1 files changed, 42 insertions, 340 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 9d6c7e595415..e9a7ac74823d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -327,7 +327,7 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 			pgoff_t index, void *expected, void *replacement)
 {
 	struct radix_tree_node *node;
-	void **pslot;
+	void __rcu **pslot;
 	void *item;
 
 	VM_BUG_ON(!expected);
@@ -395,7 +395,7 @@ static bool shmem_confirm_swap(struct address_space *mapping,
 #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
 /* ifdef here to avoid bloating shmem.o when not necessary */
 
-int shmem_huge __read_mostly;
+static int shmem_huge __read_mostly;
 
 #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS)
 static int shmem_parse_huge(const char *str)
@@ -571,6 +571,15 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 }
 #endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
 
+static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+	    (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) &&
+	    shmem_huge != SHMEM_HUGE_DENY)
+		return true;
+	return false;
+}
+
 /*
  * Like add_to_page_cache_locked, but error if expected item has gone.
  */
@@ -682,7 +691,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 						pgoff_t start, pgoff_t end)
 {
 	struct radix_tree_iter iter;
-	void **slot;
+	void __rcu **slot;
 	struct page *page;
 	unsigned long swapped = 0;
 
@@ -988,6 +997,7 @@ static int shmem_getattr(const struct path *path, struct kstat *stat,
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb);
 
 	if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
 		spin_lock_irq(&info->lock);
@@ -995,6 +1005,10 @@ static int shmem_getattr(const struct path *path, struct kstat *stat,
 		spin_unlock_irq(&info->lock);
 	}
 	generic_fillattr(inode, stat);
+
+	if (is_huge_enabled(sb_info))
+		stat->blksize = HPAGE_PMD_SIZE;
+
 	return 0;
 }
 
@@ -1098,13 +1112,19 @@ static void shmem_evict_inode(struct inode *inode)
 static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
 {
 	struct radix_tree_iter iter;
-	void **slot;
+	void __rcu **slot;
 	unsigned long found = -1;
 	unsigned int checked = 0;
 
 	rcu_read_lock();
 	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (*slot == item) {
+		void *entry = radix_tree_deref_slot(slot);
+
+		if (radix_tree_deref_retry(entry)) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+		if (entry == item) {
 			found = iter.index;
 			break;
 		}
@@ -1322,9 +1342,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (!swap.val)
 		goto redirty;
 
-	if (mem_cgroup_try_charge_swap(page, swap))
-		goto free_swap;
-
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
 	 * if it's not already there.  Do it now before the page is
@@ -1353,7 +1370,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-free_swap:
 	put_swap_page(page, swap);
 redirty:
 	set_page_dirty(page);
@@ -1404,10 +1420,9 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma,
 		struct shmem_inode_info *info, pgoff_t index)
 {
 	/* Create a pseudo vma that just contains the policy */
-	vma->vm_start = 0;
+	memset(vma, 0, sizeof(*vma));
 	/* Bias interleave by inode number to distribute better across nodes */
 	vma->vm_pgoff = index + info->vfs_inode.i_ino;
-	vma->vm_ops = NULL;
 	vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
 }
 
@@ -1931,14 +1946,14 @@ static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, in
 	return ret;
 }
 
-static int shmem_fault(struct vm_fault *vmf)
+static vm_fault_t shmem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
 	enum sgp_type sgp;
-	int error;
-	int ret = VM_FAULT_LOCKED;
+	int err;
+	vm_fault_t ret = VM_FAULT_LOCKED;
 
 	/*
 	 * Trinity finds that probing a hole which tmpfs is punching can
@@ -2006,10 +2021,10 @@ static int shmem_fault(struct vm_fault *vmf)
 	else if (vma->vm_flags & VM_HUGEPAGE)
 		sgp = SGP_HUGE;
 
-	error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
+	err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
 				  gfp, vma, vmf, &ret);
-	if (error)
-		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
+	if (err)
+		return vmf_error(err);
 	return ret;
 }
 
@@ -2616,241 +2631,6 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	return offset;
 }
 
-/*
- * We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
- * so reuse a tag which we firmly believe is never set or cleared on shmem.
- */
-#define SHMEM_TAG_PINNED        PAGECACHE_TAG_TOWRITE
-#define LAST_SCAN               4       /* about 150ms max */
-
-static void shmem_tag_pins(struct address_space *mapping)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	pgoff_t start;
-	struct page *page;
-
-	lru_add_drain();
-	start = 0;
-	rcu_read_lock();
-
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
-		page = radix_tree_deref_slot(slot);
-		if (!page || radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-		} else if (page_count(page) - page_mapcount(page) > 1) {
-			xa_lock_irq(&mapping->i_pages);
-			radix_tree_tag_set(&mapping->i_pages, iter.index,
-					   SHMEM_TAG_PINNED);
-			xa_unlock_irq(&mapping->i_pages);
-		}
-
-		if (need_resched()) {
-			slot = radix_tree_iter_resume(slot, &iter);
-			cond_resched_rcu();
-		}
-	}
-	rcu_read_unlock();
-}
-
-/*
- * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
- * via get_user_pages(), drivers might have some pending I/O without any active
- * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
- * and see whether it has an elevated ref-count. If so, we tag them and wait for
- * them to be dropped.
- * The caller must guarantee that no new user will acquire writable references
- * to those pages to avoid races.
- */
-static int shmem_wait_for_pins(struct address_space *mapping)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	pgoff_t start;
-	struct page *page;
-	int error, scan;
-
-	shmem_tag_pins(mapping);
-
-	error = 0;
-	for (scan = 0; scan <= LAST_SCAN; scan++) {
-		if (!radix_tree_tagged(&mapping->i_pages, SHMEM_TAG_PINNED))
-			break;
-
-		if (!scan)
-			lru_add_drain_all();
-		else if (schedule_timeout_killable((HZ << scan) / 200))
-			scan = LAST_SCAN;
-
-		start = 0;
-		rcu_read_lock();
-		radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter,
-					   start, SHMEM_TAG_PINNED) {
-
-			page = radix_tree_deref_slot(slot);
-			if (radix_tree_exception(page)) {
-				if (radix_tree_deref_retry(page)) {
-					slot = radix_tree_iter_retry(&iter);
-					continue;
-				}
-
-				page = NULL;
-			}
-
-			if (page &&
-			    page_count(page) - page_mapcount(page) != 1) {
-				if (scan < LAST_SCAN)
-					goto continue_resched;
-
-				/*
-				 * On the last scan, we clean up all those tags
-				 * we inserted; but make a note that we still
-				 * found pages pinned.
-				 */
-				error = -EBUSY;
-			}
-
-			xa_lock_irq(&mapping->i_pages);
-			radix_tree_tag_clear(&mapping->i_pages,
-					     iter.index, SHMEM_TAG_PINNED);
-			xa_unlock_irq(&mapping->i_pages);
-continue_resched:
-			if (need_resched()) {
-				slot = radix_tree_iter_resume(slot, &iter);
-				cond_resched_rcu();
-			}
-		}
-		rcu_read_unlock();
-	}
-
-	return error;
-}
-
-static unsigned int *memfd_file_seals_ptr(struct file *file)
-{
-	if (file->f_op == &shmem_file_operations)
-		return &SHMEM_I(file_inode(file))->seals;
-
-#ifdef CONFIG_HUGETLBFS
-	if (file->f_op == &hugetlbfs_file_operations)
-		return &HUGETLBFS_I(file_inode(file))->seals;
-#endif
-
-	return NULL;
-}
-
-#define F_ALL_SEALS (F_SEAL_SEAL | \
-		     F_SEAL_SHRINK | \
-		     F_SEAL_GROW | \
-		     F_SEAL_WRITE)
-
-static int memfd_add_seals(struct file *file, unsigned int seals)
-{
-	struct inode *inode = file_inode(file);
-	unsigned int *file_seals;
-	int error;
-
-	/*
-	 * SEALING
-	 * Sealing allows multiple parties to share a shmem-file but restrict
-	 * access to a specific subset of file operations. Seals can only be
-	 * added, but never removed. This way, mutually untrusted parties can
-	 * share common memory regions with a well-defined policy. A malicious
-	 * peer can thus never perform unwanted operations on a shared object.
-	 *
-	 * Seals are only supported on special shmem-files and always affect
-	 * the whole underlying inode. Once a seal is set, it may prevent some
-	 * kinds of access to the file. Currently, the following seals are
-	 * defined:
-	 *   SEAL_SEAL: Prevent further seals from being set on this file
-	 *   SEAL_SHRINK: Prevent the file from shrinking
-	 *   SEAL_GROW: Prevent the file from growing
-	 *   SEAL_WRITE: Prevent write access to the file
-	 *
-	 * As we don't require any trust relationship between two parties, we
-	 * must prevent seals from being removed. Therefore, sealing a file
-	 * only adds a given set of seals to the file, it never touches
-	 * existing seals. Furthermore, the "setting seals"-operation can be
-	 * sealed itself, which basically prevents any further seal from being
-	 * added.
-	 *
-	 * Semantics of sealing are only defined on volatile files. Only
-	 * anonymous shmem files support sealing. More importantly, seals are
-	 * never written to disk. Therefore, there's no plan to support it on
-	 * other file types.
-	 */
-
-	if (!(file->f_mode & FMODE_WRITE))
-		return -EPERM;
-	if (seals & ~(unsigned int)F_ALL_SEALS)
-		return -EINVAL;
-
-	inode_lock(inode);
-
-	file_seals = memfd_file_seals_ptr(file);
-	if (!file_seals) {
-		error = -EINVAL;
-		goto unlock;
-	}
-
-	if (*file_seals & F_SEAL_SEAL) {
-		error = -EPERM;
-		goto unlock;
-	}
-
-	if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) {
-		error = mapping_deny_writable(file->f_mapping);
-		if (error)
-			goto unlock;
-
-		error = shmem_wait_for_pins(file->f_mapping);
-		if (error) {
-			mapping_allow_writable(file->f_mapping);
-			goto unlock;
-		}
-	}
-
-	*file_seals |= seals;
-	error = 0;
-
-unlock:
-	inode_unlock(inode);
-	return error;
-}
-
-static int memfd_get_seals(struct file *file)
-{
-	unsigned int *seals = memfd_file_seals_ptr(file);
-
-	return seals ? *seals : -EINVAL;
-}
-
-long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	long error;
-
-	switch (cmd) {
-	case F_ADD_SEALS:
-		/* disallow upper 32bit */
-		if (arg > UINT_MAX)
-			return -EINVAL;
-
-		error = memfd_add_seals(file, arg);
-		break;
-	case F_GET_SEALS:
-		error = memfd_get_seals(file);
-		break;
-	default:
-		error = -EINVAL;
-		break;
-	}
-
-	return error;
-}
-
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
@@ -3428,6 +3208,15 @@ static int shmem_match(struct inode *ino, void *vfh)
 	return ino->i_ino == inum && fh[0] == ino->i_generation;
 }
 
+/* Find any alias of inode, but prefer a hashed alias */
+static struct dentry *shmem_find_alias(struct inode *inode)
+{
+	struct dentry *alias = d_find_alias(inode);
+
+	return alias ?: d_find_any_alias(inode);
+}
+
+
 static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
 		struct fid *fid, int fh_len, int fh_type)
 {
@@ -3444,7 +3233,7 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
 	inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
 			shmem_match, fid->raw);
 	if (inode) {
-		dentry = d_find_alias(inode);
+		dentry = shmem_find_alias(inode);
 		iput(inode);
 	}
 
@@ -3673,93 +3462,6 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
-#define MFD_NAME_PREFIX "memfd:"
-#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
-#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
-
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
-
-SYSCALL_DEFINE2(memfd_create,
-		const char __user *, uname,
-		unsigned int, flags)
-{
-	unsigned int *file_seals;
-	struct file *file;
-	int fd, error;
-	char *name;
-	long len;
-
-	if (!(flags & MFD_HUGETLB)) {
-		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
-			return -EINVAL;
-	} else {
-		/* Allow huge page size encoding in flags. */
-		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
-				(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
-			return -EINVAL;
-	}
-
-	/* length includes terminating zero */
-	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
-	if (len <= 0)
-		return -EFAULT;
-	if (len > MFD_NAME_MAX_LEN + 1)
-		return -EINVAL;
-
-	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	strcpy(name, MFD_NAME_PREFIX);
-	if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
-		error = -EFAULT;
-		goto err_name;
-	}
-
-	/* terminating-zero may have changed after strnlen_user() returned */
-	if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
-		error = -EFAULT;
-		goto err_name;
-	}
-
-	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
-	if (fd < 0) {
-		error = fd;
-		goto err_name;
-	}
-
-	if (flags & MFD_HUGETLB) {
-		struct user_struct *user = NULL;
-
-		file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,
-					HUGETLB_ANONHUGE_INODE,
-					(flags >> MFD_HUGE_SHIFT) &
-					MFD_HUGE_MASK);
-	} else
-		file = shmem_file_setup(name, 0, VM_NORESERVE);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_fd;
-	}
-	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
-	file->f_flags |= O_RDWR | O_LARGEFILE;
-
-	if (flags & MFD_ALLOW_SEALING) {
-		file_seals = memfd_file_seals_ptr(file);
-		*file_seals &= ~F_SEAL_SEAL;
-	}
-
-	fd_install(fd, file);
-	kfree(name);
-	return fd;
-
-err_fd:
-	put_unused_fd(fd);
-err_name:
-	kfree(name);
-	return error;
-}
-
 #endif /* CONFIG_TMPFS */
 
 static void shmem_put_super(struct super_block *sb)