Merge branch 'for-linus' into for-next

Documentation/DocBook/Makefile

@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml  \
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    80211.xml sh.xml regulator.xml w1.xml \
+	    sh.xml regulator.xml w1.xml \
 	    writing_musb_glue_layer.xml iio.xml
 
 ifeq ($(DOCBOOKS),)

Documentation/unaligned-memory-access.txt

@@ -151,7 +151,7 @@ bool ether_addr_equal(const u8 *addr1, const u8 *addr2)
 #else
 	const u16 *a = (const u16 *)addr1;
 	const u16 *b = (const u16 *)addr2;
-	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
+	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
 #endif
 }
 

Makefile

 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Roaring Lionus
 
 # *DOCUMENTATION*

arch/x86/include/asm/bitops.h

@@ -139,6 +139,19 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
 
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	bool negative;
+	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+		CC_SET(s)
+		: CC_OUT(s) (negative), ADDR
+		: "ir" ((char) ~(1 << nr)) : "memory");
+	return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
 /*
  * __clear_bit_unlock - Clears a bit in memory
  * @nr: Bit to clear

crypto/testmgr.c

@@ -1461,16 +1461,25 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, ctemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, ctemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1483,6 +1492,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1491,6 +1501,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1500,26 +1511,37 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = dtemplate[i].inlen;
+		void *input_vec;
+
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
+		memcpy(input_vec, dtemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, dtemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1532,6 +1554,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: decompression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1540,6 +1563,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Decompression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1549,10 +1573,12 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 

fs/dax.c

@@ -451,16 +451,37 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+					  pgoff_t index, bool trunc)
+{
+	int ret = 0;
+	void *entry;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	if (!trunc &&
+	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	put_unlocked_mapping_entry(mapping, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *entry;
+	int ret = __dax_invalidate_mapping_entry(mapping, index, true);
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
 	/*
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
@@ -468,16 +489,46 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * caller has seen exceptional entry for this index, we better find it
 	 * at that index as well...
 	 */
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return 0;
-	}
-	radix_tree_delete(&mapping->page_tree, index);
+	WARN_ON_ONCE(!ret);
+	return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	int ret = 0;
+	void *entry, **slot;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry) ||
+	    slot_locked(mapping, slot))
+		goto out;
+	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto out;
+	radix_tree_delete(page_tree, index);
 	mapping->nrexceptional--;
+	ret = 1;
+out:
 	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	if (ret)
+		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	return ret;
+}
 
-	return 1;
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index)
+{
+	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
 /*
@@ -488,15 +539,16 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
  * otherwise it will simply fall out of the page cache under memory
  * pressure without ever having been dirtied.
  */
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
 	struct page *page;
+	int ret;
 
 	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(entry)) {
-		vmf->page = entry;
-		return VM_FAULT_LOCKED;
+	if (!radix_tree_exceptional_entry(*entry)) {
+		page = *entry;
+		goto out;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
@@ -504,8 +556,17 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 				   vmf->gfp_mask | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
+ out:
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = finish_fault(vmf);
+	vmf->page = NULL;
+	*entry = page;
+	if (!ret) {
+		/* Grab reference for PTE that is now referencing the page */
+		get_page(page);
+		return VM_FAULT_NOPAGE;
+	}
+	return ret;
 }
 
 static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
 		return -EIO;
 
+	/*
+	 * Write can allocate block for an area which has a hole page mapped
+	 * into page tables. We have to tear down these mappings so that data
+	 * written by write(2) is visible in mmap.
+	 */
+	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pos >> PAGE_SHIFT,
+					      (end - 1) >> PAGE_SHIFT);
+	}
+
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE)
 		flags |= IOMAP_WRITE;
 
-	/*
-	 * Yes, even DAX files can have page cache attached to them:  A zeroed
-	 * page is inserted into the pagecache when we have to serve a write
-	 * fault on a hole.  It should never be dirtied and can simply be
-	 * dropped from the pagecache once we get real data for the page.
-	 *
-	 * XXX: This is racy against mmap, and there's nothing we can do about
-	 * it. We'll eventually need to shift this down even further so that
-	 * we can check if we allocated blocks over a hole first.
-	 */
-	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT,
-				(pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+static int dax_fault_return(int error)
+{
+	if (error == 0)
+		return VM_FAULT_NOPAGE;
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 /**
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		error = PTR_ERR(entry);
-		goto out;
-	}
-
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
@@ -1071,9 +1129,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		return dax_fault_return(error);
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;		/* fs corruption? */
+		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
+		goto finish_iomap;
+	}
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
 		goto finish_iomap;
 	}
 
@@ -1096,13 +1160,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto finish_iomap;
+			goto error_unlock_entry;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto finish_iomap;
+		goto unlock_entry;
 	}
 
 	switch (iomap.type) {
@@ -1114,12 +1178,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
 				PAGE_SIZE, &entry, vma, vmf);
+		/* -EBUSY is fine, somebody else faulted on the same PTE */
+		if (error == -EBUSY)
+			error = 0;
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, entry, vmf);
-			break;
+			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			goto unlock_entry;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1128,31 +1195,25 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
+ error_unlock_entry:
+	vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error || (vmf_ret & VM_FAULT_ERROR)) {
-			/* keep previous error */
-			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PAGE_SIZE,
-					PAGE_SIZE, flags, &iomap);
-		}
-	}
- unlock_entry:
-	if (vmf_ret != VM_FAULT_LOCKED || error)
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM | major;
-	/* -EBUSY is fine, somebody else faulted on the same PTE */
-	if (error < 0 && error != -EBUSY)
-		return VM_FAULT_SIGBUS | major;
-	if (vmf_ret) {
-		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return vmf_ret;
+		int copied = PAGE_SIZE;
+
+		if (vmf_ret & VM_FAULT_ERROR)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PTE we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
-	return VM_FAULT_NOPAGE | major;
+	return vmf_ret;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
@@ -1276,16 +1337,6 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto fallback;
-
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
@@ -1294,10 +1345,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		goto fallback;
+
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto finish_iomap;
+
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto finish_iomap;
+			goto unlock_entry;
 		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
 				&entry);
 		break;
@@ -1319,20 +1381,23 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		break;
 	}
 
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (result == VM_FAULT_FALLBACK) {
-			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
-					iomap_flags, &iomap);
-			if (error)
-				result = VM_FAULT_FALLBACK;
-		}
+		int copied = PMD_SIZE;
+
+		if (result == VM_FAULT_FALLBACK)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PMD we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+				&iomap);
 	}
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, pmd, address);

fs/ext2/inode.c

@@ -751,9 +751,8 @@ static int ext2_get_blocks(struct inode *inode,
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	} else {
-		*new = true;
 	}
+	*new = true;
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);

fs/ext4/file.c

@@ -258,7 +258,6 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -266,24 +265,12 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-						EXT4_DATA_TRANS_BLOCKS(sb));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -292,7 +279,6 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 						pmd_t *pmd, unsigned int flags)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = flags & FAULT_FLAG_WRITE;
@@ -300,27 +286,13 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else {
-		result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-					     &ext4_iomap_ops);
 	}
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+				     &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }

include/linux/dax.h

@@ -41,6 +41,9 @@ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		pgoff_t index, void *entry, bool wake_all);
 

include/linux/page-flags.h

@@ -73,13 +73,13 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
-	PG_waiters,		/* Page has waiters, check its waitqueue */
 	PG_error,
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,

mm/filemap.c

@@ -912,6 +912,29 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
 
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters, mem);
+}
+
+#endif
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -921,16 +944,19 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
  */
 void unlock_page(struct page *page)
 {
+	BUILD_BUG_ON(PG_waiters != 7);
 	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_atomic();
-	wake_up_page(page, PG_locked);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
 

mm/truncate.c

@@ -24,20 +24,12 @@
 #include <linux/rmap.h>
 #include "internal.h"
 
-static void clear_exceptional_entry(struct address_space *mapping,
-				    pgoff_t index, void *entry)
+static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
+			       void *entry)
 {
 	struct radix_tree_node *node;
 	void **slot;
 
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
-		return;
-
-	if (dax_mapping(mapping)) {
-		dax_delete_mapping_entry(mapping, index);
-		return;
-	}
 	spin_lock_irq(&mapping->tree_lock);
 	/*
 	 * Regular page slots are stabilized by the page lock even
@@ -55,6 +47,56 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
+/*
+ * Unconditionally remove exceptional entry. Usually called from truncate path.
+ */
+static void truncate_exceptional_entry(struct address_space *mapping,
+				       pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	if (dax_mapping(mapping)) {
+		dax_delete_mapping_entry(mapping, index);
+		return;
+	}
+	clear_shadow_entry(mapping, index, entry);
+}
+
+/*
+ * Invalidate exceptional entry if easily possible. This handles exceptional
+ * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
+ * clean entries.
+ */
+static int invalidate_exceptional_entry(struct address_space *mapping,
+					pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
+/*
+ * Invalidate exceptional entry if clean. This handles exceptional entries for
+ * invalidate_inode_pages2() so for DAX it evicts only clean entries.
+ */
+static int invalidate_exceptional_entry2(struct address_space *mapping,
+					 pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry_sync(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
 /**
  * do_invalidatepage - invalidate part or all of a page
  * @page: the page which is affected
@@ -262,7 +304,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -351,7 +394,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			}
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -470,7 +514,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				invalidate_exceptional_entry(mapping, index,
+							     page);
 				continue;
 			}
 
@@ -592,7 +637,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				if (!invalidate_exceptional_entry2(mapping,
+								   index, page))
+					ret = -EBUSY;
 				continue;
 			}
 

sound/firewire/amdtp-stream.c

@@ -69,7 +69,7 @@ static void pcm_period_tasklet(unsigned long data);
  * @protocol_size: the size to allocate newly for protocol
  */
 int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
-		      enum amdtp_stream_direction dir, enum cip_flags flags,
+		      enum amdtp_stream_direction dir, int flags,
 		      unsigned int fmt,
 		      amdtp_stream_process_data_blocks_t process_data_blocks,
 		      unsigned int protocol_size)

sound/firewire/amdtp-stream.h

@@ -93,7 +93,7 @@ typedef unsigned int (*amdtp_stream_process_data_blocks_t)(
 						unsigned int *syt);
 struct amdtp_stream {
 	struct fw_unit *unit;
-	enum cip_flags flags;
+	int flags;
 	enum amdtp_stream_direction direction;
 	struct mutex mutex;
 
@@ -137,7 +137,7 @@ struct amdtp_stream {
 };
 
 int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
-		      enum amdtp_stream_direction dir, enum cip_flags flags,
+		      enum amdtp_stream_direction dir, int flags,
 		      unsigned int fmt,
 		      amdtp_stream_process_data_blocks_t process_data_blocks,
 		      unsigned int protocol_size);

sound/firewire/fireworks/fireworks_stream.c

@@ -117,7 +117,7 @@ destroy_stream(struct snd_efw *efw, struct amdtp_stream *stream)
 		conn = &efw->in_conn;
 
 	amdtp_stream_destroy(stream);
-	cmp_connection_destroy(&efw->out_conn);
+	cmp_connection_destroy(conn);
 }
 
 static int

sound/firewire/tascam/tascam-stream.c

@@ -343,7 +343,7 @@ int snd_tscm_stream_init_duplex(struct snd_tscm *tscm)
 	if (err < 0)
 		amdtp_stream_destroy(&tscm->rx_stream);
 
-	return 0;
+	return err;
 }
 
 /* At bus reset, streaming is stopped and some registers are clear. */