Merge tag 'dax-locking-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull DAX locking updates from Ross Zwisler:
 "Filesystem DAX locking for 4.7

   - We use a bit in an exceptional radix tree entry as a lock bit and
     use it similarly to how page lock is used for normal faults.  This
     fixes races between hole instantiation and read faults of the same
     index.

   - Filesystem DAX PMD faults are disabled, and will be re-enabled when
     PMD locking is implemented"

* tag 'dax-locking-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  dax: Remove i_mmap_lock protection
  dax: Use radix tree entry lock to protect cow faults
  dax: New fault locking
  dax: Allow DAX code to replace exceptional entries
  dax: Define DAX lock bit for radix tree exceptional entry
  dax: Make huge page handling depend of CONFIG_BROKEN
  dax: Fix condition for filling of PMD holes

fs/Kconfig

@@ -52,6 +52,7 @@ config FS_DAX_PMD
 	depends on FS_DAX
 	depends on ZONE_DEVICE
 	depends on TRANSPARENT_HUGEPAGE
+	depends on BROKEN
 
 endif # BLOCK
 

include/linux/dax.h

@@ -3,17 +3,25 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/radix-tree.h>
 #include <asm/pgtable.h>
 
+/* We use lowest available exceptional entry bit for locking */
+#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
 		  get_block_t, dio_iodone_t, int flags);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+				   pgoff_t index, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
 int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 		unsigned int offset, unsigned int length);
 #else
@@ -22,6 +30,12 @@ static inline struct page *read_dax_sector(struct block_device *bdev,
 {
 	return ERR_PTR(-ENXIO);
 }
+/* Shouldn't ever be called when dax is disabled. */
+static inline void dax_unlock_mapping_entry(struct address_space *mapping,
+					    pgoff_t index)
+{
+	BUG();
+}
 static inline int __dax_zero_page_range(struct block_device *bdev,
 		sector_t sector, unsigned int offset, unsigned int length)
 {
@@ -29,7 +43,7 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
 }
 #endif
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
 int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
 				unsigned int flags, get_block_t);
 int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,

include/linux/mm.h

@@ -303,6 +303,12 @@ struct vm_fault {
 					 * is set (which is also implied by
 					 * VM_FAULT_ERROR).
 					 */
+	void *entry;			/* ->fault handler can alternatively
+					 * return locked DAX entry. In that
+					 * case handler should return
+					 * VM_FAULT_DAX_LOCKED and fill in
+					 * entry here.
+					 */
 	/* for ->map_pages() only */
 	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
 					 * max_pgoff inclusive */
@@ -1076,6 +1082,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 #define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
 #define VM_FAULT_FALLBACK 0x0800	/* huge page fault failed, fall back to small */
+#define VM_FAULT_DAX_LOCKED 0x1000	/* ->fault has locked DAX entry */
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 

mm/filemap.c

@@ -143,13 +143,15 @@ static void page_cache_tree_delete(struct address_space *mapping,
 			return;
 
 	/*
-	 * Track node that only contains shadow entries.
+	 * Track node that only contains shadow entries. DAX mappings contain
+	 * no shadow entries and may contain other exceptional entries so skip
+	 * those.
 	 *
 	 * Avoid acquiring the list_lru lock if already tracked.  The
 	 * list_empty() test is safe as node->private_list is
 	 * protected by mapping->tree_lock.
 	 */
-	if (!workingset_node_pages(node) &&
+	if (!dax_mapping(mapping) && !workingset_node_pages(node) &&
 	    list_empty(&node->private_list)) {
 		node->private_data = mapping;
 		list_lru_add(&workingset_shadow_nodes, &node->private_list);
@@ -580,14 +582,24 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		if (!radix_tree_exceptional_entry(p))
 			return -EEXIST;
 
-		if (WARN_ON(dax_mapping(mapping)))
-			return -EINVAL;
-
-		if (shadowp)
-			*shadowp = p;
 		mapping->nrexceptional--;
-		if (node)
-			workingset_node_shadows_dec(node);
+		if (!dax_mapping(mapping)) {
+			if (shadowp)
+				*shadowp = p;
+			if (node)
+				workingset_node_shadows_dec(node);
+		} else {
+			/* DAX can replace empty locked entry with a hole */
+			WARN_ON_ONCE(p !=
+				(void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+					 RADIX_DAX_ENTRY_LOCK));
+			/* DAX accounts exceptional entries as normal pages */
+			if (node)
+				workingset_node_pages_dec(node);
+			/* Wakeup waiters for exceptional entry lock */
+			dax_wake_mapping_entry_waiter(mapping, page->index,
+						      false);
+		}
 	}
 	radix_tree_replace_slot(slot, page);
 	mapping->nrpages++;

mm/memory.c

@@ -63,6 +63,7 @@
 #include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/dax.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -2492,8 +2493,6 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
 
-
-	/* DAX uses i_mmap_lock to serialise file truncate vs page fault */
 	i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
@@ -2825,7 +2824,8 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 			pgoff_t pgoff, unsigned int flags,
-			struct page *cow_page, struct page **page)
+			struct page *cow_page, struct page **page,
+			void **entry)
 {
 	struct vm_fault vmf;
 	int ret;
@@ -2840,8 +2840,10 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	ret = vma->vm_ops->fault(vma, &vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
-	if (!vmf.page)
-		goto out;
+	if (ret & VM_FAULT_DAX_LOCKED) {
+		*entry = vmf.entry;
+		return ret;
+	}
 
 	if (unlikely(PageHWPoison(vmf.page))) {
 		if (ret & VM_FAULT_LOCKED)
@@ -2855,7 +2857,6 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	else
 		VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
 
- out:
 	*page = vmf.page;
 	return ret;
 }
@@ -3048,7 +3049,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte_unmap_unlock(pte, ptl);
 	}
 
-	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 
@@ -3071,6 +3072,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
 {
 	struct page *fault_page, *new_page;
+	void *fault_entry;
 	struct mem_cgroup *memcg;
 	spinlock_t *ptl;
 	pte_t *pte;
@@ -3088,26 +3090,24 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 	}
 
-	ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page,
+			 &fault_entry);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		goto uncharge_out;
 
-	if (fault_page)
+	if (!(ret & VM_FAULT_DAX_LOCKED))
 		copy_user_highpage(new_page, fault_page, address, vma);
 	__SetPageUptodate(new_page);
 
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (unlikely(!pte_same(*pte, orig_pte))) {
 		pte_unmap_unlock(pte, ptl);
-		if (fault_page) {
+		if (!(ret & VM_FAULT_DAX_LOCKED)) {
 			unlock_page(fault_page);
 			put_page(fault_page);
 		} else {
-			/*
-			 * The fault handler has no page to lock, so it holds
-			 * i_mmap_lock for read to protect against truncate.
-			 */
-			i_mmap_unlock_read(vma->vm_file->f_mapping);
+			dax_unlock_mapping_entry(vma->vm_file->f_mapping,
+						 pgoff);
 		}
 		goto uncharge_out;
 	}
@@ -3115,15 +3115,11 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	mem_cgroup_commit_charge(new_page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pte_unmap_unlock(pte, ptl);
-	if (fault_page) {
+	if (!(ret & VM_FAULT_DAX_LOCKED)) {
 		unlock_page(fault_page);
 		put_page(fault_page);
 	} else {
-		/*
-		 * The fault handler has no page to lock, so it holds
-		 * i_mmap_lock for read to protect against truncate.
-		 */
-		i_mmap_unlock_read(vma->vm_file->f_mapping);
+		dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff);
 	}
 	return ret;
 uncharge_out:
@@ -3143,7 +3139,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int dirtied = 0;
 	int ret, tmp;
 
-	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
+	ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 

mm/truncate.c

@@ -34,40 +34,38 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	if (shmem_mapping(mapping))
 		return;
 
-	spin_lock_irq(&mapping->tree_lock);
-
 	if (dax_mapping(mapping)) {
-		if (radix_tree_delete_item(&mapping->page_tree, index, entry))
-			mapping->nrexceptional--;
-	} else {
-		/*
-		 * Regular page slots are stabilized by the page lock even
-		 * without the tree itself locked.  These unlocked entries
-		 * need verification under the tree lock.
-		 */
-		if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
-					&slot))
-			goto unlock;
-		if (*slot != entry)
-			goto unlock;
-		radix_tree_replace_slot(slot, NULL);
-		mapping->nrexceptional--;
-		if (!node)
-			goto unlock;
-		workingset_node_shadows_dec(node);
-		/*
-		 * Don't track node without shadow entries.
-		 *
-		 * Avoid acquiring the list_lru lock if already untracked.
-		 * The list_empty() test is safe as node->private_list is
-		 * protected by mapping->tree_lock.
-		 */
-		if (!workingset_node_shadows(node) &&
-		    !list_empty(&node->private_list))
-			list_lru_del(&workingset_shadow_nodes,
-					&node->private_list);
-		__radix_tree_delete_node(&mapping->page_tree, node);
+		dax_delete_mapping_entry(mapping, index);
+		return;
 	}
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node,
+				&slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrexceptional--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes,
+				&node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
 unlock:
 	spin_unlock_irq(&mapping->tree_lock);
 }