Merge branch 'disintegrate-asm-generic' of git://git.infradead.org/users/dhowells/linux-headers into asm-generic

Patches from David Howells <dhowells@redhat.com>:

This is to complete part of the UAPI disintegration for which the
preparatory patches were pulled recently.

Note that there are some fixup patches which are at the base of the
branch aimed at you, plus all arches get the asm-generic branch merged in too.

* 'disintegrate-asm-generic' of git://git.infradead.org/users/dhowells/linux-headers:
  UAPI: (Scripted) Disintegrate include/asm-generic
  UAPI: Fix conditional header installation handling (notably kvm_para.h on m68k)
  c6x: remove c6x signal.h
  UAPI: Split compound conditionals containing __KERNEL__ in Arm64
  UAPI: Fix the guards on various asm/unistd.h files

Signed-off-by: Arnd Bergmann <arnd@arndb.de>

12 files changed, 83 insertions, 201 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index bcb63ac48cc5..f468185b3b28 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -419,7 +419,7 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 }
 
 /**
- * reserve_bootmem - mark a page range as usable
+ * reserve_bootmem - mark a page range as reserved
  * @addr: starting address of the range
  * @size: size of the range in bytes
  * @flags: reservation flags (see linux/bootmem.h)
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 9b75a045dbf4..a47f0f50c89f 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -26,7 +26,7 @@
  */
 SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 {
-	struct file *file = fget(fd);
+	struct fd f = fdget(fd);
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
 	loff_t endbyte;			/* inclusive */
@@ -35,15 +35,15 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 	unsigned long nrpages;
 	int ret = 0;
 
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
-	if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) {
+	if (S_ISFIFO(f.file->f_path.dentry->d_inode->i_mode)) {
 		ret = -ESPIPE;
 		goto out;
 	}
 
-	mapping = file->f_mapping;
+	mapping = f.file->f_mapping;
 	if (!mapping || len < 0) {
 		ret = -EINVAL;
 		goto out;
@@ -76,21 +76,21 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
-		file->f_ra.ra_pages = bdi->ra_pages;
-		spin_lock(&file->f_lock);
-		file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		f.file->f_ra.ra_pages = bdi->ra_pages;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_RANDOM:
-		spin_lock(&file->f_lock);
-		file->f_mode |= FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode |= FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_SEQUENTIAL:
-		file->f_ra.ra_pages = bdi->ra_pages * 2;
-		spin_lock(&file->f_lock);
-		file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		f.file->f_ra.ra_pages = bdi->ra_pages * 2;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_WILLNEED:
 		/* First and last PARTIAL page! */
@@ -106,7 +106,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		 * Ignore return value because fadvise() shall return
 		 * success even if filesystem can't retrieve a hint,
 		 */
-		force_page_cache_readahead(mapping, file, start_index,
+		force_page_cache_readahead(mapping, f.file, start_index,
 					   nrpages);
 		break;
 	case POSIX_FADV_NOREUSE:
@@ -128,7 +128,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		ret = -EINVAL;
 	}
 out:
-	fput(file);
+	fdput(f);
 	return ret;
 }
 #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
diff --git a/mm/fremap.c b/mm/fremap.c
index 9ed4fd432467..048659c0c03d 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -195,10 +195,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		 */
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
-			struct file *file = vma->vm_file;
+			struct file *file = get_file(vma->vm_file);
 
 			flags &= MAP_NONBLOCK;
-			get_file(file);
 			addr = mmap_region(file, start, size,
 					flags, vma->vm_flags, pgoff);
 			fput(file);
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 6b3e71a2cd48..2890e67d6026 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -44,6 +44,13 @@ EXPORT_SYMBOL(frontswap_enabled);
  */
 static bool frontswap_writethrough_enabled __read_mostly;
 
+/*
+ * If enabled, the underlying tmem implementation is capable of doing
+ * exclusive gets, so frontswap_load, on a successful tmem_get must
+ * mark the page as no longer in frontswap AND mark it dirty.
+ */
+static bool frontswap_tmem_exclusive_gets_enabled __read_mostly;
+
 #ifdef CONFIG_DEBUG_FS
 /*
  * Counters available via /sys/kernel/debug/frontswap (if debugfs is
@@ -97,6 +104,15 @@ void frontswap_writethrough(bool enable)
 EXPORT_SYMBOL(frontswap_writethrough);
 
 /*
+ * Enable/disable frontswap exclusive gets (see above).
+ */
+void frontswap_tmem_exclusive_gets(bool enable)
+{
+	frontswap_tmem_exclusive_gets_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_tmem_exclusive_gets);
+
+/*
  * Called when a swap device is swapon'd.
  */
 void __frontswap_init(unsigned type)
@@ -174,8 +190,13 @@ int __frontswap_load(struct page *page)
 	BUG_ON(sis == NULL);
 	if (frontswap_test(sis, offset))
 		ret = frontswap_ops.load(type, offset, page);
-	if (ret == 0)
+	if (ret == 0) {
 		inc_frontswap_loads();
+		if (frontswap_tmem_exclusive_gets_enabled) {
+			SetPageDirty(page);
+			frontswap_clear(sis, offset);
+		}
+	}
 	return ret;
 }
 EXPORT_SYMBOL(__frontswap_load);
@@ -263,6 +284,11 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 	return ret;
 }
 
+/*
+ * Used to check if it's necessory and feasible to unuse pages.
+ * Return 1 when nothing to do, 0 when need to shink pages,
+ * error code when there is an error.
+ */
 static int __frontswap_shrink(unsigned long target_pages,
 				unsigned long *pages_to_unuse,
 				int *type)
@@ -275,7 +301,7 @@ static int __frontswap_shrink(unsigned long target_pages,
 	if (total_pages <= target_pages) {
 		/* Nothing to do */
 		*pages_to_unuse = 0;
-		return 0;
+		return 1;
 	}
 	total_pages_to_unuse = total_pages - target_pages;
 	return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type);
@@ -292,7 +318,7 @@ static int __frontswap_shrink(unsigned long target_pages,
 void frontswap_shrink(unsigned long target_pages)
 {
 	unsigned long pages_to_unuse = 0;
-	int type, ret;
+	int uninitialized_var(type), ret;
 
 	/*
 	 * we don't want to hold swap_lock while doing a very
@@ -302,7 +328,7 @@ void frontswap_shrink(unsigned long target_pages)
 	spin_lock(&swap_lock);
 	ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
 	spin_unlock(&swap_lock);
-	if (ret == 0 && pages_to_unuse)
+	if (ret == 0)
 		try_to_unuse(type, true, pages_to_unuse);
 	return;
 }
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 45eb6217bf38..0de83b4541e9 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1483,13 +1483,11 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct kmemleak_object *prev_obj = v;
 	struct kmemleak_object *next_obj = NULL;
-	struct list_head *n = &prev_obj->object_list;
+	struct kmemleak_object *obj = prev_obj;
 
 	++(*pos);
 
-	list_for_each_continue_rcu(n, &object_list) {
-		struct kmemleak_object *obj =
-			list_entry(n, struct kmemleak_object, object_list);
+	list_for_each_entry_continue_rcu(obj, &object_list, object_list) {
 		if (get_object(obj)) {
 			next_obj = obj;
 			break;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 795e525afaba..a72f2ffdc3d0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4973,6 +4973,13 @@ mem_cgroup_create(struct cgroup *cont)
 	} else {
 		res_counter_init(&memcg->res, NULL);
 		res_counter_init(&memcg->memsw, NULL);
+		/*
+		 * Deeper hierachy with use_hierarchy == false doesn't make
+		 * much sense so let cgroup subsystem know about this
+		 * unfortunate state in our controller.
+		 */
+		if (parent && parent != root_mem_cgroup)
+			mem_cgroup_subsys.broken_hierarchy = true;
 	}
 	memcg->last_scanned_node = MAX_NUMNODES;
 	INIT_LIST_HEAD(&memcg->oom_notify);
diff --git a/mm/mmap.c b/mm/mmap.c
index ae18a48e7e4e..872441e81914 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1301,8 +1301,7 @@ munmap_back:
 				goto free_vma;
 			correct_wcount = 1;
 		}
-		vma->vm_file = file;
-		get_file(file);
+		vma->vm_file = get_file(file);
 		error = file->f_op->mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
diff --git a/mm/nommu.c b/mm/nommu.c
index d4b0c10872de..dee2ff89fd58 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1282,10 +1282,8 @@ unsigned long do_mmap_pgoff(struct file *file,
 	vma->vm_pgoff = pgoff;
 
 	if (file) {
-		region->vm_file = file;
-		get_file(file);
-		vma->vm_file = file;
-		get_file(file);
+		region->vm_file = get_file(file);
+		vma->vm_file = get_file(file);
 		if (vm_flags & VM_EXECUTABLE) {
 			added_exe_file_vma(current->mm);
 			vma->vm_mm = current->mm;
diff --git a/mm/readahead.c b/mm/readahead.c
index ea8f8fa21649..7963f2391236 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -579,19 +579,19 @@ do_readahead(struct address_space *mapping, struct file *filp,
 SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
-	struct file *file;
+	struct fd f;
 
 	ret = -EBADF;
-	file = fget(fd);
-	if (file) {
-		if (file->f_mode & FMODE_READ) {
-			struct address_space *mapping = file->f_mapping;
+	f = fdget(fd);
+	if (f.file) {
+		if (f.file->f_mode & FMODE_READ) {
+			struct address_space *mapping = f.file->f_mapping;
 			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
 			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
 			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, file, start, len);
+			ret = do_readahead(mapping, f.file, start, len);
 		}
-		fput(file);
+		fdput(f);
 	}
 	return ret;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index d4e184e2a38e..d3752110c8c7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -77,13 +77,6 @@ static struct vfsmount *shm_mnt;
 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */
 #define SHORT_SYMLINK_LEN 128
 
-struct shmem_xattr {
-	struct list_head list;	/* anchored by shmem_inode_info->xattr_list */
-	char *name;		/* xattr name */
-	size_t size;
-	char value[0];
-};
-
 /*
  * shmem_fallocate and shmem_writepage communicate via inode->i_private
  * (with i_mutex making sure that it has only one user at a time):
@@ -636,7 +629,6 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 static void shmem_evict_inode(struct inode *inode)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_xattr *xattr, *nxattr;
 
 	if (inode->i_mapping->a_ops == &shmem_aops) {
 		shmem_unacct_size(info->flags, inode->i_size);
@@ -650,10 +642,7 @@ static void shmem_evict_inode(struct inode *inode)
 	} else
 		kfree(info->symlink);
 
-	list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) {
-		kfree(xattr->name);
-		kfree(xattr);
-	}
+	simple_xattrs_free(&info->xattrs);
 	BUG_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
 	clear_inode(inode);
@@ -1377,7 +1366,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		spin_lock_init(&info->lock);
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
-		INIT_LIST_HEAD(&info->xattr_list);
+		simple_xattrs_init(&info->xattrs);
 		cache_no_acl(inode);
 
 		switch (mode & S_IFMT) {
@@ -2060,28 +2049,6 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co
  */
 
 /*
- * Allocate new xattr and copy in the value; but leave the name to callers.
- */
-static struct shmem_xattr *shmem_xattr_alloc(const void *value, size_t size)
-{
-	struct shmem_xattr *new_xattr;
-	size_t len;
-
-	/* wrap around? */
-	len = sizeof(*new_xattr) + size;
-	if (len <= sizeof(*new_xattr))
-		return NULL;
-
-	new_xattr = kmalloc(len, GFP_KERNEL);
-	if (!new_xattr)
-		return NULL;
-
-	new_xattr->size = size;
-	memcpy(new_xattr->value, value, size);
-	return new_xattr;
-}
-
-/*
  * Callback for security_inode_init_security() for acquiring xattrs.
  */
 static int shmem_initxattrs(struct inode *inode,
@@ -2090,11 +2057,11 @@ static int shmem_initxattrs(struct inode *inode,
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	const struct xattr *xattr;
-	struct shmem_xattr *new_xattr;
+	struct simple_xattr *new_xattr;
 	size_t len;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		new_xattr = shmem_xattr_alloc(xattr->value, xattr->value_len);
+		new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len);
 		if (!new_xattr)
 			return -ENOMEM;
 
@@ -2111,91 +2078,12 @@ static int shmem_initxattrs(struct inode *inode,
 		memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN,
 		       xattr->name, len);
 
-		spin_lock(&info->lock);
-		list_add(&new_xattr->list, &info->xattr_list);
-		spin_unlock(&info->lock);
+		simple_xattr_list_add(&info->xattrs, new_xattr);
 	}
 
 	return 0;
 }
 
-static int shmem_xattr_get(struct dentry *dentry, const char *name,
-			   void *buffer, size_t size)
-{
-	struct shmem_inode_info *info;
-	struct shmem_xattr *xattr;
-	int ret = -ENODATA;
-
-	info = SHMEM_I(dentry->d_inode);
-
-	spin_lock(&info->lock);
-	list_for_each_entry(xattr, &info->xattr_list, list) {
-		if (strcmp(name, xattr->name))
-			continue;
-
-		ret = xattr->size;
-		if (buffer) {
-			if (size < xattr->size)
-				ret = -ERANGE;
-			else
-				memcpy(buffer, xattr->value, xattr->size);
-		}
-		break;
-	}
-	spin_unlock(&info->lock);
-	return ret;
-}
-
-static int shmem_xattr_set(struct inode *inode, const char *name,
-			   const void *value, size_t size, int flags)
-{
-	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_xattr *xattr;
-	struct shmem_xattr *new_xattr = NULL;
-	int err = 0;
-
-	/* value == NULL means remove */
-	if (value) {
-		new_xattr = shmem_xattr_alloc(value, size);
-		if (!new_xattr)
-			return -ENOMEM;
-
-		new_xattr->name = kstrdup(name, GFP_KERNEL);
-		if (!new_xattr->name) {
-			kfree(new_xattr);
-			return -ENOMEM;
-		}
-	}
-
-	spin_lock(&info->lock);
-	list_for_each_entry(xattr, &info->xattr_list, list) {
-		if (!strcmp(name, xattr->name)) {
-			if (flags & XATTR_CREATE) {
-				xattr = new_xattr;
-				err = -EEXIST;
-			} else if (new_xattr) {
-				list_replace(&xattr->list, &new_xattr->list);
-			} else {
-				list_del(&xattr->list);
-			}
-			goto out;
-		}
-	}
-	if (flags & XATTR_REPLACE) {
-		xattr = new_xattr;
-		err = -ENODATA;
-	} else {
-		list_add(&new_xattr->list, &info->xattr_list);
-		xattr = NULL;
-	}
-out:
-	spin_unlock(&info->lock);
-	if (xattr)
-		kfree(xattr->name);
-	kfree(xattr);
-	return err;
-}
-
 static const struct xattr_handler *shmem_xattr_handlers[] = {
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	&generic_acl_access_handler,
@@ -2226,6 +2114,7 @@ static int shmem_xattr_validate(const char *name)
 static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
 			      void *buffer, size_t size)
 {
+	struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
 	int err;
 
 	/*
@@ -2240,12 +2129,13 @@ static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
 	if (err)
 		return err;
 
-	return shmem_xattr_get(dentry, name, buffer, size);
+	return simple_xattr_get(&info->xattrs, name, buffer, size);
 }
 
 static int shmem_setxattr(struct dentry *dentry, const char *name,
 			  const void *value, size_t size, int flags)
 {
+	struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
 	int err;
 
 	/*
@@ -2260,15 +2150,12 @@ static int shmem_setxattr(struct dentry *dentry, const char *name,
 	if (err)
 		return err;
 
-	if (size == 0)
-		value = "";  /* empty EA, do not remove */
-
-	return shmem_xattr_set(dentry->d_inode, name, value, size, flags);
-
+	return simple_xattr_set(&info->xattrs, name, value, size, flags);
 }
 
 static int shmem_removexattr(struct dentry *dentry, const char *name)
 {
+	struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
 	int err;
 
 	/*
@@ -2283,45 +2170,13 @@ static int shmem_removexattr(struct dentry *dentry, const char *name)
 	if (err)
 		return err;
 
-	return shmem_xattr_set(dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
-}
-
-static bool xattr_is_trusted(const char *name)
-{
-	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
+	return simple_xattr_remove(&info->xattrs, name);
 }
 
 static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
-	bool trusted = capable(CAP_SYS_ADMIN);
-	struct shmem_xattr *xattr;
-	struct shmem_inode_info *info;
-	size_t used = 0;
-
-	info = SHMEM_I(dentry->d_inode);
-
-	spin_lock(&info->lock);
-	list_for_each_entry(xattr, &info->xattr_list, list) {
-		size_t len;
-
-		/* skip "trusted." attributes for unprivileged callers */
-		if (!trusted && xattr_is_trusted(xattr->name))
-			continue;
-
-		len = strlen(xattr->name) + 1;
-		used += len;
-		if (buffer) {
-			if (size < used) {
-				used = -ERANGE;
-				break;
-			}
-			memcpy(buffer, xattr->name, len);
-			buffer += len;
-		}
-	}
-	spin_unlock(&info->lock);
-
-	return used;
+	struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
+	return simple_xattr_list(&info->xattrs, buffer, size);
 }
 #endif /* CONFIG_TMPFS_XATTR */
 
diff --git a/mm/slab.c b/mm/slab.c
index c6854759bcf1..11339110271e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -900,7 +900,7 @@ static void __cpuinit start_cpu_timer(int cpu)
 	 */
 	if (keventd_up() && reap_work->work.func == NULL) {
 		init_reap_node(cpu);
-		INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap);
+		INIT_DEFERRABLE_WORK(reap_work, cache_reap);
 		schedule_delayed_work_on(cpu, reap_work,
 					__round_jiffies_relative(HZ, cpu));
 	}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index df7a6748231d..b3e3b9d525d0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1157,7 +1157,7 @@ static void __cpuinit start_cpu_timer(int cpu)
 {
 	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
-	INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+	INIT_DEFERRABLE_WORK(work, vmstat_update);
 	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }