1 files changed, 349 insertions, 20 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 302d1cf7ad07..a42add14331c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -66,6 +66,9 @@ static struct vfsmount *shm_mnt;
 #include <linux/highmem.h>
 #include <linux/seq_file.h>
 #include <linux/magic.h>
+#include <linux/syscalls.h>
+#include <linux/fcntl.h>
+#include <uapi/linux/memfd.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -419,7 +422,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -447,7 +449,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -495,7 +496,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			index = start;
 			continue;
 		}
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -531,7 +531,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		index++;
 	}
 
@@ -551,6 +550,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	int error;
 
 	error = inode_change_ok(inode, attr);
@@ -561,6 +561,11 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
 
+		/* protected by i_mutex */
+		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
+		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
+			return -EPERM;
+
 		if (newsize != oldsize) {
 			error = shmem_reacct_size(SHMEM_I(inode)->flags,
 					oldsize, newsize);
@@ -621,7 +626,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 	radswap = swp_to_radix_entry(swap);
 	index = radix_tree_locate_item(&mapping->page_tree, radswap);
 	if (index == -1)
-		return 0;
+		return -EAGAIN;	/* tell shmem_unuse we found nothing */
 
 	/*
 	 * Move _head_ to start search for next from here.
@@ -680,7 +685,6 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 			spin_unlock(&info->lock);
 			swap_free(swap);
 		}
-		error = 1;	/* not an error, but entry was found */
 	}
 	return error;
 }
@@ -692,7 +696,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 {
 	struct list_head *this, *next;
 	struct shmem_inode_info *info;
-	int found = 0;
+	struct mem_cgroup *memcg;
 	int error = 0;
 
 	/*
@@ -707,26 +711,32 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL);
+	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
+	error = -EAGAIN;
 
 	mutex_lock(&shmem_swaplist_mutex);
 	list_for_each_safe(this, next, &shmem_swaplist) {
 		info = list_entry(this, struct shmem_inode_info, swaplist);
 		if (info->swapped)
-			found = shmem_unuse_inode(info, swap, &page);
+			error = shmem_unuse_inode(info, swap, &page);
 		else
 			list_del_init(&info->swaplist);
 		cond_resched();
-		if (found)
+		if (error != -EAGAIN)
 			break;
+		/* found nothing in this: move on to search the next */
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
 
-	if (found < 0)
-		error = found;
+	if (error) {
+		if (error != -ENOMEM)
+			error = 0;
+		mem_cgroup_cancel_charge(page, memcg);
+	} else
+		mem_cgroup_commit_charge(page, memcg, true);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -830,7 +840,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-	swapcache_free(swap, NULL);
+	swapcache_free(swap);
 redirty:
 	set_page_dirty(page);
 	if (wbc->for_reclaim)
@@ -1003,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_replace_page_cache(oldpage, newpage);
+		mem_cgroup_migrate(oldpage, newpage, false);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
@@ -1030,6 +1040,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info;
 	struct shmem_sb_info *sbinfo;
+	struct mem_cgroup *memcg;
 	struct page *page;
 	swp_entry_t swap;
 	int error;
@@ -1108,8 +1119,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_charge_file(page, current->mm,
-						gfp & GFP_RECLAIM_MASK);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						swp_to_radix_entry(swap));
@@ -1125,12 +1135,16 @@ repeat:
 			 * Reset swap.val? No, leave it so "failed" goes back to
 			 * "repeat": reading a hole and writing should succeed.
 			 */
-			if (error)
+			if (error) {
+				mem_cgroup_cancel_charge(page, memcg);
 				delete_from_swap_cache(page);
+			}
 		}
 		if (error)
 			goto failed;
 
+		mem_cgroup_commit_charge(page, memcg, true);
+
 		spin_lock(&info->lock);
 		info->swapped--;
 		shmem_recalc_inode(inode);
@@ -1168,8 +1182,7 @@ repeat:
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_charge_file(page, current->mm,
-						gfp & GFP_RECLAIM_MASK);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
 		if (error)
 			goto decused;
 		error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
@@ -1179,9 +1192,10 @@ repeat:
 			radix_tree_preload_end();
 		}
 		if (error) {
-			mem_cgroup_uncharge_cache_page(page);
+			mem_cgroup_cancel_charge(page, memcg);
 			goto decused;
 		}
+		mem_cgroup_commit_charge(page, memcg, false);
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
@@ -1407,6 +1421,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
+		info->seals = F_SEAL_SEAL;
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);
@@ -1465,7 +1480,17 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+
+	/* i_mutex is held by caller */
+	if (unlikely(info->seals)) {
+		if (info->seals & F_SEAL_WRITE)
+			return -EPERM;
+		if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
+			return -EPERM;
+	}
+
 	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 }
 
@@ -1803,11 +1828,233 @@ 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();
+
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		page = radix_tree_deref_slot(slot);
+		if (!page || radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+		} else if (page_count(page) - page_mapcount(page) > 1) {
+			spin_lock_irq(&mapping->tree_lock);
+			radix_tree_tag_set(&mapping->page_tree, iter.index,
+					   SHMEM_TAG_PINNED);
+			spin_unlock_irq(&mapping->tree_lock);
+		}
+
+		if (need_resched()) {
+			cond_resched_rcu();
+			start = iter.index + 1;
+			goto restart;
+		}
+	}
+	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->page_tree, 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();
+restart:
+		radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
+					   start, SHMEM_TAG_PINNED) {
+
+			page = radix_tree_deref_slot(slot);
+			if (radix_tree_exception(page)) {
+				if (radix_tree_deref_retry(page))
+					goto restart;
+
+				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;
+			}
+
+			spin_lock_irq(&mapping->tree_lock);
+			radix_tree_tag_clear(&mapping->page_tree,
+					     iter.index, SHMEM_TAG_PINNED);
+			spin_unlock_irq(&mapping->tree_lock);
+continue_resched:
+			if (need_resched()) {
+				cond_resched_rcu();
+				start = iter.index + 1;
+				goto restart;
+			}
+		}
+		rcu_read_unlock();
+	}
+
+	return error;
+}
+
+#define F_ALL_SEALS (F_SEAL_SEAL | \
+		     F_SEAL_SHRINK | \
+		     F_SEAL_GROW | \
+		     F_SEAL_WRITE)
+
+int shmem_add_seals(struct file *file, unsigned int seals)
+{
+	struct inode *inode = file_inode(file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	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_op != &shmem_file_operations)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EPERM;
+	if (seals & ~(unsigned int)F_ALL_SEALS)
+		return -EINVAL;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (info->seals & F_SEAL_SEAL) {
+		error = -EPERM;
+		goto unlock;
+	}
+
+	if ((seals & F_SEAL_WRITE) && !(info->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;
+		}
+	}
+
+	info->seals |= seals;
+	error = 0;
+
+unlock:
+	mutex_unlock(&inode->i_mutex);
+	return error;
+}
+EXPORT_SYMBOL_GPL(shmem_add_seals);
+
+int shmem_get_seals(struct file *file)
+{
+	if (file->f_op != &shmem_file_operations)
+		return -EINVAL;
+
+	return SHMEM_I(file_inode(file))->seals;
+}
+EXPORT_SYMBOL_GPL(shmem_get_seals);
+
+long shmem_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 = shmem_add_seals(file, arg);
+		break;
+	case F_GET_SEALS:
+		error = shmem_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)
 {
 	struct inode *inode = file_inode(file);
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_falloc shmem_falloc;
 	pgoff_t start, index, end;
 	int error;
@@ -1823,6 +2070,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
 		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
 
+		/* protected by i_mutex */
+		if (info->seals & F_SEAL_WRITE) {
+			error = -EPERM;
+			goto out;
+		}
+
 		shmem_falloc.waitq = &shmem_falloc_waitq;
 		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
 		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
@@ -1849,6 +2102,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	if (error)
 		goto out;
 
+	if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) {
+		error = -EPERM;
+		goto out;
+	}
+
 	start = offset >> PAGE_CACHE_SHIFT;
 	end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	/* Try to avoid a swapstorm if len is impossible to satisfy */
@@ -2584,6 +2842,77 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 	shmem_show_mpol(seq, sbinfo->mpol);
 	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)
+
+SYSCALL_DEFINE2(memfd_create,
+		const char __user *, uname,
+		unsigned int, flags)
+{
+	struct shmem_inode_info *info;
+	struct file *file;
+	int fd, error;
+	char *name;
+	long len;
+
+	if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+		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_TEMPORARY);
+	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;
+	}
+
+	file = shmem_file_setup(name, 0, VM_NORESERVE);
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto err_fd;
+	}
+	info = SHMEM_I(file_inode(file));
+	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
+	file->f_flags |= O_RDWR | O_LARGEFILE;
+	if (flags & MFD_ALLOW_SEALING)
+		info->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)