio))
+		ref = 0;
+	else
+		ref = --folio->share;
+
+	if (ref)
+		return ref;
+
+	folio->mapping = NULL;
+	order = folio_order(folio);
+	if (!order)
+		return 0;
+
+	for (i = 0; i < (1UL << order); i++) {
+		struct dev_pagemap *pgmap = page_pgmap(&folio->page);
+		struct page *page = folio_page(folio, i);
+		struct folio *new_folio = (struct folio *)page;
+
+		ClearPageHead(page);
+		clear_compound_head(page);
+
+		new_folio->mapping = NULL;
 		/*
-		 * Reset the index if the page was already mapped
-		 * regularly before.
+		 * Reset pgmap which was over-written by
+		 * prep_compound_page().
 		 */
-		if (page->mapping)
-			page->share = 1;
-		page->mapping = PAGE_MAPPING_DAX_SHARED;
+		new_folio->pgmap = pgmap;
+		new_folio->share = 0;
+		WARN_ON_ONCE(folio_ref_count(new_folio));
 	}
-	page->share++;
+
+	return ref;
 }
 
-static inline unsigned long dax_page_share_put(struct page *page)
+static void dax_folio_init(void *entry)
 {
-	return --page->share;
+	struct folio *folio = dax_to_folio(entry);
+	int order = dax_entry_order(entry);
+
+	/*
+	 * Folio should have been split back to order-0 pages in
+	 * dax_folio_put() when they were removed from their
+	 * final mapping.
+	 */
+	WARN_ON_ONCE(folio_order(folio));
+
+	if (order > 0) {
+		prep_compound_page(&folio->page, order);
+		if (order > 1)
+			INIT_LIST_HEAD(&folio->_deferred_list);
+		WARN_ON_ONCE(folio_ref_count(folio));
+	}
 }
 
-/*
- * When it is called in dax_insert_entry(), the shared flag will indicate that
- * whether this entry is shared by multiple files.  If so, set the page->mapping
- * PAGE_MAPPING_DAX_SHARED, and use page->share as refcount.
- */
 static void dax_associate_entry(void *entry, struct address_space *mapping,
-		struct vm_area_struct *vma, unsigned long address, bool shared)
+				struct vm_area_struct *vma,
+				unsigned long address, bool shared)
 {
-	unsigned long size = dax_entry_size(entry), pfn, index;
-	int i = 0;
+	unsigned long size = dax_entry_size(entry), index;
+	struct folio *folio = dax_to_folio(entry);
+
+	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry))
+		return;
 
 	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);
+	if (shared && (folio->mapping || dax_folio_is_shared(folio))) {
+		if (folio->mapping)
+			dax_folio_make_shared(folio);
 
-		if (shared) {
-			dax_page_share_get(page);
-		} else {
-			WARN_ON_ONCE(page->mapping);
-			page->mapping = mapping;
-			page->index = index + i++;
-		}
+		WARN_ON_ONCE(!folio->share);
+		WARN_ON_ONCE(dax_entry_order(entry) != folio_order(folio));
+		folio->share++;
+	} else {
+		WARN_ON_ONCE(folio->mapping);
+		dax_folio_init(entry);
+		folio = dax_to_folio(entry);
+		folio->mapping = mapping;
+		folio->index = index;
 	}
 }
 
 static void dax_disassociate_entry(void *entry, struct address_space *mapping,
-		bool trunc)
+				bool trunc)
 {
-	unsigned long pfn;
+	struct folio *folio = dax_to_folio(entry);
 
 	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
 		return;
 
-	for_each_mapped_pfn(entry, pfn) {
-		struct page *page = pfn_to_page(pfn);
-
-		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
-		if (dax_page_is_shared(page)) {
-			/* keep the shared flag if this page is still shared */
-			if (dax_page_share_put(page) > 0)
-				continue;
-		} else
-			WARN_ON_ONCE(page->mapping && page->mapping != mapping);
-		page->mapping = NULL;
-		page->index = 0;
-	}
+	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry))
+		return;
+
+	dax_folio_put(folio);
 }
 
 static struct page *dax_busy_page(void *entry)
 {
-	unsigned long pfn;
+	struct folio *folio = dax_to_folio(entry);
 
-	for_each_mapped_pfn(entry, pfn) {
-		struct page *page = pfn_to_page(pfn);
+	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry))
+		return NULL;
 
-		if (page_ref_count(page) > 1)
-			return page;
-	}
-	return NULL;
+	if (folio_ref_count(folio) - folio_mapcount(folio))
+		return &folio->page;
+	else
+		return NULL;
 }
 
 /**
@@ -580,7 +663,7 @@ static void *grab_mapping_entry(struct xa_state *xas,
 retry:
 	pmd_downgrade = false;
 	xas_lock_irq(xas);
-	entry = get_unlocked_entry(xas, order);
+	entry = get_next_unlocked_entry(xas, order);
 
 	if (entry) {
 		if (dax_is_conflict(entry))
@@ -690,7 +773,7 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping,
 	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
 		return NULL;
 
-	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+	if (!dax_mapping(mapping))
 		return NULL;
 
 	/* If end == LLONG_MAX, all pages from start to till end of file */
@@ -716,8 +799,7 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping,
 	xas_for_each(&xas, entry, end_idx) {
 		if (WARN_ON_ONCE(!xa_is_value(entry)))
 			continue;
-		if (unlikely(dax_is_locked(entry)))
-			entry = get_unlocked_entry(&xas, 0);
+		entry = wait_entry_unlocked_exclusive(&xas, entry);
 		if (entry)
 			page = dax_busy_page(entry);
 		put_unlocked_entry(&xas, entry, WAKE_NEXT);
@@ -743,14 +825,14 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 EXPORT_SYMBOL_GPL(dax_layout_busy_page);
 
 static int __dax_invalidate_entry(struct address_space *mapping,
-					  pgoff_t index, bool trunc)
+				  pgoff_t index, bool trunc)
 {
 	XA_STATE(xas, &mapping->i_pages, index);
 	int ret = 0;
 	void *entry;
 
 	xas_lock_irq(&xas);
-	entry = get_unlocked_entry(&xas, 0);
+	entry = get_next_unlocked_entry(&xas, 0);
 	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
 		goto out;
 	if (!trunc &&
@@ -776,7 +858,9 @@ static int __dax_clear_dirty_range(struct address_space *mapping,
 
 	xas_lock_irq(&xas);
 	xas_for_each(&xas, entry, end) {
-		entry = get_unlocked_entry(&xas, 0);
+		entry = wait_entry_unlocked_exclusive(&xas, entry);
+		if (!entry)
+			continue;
 		xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
 		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		put_unlocked_entry(&xas, entry, WAKE_NEXT);
@@ -813,6 +897,107 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	return ret;
 }
 
+void dax_delete_mapping_range(struct address_space *mapping,
+				loff_t start, loff_t end)
+{
+	void *entry;
+	pgoff_t start_idx = start >> PAGE_SHIFT;
+	pgoff_t end_idx;
+	XA_STATE(xas, &mapping->i_pages, start_idx);
+
+	/* If end == LLONG_MAX, all pages from start to till end of file */
+	if (end == LLONG_MAX)
+		end_idx = ULONG_MAX;
+	else
+		end_idx = end >> PAGE_SHIFT;
+
+	xas_lock_irq(&xas);
+	xas_for_each(&xas, entry, end_idx) {
+		if (!xa_is_value(entry))
+			continue;
+		entry = wait_entry_unlocked_exclusive(&xas, entry);
+		if (!entry)
+			continue;
+		dax_disassociate_entry(entry, mapping, true);
+		xas_store(&xas, NULL);
+		mapping->nrpages -= 1UL << dax_entry_order(entry);
+		put_unlocked_entry(&xas, entry, WAKE_ALL);
+	}
+	xas_unlock_irq(&xas);
+}
+EXPORT_SYMBOL_GPL(dax_delete_mapping_range);
+
+static int wait_page_idle(struct page *page,
+			void (cb)(struct inode *),
+			struct inode *inode)
+{
+	return ___wait_var_event(page, dax_page_is_idle(page),
+				TASK_INTERRUPTIBLE, 0, 0, cb(inode));
+}
+
+static void wait_page_idle_uninterruptible(struct page *page,
+					struct inode *inode)
+{
+	___wait_var_event(page, dax_page_is_idle(page),
+			TASK_UNINTERRUPTIBLE, 0, 0, schedule());
+}
+
+/*
+ * Unmaps the inode and waits for any DMA to complete prior to deleting the
+ * DAX mapping entries for the range.
+ *
+ * For NOWAIT behavior, pass @cb as NULL to early-exit on first found
+ * busy page
+ */
+int dax_break_layout(struct inode *inode, loff_t start, loff_t end,
+		void (cb)(struct inode *))
+{
+	struct page *page;
+	int error = 0;
+
+	if (!dax_mapping(inode->i_mapping))
+		return 0;
+
+	do {
+		page = dax_layout_busy_page_range(inode->i_mapping, start, end);
+		if (!page)
+			break;
+		if (!cb) {
+			error = -ERESTARTSYS;
+			break;
+		}
+
+		error = wait_page_idle(page, cb, inode);
+	} while (error == 0);
+
+	if (!page)
+		dax_delete_mapping_range(inode->i_mapping, start, end);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(dax_break_layout);
+
+void dax_break_layout_final(struct inode *inode)
+{
+	struct page *page;
+
+	if (!dax_mapping(inode->i_mapping))
+		return;
+
+	do {
+		page = dax_layout_busy_page_range(inode->i_mapping, 0,
+						LLONG_MAX);
+		if (!page)
+			break;
+
+		wait_page_idle_uninterruptible(page, inode);
+	} while (true);
+
+	if (!page)
+		dax_delete_mapping_range(inode->i_mapping, 0, LLONG_MAX);
+}
+EXPORT_SYMBOL_GPL(dax_break_layout_final);
+
 /*
  * Invalidate DAX entry if it is clean.
  */
@@ -895,8 +1080,9 @@ static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
 		void *old;
 
 		dax_disassociate_entry(entry, mapping, false);
-		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address,
-				shared);
+		dax_associate_entry(new_entry, mapping, vmf->vma,
+					vmf->address, shared);
+
 		/*
 		 * Only swap our new entry into the page cache if the current
 		 * entry is a zero page or an empty entry.  If a normal PTE or
@@ -940,7 +1126,7 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
 	if (unlikely(dax_is_locked(entry))) {
 		void *old_entry = entry;
 
-		entry = get_unlocked_entry(xas, 0);
+		entry = get_next_unlocked_entry(xas, 0);
 
 		/* Entry got punched out / reallocated? */
 		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
@@ -1084,9 +1270,7 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
 		goto out;
 	if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
 		goto out;
-	/* For larger pages we need devmap */
-	if (length > 1 && !pfn_t_devmap(*pfnp))
-		goto out;
+
 	rc = 0;
 
 out_check_addr:
@@ -1193,7 +1377,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 
 	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE);
 
-	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
+	ret = vmf_insert_page_mkwrite(vmf, pfn_t_to_page(pfn), false);
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
 }
@@ -1664,7 +1848,8 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
 	loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT;
 	bool write = iter->flags & IOMAP_WRITE;
 	unsigned long entry_flags = pmd ? DAX_PMD : 0;
-	int err = 0;
+	struct folio *folio;
+	int ret, err = 0;
 	pfn_t pfn;
 	void *kaddr;
 
@@ -1696,17 +1881,19 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
 			return dax_fault_return(err);
 	}
 
+	folio = dax_to_folio(*entry);
 	if (dax_fault_is_synchronous(iter, vmf->vma))
 		return dax_fault_synchronous_pfnp(pfnp, pfn);
 
-	/* insert PMD pfn */
+	folio_ref_inc(folio);
 	if (pmd)
-		return vmf_insert_pfn_pmd(vmf, pfn, write);
+		ret = vmf_insert_folio_pmd(vmf, pfn_folio(pfn_t_to_pfn(pfn)),
+					write);
+	else
+		ret = vmf_insert_page_mkwrite(vmf, pfn_t_to_page(pfn), write);
+	folio_put(folio);
 
-	/* insert PTE pfn */
-	if (write)
-		return vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
-	return vmf_insert_mixed(vmf->vma, vmf->address, pfn);
+	return ret;
 }
 
 static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
@@ -1949,11 +2136,12 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
+	struct folio *folio;
 	void *entry;
 	vm_fault_t ret;
 
 	xas_lock_irq(&xas);
-	entry = get_unlocked_entry(&xas, order);
+	entry = get_next_unlocked_entry(&xas, order);
 	/* Did we race with someone splitting entry or so? */
 	if (!entry || dax_is_conflict(entry) ||
 	    (order == 0 && !dax_is_pte_entry(entry))) {
@@ -1966,14 +2154,17 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 	xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
 	dax_lock_entry(&xas, entry);
 	xas_unlock_irq(&xas);
+	folio = pfn_folio(pfn_t_to_pfn(pfn));
+	folio_ref_inc(folio);
 	if (order == 0)
-		ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
+		ret = vmf_insert_page_mkwrite(vmf, &folio->page, true);
 #ifdef CONFIG_FS_DAX_PMD
 	else if (order == PMD_ORDER)
-		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
+		ret = vmf_insert_folio_pmd(vmf, folio, FAULT_FLAG_WRITE);
 #endif
 	else
 		ret = VM_FAULT_FALLBACK;
+	folio_put(folio);
 	dax_unlock_entry(&xas, entry);
 	trace_dax_insert_pfn_mkwrite(mapping->host, vmf, ret);
 	return ret;