Commit 396d1099 authored by Linus Torvalds's avatar Linus Torvalds

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

Pull ext4 updates from Ted Ts'o:
 "The major change this cycle is deleting ext4's copy of the file system
  encryption code and switching things over to using the copies in
  fs/crypto.  I've updated the MAINTAINERS file to add an entry for
  fs/crypto listing Jaeguk Kim and myself as the maintainers.

  There are also a number of bug fixes, most notably for some problems
  found by American Fuzzy Lop (AFL) courtesy of Vegard Nossum.  Also
  fixed is a writeback deadlock detected by generic/130, and some
  potential races in the metadata checksum code"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (21 commits)
  ext4: verify extent header depth
  ext4: short-cut orphan cleanup on error
  ext4: fix reference counting bug on block allocation error
  MAINTAINRES: fs-crypto maintainers update
  ext4 crypto: migrate into vfs's crypto engine
  ext2: fix filesystem deadlock while reading corrupted xattr block
  ext4: fix project quota accounting without quota limits enabled
  ext4: validate s_reserved_gdt_blocks on mount
  ext4: remove unused page_idx
  ext4: don't call ext4_should_journal_data() on the journal inode
  ext4: Fix WARN_ON_ONCE in ext4_commit_super()
  ext4: fix deadlock during page writeback
  ext4: correct error value of function verifying dx checksum
  ext4: avoid modifying checksum fields directly during checksum verification
  ext4: check for extents that wrap around
  jbd2: make journal y2038 safe
  jbd2: track more dependencies on transaction commit
  jbd2: move lockdep tracking to journal_s
  jbd2: move lockdep instrumentation for jbd2 handles
  ext4: respect the nobarrier mount option in nojournal mode
  ...
parents 59ebc44e 7bc94916
......@@ -4942,6 +4942,13 @@ F: Documentation/filesystems/caching/
F: fs/fscache/
F: include/linux/fscache*.h
FS-CRYPTO: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
M: Theodore Y. Ts'o <tytso@mit.edu>
M: Jaegeuk Kim <jaegeuk@kernel.org>
S: Supported
F: fs/crypto/
F: include/linux/fscrypto.h
F2FS FILE SYSTEM
M: Jaegeuk Kim <jaegeuk@kernel.org>
M: Changman Lee <cm224.lee@samsung.com>
......
......@@ -1193,6 +1193,27 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
return 1;
}
/*
* Returns 1 if the passed-in block region is valid; 0 if some part overlaps
* with filesystem metadata blocksi.
*/
int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
unsigned int count)
{
if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
(start_blk + count < start_blk) ||
(start_blk > le32_to_cpu(sbi->s_es->s_blocks_count)))
return 0;
/* Ensure we do not step over superblock */
if ((start_blk <= sbi->s_sb_block) &&
(start_blk + count >= sbi->s_sb_block))
return 0;
return 1;
}
/*
* ext2_new_blocks() -- core block(s) allocation function
* @inode: file inode
......
......@@ -367,6 +367,7 @@ struct ext2_inode {
*/
#define EXT2_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT2_ERROR_FS 0x0002 /* Errors detected */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
/*
* Mount flags
......@@ -739,6 +740,8 @@ extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
unsigned long *, int *);
extern int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
unsigned int count);
extern void ext2_free_blocks (struct inode *, unsigned long,
unsigned long);
extern unsigned long ext2_count_free_blocks (struct super_block *);
......
......@@ -1389,6 +1389,16 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
ei->i_frag_size = raw_inode->i_fsize;
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
ei->i_dir_acl = 0;
if (ei->i_file_acl &&
!ext2_data_block_valid(EXT2_SB(sb), ei->i_file_acl, 1)) {
ext2_error(sb, "ext2_iget", "bad extended attribute block %u",
ei->i_file_acl);
brelse(bh);
ret = -EFSCORRUPTED;
goto bad_inode;
}
if (S_ISREG(inode->i_mode))
inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
else
......
......@@ -759,10 +759,19 @@ void
ext2_xattr_delete_inode(struct inode *inode)
{
struct buffer_head *bh = NULL;
struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
down_write(&EXT2_I(inode)->xattr_sem);
if (!EXT2_I(inode)->i_file_acl)
goto cleanup;
if (!ext2_data_block_valid(sbi, EXT2_I(inode)->i_file_acl, 0)) {
ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
"inode %ld: xattr block %d is out of data blocks range",
inode->i_ino, EXT2_I(inode)->i_file_acl);
goto cleanup;
}
bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl);
if (!bh) {
ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
......
......@@ -99,17 +99,9 @@ config EXT4_FS_SECURITY
extended attributes for file security labels, say N.
config EXT4_ENCRYPTION
tristate "Ext4 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_CTR
select CRYPTO_SHA256
select KEYS
select ENCRYPTED_KEYS
select FS_ENCRYPTION
help
Enable encryption of ext4 files and directories. This
feature is similar to ecryptfs, but it is more memory
......
......@@ -12,5 +12,3 @@ ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.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
......@@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb,
memset(bh->b_data, 0, sb->s_blocksize);
bit_max = ext4_num_base_meta_clusters(sb, block_group);
if ((bit_max >> 3) >= bh->b_size)
return -EFSCORRUPTED;
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
......@@ -610,7 +613,9 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
smp_mb();
if (EXT4_SB(sb)->s_mb_free_pending)
jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
return 1;
}
......
This diff is collapsed.
This diff is collapsed.
/*
* 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 <crypto/skcipher.h>
#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 derivation.
* @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 skcipher_request *req = NULL;
DECLARE_EXT4_COMPLETION_RESULT(ecr);
struct scatterlist src_sg, dst_sg;
struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
if (IS_ERR(tfm)) {
res = PTR_ERR(tfm);
tfm = NULL;
goto out;
}
crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
req = skcipher_request_alloc(tfm, GFP_NOFS);
if (!req) {
res = -ENOMEM;
goto out;
}
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
derive_crypt_complete, &ecr);
res = crypto_skcipher_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);
skcipher_request_set_crypt(req, &src_sg, &dst_sg,
EXT4_AES_256_XTS_KEY_SIZE, NULL);
res = crypto_skcipher_encrypt(req);
if (res == -EINPROGRESS || res == -EBUSY) {
wait_for_completion(&ecr.completion);
res = ecr.res;
}
out:
skcipher_request_free(req);
crypto_free_skcipher(tfm);
return res;
}
void ext4_free_crypt_info(struct ext4_crypt_info *ci)
{
if (!ci)
return;
if (ci->ci_keyring_key)
key_put(ci->ci_keyring_key);
crypto_free_skcipher(ci->ci_ctfm);
kmem_cache_free(ext4_crypt_info_cachep, ci);
}
void ext4_free_encryption_info(struct inode *inode,
struct ext4_crypt_info *ci)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_crypt_info *prev;
if (ci == NULL)
ci = ACCESS_ONCE(ei->i_crypt_info);
if (ci == NULL)
return;
prev = cmpxchg(&ei->i_crypt_info, ci, NULL);
if (prev != ci)
return;
ext4_free_crypt_info(ci);
}
int _ext4_get_encryption_info(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_crypt_info *crypt_info;
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;
const struct user_key_payload *ukp;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct crypto_skcipher *ctfm;
const char *cipher_str;
char raw_key[EXT4_MAX_KEY_SIZE];
char mode;
int res;
if (!ext4_read_workqueue) {
res = ext4_init_crypto();
if (res)
return res;
}
retry:
crypt_info = ACCESS_ONCE(ei->i_crypt_info);
if (crypt_info) {
if (!crypt_info->ci_keyring_key ||
key_validate(crypt_info->ci_keyring_key) == 0)
return 0;
ext4_free_encryption_info(inode, crypt_info);
goto retry;
}
res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
&ctx, sizeof(ctx));
if (res < 0) {
if (!DUMMY_ENCRYPTION_ENABLED(sbi))
return res;
ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
ctx.filenames_encryption_mode =
EXT4_ENCRYPTION_MODE_AES_256_CTS;
ctx.flags = 0;
} else if (res != sizeof(ctx))
return -EINVAL;
res = 0;
crypt_info = kmem_cache_alloc(ext4_crypt_info_cachep, GFP_KERNEL);
if (!crypt_info)
return -ENOMEM;
crypt_info->ci_flags = ctx.flags;
crypt_info->ci_data_mode = ctx.contents_encryption_mode;
crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
crypt_info->ci_ctfm = NULL;
crypt_info->ci_keyring_key = NULL;
memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
sizeof(crypt_info->ci_master_key));
if (S_ISREG(inode->i_mode))
mode = crypt_info->ci_data_mode;
else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
mode = crypt_info->ci_filename_mode;
else
BUG();
switch (mode) {
case EXT4_ENCRYPTION_MODE_AES_256_XTS:
cipher_str = "xts(aes)";
break;
case EXT4_ENCRYPTION_MODE_AES_256_CTS:
cipher_str = "cts(cbc(aes))";
break;
default:
printk_once(KERN_WARNING
"ext4: unsupported key mode %d (ino %u)\n",
mode, (unsigned) inode->i_ino);
res = -ENOKEY;
goto out;
}
if (DUMMY_ENCRYPTION_ENABLED(sbi)) {
memset(raw_key, 0x42, EXT4_AES_256_XTS_KEY_SIZE);
goto got_key;
}
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;
}
crypt_info->ci_keyring_key = keyring_key;
if (keyring_key->type != &key_type_logon) {
printk_once(KERN_WARNING
"ext4: key type must be logon\n");
res = -ENOKEY;
goto out;
}
down_read(&keyring_key->sem);
ukp = user_key_payload(keyring_key);
if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
res = -EINVAL;
up_read(&keyring_key->sem);
goto out;
}
master_key = (struct ext4_encryption_key *)ukp->data;
BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE !=
EXT4_KEY_DERIVATION_NONCE_SIZE);
if (master_key->size != EXT4_AES_256_XTS_KEY_SIZE) {
printk_once(KERN_WARNING
"ext4: key size incorrect: %d\n",
master_key->size);
res = -ENOKEY;
up_read(&keyring_key->sem);
goto out;
}
res = ext4_derive_key_aes(ctx.nonce, master_key->raw,
raw_key);
up_read(&keyring_key->sem);
if (res)
goto out;
got_key:
ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
if (!ctfm || IS_ERR(ctfm)) {
res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
printk(KERN_DEBUG
"%s: error %d (inode %u) allocating crypto tfm\n",
__func__, res, (unsigned) inode->i_ino);
goto out;
}
crypt_info->ci_ctfm = ctfm;
crypto_skcipher_clear_flags(ctfm, ~0);
crypto_tfm_set_flags(crypto_skcipher_tfm(ctfm),
CRYPTO_TFM_REQ_WEAK_KEY);
res = crypto_skcipher_setkey(ctfm, raw_key,
ext4_encryption_key_size(mode));
if (res)
goto out;
memzero_explicit(raw_key, sizeof(raw_key));
if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) != NULL) {
ext4_free_crypt_info(crypt_info);
goto retry;
}
return 0;
out:
if (res == -ENOKEY)
res = 0;
ext4_free_crypt_info(crypt_info);
memzero_explicit(raw_key, sizeof(raw_key));
return res;
}
int ext4_has_encryption_key(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
return (ei->i_crypt_info != NULL);
}
/*
* 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_jbd2.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.flags ==
policy->flags) &&
(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;
handle_t *handle;
int res, res2;
res = ext4_convert_inline_data(inode);
if (res)
return res;
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);
return -EINVAL;
}
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);
return -EINVAL;
}
if (policy->flags & ~EXT4_POLICY_FLAGS_VALID)
return -EINVAL;
ctx.contents_encryption_mode = policy->contents_encryption_mode;
ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
ctx.flags = policy->flags;
BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE);
get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
handle = ext4_journal_start(inode, EXT4_HT_MISC,
ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle))
return PTR_ERR(handle);
res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
sizeof(ctx), 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
}
res2 = ext4_journal_stop(handle);
if (!res)
res = res2;
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 (!S_ISDIR(inode->i_mode))
return -EINVAL;
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;
policy->flags = ctx.flags;
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_crypt_info *parent_ci, *child_ci;
int res;
if ((parent == NULL) || (child == NULL)) {
pr_err("parent %p child %p\n", parent, child);
WARN_ON(1); /* Should never happen */
return 0;
}
/* no restrictions if the parent directory is not encrypted */
if (!ext4_encrypted_inode(parent))
return 1;
/* if the child directory is not encrypted, this is always a problem */
if (!ext4_encrypted_inode(child))
return 0;
res = ext4_get_encryption_info(parent);
if (res)
return 0;
res = ext4_get_encryption_info(child);
if (res)
return 0;
parent_ci = EXT4_I(parent)->i_crypt_info;
child_ci = EXT4_I(child)->i_crypt_info;
if (!parent_ci && !child_ci)
return 1;
if (!parent_ci || !child_ci)
return 0;
return (memcmp(parent_ci->ci_master_key,
child_ci->ci_master_key,
EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
(parent_ci->ci_flags == child_ci->ci_flags));
}
/**
* 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;
struct ext4_crypt_info *ci;
int res;
res = ext4_get_encryption_info(parent);
if (res < 0)
return res;
ci = EXT4_I(parent)->i_crypt_info;
if (ci == NULL)
return -ENOKEY;
ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) {
ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
ctx.filenames_encryption_mode =
EXT4_ENCRYPTION_MODE_AES_256_CTS;
ctx.flags = 0;
memset(ctx.master_key_descriptor, 0x42,
EXT4_KEY_DESCRIPTOR_SIZE);
res = 0;
} else {
ctx.contents_encryption_mode = ci->ci_data_mode;
ctx.filenames_encryption_mode = ci->ci_filename_mode;
ctx.flags = ci->ci_flags;
memcpy(ctx.master_key_descriptor, ci->ci_master_key,
EXT4_KEY_DESCRIPTOR_SIZE);
}
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);
if (!res) {
ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT);
ext4_clear_inode_state(child, EXT4_STATE_MAY_INLINE_DATA);
res = ext4_get_encryption_info(child);
}
return res;
}
......@@ -109,10 +109,10 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
struct super_block *sb = inode->i_sb;
struct buffer_head *bh = NULL;
int dir_has_error = 0;
struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
if (ext4_encrypted_inode(inode)) {
err = ext4_get_encryption_info(inode);
err = fscrypt_get_encryption_info(inode);
if (err && err != -ENOKEY)
return err;
}
......@@ -139,8 +139,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
}
if (ext4_encrypted_inode(inode)) {
err = ext4_fname_crypto_alloc_buffer(inode, EXT4_NAME_LEN,
&fname_crypto_str);
err = fscrypt_fname_alloc_buffer(inode, EXT4_NAME_LEN, &fstr);
if (err < 0)
return err;
}
......@@ -253,16 +252,19 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
get_dtype(sb, de->file_type)))
goto done;
} else {
int save_len = fname_crypto_str.len;
int save_len = fstr.len;
struct fscrypt_str de_name =
FSTR_INIT(de->name,
de->name_len);
/* Directory is encrypted */
err = ext4_fname_disk_to_usr(inode,
NULL, de, &fname_crypto_str);
fname_crypto_str.len = save_len;
err = fscrypt_fname_disk_to_usr(inode,
0, 0, &de_name, &fstr);
fstr.len = save_len;
if (err < 0)
goto errout;
if (!dir_emit(ctx,
fname_crypto_str.name, err,
fstr.name, err,
le32_to_cpu(de->inode),
get_dtype(sb, de->file_type)))
goto done;
......@@ -281,7 +283,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
err = 0;
errout:
#ifdef CONFIG_EXT4_FS_ENCRYPTION
ext4_fname_crypto_free_buffer(&fname_crypto_str);
fscrypt_fname_free_buffer(&fstr);
#endif
brelse(bh);
return err;
......@@ -432,7 +434,7 @@ void ext4_htree_free_dir_info(struct dir_private_info *p)
int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent,
struct ext4_str *ent_name)
struct fscrypt_str *ent_name)
{
struct rb_node **p, *parent = NULL;
struct fname *fname, *new_fn;
......@@ -609,7 +611,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
static int ext4_dir_open(struct inode * inode, struct file * filp)
{
if (ext4_encrypted_inode(inode))
return ext4_get_encryption_info(inode) ? -EACCES : 0;
return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
return 0;
}
......
This diff is collapsed.
/*
* 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 flags;
char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
} __attribute__((__packed__));
#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1
#define EXT4_KEY_DERIVATION_NONCE_SIZE 16
#define EXT4_POLICY_FLAGS_PAD_4 0x00
#define EXT4_POLICY_FLAGS_PAD_8 0x01
#define EXT4_POLICY_FLAGS_PAD_16 0x02
#define EXT4_POLICY_FLAGS_PAD_32 0x03
#define EXT4_POLICY_FLAGS_PAD_MASK 0x03
#define EXT4_POLICY_FLAGS_VALID 0x03
/**
* 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 flags;
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
/* This is passed in from userspace into the kernel keyring */
struct ext4_encryption_key {
__u32 mode;
char raw[EXT4_MAX_KEY_SIZE];
__u32 size;
} __attribute__((__packed__));
struct ext4_crypt_info {
char ci_data_mode;
char ci_filename_mode;
char ci_flags;
struct crypto_skcipher *ci_ctfm;
struct key *ci_keyring_key;
char ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
};
#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
#define EXT4_WRITE_PATH_FL 0x00000002
struct ext4_crypto_ctx {
union {
struct {
struct page *bounce_page; /* Ciphertext page */
struct page *control_page; /* Original page */
} w;
struct {
struct bio *bio;
struct work_struct work;
} r;
struct list_head free_list; /* Free list */
};
char flags; /* Flags */
char 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;
};
/**
* 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 */
......@@ -175,6 +175,13 @@ struct ext4_journal_cb_entry {
* There is no guaranteed calling order of multiple registered callbacks on
* the same transaction.
*/
static inline void _ext4_journal_callback_add(handle_t *handle,
struct ext4_journal_cb_entry *jce)
{
/* Add the jce to transaction's private list */
list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
}
static inline void ext4_journal_callback_add(handle_t *handle,
void (*func)(struct super_block *sb,
struct ext4_journal_cb_entry *jce,
......@@ -187,10 +194,11 @@ static inline void ext4_journal_callback_add(handle_t *handle,
/* Add the jce to transaction's private list */
jce->jce_func = func;
spin_lock(&sbi->s_md_lock);
list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
_ext4_journal_callback_add(handle, jce);
spin_unlock(&sbi->s_md_lock);
}
/**
* ext4_journal_callback_del: delete a registered callback
* @handle: active journal transaction handle on which callback was registered
......
......@@ -381,9 +381,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
ext4_lblk_t last = lblock + len - 1;
if (len == 0 || lblock > last)
/*
* We allow neither:
* - zero length
* - overflow/wrap-around
*/
if (lblock + len <= lblock)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
......@@ -474,6 +478,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
error_msg = "invalid extent entries";
goto corrupted;
}
if (unlikely(depth > 32)) {
error_msg = "too large eh_depth";
goto corrupted;
}
/* Verify checksum on non-root extent tree nodes */
if (ext_depth(inode) != depth &&
!ext4_extent_block_csum_verify(inode, eh)) {
......
......@@ -303,10 +303,10 @@ 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_get_encryption_info(inode);
int err = fscrypt_get_encryption_info(inode);
if (err)
return 0;
if (ext4_encryption_info(inode) == NULL)
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
file_accessed(file);
......@@ -362,16 +362,16 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
}
}
if (ext4_encrypted_inode(inode)) {
ret = ext4_get_encryption_info(inode);
ret = fscrypt_get_encryption_info(inode);
if (ret)
return -EACCES;
if (ext4_encryption_info(inode) == NULL)
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
dir = dget_parent(file_dentry(filp));
if (ext4_encrypted_inode(d_inode(dir)) &&
!ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
ext4_warning(inode->i_sb,
"Inconsistent encryption contexts: %lu/%lu",
(unsigned long) d_inode(dir)->i_ino,
......
......@@ -106,9 +106,11 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
if (!journal) {
ret = generic_file_fsync(file, start, end, datasync);
ret = __generic_file_fsync(file, start, end, datasync);
if (!ret && !hlist_empty(&inode->i_dentry))
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
goto issue_flush;
goto out;
}
......@@ -140,6 +142,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
issue_flush:
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
......
......@@ -767,10 +767,10 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
if ((ext4_encrypted_inode(dir) ||
DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
err = ext4_get_encryption_info(dir);
err = fscrypt_get_encryption_info(dir);
if (err)
return ERR_PTR(err);
if (ext4_encryption_info(dir) == NULL)
if (!fscrypt_has_encryption_key(dir))
return ERR_PTR(-EPERM);
if (!handle)
nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
......@@ -1115,7 +1115,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
}
if (encrypt) {
err = ext4_inherit_context(dir, inode);
/* give pointer to avoid set_context with journal ops. */
err = fscrypt_inherit_context(dir, inode, &encrypt, true);
if (err)
goto fail_free_drop;
}
......
......@@ -1326,7 +1326,7 @@ 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;
struct fscrypt_str tmp_str;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
......@@ -1739,20 +1739,20 @@ ext4_get_inline_entry(struct inode *inode,
return (struct ext4_dir_entry_2 *)(inline_pos + offset);
}
int empty_inline_dir(struct inode *dir, int *has_inline_data)
bool empty_inline_dir(struct inode *dir, int *has_inline_data)
{
int err, inline_size;
struct ext4_iloc iloc;
void *inline_pos;
unsigned int offset;
struct ext4_dir_entry_2 *de;
int ret = 1;
bool ret = true;
err = ext4_get_inode_loc(dir, &iloc);
if (err) {
EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
err, dir->i_ino);
return 1;
return true;
}
down_read(&EXT4_I(dir)->xattr_sem);
......@@ -1766,7 +1766,7 @@ int empty_inline_dir(struct inode *dir, int *has_inline_data)
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - no `..'",
dir->i_ino);
ret = 1;
ret = true;
goto out;
}
......@@ -1784,11 +1784,11 @@ int empty_inline_dir(struct inode *dir, int *has_inline_data)
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
ret = 1;
ret = true;
goto out;
}
if (le32_to_cpu(de->inode)) {
ret = 0;
ret = false;
goto out;
}
offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
......
......@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u16 csum_lo;
__u16 csum_hi = 0;
__u32 csum;
__u16 dummy_csum = 0;
int offset = offsetof(struct ext4_inode, i_checksum_lo);
unsigned int csum_size = sizeof(dummy_csum);
csum_lo = le16_to_cpu(raw->i_checksum_lo);
raw->i_checksum_lo = 0;
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
csum_hi = le16_to_cpu(raw->i_checksum_hi);
raw->i_checksum_hi = 0;
}
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
EXT4_INODE_SIZE(inode->i_sb));
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_GOOD_OLD_INODE_SIZE - offset);
raw->i_checksum_lo = cpu_to_le16(csum_lo);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
raw->i_checksum_hi = cpu_to_le16(csum_hi);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
offset = offsetof(struct ext4_inode, i_checksum_hi);
csum = ext4_chksum(sbi, csum, (__u8 *)raw +
EXT4_GOOD_OLD_INODE_SIZE,
offset - EXT4_GOOD_OLD_INODE_SIZE);
if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_INODE_SIZE(inode->i_sb) -
offset);
}
}
return csum;
}
......@@ -205,9 +211,9 @@ void ext4_evict_inode(struct inode *inode)
* Note that directories do not have this problem because they
* don't use page cache.
*/
if (ext4_should_journal_data(inode) &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
inode->i_ino != EXT4_JOURNAL_INO) {
if (inode->i_ino != EXT4_JOURNAL_INO &&
ext4_should_journal_data(inode) &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
......@@ -386,7 +392,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
int ret;
if (ext4_encrypted_inode(inode))
return ext4_encrypted_zeroout(inode, lblk, pblk, len);
return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
if (ret > 0)
......@@ -1152,7 +1158,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
if (unlikely(err))
page_zero_new_buffers(page, from, to);
else if (decrypt)
err = ext4_decrypt(page);
err = fscrypt_decrypt_page(page);
return err;
}
#endif
......@@ -2748,13 +2754,36 @@ static int ext4_writepages(struct address_space *mapping,
done = true;
}
}
ext4_journal_stop(handle);
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
* to finish which may depend on writeback of pages to
* complete or on page lock to be released. In that
* case, we have to wait until after after we have
* submitted all the IO, released page locks we hold,
* and dropped io_end reference (for extent conversion
* to be able to complete) before stopping the handle.
*/
if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
ext4_journal_stop(handle);
handle = NULL;
}
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
/* Drop our io_end reference we got from init */
ext4_put_io_end(mpd.io_submit.io_end);
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
* we are still holding the transaction as we can
* release the last reference to io_end which may end
* up doing unwritten extent conversion.
*/
if (handle) {
ext4_put_io_end_defer(mpd.io_submit.io_end);
ext4_journal_stop(handle);
} else
ext4_put_io_end(mpd.io_submit.io_end);
if (ret == -ENOSPC && sbi->s_journal) {
/*
......@@ -3706,9 +3735,9 @@ static int __ext4_block_zero_page_range(handle_t *handle,
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(!fscrypt_has_encryption_key(inode));
BUG_ON(blocksize != PAGE_SIZE);
WARN_ON_ONCE(ext4_decrypt(page));
WARN_ON_ONCE(fscrypt_decrypt_page(page));
}
}
if (ext4_should_journal_data(inode)) {
......
......@@ -308,6 +308,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
kprojid_t kprojid;
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct dquot *transfer_to[MAXQUOTAS] = { };
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_PROJECT)) {
......@@ -361,17 +362,14 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
if (err)
goto out_stop;
if (sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
struct dquot *transfer_to[MAXQUOTAS] = { };
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
err = __dquot_transfer(inode, transfer_to);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
}
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
err = __dquot_transfer(inode, transfer_to);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
}
EXT4_I(inode)->i_projid = kprojid;
inode->i_ctime = ext4_current_time(inode);
out_dirty:
......@@ -772,19 +770,13 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
int err = 0;
struct fscrypt_policy policy;
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;
(struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
return fscrypt_process_policy(inode, &policy);
#else
return -EOPNOTSUPP;
#endif
......@@ -827,12 +819,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
case EXT4_IOC_GET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
struct fscrypt_policy policy;
int err = 0;
if (!ext4_encrypted_inode(inode))
return -ENOENT;
err = ext4_get_policy(inode, &policy);
err = fscrypt_get_policy(inode, &policy);
if (err)
return err;
if (copy_to_user((void __user *)arg, &policy, sizeof(policy)))
......
......@@ -2627,6 +2627,7 @@ int ext4_mb_init(struct super_block *sb)
spin_lock_init(&sbi->s_md_lock);
spin_lock_init(&sbi->s_bal_lock);
sbi->s_mb_free_pending = 0;
sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN;
......@@ -2814,6 +2815,9 @@ static void ext4_free_data_callback(struct super_block *sb,
/* we expect to find existing buddy because it's pinned */
BUG_ON(err != 0);
spin_lock(&EXT4_SB(sb)->s_md_lock);
EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count;
spin_unlock(&EXT4_SB(sb)->s_md_lock);
db = e4b.bd_info;
/* there are blocks to put in buddy to make them really free */
......@@ -2939,7 +2943,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata", block, block+len);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
* Fix the bitmap and return EFSCORRUPTED
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
......@@ -2948,7 +2952,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
err = -EAGAIN;
err = -EFSCORRUPTED;
goto out_err;
}
......@@ -4513,18 +4517,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
if (*errp == -EAGAIN) {
/*
* drop the reference that we took
* in ext4_mb_use_best_found
*/
ext4_mb_release_context(ac);
ac->ac_b_ex.fe_group = 0;
ac->ac_b_ex.fe_start = 0;
ac->ac_b_ex.fe_len = 0;
ac->ac_status = AC_STATUS_CONTINUE;
goto repeat;
} else if (*errp) {
if (*errp) {
ext4_discard_allocated_blocks(ac);
goto errout;
} else {
......@@ -4583,6 +4576,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
{
ext4_group_t group = e4b->bd_group;
ext4_grpblk_t cluster;
ext4_grpblk_t clusters = new_entry->efd_count;
struct ext4_free_data *entry;
struct ext4_group_info *db = e4b->bd_info;
struct super_block *sb = e4b->bd_sb;
......@@ -4649,8 +4643,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
}
}
/* Add the extent to transaction's private list */
ext4_journal_callback_add(handle, ext4_free_data_callback,
&new_entry->efd_jce);
new_entry->efd_jce.jce_func = ext4_free_data_callback;
spin_lock(&sbi->s_md_lock);
_ext4_journal_callback_add(handle, &new_entry->efd_jce);
sbi->s_mb_free_pending += clusters;
spin_unlock(&sbi->s_md_lock);
return 0;
}
......
This diff is collapsed.
......@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/backing-dev.h>
#include <linux/fscrypto.h>
#include "ext4_jbd2.h"
#include "xattr.h"
......@@ -67,7 +68,6 @@ static void ext4_finish_bio(struct bio *bio)
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;
......@@ -82,8 +82,7 @@ static void ext4_finish_bio(struct bio *bio)
if (!page->mapping) {
/* The bounce data pages are unmapped. */
data_page = page;
ctx = (struct ext4_crypto_ctx *)page_private(data_page);
page = ctx->w.control_page;
fscrypt_pullback_bio_page(&page, false);
}
#endif
......@@ -113,8 +112,8 @@ static void ext4_finish_bio(struct bio *bio)
local_irq_restore(flags);
if (!under_io) {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
if (ctx)
ext4_restore_control_page(data_page);
if (data_page)
fscrypt_restore_control_page(data_page);
#endif
end_page_writeback(page);
}
......@@ -473,7 +472,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
gfp_t gfp_flags = GFP_NOFS;
retry_encrypt:
data_page = ext4_encrypt(inode, page, gfp_flags);
data_page = fscrypt_encrypt_page(inode, page, gfp_flags);
if (IS_ERR(data_page)) {
ret = PTR_ERR(data_page);
if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
......@@ -511,7 +510,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
if (ret) {
out:
if (data_page)
ext4_restore_control_page(data_page);
fscrypt_restore_control_page(data_page);
printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
redirty_page_for_writepage(wbc, page);
do {
......
......@@ -46,37 +46,6 @@
#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, r.work);
struct bio *bio = ctx->r.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(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
......@@ -104,14 +73,10 @@ static void mpage_end_io(struct bio *bio)
int i;
if (ext4_bio_encrypted(bio)) {
struct ext4_crypto_ctx *ctx = bio->bi_private;
if (bio->bi_error) {
ext4_release_crypto_ctx(ctx);
fscrypt_release_ctx(bio->bi_private);
} else {
INIT_WORK(&ctx->r.work, completion_pages);
ctx->r.bio = bio;
queue_work(ext4_read_workqueue, &ctx->r.work);
fscrypt_decrypt_bio_pages(bio->bi_private, bio);
return;
}
}
......@@ -135,7 +100,6 @@ int ext4_mpage_readpages(struct address_space *mapping,
unsigned nr_pages)
{
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
......@@ -157,7 +121,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
map.m_len = 0;
map.m_flags = 0;
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
for (; nr_pages; nr_pages--) {
int fully_mapped = 1;
unsigned first_hole = blocks_per_page;
......@@ -275,11 +239,11 @@ int ext4_mpage_readpages(struct address_space *mapping,
bio = NULL;
}
if (bio == NULL) {
struct ext4_crypto_ctx *ctx = NULL;
struct fscrypt_ctx *ctx = NULL;
if (ext4_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
ctx = fscrypt_get_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
goto set_error_page;
}
......@@ -287,7 +251,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
min_t(int, nr_pages, BIO_MAX_PAGES));
if (!bio) {
if (ctx)
ext4_release_crypto_ctx(ctx);
fscrypt_release_ctx(ctx);
goto set_error_page;
}
bio->bi_bdev = bdev;
......
......@@ -945,9 +945,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_datasync_tid = 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_crypt_info = NULL;
#endif
return &ei->vfs_inode;
}
......@@ -1026,8 +1023,7 @@ void ext4_clear_inode(struct inode *inode)
EXT4_I(inode)->jinode = NULL;
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
if (EXT4_I(inode)->i_crypt_info)
ext4_free_encryption_info(inode, EXT4_I(inode)->i_crypt_info);
fscrypt_put_encryption_info(inode, NULL);
#endif
}
......@@ -1094,6 +1090,90 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
return try_to_free_buffers(page);
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
{
return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
}
static int ext4_key_prefix(struct inode *inode, u8 **key)
{
*key = EXT4_SB(inode->i_sb)->key_prefix;
return EXT4_SB(inode->i_sb)->key_prefix_size;
}
static int ext4_prepare_context(struct inode *inode)
{
return ext4_convert_inline_data(inode);
}
static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
handle_t *handle;
int res, res2;
/* fs_data is null when internally used. */
if (fs_data) {
res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
ext4_clear_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA);
}
return res;
}
handle = ext4_journal_start(inode, EXT4_HT_MISC,
ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle))
return PTR_ERR(handle);
res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
}
res2 = ext4_journal_stop(handle);
if (!res)
res = res2;
return res;
}
static int ext4_dummy_context(struct inode *inode)
{
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
static unsigned ext4_max_namelen(struct inode *inode)
{
return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
EXT4_NAME_LEN;
}
static struct fscrypt_operations ext4_cryptops = {
.get_context = ext4_get_context,
.key_prefix = ext4_key_prefix,
.prepare_context = ext4_prepare_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
.is_encrypted = ext4_encrypted_inode,
.empty_dir = ext4_empty_dir,
.max_namelen = ext4_max_namelen,
};
#else
static struct fscrypt_operations ext4_cryptops = {
.is_encrypted = ext4_encrypted_inode,
};
#endif
#ifdef CONFIG_QUOTA
static char *quotatypes[] = INITQFNAMES;
#define QTYPE2NAME(t) (quotatypes[t])
......@@ -2068,23 +2148,25 @@ static int ext4_fill_flex_info(struct super_block *sb)
static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
int offset;
int offset = offsetof(struct ext4_group_desc, bg_checksum);
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
__le16 save_csum;
__u32 csum32;
__u16 dummy_csum = 0;
save_csum = gdp->bg_checksum;
gdp->bg_checksum = 0;
csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
sizeof(le_group));
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
sbi->s_desc_size);
gdp->bg_checksum = save_csum;
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
sizeof(dummy_csum));
offset += sizeof(dummy_csum);
if (offset < sbi->s_desc_size)
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
sbi->s_desc_size - offset);
crc = csum32 & 0xFFFF;
goto out;
......@@ -2094,8 +2176,6 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
if (!ext4_has_feature_gdt_csum(sb))
return 0;
offset = offsetof(struct ext4_group_desc, bg_checksum);
crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
crc = crc16(crc, (__u8 *)gdp, offset);
......@@ -2278,6 +2358,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
while (es->s_last_orphan) {
struct inode *inode;
/*
* We may have encountered an error during cleanup; if
* so, skip the rest.
*/
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
es->s_last_orphan = 0;
break;
}
inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
if (IS_ERR(inode)) {
es->s_last_orphan = 0;
......@@ -3416,6 +3506,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
ext4_msg(sb, KERN_ERR,
"Number of reserved GDT blocks insanely large: %d",
le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
goto failed_mount;
}
if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
err = bdev_dax_supported(sb, blocksize);
if (err)
......@@ -3686,6 +3783,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_op = &ext4_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
sb->s_cop = &ext4_cryptops;
#ifdef CONFIG_QUOTA
sb->dq_op = &ext4_quota_operations;
if (ext4_has_feature_quota(sb))
......@@ -3996,6 +4094,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
kfree(orig_data);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
EXT4_KEY_DESC_PREFIX_SIZE);
sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
#endif
return 0;
cantfind_ext4:
......@@ -4327,20 +4430,6 @@ static int ext4_commit_super(struct super_block *sb, int sync)
if (!sbh || block_device_ejected(sb))
return error;
if (buffer_write_io_error(sbh)) {
/*
* Oh, dear. A previous attempt to write the
* superblock failed. This could happen because the
* USB device was yanked out. Or it could happen to
* be a transient write error and maybe the block will
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
ext4_msg(sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
......@@ -4371,7 +4460,23 @@ static int ext4_commit_super(struct super_block *sb, int sync)
&EXT4_SB(sb)->s_freeinodes_counter));
BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
lock_buffer(sbh);
if (buffer_write_io_error(sbh)) {
/*
* Oh, dear. A previous attempt to write the
* superblock failed. This could happen because the
* USB device was yanked out. Or it could happen to
* be a transient write error and maybe the block will
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
ext4_msg(sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
mark_buffer_dirty(sbh);
unlock_buffer(sbh);
if (sync) {
error = __sync_dirty_buffer(sbh,
test_opt(sb, BARRIER) ? WRITE_FUA : WRITE_SYNC);
......@@ -5422,7 +5527,6 @@ static int __init ext4_init_fs(void)
static void __exit ext4_exit_fs(void)
{
ext4_exit_crypto();
ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
......
......@@ -22,23 +22,22 @@
#include "ext4.h"
#include "xattr.h"
#ifdef CONFIG_EXT4_FS_ENCRYPTION
static const char *ext4_encrypted_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
struct page *cpage = NULL;
char *caddr, *paddr = NULL;
struct ext4_str cstr, pstr;
struct ext4_encrypted_symlink_data *sd;
struct fscrypt_str cstr, pstr;
struct fscrypt_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;
u32 max_size = inode->i_sb->s_blocksize;
if (!dentry)
return ERR_PTR(-ECHILD);
res = ext4_get_encryption_info(inode);
res = fscrypt_get_encryption_info(inode);
if (res)
return ERR_PTR(res);
......@@ -54,30 +53,27 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
}
/* Symlink is encrypted */
sd = (struct ext4_encrypted_symlink_data *)caddr;
sd = (struct fscrypt_symlink_data *)caddr;
cstr.name = sd->encrypted_path;
cstr.len = le16_to_cpu(sd->len);
if ((cstr.len +
sizeof(struct ext4_encrypted_symlink_data) - 1) >
max_size) {
if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
/* Symlink data on the disk is corrupted */
res = -EFSCORRUPTED;
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;
res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
if (res)
goto errout;
}
pstr.name = paddr;
pstr.len = plen;
res = _ext4_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
if (res < 0)
goto errout;
paddr = pstr.name;
/* Null-terminate the name */
if (res <= plen)
if (res <= pstr.len)
paddr[res] = '\0';
if (cpage)
put_page(cpage);
......@@ -99,7 +95,6 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = {
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
};
#endif
const struct inode_operations ext4_symlink_inode_operations = {
.readlink = generic_readlink,
......
......@@ -121,17 +121,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le32 save_csum;
__le64 dsk_block_nr = cpu_to_le64(block_nr);
__u32 dummy_csum = 0;
int offset = offsetof(struct ext4_xattr_header, h_checksum);
save_csum = hdr->h_checksum;
hdr->h_checksum = 0;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
sizeof(dsk_block_nr));
csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
EXT4_BLOCK_SIZE(inode->i_sb));
csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
offset += sizeof(dummy_csum);
csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
EXT4_BLOCK_SIZE(inode->i_sb) - offset);
hdr->h_checksum = save_csum;
return cpu_to_le32(csum);
}
......
......@@ -124,7 +124,7 @@ static int journal_submit_commit_record(journal_t *journal,
struct commit_header *tmp;
struct buffer_head *bh;
int ret;
struct timespec now = current_kernel_time();
struct timespec64 now = current_kernel_time64();
*cbh = NULL;
......
......@@ -691,6 +691,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
{
int err = 0;
jbd2_might_wait_for_commit(journal);
read_lock(&journal->j_state_lock);
#ifdef CONFIG_JBD2_DEBUG
if (!tid_geq(journal->j_commit_request, tid)) {
......@@ -1091,6 +1092,7 @@ static void jbd2_stats_proc_exit(journal_t *journal)
static journal_t * journal_init_common (void)
{
static struct lock_class_key jbd2_trans_commit_key;
journal_t *journal;
int err;
......@@ -1126,6 +1128,9 @@ static journal_t * journal_init_common (void)
spin_lock_init(&journal->j_history_lock);
lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle",
&jbd2_trans_commit_key, 0);
return journal;
}
......
......@@ -182,6 +182,8 @@ static int add_transaction_credits(journal_t *journal, int blocks,
int needed;
int total = blocks + rsv_blocks;
jbd2_might_wait_for_commit(journal);
/*
* If the current transaction is locked down for commit, wait
* for the lock to be released.
......@@ -382,13 +384,11 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
read_unlock(&journal->j_state_lock);
current->journal_info = handle;
lock_map_acquire(&handle->h_lockdep_map);
rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
jbd2_journal_free_transaction(new_transaction);
return 0;
}
static struct lock_class_key jbd2_handle_key;
/* Allocate a new handle. This should probably be in a slab... */
static handle_t *new_handle(int nblocks)
{
......@@ -398,9 +398,6 @@ static handle_t *new_handle(int nblocks)
handle->h_buffer_credits = nblocks;
handle->h_ref = 1;
lockdep_init_map(&handle->h_lockdep_map, "jbd2_handle",
&jbd2_handle_key, 0);
return handle;
}
......@@ -672,7 +669,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
if (need_to_start)
jbd2_log_start_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
handle->h_buffer_credits = nblocks;
ret = start_this_handle(journal, handle, gfp_mask);
return ret;
......@@ -700,6 +697,8 @@ void jbd2_journal_lock_updates(journal_t *journal)
{
DEFINE_WAIT(wait);
jbd2_might_wait_for_commit(journal);
write_lock(&journal->j_state_lock);
++journal->j_barrier_count;
......@@ -1750,11 +1749,11 @@ int jbd2_journal_stop(handle_t *handle)
wake_up(&journal->j_wait_transaction_locked);
}
rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
if (wait_for_commit)
err = jbd2_log_wait_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
if (handle->h_rsv_handle)
jbd2_journal_free_reserved(handle->h_rsv_handle);
free_and_exit:
......
......@@ -491,10 +491,6 @@ struct jbd2_journal_handle
unsigned long h_start_jiffies;
unsigned int h_requested_credits;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map h_lockdep_map;
#endif
};
......@@ -793,6 +789,7 @@ jbd2_time_diff(unsigned long start, unsigned long end)
* @j_proc_entry: procfs entry for the jbd statistics directory
* @j_stats: Overall statistics
* @j_private: An opaque pointer to fs-private information.
* @j_trans_commit_map: Lockdep entity to track transaction commit dependencies
*/
struct journal_s
......@@ -1035,8 +1032,26 @@ struct journal_s
/* Precomputed journal UUID checksum for seeding other checksums */
__u32 j_csum_seed;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Lockdep entity to track transaction commit dependencies. Handles
* hold this "lock" for read, when we wait for commit, we acquire the
* "lock" for writing. This matches the properties of jbd2 journalling
* where the running transaction has to wait for all handles to be
* dropped to commit that transaction and also acquiring a handle may
* require transaction commit to finish.
*/
struct lockdep_map j_trans_commit_map;
#endif
};
#define jbd2_might_wait_for_commit(j) \
do { \
rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \
rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \
} while (0)
/* journal feature predicate functions */
#define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \
static inline bool jbd2_has_feature_##name(journal_t *j) \
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment