Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "A few bug fixes and add support for file-system level encryption in
  ext4"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (31 commits)
  ext4 crypto: enable encryption feature flag
  ext4 crypto: add symlink encryption
  ext4 crypto: enable filename encryption
  ext4 crypto: filename encryption modifications
  ext4 crypto: partial update to namei.c for fname crypto
  ext4 crypto: insert encrypted filenames into a leaf directory block
  ext4 crypto: teach ext4_htree_store_dirent() to store decrypted filenames
  ext4 crypto: filename encryption facilities
  ext4 crypto: implement the ext4 decryption read path
  ext4 crypto: implement the ext4 encryption write path
  ext4 crypto: inherit encryption policies on inode and directory create
  ext4 crypto: enforce context consistency
  ext4 crypto: add encryption key management facilities
  ext4 crypto: add ext4 encryption facilities
  ext4 crypto: add encryption policy and password salt support
  ext4 crypto: add encryption xattr support
  ext4 crypto: export ext4_empty_dir()
  ext4 crypto: add ext4 encryption Kconfig
  ext4 crypto: reserve codepoints used by the ext4 encryption feature
  ext4 crypto: add ext4_mpage_readpages()
  ...

fs/ext4/Kconfig

@@ -64,6 +64,23 @@ config EXT4_FS_SECURITY
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
 
+config EXT4_FS_ENCRYPTION
+	bool "Ext4 Encryption"
+	depends on EXT4_FS
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_XTS
+	select CRYPTO_CTS
+	select CRYPTO_SHA256
+	select KEYS
+	select ENCRYPTED_KEYS
+	help
+	  Enable encryption of ext4 files and directories.  This
+	  feature is similar to ecryptfs, but it is more memory
+	  efficient since it avoids caching the encrypted and
+	  decrypted pages in the page cache.
+
 config EXT4_DEBUG
 	bool "EXT4 debugging support"
 	depends on EXT4_FS

fs/ext4/Makefile

@@ -8,7 +8,9 @@ ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
 		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
 		mmp.o indirect.o extents_status.o xattr.o xattr_user.o \
-		xattr_trusted.o inline.o
+		xattr_trusted.o inline.o readpage.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
+ext4-$(CONFIG_EXT4_FS_ENCRYPTION)	+= crypto_policy.o crypto.o \
+		crypto_key.o crypto_fname.o

fs/ext4/acl.c

@@ -4,11 +4,6 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"

fs/ext4/balloc.c

@@ -14,7 +14,6 @@
 #include <linux/time.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
 #include "ext4.h"
@@ -641,8 +640,6 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 	 * fail EDQUOT for metdata, but we do account for it.
 	 */
 	if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
-		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 		dquot_alloc_block_nofail(inode,
 				EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
 	}

fs/ext4/bitmap.c

@@ -8,7 +8,6 @@
  */
 
 #include <linux/buffer_head.h>
-#include <linux/jbd2.h>
 #include "ext4.h"
 
 unsigned int ext4_count_free(char *bitmap, unsigned int numchars)

fs/ext4/block_validity.c

@@ -16,7 +16,6 @@
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
-#include <linux/mutex.h>
 #include <linux/slab.h>
 #include "ext4.h"
 

fs/ext4/crypto_key.c

+/*
+ * linux/fs/ext4/crypto_key.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions for ext4
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+	struct ext4_completion_result *ecr = req->data;
+
+	if (rc == -EINPROGRESS)
+		return;
+
+	ecr->res = rc;
+	complete(&ecr->completion);
+}
+
+/**
+ * ext4_derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivatio.
+ * @source_key:   Source key to which to apply derivation.
+ * @derived_key:  Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
+			       char source_key[EXT4_AES_256_XTS_KEY_SIZE],
+			       char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
+{
+	int res = 0;
+	struct ablkcipher_request *req = NULL;
+	DECLARE_EXT4_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
+								0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	ablkcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_ablkcipher_setkey(tfm, deriving_key,
+				       EXT4_AES_128_ECB_KEY_SIZE);
+	if (res < 0)
+		goto out;
+	sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
+	sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
+	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+				     EXT4_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_ablkcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		BUG_ON(req->base.data != &ecr);
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+
+out:
+	if (req)
+		ablkcipher_request_free(req);
+	if (tfm)
+		crypto_free_ablkcipher(tfm);
+	return res;
+}
+
+/**
+ * ext4_generate_encryption_key() - generates an encryption key
+ * @inode: The inode to generate the encryption key for.
+ */
+int ext4_generate_encryption_key(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_encryption_key *crypt_key = &ei->i_encryption_key;
+	char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+				 (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1];
+	struct key *keyring_key = NULL;
+	struct ext4_encryption_key *master_key;
+	struct ext4_encryption_context ctx;
+	struct user_key_payload *ukp;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+				 &ctx, sizeof(ctx));
+
+	if (res != sizeof(ctx)) {
+		if (res > 0)
+			res = -EINVAL;
+		goto out;
+	}
+	res = 0;
+
+	if (S_ISREG(inode->i_mode))
+		crypt_key->mode = ctx.contents_encryption_mode;
+	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		crypt_key->mode = ctx.filenames_encryption_mode;
+	else {
+		printk(KERN_ERR "ext4 crypto: Unsupported inode type.\n");
+		BUG();
+	}
+	crypt_key->size = ext4_encryption_key_size(crypt_key->mode);
+	BUG_ON(!crypt_key->size);
+	if (DUMMY_ENCRYPTION_ENABLED(sbi)) {
+		memset(crypt_key->raw, 0x42, EXT4_AES_256_XTS_KEY_SIZE);
+		goto out;
+	}
+	memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX,
+	       EXT4_KEY_DESC_PREFIX_SIZE);
+	sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE,
+		"%*phN", EXT4_KEY_DESCRIPTOR_SIZE,
+		ctx.master_key_descriptor);
+	full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+			    (2 * EXT4_KEY_DESCRIPTOR_SIZE)] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	if (IS_ERR(keyring_key)) {
+		res = PTR_ERR(keyring_key);
+		keyring_key = NULL;
+		goto out;
+	}
+	BUG_ON(keyring_key->type != &key_type_logon);
+	ukp = ((struct user_key_payload *)keyring_key->payload.data);
+	if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
+		res = -EINVAL;
+		goto out;
+	}
+	master_key = (struct ext4_encryption_key *)ukp->data;
+	BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE !=
+		     EXT4_KEY_DERIVATION_NONCE_SIZE);
+	BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE);
+	res = ext4_derive_key_aes(ctx.nonce, master_key->raw, crypt_key->raw);
+out:
+	if (keyring_key)
+		key_put(keyring_key);
+	if (res < 0)
+		crypt_key->mode = EXT4_ENCRYPTION_MODE_INVALID;
+	return res;
+}
+
+int ext4_has_encryption_key(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_encryption_key *crypt_key = &ei->i_encryption_key;
+
+	return (crypt_key->mode != EXT4_ENCRYPTION_MODE_INVALID);
+}

fs/ext4/crypto_policy.c

+/*
+ * linux/fs/ext4/crypto_policy.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption policy functions for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static int ext4_inode_has_encryption_context(struct inode *inode)
+{
+	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0);
+	return (res > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int ext4_is_encryption_context_consistent_with_policy(
+	struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+	struct ext4_encryption_context ctx;
+	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+				 sizeof(ctx));
+	if (res != sizeof(ctx))
+		return 0;
+	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+			EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(ctx.contents_encryption_mode ==
+		 policy->contents_encryption_mode) &&
+		(ctx.filenames_encryption_mode ==
+		 policy->filenames_encryption_mode));
+}
+
+static int ext4_create_encryption_context_from_policy(
+	struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+	struct ext4_encryption_context ctx;
+	int res = 0;
+
+	ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+	       EXT4_KEY_DESCRIPTOR_SIZE);
+	if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid contents encryption mode %d\n", __func__,
+			policy->contents_encryption_mode);
+		res = -EINVAL;
+		goto out;
+	}
+	if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid filenames encryption mode %d\n", __func__,
+			policy->filenames_encryption_mode);
+		res = -EINVAL;
+		goto out;
+	}
+	ctx.contents_encryption_mode = policy->contents_encryption_mode;
+	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+	BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE);
+	get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+
+	res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+			     sizeof(ctx), 0);
+out:
+	if (!res)
+		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+	return res;
+}
+
+int ext4_process_policy(const struct ext4_encryption_policy *policy,
+			struct inode *inode)
+{
+	if (policy->version != 0)
+		return -EINVAL;
+
+	if (!ext4_inode_has_encryption_context(inode)) {
+		if (!ext4_empty_dir(inode))
+			return -ENOTEMPTY;
+		return ext4_create_encryption_context_from_policy(inode,
+								  policy);
+	}
+
+	if (ext4_is_encryption_context_consistent_with_policy(inode, policy))
+		return 0;
+
+	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+	       __func__);
+	return -EINVAL;
+}
+
+int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
+{
+	struct ext4_encryption_context ctx;
+
+	int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+				 &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return -ENOENT;
+	if (ctx.format != EXT4_ENCRYPTION_CONTEXT_FORMAT_V1)
+		return -EINVAL;
+	policy->version = 0;
+	policy->contents_encryption_mode = ctx.contents_encryption_mode;
+	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+	       EXT4_KEY_DESCRIPTOR_SIZE);
+	return 0;
+}
+
+int ext4_is_child_context_consistent_with_parent(struct inode *parent,
+						 struct inode *child)
+{
+	struct ext4_encryption_context parent_ctx, child_ctx;
+	int res;
+
+	if ((parent == NULL) || (child == NULL)) {
+		pr_err("parent %p child %p\n", parent, child);
+		BUG_ON(1);
+	}
+	/* no restrictions if the parent directory is not encrypted */
+	if (!ext4_encrypted_inode(parent))
+		return 1;
+	res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+			     &parent_ctx, sizeof(parent_ctx));
+	if (res != sizeof(parent_ctx))
+		return 0;
+	/* if the child directory is not encrypted, this is always a problem */
+	if (!ext4_encrypted_inode(child))
+		return 0;
+	res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+			     &child_ctx, sizeof(child_ctx));
+	if (res != sizeof(child_ctx))
+		return 0;
+	return (memcmp(parent_ctx.master_key_descriptor,
+		       child_ctx.master_key_descriptor,
+		       EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ctx.contents_encryption_mode ==
+		 child_ctx.contents_encryption_mode) &&
+		(parent_ctx.filenames_encryption_mode ==
+		 child_ctx.filenames_encryption_mode));
+}
+
+/**
+ * ext4_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child:  Child inode that inherits the context from @parent.
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int ext4_inherit_context(struct inode *parent, struct inode *child)
+{
+	struct ext4_encryption_context ctx;
+	int res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+				 &ctx, sizeof(ctx));
+
+	if (res != sizeof(ctx)) {
+		if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) {
+			ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+			ctx.contents_encryption_mode =
+				EXT4_ENCRYPTION_MODE_AES_256_XTS;
+			ctx.filenames_encryption_mode =
+				EXT4_ENCRYPTION_MODE_AES_256_CTS;
+			memset(ctx.master_key_descriptor, 0x42,
+			       EXT4_KEY_DESCRIPTOR_SIZE);
+			res = 0;
+		} else {
+			goto out;
+		}
+	}
+	get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+	res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+			     sizeof(ctx), 0);
+out:
+	if (!res)
+		ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT);
+	return res;
+}

fs/ext4/dir.c

@@ -22,10 +22,8 @@
  */
 
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
-#include <linux/rbtree.h>
 #include "ext4.h"
 #include "xattr.h"
 
@@ -110,7 +108,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int err;
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
+	struct buffer_head *bh = NULL;
 	int dir_has_error = 0;
+	struct ext4_fname_crypto_ctx *enc_ctx = NULL;
+	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
@@ -127,17 +128,28 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 
 	if (ext4_has_inline_data(inode)) {
 		int has_inline_data = 1;
-		int ret = ext4_read_inline_dir(file, ctx,
+		err = ext4_read_inline_dir(file, ctx,
 					   &has_inline_data);
 		if (has_inline_data)
-			return ret;
+			return err;
+	}
+
+	enc_ctx = ext4_get_fname_crypto_ctx(inode, EXT4_NAME_LEN);
+	if (IS_ERR(enc_ctx))
+		return PTR_ERR(enc_ctx);
+	if (enc_ctx) {
+		err = ext4_fname_crypto_alloc_buffer(enc_ctx, EXT4_NAME_LEN,
+						     &fname_crypto_str);
+		if (err < 0) {
+			ext4_put_fname_crypto_ctx(&enc_ctx);
+			return err;
+		}
 	}
 
 	offset = ctx->pos & (sb->s_blocksize - 1);
 
 	while (ctx->pos < inode->i_size) {
 		struct ext4_map_blocks map;
-		struct buffer_head *bh = NULL;
 
 		map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
 		map.m_len = 1;
@@ -180,6 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					(unsigned long long)ctx->pos);
 			ctx->pos += sb->s_blocksize - offset;
 			brelse(bh);
+			bh = NULL;
 			continue;
 		}
 		set_buffer_verified(bh);
@@ -226,25 +239,44 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			offset += ext4_rec_len_from_disk(de->rec_len,
 					sb->s_blocksize);
 			if (le32_to_cpu(de->inode)) {
+				if (enc_ctx == NULL) {
+					/* Directory is not encrypted */
 					if (!dir_emit(ctx, de->name,
 					    de->name_len,
 					    le32_to_cpu(de->inode),
-						get_dtype(sb, de->file_type))) {
-					brelse(bh);
-					return 0;
+					    get_dtype(sb, de->file_type)))
+						goto done;
+				} else {
+					/* Directory is encrypted */
+					err = ext4_fname_disk_to_usr(enc_ctx,
+							de, &fname_crypto_str);
+					if (err < 0)
+						goto errout;
+					if (!dir_emit(ctx,
+					    fname_crypto_str.name, err,
+					    le32_to_cpu(de->inode),
+					    get_dtype(sb, de->file_type)))
+						goto done;
 				}
 			}
 			ctx->pos += ext4_rec_len_from_disk(de->rec_len,
 						sb->s_blocksize);
 		}
-		offset = 0;
+		if ((ctx->pos < inode->i_size) && !dir_relax(inode))
+			goto done;
 		brelse(bh);
-		if (ctx->pos < inode->i_size) {
-			if (!dir_relax(inode))
-				return 0;
-		}
+		bh = NULL;
+		offset = 0;
 	}
-	return 0;
+done:
+	err = 0;
+errout:
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	ext4_put_fname_crypto_ctx(&enc_ctx);
+	ext4_fname_crypto_free_buffer(&fname_crypto_str);
+#endif
+	brelse(bh);
+	return err;
 }
 
 static inline int is_32bit_api(void)
@@ -384,10 +416,15 @@ void ext4_htree_free_dir_info(struct dir_private_info *p)
 
 /*
  * Given a directory entry, enter it into the fname rb tree.
+ *
+ * When filename encryption is enabled, the dirent will hold the
+ * encrypted filename, while the htree will hold decrypted filename.
+ * The decrypted filename is passed in via ent_name.  parameter.
  */
 int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 			     __u32 minor_hash,
-			     struct ext4_dir_entry_2 *dirent)
+			    struct ext4_dir_entry_2 *dirent,
+			    struct ext4_str *ent_name)
 {
 	struct rb_node **p, *parent = NULL;
 	struct fname *fname, *new_fn;
@@ -398,17 +435,17 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 	p = &info->root.rb_node;
 
 	/* Create and allocate the fname structure */
-	len = sizeof(struct fname) + dirent->name_len + 1;
+	len = sizeof(struct fname) + ent_name->len + 1;
 	new_fn = kzalloc(len, GFP_KERNEL);
 	if (!new_fn)
 		return -ENOMEM;
 	new_fn->hash = hash;
 	new_fn->minor_hash = minor_hash;
 	new_fn->inode = le32_to_cpu(dirent->inode);
-	new_fn->name_len = dirent->name_len;
+	new_fn->name_len = ent_name->len;
 	new_fn->file_type = dirent->file_type;
-	memcpy(new_fn->name, dirent->name, dirent->name_len);
-	new_fn->name[dirent->name_len] = 0;
+	memcpy(new_fn->name, ent_name->name, ent_name->len);
+	new_fn->name[ent_name->len] = 0;
 
 	while (*p) {
 		parent = *p;

fs/ext4/ext4_crypto.h

+/*
+ * linux/fs/ext4/ext4_crypto.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption header content for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#ifndef _EXT4_CRYPTO_H
+#define _EXT4_CRYPTO_H
+
+#include <linux/fs.h>
+
+#define EXT4_KEY_DESCRIPTOR_SIZE 8
+
+/* Policy provided via an ioctl on the topmost directory */
+struct ext4_encryption_policy {
+	char version;
+	char contents_encryption_mode;
+	char filenames_encryption_mode;
+	char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+} __attribute__((__packed__));
+
+#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1
+#define EXT4_KEY_DERIVATION_NONCE_SIZE 16
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ *  1 byte: Protector format (1 = this version)
+ *  1 byte: File contents encryption mode
+ *  1 byte: File names encryption mode
+ *  1 byte: Reserved
+ *  8 bytes: Master Key descriptor
+ *  16 bytes: Encryption Key derivation nonce
+ */
+struct ext4_encryption_context {
+	char format;
+	char contents_encryption_mode;
+	char filenames_encryption_mode;
+	char reserved;
+	char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+	char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE];
+} __attribute__((__packed__));
+
+/* Encryption parameters */
+#define EXT4_XTS_TWEAK_SIZE 16
+#define EXT4_AES_128_ECB_KEY_SIZE 16
+#define EXT4_AES_256_GCM_KEY_SIZE 32
+#define EXT4_AES_256_CBC_KEY_SIZE 32
+#define EXT4_AES_256_CTS_KEY_SIZE 32
+#define EXT4_AES_256_XTS_KEY_SIZE 64
+#define EXT4_MAX_KEY_SIZE 64
+
+#define EXT4_KEY_DESC_PREFIX "ext4:"
+#define EXT4_KEY_DESC_PREFIX_SIZE 5
+
+struct ext4_encryption_key {
+	uint32_t mode;
+	char raw[EXT4_MAX_KEY_SIZE];
+	uint32_t size;
+};
+
+#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL             0x00000001
+#define EXT4_BOUNCE_PAGE_REQUIRES_FREE_ENCRYPT_FL     0x00000002
+
+struct ext4_crypto_ctx {
+	struct crypto_tfm *tfm;         /* Crypto API context */
+	struct page *bounce_page;       /* Ciphertext page on write path */
+	struct page *control_page;      /* Original page on write path */
+	struct bio *bio;                /* The bio for this context */
+	struct work_struct work;        /* Work queue for read complete path */
+	struct list_head free_list;     /* Free list */
+	int flags;                      /* Flags */
+	int mode;                       /* Encryption mode for tfm */
+};
+
+struct ext4_completion_result {
+	struct completion completion;
+	int res;
+};
+
+#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \
+	struct ext4_completion_result ecr = { \
+		COMPLETION_INITIALIZER((ecr).completion), 0 }
+
+static inline int ext4_encryption_key_size(int mode)
+{
+	switch (mode) {
+	case EXT4_ENCRYPTION_MODE_AES_256_XTS:
+		return EXT4_AES_256_XTS_KEY_SIZE;
+	case EXT4_ENCRYPTION_MODE_AES_256_GCM:
+		return EXT4_AES_256_GCM_KEY_SIZE;
+	case EXT4_ENCRYPTION_MODE_AES_256_CBC:
+		return EXT4_AES_256_CBC_KEY_SIZE;
+	case EXT4_ENCRYPTION_MODE_AES_256_CTS:
+		return EXT4_AES_256_CTS_KEY_SIZE;
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+#define EXT4_FNAME_NUM_SCATTER_ENTRIES	4
+#define EXT4_CRYPTO_BLOCK_SIZE		16
+#define EXT4_FNAME_CRYPTO_DIGEST_SIZE	32
+
+struct ext4_str {
+	unsigned char *name;
+	u32 len;
+};
+
+struct ext4_fname_crypto_ctx {
+	u32 lim;
+	char tmp_buf[EXT4_CRYPTO_BLOCK_SIZE];
+	struct crypto_ablkcipher *ctfm;
+	struct crypto_hash *htfm;
+	struct page *workpage;
+	struct ext4_encryption_key key;
+	unsigned has_valid_key : 1;
+	unsigned ctfm_key_is_ready : 1;
+};
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct ext4_encrypted_symlink_data {
+	__le16 len;
+	char encrypted_path[1];
+} __attribute__((__packed__));
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 encrypted_symlink_data_len(u32 l)
+{
+	if (l < EXT4_CRYPTO_BLOCK_SIZE)
+		l = EXT4_CRYPTO_BLOCK_SIZE;
+	return (l + sizeof(struct ext4_encrypted_symlink_data) - 1);
+}
+
+#endif	/* _EXT4_CRYPTO_H */

fs/ext4/extents.c

@@ -1717,12 +1717,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 {
 	unsigned short ext1_ee_len, ext2_ee_len;
 
-	/*
-	 * Make sure that both extents are initialized. We don't merge
-	 * unwritten extents so that we can be sure that end_io code has
-	 * the extent that was written properly split out and conversion to
-	 * initialized is trivial.
-	 */
 	if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
 		return 0;
 
@@ -3128,6 +3122,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 	ee_len    = ext4_ext_get_actual_len(ex);
 	ee_pblock = ext4_ext_pblock(ex);
 
+	if (ext4_encrypted_inode(inode))
+		return ext4_encrypted_zeroout(inode, ex);
+
 	ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
 	if (ret > 0)
 		ret = 0;
@@ -4535,19 +4532,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 */
 		reserved_clusters = get_reserved_cluster_alloc(inode,
 						map->m_lblk, allocated);
-		if (map_from_cluster) {
-			if (reserved_clusters) {
-				/*
-				 * We have clusters reserved for this range.
-				 * But since we are not doing actual allocation
-				 * and are simply using blocks from previously
-				 * allocated cluster, we should release the
-				 * reservation and not claim quota.
-				 */
-				ext4_da_update_reserve_space(inode,
-						reserved_clusters, 0);
-			}
-		} else {
+		if (!map_from_cluster) {
 			BUG_ON(allocated_clusters < reserved_clusters);
 			if (reserved_clusters < allocated_clusters) {
 				struct ext4_inode_info *ei = EXT4_I(inode);
@@ -4803,12 +4788,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	else
 		max_blocks -= lblk;
 
-	flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
-		EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
-		EXT4_EX_NOCACHE;
-	if (mode & FALLOC_FL_KEEP_SIZE)
-		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
-
 	mutex_lock(&inode->i_mutex);
 
 	/*
@@ -4825,15 +4804,28 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		ret = inode_newsize_ok(inode, new_size);
 		if (ret)
 			goto out_mutex;
-		/*
-		 * If we have a partial block after EOF we have to allocate
-		 * the entire block.
-		 */
-		if (partial_end)
-			max_blocks += 1;
 	}
 
+	flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
+	if (mode & FALLOC_FL_KEEP_SIZE)
+		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+	/* Preallocate the range including the unaligned edges */
+	if (partial_begin || partial_end) {
+		ret = ext4_alloc_file_blocks(file,
+				round_down(offset, 1 << blkbits) >> blkbits,
+				(round_up((offset + len), 1 << blkbits) -
+				 round_down(offset, 1 << blkbits)) >> blkbits,
+				new_size, flags, mode);
+		if (ret)
+			goto out_mutex;
+
+	}
+
+	/* Zero range excluding the unaligned edges */
 	if (max_blocks > 0) {
+		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+			  EXT4_EX_NOCACHE);
 
 		/* Now release the pages and zero block aligned part of pages*/
 		truncate_pagecache_range(inode, start, end - 1);
@@ -4847,19 +4839,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 					     flags, mode);
 		if (ret)
 			goto out_dio;
-		/*
-		 * Remove entire range from the extent status tree.
-		 *
-		 * ext4_es_remove_extent(inode, lblk, max_blocks) is
-		 * NOT sufficient.  I'm not sure why this is the case,
-		 * but let's be conservative and remove the extent
-		 * status tree for the entire inode.  There should be
-		 * no outstanding delalloc extents thanks to the
-		 * filemap_write_and_wait_range() call above.
-		 */
-		ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
-		if (ret)
-			goto out_dio;
 	}
 	if (!partial_begin && !partial_end)
 		goto out_dio;
@@ -4922,6 +4901,20 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	ext4_lblk_t lblk;
 	unsigned int blkbits = inode->i_blkbits;
 
+	/*
+	 * Encrypted inodes can't handle collapse range or insert
+	 * range since we would need to re-encrypt blocks with a
+	 * different IV or XTS tweak (which are based on the logical
+	 * block number).
+	 *
+	 * XXX It's not clear why zero range isn't working, but we'll
+	 * leave it disabled for encrypted inodes for now.  This is a
+	 * bug we should fix....
+	 */
+	if (ext4_encrypted_inode(inode) &&
+	    (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)))
+		return -EOPNOTSUPP;
+
 	/* Return error if mode is not supported */
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))

fs/ext4/extents_status.c

@@ -9,12 +9,10 @@
  *
  * Ext4 extents status tree core functions.
  */
-#include <linux/rbtree.h>
 #include <linux/list_sort.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include "ext4.h"
-#include "extents_status.h"
 
 #include <trace/events/ext4.h>
 

fs/ext4/file.c

@@ -20,7 +20,6 @@
 
 #include <linux/time.h>
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/mount.h>
 #include <linux/path.h>
 #include <linux/quotaops.h>
@@ -221,6 +220,13 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct inode *inode = file->f_mapping->host;
+
+	if (ext4_encrypted_inode(inode)) {
+		int err = ext4_generate_encryption_key(inode);
+		if (err)
+			return 0;
+	}
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -238,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct vfsmount *mnt = filp->f_path.mnt;
 	struct path path;
 	char buf[64], *cp;
+	int ret;
 
 	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
 		     !(sb->s_flags & MS_RDONLY))) {
@@ -276,11 +283,17 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	 * writing and the journal is present
 	 */
 	if (filp->f_mode & FMODE_WRITE) {
-		int ret = ext4_inode_attach_jinode(inode);
+		ret = ext4_inode_attach_jinode(inode);
 		if (ret < 0)
 			return ret;
 	}
-	return dquot_file_open(inode, filp);
+	ret = dquot_file_open(inode, filp);
+	if (!ret && ext4_encrypted_inode(inode)) {
+		ret = ext4_generate_encryption_key(inode);
+		if (ret)
+			ret = -EACCES;
+	}
+	return ret;
 }
 
 /*

fs/ext4/fsync.c

@@ -26,7 +26,6 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
-#include <linux/jbd2.h>
 #include <linux/blkdev.h>
 
 #include "ext4.h"

fs/ext4/hash.c

@@ -10,7 +10,6 @@
  */
 
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/cryptohash.h>
 #include "ext4.h"
 

fs/ext4/ialloc.c

@@ -14,7 +14,6 @@
 
 #include <linux/time.h>
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/quotaops.h>
@@ -997,6 +996,12 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	ei->i_block_group = group;
 	ei->i_last_alloc_group = ~0;
 
+	/* If the directory encrypted, then we should encrypt the inode. */
+	if ((S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) &&
+	    (ext4_encrypted_inode(dir) ||
+	     DUMMY_ENCRYPTION_ENABLED(sbi)))
+		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+
 	ext4_set_inode_flags(inode);
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
@@ -1029,11 +1034,28 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	ext4_set_inode_state(inode, EXT4_STATE_NEW);
 
 	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
-
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	if ((sbi->s_file_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID) &&
+	    (sbi->s_dir_encryption_mode == EXT4_ENCRYPTION_MODE_INVALID)) {
+		ei->i_inline_off = 0;
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+			EXT4_FEATURE_INCOMPAT_INLINE_DATA))
+			ext4_set_inode_state(inode,
+			EXT4_STATE_MAY_INLINE_DATA);
+	} else {
+		/* Inline data and encryption are incompatible
+		 * We turn off inline data since encryption is enabled */
+		ei->i_inline_off = 1;
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+			EXT4_FEATURE_INCOMPAT_INLINE_DATA))
+			ext4_clear_inode_state(inode,
+			EXT4_STATE_MAY_INLINE_DATA);
+	}
+#else
 	ei->i_inline_off = 0;
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA))
 		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
-
+#endif
 	ret = inode;
 	err = dquot_alloc_inode(inode);
 	if (err)

fs/ext4/inline.c

@@ -11,11 +11,13 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
+
+#include <linux/fiemap.h>
+
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
 #include "truncate.h"
-#include <linux/fiemap.h>
 
 #define EXT4_XATTR_SYSTEM_DATA	"data"
 #define EXT4_MIN_INLINE_DATA_SIZE	((sizeof(__le32) * EXT4_N_BLOCKS))
@@ -972,7 +974,7 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh,
 	offset = 0;
 	while ((void *)de < dlimit) {
 		de_len = ext4_rec_len_from_disk(de->rec_len, inline_size);
-		trace_printk("de: off %u rlen %u name %*.s nlen %u ino %u\n",
+		trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n",
 			     offset, de_len, de->name_len, de->name,
 			     de->name_len, le32_to_cpu(de->inode));
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
@@ -1014,7 +1016,8 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	err = ext4_journal_get_write_access(handle, iloc->bh);
 	if (err)
 		return err;
-	ext4_insert_dentry(inode, de, inline_size, name, namelen);
+	ext4_insert_dentry(dir, inode, de, inline_size, &dentry->d_name,
+			   name, namelen);
 
 	ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
 
@@ -1327,6 +1330,7 @@ int htree_inlinedir_to_tree(struct file *dir_file,
 	struct ext4_iloc iloc;
 	void *dir_buf = NULL;
 	struct ext4_dir_entry_2 fake;
+	struct ext4_str tmp_str;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -1398,8 +1402,10 @@ int htree_inlinedir_to_tree(struct file *dir_file,
 			continue;
 		if (de->inode == 0)
 			continue;
-		err = ext4_htree_store_dirent(dir_file,
-				   hinfo->hash, hinfo->minor_hash, de);
+		tmp_str.name = de->name;
+		tmp_str.len = de->name_len;
+		err = ext4_htree_store_dirent(dir_file, hinfo->hash,
+					      hinfo->minor_hash, de, &tmp_str);
 		if (err) {
 			count = err;
 			goto out;

fs/ext4/inode.c

@@ -20,7 +20,6 @@
 
 #include <linux/fs.h>
 #include <linux/time.h>
-#include <linux/jbd2.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
@@ -36,7 +35,6 @@
 #include <linux/kernel.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
-#include <linux/ratelimit.h>
 #include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
@@ -140,7 +138,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 /*
  * Test whether an inode is a fast symlink.
  */
-static int ext4_inode_is_fast_symlink(struct inode *inode)
+int ext4_inode_is_fast_symlink(struct inode *inode)
 {
         int ea_blocks = EXT4_I(inode)->i_file_acl ?
 		EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
@@ -887,6 +885,95 @@ int do_journal_get_write_access(handle_t *handle,
 
 static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
+				  get_block_t *get_block)
+{
+	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned to = from + len;
+	struct inode *inode = page->mapping->host;
+	unsigned block_start, block_end;
+	sector_t block;
+	int err = 0;
+	unsigned blocksize = inode->i_sb->s_blocksize;
+	unsigned bbits;
+	struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
+	bool decrypt = false;
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(from > PAGE_CACHE_SIZE);
+	BUG_ON(to > PAGE_CACHE_SIZE);
+	BUG_ON(from > to);
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+	head = page_buffers(page);
+	bbits = ilog2(blocksize);
+	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+
+	for (bh = head, block_start = 0; bh != head || !block_start;
+	    block++, block_start = block_end, bh = bh->b_this_page) {
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (PageUptodate(page)) {
+				if (!buffer_uptodate(bh))
+					set_buffer_uptodate(bh);
+			}
+			continue;
+		}
+		if (buffer_new(bh))
+			clear_buffer_new(bh);
+		if (!buffer_mapped(bh)) {
+			WARN_ON(bh->b_size != blocksize);
+			err = get_block(inode, block, bh, 1);
+			if (err)
+				break;
+			if (buffer_new(bh)) {
+				unmap_underlying_metadata(bh->b_bdev,
+							  bh->b_blocknr);
+				if (PageUptodate(page)) {
+					clear_buffer_new(bh);
+					set_buffer_uptodate(bh);
+					mark_buffer_dirty(bh);
+					continue;
+				}
+				if (block_end > to || block_start < from)
+					zero_user_segments(page, to, block_end,
+							   block_start, from);
+				continue;
+			}
+		}
+		if (PageUptodate(page)) {
+			if (!buffer_uptodate(bh))
+				set_buffer_uptodate(bh);
+			continue;
+		}
+		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
+		    !buffer_unwritten(bh) &&
+		    (block_start < from || block_end > to)) {
+			ll_rw_block(READ, 1, &bh);
+			*wait_bh++ = bh;
+			decrypt = ext4_encrypted_inode(inode) &&
+				S_ISREG(inode->i_mode);
+		}
+	}
+	/*
+	 * If we issued read requests, let them complete.
+	 */
+	while (wait_bh > wait) {
+		wait_on_buffer(*--wait_bh);
+		if (!buffer_uptodate(*wait_bh))
+			err = -EIO;
+	}
+	if (unlikely(err))
+		page_zero_new_buffers(page, from, to);
+	else if (decrypt)
+		err = ext4_decrypt_one(inode, page);
+	return err;
+}
+#endif
+
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len, unsigned flags,
 			    struct page **pagep, void **fsdata)
@@ -949,11 +1036,19 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	/* In case writeback began while the page was unlocked */
 	wait_for_stable_page(page);
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	if (ext4_should_dioread_nolock(inode))
+		ret = ext4_block_write_begin(page, pos, len,
+					     ext4_get_block_write);
+	else
+		ret = ext4_block_write_begin(page, pos, len,
+					     ext4_get_block);
+#else
 	if (ext4_should_dioread_nolock(inode))
 		ret = __block_write_begin(page, pos, len, ext4_get_block_write);
 	else
 		ret = __block_write_begin(page, pos, len, ext4_get_block);
-
+#endif
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, page_buffers(page),
 					     from, to, NULL,
@@ -2575,7 +2670,12 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	/* In case writeback began while the page was unlocked */
 	wait_for_stable_page(page);
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	ret = ext4_block_write_begin(page, pos, len,
+				     ext4_da_get_block_prep);
+#else
 	ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
+#endif
 	if (ret < 0) {
 		unlock_page(page);
 		ext4_journal_stop(handle);
@@ -2821,7 +2921,7 @@ static int ext4_readpage(struct file *file, struct page *page)
 		ret = ext4_readpage_inline(inode, page);
 
 	if (ret == -EAGAIN)
-		return mpage_readpage(page, ext4_get_block);
+		return ext4_mpage_readpages(page->mapping, NULL, page, 1);
 
 	return ret;
 }
@@ -2836,7 +2936,7 @@ ext4_readpages(struct file *file, struct address_space *mapping,
 	if (ext4_has_inline_data(inode))
 		return 0;
 
-	return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
+	return ext4_mpage_readpages(mapping, pages, NULL, nr_pages);
 }
 
 static void ext4_invalidatepage(struct page *page, unsigned int offset,
@@ -3033,6 +3133,9 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
+#endif
 	if (IS_DAX(inode))
 		ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
 				ext4_end_io_dio, dio_flags);
@@ -3097,6 +3200,11 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+		return 0;
+#endif
+
 	/*
 	 * If we are doing data journalling we don't support O_DIRECT
 	 */
@@ -3261,6 +3369,13 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
 			goto unlock;
+		if (S_ISREG(inode->i_mode) &&
+		    ext4_encrypted_inode(inode)) {
+			/* We expect the key to be set. */
+			BUG_ON(!ext4_has_encryption_key(inode));
+			BUG_ON(blocksize != PAGE_CACHE_SIZE);
+			WARN_ON_ONCE(ext4_decrypt_one(inode, page));
+		}
 	}
 	if (ext4_should_journal_data(inode)) {
 		BUFFER_TRACE(bh, "get write access");
@@ -4096,7 +4211,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &ext4_dir_inode_operations;
 		inode->i_fop = &ext4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (ext4_inode_is_fast_symlink(inode)) {
+		if (ext4_inode_is_fast_symlink(inode) &&
+		    !ext4_encrypted_inode(inode)) {
 			inode->i_op = &ext4_fast_symlink_inode_operations;
 			nd_terminate_link(ei->i_data, inode->i_size,
 				sizeof(ei->i_data) - 1);

fs/ext4/ioctl.c

@@ -8,12 +8,12 @@
  */
 
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/capability.h>
 #include <linux/time.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
 #include <linux/file.h>
+#include <linux/random.h>
 #include <asm/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -196,6 +196,16 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	return err;
 }
 
+static int uuid_is_zero(__u8 u[16])
+{
+	int	i;
+
+	for (i = 0; i < 16; i++)
+		if (u[i])
+			return 0;
+	return 1;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -615,7 +625,78 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 	case EXT4_IOC_PRECACHE_EXTENTS:
 		return ext4_ext_precache(inode);
+	case EXT4_IOC_SET_ENCRYPTION_POLICY: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+		struct ext4_encryption_policy policy;
+		int err = 0;
+
+		if (copy_from_user(&policy,
+				   (struct ext4_encryption_policy __user *)arg,
+				   sizeof(policy))) {
+			err = -EFAULT;
+			goto encryption_policy_out;
+		}
+
+		err = ext4_process_policy(&policy, inode);
+encryption_policy_out:
+		return err;
+#else
+		return -EOPNOTSUPP;
+#endif
+	}
+	case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+		int err, err2;
+		struct ext4_sb_info *sbi = EXT4_SB(sb);
+		handle_t *handle;
+
+		if (!ext4_sb_has_crypto(sb))
+			return -EOPNOTSUPP;
+		if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
+			err = mnt_want_write_file(filp);
+			if (err)
+				return err;
+			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+			if (IS_ERR(handle)) {
+				err = PTR_ERR(handle);
+				goto pwsalt_err_exit;
+			}
+			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+			if (err)
+				goto pwsalt_err_journal;
+			generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+			err = ext4_handle_dirty_metadata(handle, NULL,
+							 sbi->s_sbh);
+		pwsalt_err_journal:
+			err2 = ext4_journal_stop(handle);
+			if (err2 && !err)
+				err = err2;
+		pwsalt_err_exit:
+			mnt_drop_write_file(filp);
+			if (err)
+				return err;
+		}
+		if (copy_to_user((void *) arg, sbi->s_es->s_encrypt_pw_salt,
+				 16))
+			return -EFAULT;
+		return 0;
+	}
+	case EXT4_IOC_GET_ENCRYPTION_POLICY: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+		struct ext4_encryption_policy policy;
+		int err = 0;
 
+		if (!ext4_encrypted_inode(inode))
+			return -ENOENT;
+		err = ext4_get_policy(inode, &policy);
+		if (err)
+			return err;
+		if (copy_to_user((void *)arg, &policy, sizeof(policy)))
+			return -EFAULT;
+		return 0;
+#else
+		return -EOPNOTSUPP;
+#endif
+	}
 	default:
 		return -ENOTTY;
 	}
@@ -680,6 +761,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FITRIM:
 	case EXT4_IOC_RESIZE_FS:
 	case EXT4_IOC_PRECACHE_EXTENTS:
+	case EXT4_IOC_SET_ENCRYPTION_POLICY:
+	case EXT4_IOC_GET_ENCRYPTION_PWSALT:
+	case EXT4_IOC_GET_ENCRYPTION_POLICY:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/ext4/page-io.c

@@ -8,7 +8,6 @@
 
 #include <linux/fs.h>
 #include <linux/time.h>
-#include <linux/jbd2.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
@@ -24,7 +23,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/ratelimit.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -68,6 +66,10 @@ static void ext4_finish_bio(struct bio *bio)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+		struct page *data_page = NULL;
+		struct ext4_crypto_ctx *ctx = NULL;
+#endif
 		struct buffer_head *bh, *head;
 		unsigned bio_start = bvec->bv_offset;
 		unsigned bio_end = bio_start + bvec->bv_len;
@@ -77,6 +79,15 @@ static void ext4_finish_bio(struct bio *bio)
 		if (!page)
 			continue;
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+		if (!page->mapping) {
+			/* The bounce data pages are unmapped. */
+			data_page = page;
+			ctx = (struct ext4_crypto_ctx *)page_private(data_page);
+			page = ctx->control_page;
+		}
+#endif
+
 		if (error) {
 			SetPageError(page);
 			set_bit(AS_EIO, &page->mapping->flags);
@@ -101,9 +112,14 @@ static void ext4_finish_bio(struct bio *bio)
 		} while ((bh = bh->b_this_page) != head);
 		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
 		local_irq_restore(flags);
-		if (!under_io)
+		if (!under_io) {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+			if (ctx)
+				ext4_restore_control_page(data_page);
+#endif
 			end_page_writeback(page);
 		}
+	}
 }
 
 static void ext4_release_io_end(ext4_io_end_t *io_end)
@@ -377,6 +393,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
 
 static int io_submit_add_bh(struct ext4_io_submit *io,
 			    struct inode *inode,
+			    struct page *page,
 			    struct buffer_head *bh)
 {
 	int ret;
@@ -390,7 +407,7 @@ static int io_submit_add_bh(struct ext4_io_submit *io,
 		if (ret)
 			return ret;
 	}
-	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+	ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
 	if (ret != bh->b_size)
 		goto submit_and_retry;
 	io->io_next_block++;
@@ -403,6 +420,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct writeback_control *wbc,
 			bool keep_towrite)
 {
+	struct page *data_page = NULL;
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, blocksize;
 	struct buffer_head *bh, *head;
@@ -462,19 +480,29 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		set_buffer_async_write(bh);
 	} while ((bh = bh->b_this_page) != head);
 
-	/* Now submit buffers to write */
 	bh = head = page_buffers(page);
+
+	if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+		data_page = ext4_encrypt(inode, page);
+		if (IS_ERR(data_page)) {
+			ret = PTR_ERR(data_page);
+			data_page = NULL;
+			goto out;
+		}
+	}
+
+	/* Now submit buffers to write */
 	do {
 		if (!buffer_async_write(bh))
 			continue;
-		ret = io_submit_add_bh(io, inode, bh);
+		ret = io_submit_add_bh(io, inode,
+				       data_page ? data_page : page, bh);
 		if (ret) {
 			/*
 			 * We only get here on ENOMEM.  Not much else
 			 * we can do but mark the page as dirty, and
 			 * better luck next time.
 			 */
-			redirty_page_for_writepage(wbc, page);
 			break;
 		}
 		nr_submitted++;
@@ -483,6 +511,11 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	/* Error stopped previous loop? Clean up buffers... */
 	if (ret) {
+	out:
+		if (data_page)
+			ext4_restore_control_page(data_page);
+		printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
+		redirty_page_for_writepage(wbc, page);
 		do {
 			clear_buffer_async_write(bh);
 			bh = bh->b_this_page;

fs/ext4/readpage.c

+/*
+ * linux/fs/ext4/readpage.c
+ *
+ * Copyright (C) 2002, Linus Torvalds.
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This was originally taken from fs/mpage.c
+ *
+ * The intent is the ext4_mpage_readpages() function here is intended
+ * to replace mpage_readpages() in the general case, not just for
+ * encrypted files.  It has some limitations (see below), where it
+ * will fall back to read_block_full_page(), but these limitations
+ * should only be hit when page_size != block_size.
+ *
+ * This will allow us to attach a callback function to support ext4
+ * encryption.
+ *
+ * If anything unusual happens, such as:
+ *
+ * - encountering a page which has buffers
+ * - encountering a page which has a non-hole after a hole
+ * - encountering a page with non-contiguous blocks
+ *
+ * then this code just gives up and calls the buffer_head-based read function.
+ * It does handle a page which has holes at the end - that is a common case:
+ * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/kdev_t.h>
+#include <linux/gfp.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/highmem.h>
+#include <linux/prefetch.h>
+#include <linux/mpage.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/cleancache.h>
+
+#include "ext4.h"
+
+/*
+ * Call ext4_decrypt on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	struct ext4_crypto_ctx *ctx =
+		container_of(work, struct ext4_crypto_ctx, work);
+	struct bio	*bio	= ctx->bio;
+	struct bio_vec	*bv;
+	int		i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+
+		int ret = ext4_decrypt(ctx, page);
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else
+			SetPageUptodate(page);
+		unlock_page(page);
+	}
+	ext4_release_crypto_ctx(ctx);
+	bio_put(bio);
+#else
+	BUG();
+#endif
+}
+
+static inline bool ext4_bio_encrypted(struct bio *bio)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	return unlikely(bio->bi_private != NULL);
+#else
+	return false;
+#endif
+}
+
+/*
+ * I/O completion handler for multipage BIOs.
+ *
+ * The mpage code never puts partial pages into a BIO (except for end-of-file).
+ * If a page does not map to a contiguous run of blocks then it simply falls
+ * back to block_read_full_page().
+ *
+ * Why is this?  If a page's completion depends on a number of different BIOs
+ * which can complete in any order (or at the same time) then determining the
+ * status of that page is hard.  See end_buffer_async_read() for the details.
+ * There is no point in duplicating all that complexity.
+ */
+static void mpage_end_io(struct bio *bio, int err)
+{
+	struct bio_vec *bv;
+	int i;
+
+	if (ext4_bio_encrypted(bio)) {
+		struct ext4_crypto_ctx *ctx = bio->bi_private;
+
+		if (err) {
+			ext4_release_crypto_ctx(ctx);
+		} else {
+			INIT_WORK(&ctx->work, completion_pages);
+			ctx->bio = bio;
+			queue_work(ext4_read_workqueue, &ctx->work);
+			return;
+		}
+	}
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+
+		if (!err) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	}
+
+	bio_put(bio);
+}
+
+int ext4_mpage_readpages(struct address_space *mapping,
+			 struct list_head *pages, struct page *page,
+			 unsigned nr_pages)
+{
+	struct bio *bio = NULL;
+	unsigned page_idx;
+	sector_t last_block_in_bio = 0;
+
+	struct inode *inode = mapping->host;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	sector_t block_in_file;
+	sector_t last_block;
+	sector_t last_block_in_file;
+	sector_t blocks[MAX_BUF_PER_PAGE];
+	unsigned page_block;
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	int length;
+	unsigned relative_block = 0;
+	struct ext4_map_blocks map;
+
+	map.m_pblk = 0;
+	map.m_lblk = 0;
+	map.m_len = 0;
+	map.m_flags = 0;
+
+	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+		int fully_mapped = 1;
+		unsigned first_hole = blocks_per_page;
+
+		prefetchw(&page->flags);
+		if (pages) {
+			page = list_entry(pages->prev, struct page, lru);
+			list_del(&page->lru);
+			if (add_to_page_cache_lru(page, mapping,
+						  page->index, GFP_KERNEL))
+				goto next_page;
+		}
+
+		if (page_has_buffers(page))
+			goto confused;
+
+		block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+		last_block = block_in_file + nr_pages * blocks_per_page;
+		last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+		if (last_block > last_block_in_file)
+			last_block = last_block_in_file;
+		page_block = 0;
+
+		/*
+		 * Map blocks using the previous result first.
+		 */
+		if ((map.m_flags & EXT4_MAP_MAPPED) &&
+		    block_in_file > map.m_lblk &&
+		    block_in_file < (map.m_lblk + map.m_len)) {
+			unsigned map_offset = block_in_file - map.m_lblk;
+			unsigned last = map.m_len - map_offset;
+
+			for (relative_block = 0; ; relative_block++) {
+				if (relative_block == last) {
+					/* needed? */
+					map.m_flags &= ~EXT4_MAP_MAPPED;
+					break;
+				}
+				if (page_block == blocks_per_page)
+					break;
+				blocks[page_block] = map.m_pblk + map_offset +
+					relative_block;
+				page_block++;
+				block_in_file++;
+			}
+		}
+
+		/*
+		 * Then do more ext4_map_blocks() calls until we are
+		 * done with this page.
+		 */
+		while (page_block < blocks_per_page) {
+			if (block_in_file < last_block) {
+				map.m_lblk = block_in_file;
+				map.m_len = last_block - block_in_file;
+
+				if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
+				set_error_page:
+					SetPageError(page);
+					zero_user_segment(page, 0,
+							  PAGE_CACHE_SIZE);
+					unlock_page(page);
+					goto next_page;
+				}
+			}
+			if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
+				fully_mapped = 0;
+				if (first_hole == blocks_per_page)
+					first_hole = page_block;
+				page_block++;
+				block_in_file++;
+				continue;
+			}
+			if (first_hole != blocks_per_page)
+				goto confused;		/* hole -> non-hole */
+
+			/* Contiguous blocks? */
+			if (page_block && blocks[page_block-1] != map.m_pblk-1)
+				goto confused;
+			for (relative_block = 0; ; relative_block++) {
+				if (relative_block == map.m_len) {
+					/* needed? */
+					map.m_flags &= ~EXT4_MAP_MAPPED;
+					break;
+				} else if (page_block == blocks_per_page)
+					break;
+				blocks[page_block] = map.m_pblk+relative_block;
+				page_block++;
+				block_in_file++;
+			}
+		}
+		if (first_hole != blocks_per_page) {
+			zero_user_segment(page, first_hole << blkbits,
+					  PAGE_CACHE_SIZE);
+			if (first_hole == 0) {
+				SetPageUptodate(page);
+				unlock_page(page);
+				goto next_page;
+			}
+		} else if (fully_mapped) {
+			SetPageMappedToDisk(page);
+		}
+		if (fully_mapped && blocks_per_page == 1 &&
+		    !PageUptodate(page) && cleancache_get_page(page) == 0) {
+			SetPageUptodate(page);
+			goto confused;
+		}
+
+		/*
+		 * This page will go to BIO.  Do we need to send this
+		 * BIO off first?
+		 */
+		if (bio && (last_block_in_bio != blocks[0] - 1)) {
+		submit_and_realloc:
+			submit_bio(READ, bio);
+			bio = NULL;
+		}
+		if (bio == NULL) {
+			struct ext4_crypto_ctx *ctx = NULL;
+
+			if (ext4_encrypted_inode(inode) &&
+			    S_ISREG(inode->i_mode)) {
+				ctx = ext4_get_crypto_ctx(inode);
+				if (IS_ERR(ctx))
+					goto set_error_page;
+			}
+			bio = bio_alloc(GFP_KERNEL,
+				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+			if (!bio) {
+				if (ctx)
+					ext4_release_crypto_ctx(ctx);
+				goto set_error_page;
+			}
+			bio->bi_bdev = bdev;
+			bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
+			bio->bi_end_io = mpage_end_io;
+			bio->bi_private = ctx;
+		}
+
+		length = first_hole << blkbits;
+		if (bio_add_page(bio, page, length, 0) < length)
+			goto submit_and_realloc;
+
+		if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
+		     (relative_block == map.m_len)) ||
+		    (first_hole != blocks_per_page)) {
+			submit_bio(READ, bio);
+			bio = NULL;
+		} else
+			last_block_in_bio = blocks[blocks_per_page - 1];
+		goto next_page;
+	confused:
+		if (bio) {
+			submit_bio(READ, bio);
+			bio = NULL;
+		}
+		if (!PageUptodate(page))
+			block_read_full_page(page, ext4_get_block);
+		else
+			unlock_page(page);
+	next_page:
+		if (pages)
+			page_cache_release(page);
+	}
+	BUG_ON(pages && !list_empty(pages));
+	if (bio)
+		submit_bio(READ, bio);
+	return 0;
+}

fs/ext4/super.c

@@ -21,7 +21,6 @@
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
-#include <linux/jbd2.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/blkdev.h>
@@ -323,22 +322,6 @@ static void save_error_info(struct super_block *sb, const char *func,
 	ext4_commit_super(sb, 1);
 }
 
-/*
- * The del_gendisk() function uninitializes the disk-specific data
- * structures, including the bdi structure, without telling anyone
- * else.  Once this happens, any attempt to call mark_buffer_dirty()
- * (for example, by ext4_commit_super), will cause a kernel OOPS.
- * This is a kludge to prevent these oops until we can put in a proper
- * hook in del_gendisk() to inform the VFS and file system layers.
- */
-static int block_device_ejected(struct super_block *sb)
-{
-	struct inode *bd_inode = sb->s_bdev->bd_inode;
-	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
-
-	return bdi->dev == NULL;
-}
-
 static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 {
 	struct super_block		*sb = journal->j_private;
@@ -893,6 +876,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	ei->i_encryption_key.mode = EXT4_ENCRYPTION_MODE_INVALID;
+#endif
 
 	return &ei->vfs_inode;
 }
@@ -1120,7 +1106,7 @@ enum {
 	Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
 	Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
-	Opt_data_err_abort, Opt_data_err_ignore,
+	Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
@@ -1211,6 +1197,7 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
+	{Opt_test_dummy_encryption, "test_dummy_encryption"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1412,6 +1399,7 @@ static const struct mount_opts {
 	{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
 	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
+	{Opt_test_dummy_encryption, 0, MOPT_GTE0},
 	{Opt_err, 0, 0}
 };
 
@@ -1588,6 +1576,15 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		*journal_ioprio =
 			IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
+	} else if (token == Opt_test_dummy_encryption) {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+		sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION;
+		ext4_msg(sb, KERN_WARNING,
+			 "Test dummy encryption mode enabled");
+#else
+		ext4_msg(sb, KERN_WARNING,
+			 "Test dummy encryption mount option ignored");
+#endif
 	} else if (m->flags & MOPT_DATAJ) {
 		if (is_remount) {
 			if (!sbi->s_journal)
@@ -2685,11 +2682,13 @@ static struct attribute *ext4_attrs[] = {
 EXT4_INFO_ATTR(lazy_itable_init);
 EXT4_INFO_ATTR(batched_discard);
 EXT4_INFO_ATTR(meta_bg_resize);
+EXT4_INFO_ATTR(encryption);
 
 static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(lazy_itable_init),
 	ATTR_LIST(batched_discard),
 	ATTR_LIST(meta_bg_resize),
+	ATTR_LIST(encryption),
 	NULL,
 };
 
@@ -3448,6 +3447,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (sb->s_bdev->bd_part)
 		sbi->s_sectors_written_start =
 			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	/* Modes of operations for file and directory encryption. */
+	sbi->s_file_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
+	sbi->s_dir_encryption_mode = EXT4_ENCRYPTION_MODE_INVALID;
+#endif
 
 	/* Cleanup superblock name */
 	for (cp = sb->s_id; (cp = strchr(cp, '/'));)
@@ -3692,6 +3696,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	}
 
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) &&
+	    es->s_encryption_level) {
+		ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
+			 es->s_encryption_level);
+		goto failed_mount;
+	}
+
 	if (sb->s_blocksize != blocksize) {
 		/* Validate the filesystem blocksize */
 		if (!sb_set_blocksize(sb, blocksize)) {
@@ -4054,6 +4065,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	}
 
+	if (unlikely(sbi->s_mount_flags & EXT4_MF_TEST_DUMMY_ENCRYPTION) &&
+	    !(sb->s_flags & MS_RDONLY) &&
+	    !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) {
+		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT);
+		ext4_commit_super(sb, 1);
+	}
+
 	/*
 	 * Get the # of file system overhead blocks from the
 	 * superblock if present.
@@ -4570,7 +4588,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
 	int error = 0;
 
-	if (!sbh || block_device_ejected(sb))
+	if (!sbh)
 		return error;
 	if (buffer_write_io_error(sbh)) {
 		/*

fs/ext4/symlink.c

@@ -18,12 +18,100 @@
  */
 
 #include <linux/fs.h>
-#include <linux/jbd2.h>
 #include <linux/namei.h>
 #include "ext4.h"
 #include "xattr.h"
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct page *cpage = NULL;
+	char *caddr, *paddr = NULL;
+	struct ext4_str cstr, pstr;
+	struct inode *inode = dentry->d_inode;
+	struct ext4_fname_crypto_ctx *ctx = NULL;
+	struct ext4_encrypted_symlink_data *sd;
+	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
+	int res;
+	u32 plen, max_size = inode->i_sb->s_blocksize;
+
+	if (!ext4_encrypted_inode(inode))
+		return page_follow_link_light(dentry, nd);
+
+	ctx = ext4_get_fname_crypto_ctx(inode, inode->i_sb->s_blocksize);
+	if (IS_ERR(ctx))
+		return ctx;
+
+	if (ext4_inode_is_fast_symlink(inode)) {
+		caddr = (char *) EXT4_I(dentry->d_inode)->i_data;
+		max_size = sizeof(EXT4_I(dentry->d_inode)->i_data);
+	} else {
+		cpage = read_mapping_page(inode->i_mapping, 0, NULL);
+		if (IS_ERR(cpage)) {
+			ext4_put_fname_crypto_ctx(&ctx);
+			return cpage;
+		}
+		caddr = kmap(cpage);
+		caddr[size] = 0;
+	}
+
+	/* Symlink is encrypted */
+	sd = (struct ext4_encrypted_symlink_data *)caddr;
+	cstr.name = sd->encrypted_path;
+	cstr.len  = le32_to_cpu(sd->len);
+	if ((cstr.len +
+	     sizeof(struct ext4_encrypted_symlink_data) - 1) >
+	    max_size) {
+		/* Symlink data on the disk is corrupted */
+		res = -EIO;
+		goto errout;
+	}
+	plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ?
+		EXT4_FNAME_CRYPTO_DIGEST_SIZE*2 : cstr.len;
+	paddr = kmalloc(plen + 1, GFP_NOFS);
+	if (!paddr) {
+		res = -ENOMEM;
+		goto errout;
+	}
+	pstr.name = paddr;
+	res = _ext4_fname_disk_to_usr(ctx, &cstr, &pstr);
+	if (res < 0)
+		goto errout;
+	/* Null-terminate the name */
+	if (res <= plen)
+		paddr[res] = '\0';
+	nd_set_link(nd, paddr);
+	ext4_put_fname_crypto_ctx(&ctx);
+	if (cpage) {
+		kunmap(cpage);
+		page_cache_release(cpage);
+	}
+	return NULL;
+errout:
+	ext4_put_fname_crypto_ctx(&ctx);
+	if (cpage) {
+		kunmap(cpage);
+		page_cache_release(cpage);
+	}
+	kfree(paddr);
+	return ERR_PTR(res);
+}
+
+static void ext4_put_link(struct dentry *dentry, struct nameidata *nd,
+			  void *cookie)
+{
+	struct page *page = cookie;
+
+	if (!page) {
+		kfree(nd_get_link(nd));
+	} else {
+		kunmap(page);
+		page_cache_release(page);
+	}
+}
+#endif
+
+static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
 	nd_set_link(nd, (char *) ei->i_data);
@@ -32,8 +120,13 @@ static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+	.follow_link    = ext4_follow_link,
+	.put_link       = ext4_put_link,
+#else
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
+#endif
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -43,7 +136,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= ext4_follow_link,
+	.follow_link    = ext4_follow_fast_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,

fs/ext4/xattr.c

@@ -55,7 +55,6 @@
 #include <linux/slab.h>
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
-#include <linux/rwsem.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
@@ -639,8 +638,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
 		free += EXT4_XATTR_LEN(name_len);
 	}
 	if (i->value) {
-		if (free < EXT4_XATTR_SIZE(i->value_len) ||
-		    free < EXT4_XATTR_LEN(name_len) +
+		if (free < EXT4_XATTR_LEN(name_len) +
 			   EXT4_XATTR_SIZE(i->value_len))
 			return -ENOSPC;
 	}

fs/ext4/xattr.h

@@ -23,6 +23,7 @@
 #define EXT4_XATTR_INDEX_SECURITY	        6
 #define EXT4_XATTR_INDEX_SYSTEM			7
 #define EXT4_XATTR_INDEX_RICHACL		8
+#define EXT4_XATTR_INDEX_ENCRYPTION		9
 
 struct ext4_xattr_header {
 	__le32	h_magic;	/* magic number for identification */
@@ -98,6 +99,8 @@ extern const struct xattr_handler ext4_xattr_user_handler;
 extern const struct xattr_handler ext4_xattr_trusted_handler;
 extern const struct xattr_handler ext4_xattr_security_handler;
 
+#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
+
 extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
 
 extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);