linux/drivers/md/dm-crypt.c

2104 lines
50 KiB
C
Raw Normal View History

/*
* Copyright (C) 2003 Jana Saout <jana@saout.de>
* Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
* Copyright (C) 2006-2015 Red Hat, Inc. All rights reserved.
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
* Copyright (C) 2013 Milan Broz <gmazyland@gmail.com>
*
* This file is released under the GPL.
*/
#include <linux/completion.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/crypto.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/backing-dev.h>
#include <linux/atomic.h>
#include <linux/scatterlist.h>
#include <linux/rbtree.h>
#include <asm/page.h>
#include <asm/unaligned.h>
#include <crypto/hash.h>
#include <crypto/md5.h>
#include <crypto/algapi.h>
#include <crypto/skcipher.h>
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "crypt"
/*
* context holding the current state of a multi-part conversion
*/
struct convert_context {
struct completion restart;
struct bio *bio_in;
struct bio *bio_out;
struct bvec_iter iter_in;
struct bvec_iter iter_out;
sector_t cc_sector;
atomic_t cc_pending;
struct skcipher_request *req;
};
/*
* per bio private data
*/
struct dm_crypt_io {
struct crypt_config *cc;
struct bio *base_bio;
struct work_struct work;
struct convert_context ctx;
atomic_t io_pending;
int error;
sector_t sector;
struct rb_node rb_node;
} CRYPTO_MINALIGN_ATTR;
struct dm_crypt_request {
struct convert_context *ctx;
struct scatterlist sg_in;
struct scatterlist sg_out;
sector_t iv_sector;
};
struct crypt_config;
struct crypt_iv_operations {
int (*ctr)(struct crypt_config *cc, struct dm_target *ti,
const char *opts);
void (*dtr)(struct crypt_config *cc);
int (*init)(struct crypt_config *cc);
int (*wipe)(struct crypt_config *cc);
int (*generator)(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq);
int (*post)(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq);
};
struct iv_essiv_private {
struct crypto_ahash *hash_tfm;
u8 *salt;
};
struct iv_benbi_private {
int shift;
};
#define LMK_SEED_SIZE 64 /* hash + 0 */
struct iv_lmk_private {
struct crypto_shash *hash_tfm;
u8 *seed;
};
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
#define TCW_WHITENING_SIZE 16
struct iv_tcw_private {
struct crypto_shash *crc32_tfm;
u8 *iv_seed;
u8 *whitening;
};
/*
* Crypt: maps a linear range of a block device
* and encrypts / decrypts at the same time.
*/
enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
dm crypt: fix a possible hang due to race condition on exit A kernel thread executes __set_current_state(TASK_INTERRUPTIBLE), __add_wait_queue, spin_unlock_irq and then tests kthread_should_stop(). It is possible that the processor reorders memory accesses so that kthread_should_stop() is executed before __set_current_state(). If such reordering happens, there is a possible race on thread termination: CPU 0: calls kthread_should_stop() it tests KTHREAD_SHOULD_STOP bit, returns false CPU 1: calls kthread_stop(cc->write_thread) sets the KTHREAD_SHOULD_STOP bit calls wake_up_process on the kernel thread, that sets the thread state to TASK_RUNNING CPU 0: sets __set_current_state(TASK_INTERRUPTIBLE) spin_unlock_irq(&cc->write_thread_wait.lock) schedule() - and the process is stuck and never terminates, because the state is TASK_INTERRUPTIBLE and wake_up_process on CPU 1 already terminated Fix this race condition by using a new flag DM_CRYPT_EXIT_THREAD to signal that the kernel thread should exit. The flag is set and tested while holding cc->write_thread_wait.lock, so there is no possibility of racy access to the flag. Also, remove the unnecessary set_task_state(current, TASK_RUNNING) following the schedule() call. When the process was woken up, its state was already set to TASK_RUNNING. Other kernel code also doesn't set the state to TASK_RUNNING following schedule() (for example, do_wait_for_common in completion.c doesn't do it). Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-11-19 12:36:50 +00:00
DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
DM_CRYPT_EXIT_THREAD};
/*
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
* The fields in here must be read only after initialization.
*/
struct crypt_config {
struct dm_dev *dev;
sector_t start;
/*
* pool for per bio private data, crypto requests and
* encryption requeusts/buffer pages
*/
mempool_t *req_pool;
mempool_t *page_pool;
struct bio_set *bs;
struct mutex bio_alloc_lock;
struct workqueue_struct *io_queue;
struct workqueue_struct *crypt_queue;
struct task_struct *write_thread;
wait_queue_head_t write_thread_wait;
struct rb_root write_tree;
char *cipher;
char *cipher_string;
struct crypt_iv_operations *iv_gen_ops;
union {
struct iv_essiv_private essiv;
struct iv_benbi_private benbi;
struct iv_lmk_private lmk;
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
struct iv_tcw_private tcw;
} iv_gen_private;
sector_t iv_offset;
unsigned int iv_size;
/* ESSIV: struct crypto_cipher *essiv_tfm */
void *iv_private;
struct crypto_skcipher **tfms;
unsigned tfms_count;
/*
* Layout of each crypto request:
*
* struct skcipher_request
* context
* padding
* struct dm_crypt_request
* padding
* IV
*
* The padding is added so that dm_crypt_request and the IV are
* correctly aligned.
*/
unsigned int dmreq_start;
unsigned int per_bio_data_size;
unsigned long flags;
unsigned int key_size;
unsigned int key_parts; /* independent parts in key buffer */
unsigned int key_extra_size; /* additional keys length */
u8 key[0];
};
#define MIN_IOS 16
static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
/*
* Use this to access cipher attributes that are the same for each CPU.
*/
static struct crypto_skcipher *any_tfm(struct crypt_config *cc)
{
return cc->tfms[0];
}
/*
* Different IV generation algorithms:
*
* plain: the initial vector is the 32-bit little-endian version of the sector
* number, padded with zeros if necessary.
*
* plain64: the initial vector is the 64-bit little-endian version of the sector
* number, padded with zeros if necessary.
*
* essiv: "encrypted sector|salt initial vector", the sector number is
* encrypted with the bulk cipher using a salt as key. The salt
* should be derived from the bulk cipher's key via hashing.
*
* benbi: the 64-bit "big-endian 'narrow block'-count", starting at 1
* (needed for LRW-32-AES and possible other narrow block modes)
*
* null: the initial vector is always zero. Provides compatibility with
* obsolete loop_fish2 devices. Do not use for new devices.
*
* lmk: Compatible implementation of the block chaining mode used
* by the Loop-AES block device encryption system
* designed by Jari Ruusu. See http://loop-aes.sourceforge.net/
* It operates on full 512 byte sectors and uses CBC
* with an IV derived from the sector number, the data and
* optionally extra IV seed.
* This means that after decryption the first block
* of sector must be tweaked according to decrypted data.
* Loop-AES can use three encryption schemes:
* version 1: is plain aes-cbc mode
* version 2: uses 64 multikey scheme with lmk IV generator
* version 3: the same as version 2 with additional IV seed
* (it uses 65 keys, last key is used as IV seed)
*
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
* tcw: Compatible implementation of the block chaining mode used
* by the TrueCrypt device encryption system (prior to version 4.1).
* For more info see: https://gitlab.com/cryptsetup/cryptsetup/wikis/TrueCryptOnDiskFormat
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
* It operates on full 512 byte sectors and uses CBC
* with an IV derived from initial key and the sector number.
* In addition, whitening value is applied on every sector, whitening
* is calculated from initial key, sector number and mixed using CRC32.
* Note that this encryption scheme is vulnerable to watermarking attacks
* and should be used for old compatible containers access only.
*
* plumb: unimplemented, see:
* http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454
*/
static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
memset(iv, 0, cc->iv_size);
*(__le32 *)iv = cpu_to_le32(dmreq->iv_sector & 0xffffffff);
return 0;
}
static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
memset(iv, 0, cc->iv_size);
*(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);
return 0;
}
/* Initialise ESSIV - compute salt but no local memory allocations */
static int crypt_iv_essiv_init(struct crypt_config *cc)
{
struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
AHASH_REQUEST_ON_STACK(req, essiv->hash_tfm);
struct scatterlist sg;
struct crypto_cipher *essiv_tfm;
int err;
sg_init_one(&sg, cc->key, cc->key_size);
ahash_request_set_tfm(req, essiv->hash_tfm);
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
ahash_request_set_crypt(req, &sg, essiv->salt, cc->key_size);
err = crypto_ahash_digest(req);
ahash_request_zero(req);
if (err)
return err;
essiv_tfm = cc->iv_private;
err = crypto_cipher_setkey(essiv_tfm, essiv->salt,
crypto_ahash_digestsize(essiv->hash_tfm));
if (err)
return err;
return 0;
}
/* Wipe salt and reset key derived from volume key */
static int crypt_iv_essiv_wipe(struct crypt_config *cc)
{
struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
unsigned salt_size = crypto_ahash_digestsize(essiv->hash_tfm);
struct crypto_cipher *essiv_tfm;
int r, err = 0;
memset(essiv->salt, 0, salt_size);
essiv_tfm = cc->iv_private;
r = crypto_cipher_setkey(essiv_tfm, essiv->salt, salt_size);
if (r)
err = r;
return err;
}
/* Set up per cpu cipher state */
static struct crypto_cipher *setup_essiv_cpu(struct crypt_config *cc,
struct dm_target *ti,
u8 *salt, unsigned saltsize)
{
struct crypto_cipher *essiv_tfm;
int err;
/* Setup the essiv_tfm with the given salt */
essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(essiv_tfm)) {
ti->error = "Error allocating crypto tfm for ESSIV";
return essiv_tfm;
}
if (crypto_cipher_blocksize(essiv_tfm) !=
crypto_skcipher_ivsize(any_tfm(cc))) {
ti->error = "Block size of ESSIV cipher does "
"not match IV size of block cipher";
crypto_free_cipher(essiv_tfm);
return ERR_PTR(-EINVAL);
}
err = crypto_cipher_setkey(essiv_tfm, salt, saltsize);
if (err) {
ti->error = "Failed to set key for ESSIV cipher";
crypto_free_cipher(essiv_tfm);
return ERR_PTR(err);
}
return essiv_tfm;
}
static void crypt_iv_essiv_dtr(struct crypt_config *cc)
{
struct crypto_cipher *essiv_tfm;
struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
crypto_free_ahash(essiv->hash_tfm);
essiv->hash_tfm = NULL;
kzfree(essiv->salt);
essiv->salt = NULL;
essiv_tfm = cc->iv_private;
if (essiv_tfm)
crypto_free_cipher(essiv_tfm);
cc->iv_private = NULL;
}
static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
const char *opts)
{
struct crypto_cipher *essiv_tfm = NULL;
struct crypto_ahash *hash_tfm = NULL;
u8 *salt = NULL;
int err;
if (!opts) {
ti->error = "Digest algorithm missing for ESSIV mode";
return -EINVAL;
}
/* Allocate hash algorithm */
hash_tfm = crypto_alloc_ahash(opts, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(hash_tfm)) {
ti->error = "Error initializing ESSIV hash";
err = PTR_ERR(hash_tfm);
goto bad;
}
salt = kzalloc(crypto_ahash_digestsize(hash_tfm), GFP_KERNEL);
if (!salt) {
ti->error = "Error kmallocing salt storage in ESSIV";
err = -ENOMEM;
goto bad;
}
cc->iv_gen_private.essiv.salt = salt;
cc->iv_gen_private.essiv.hash_tfm = hash_tfm;
essiv_tfm = setup_essiv_cpu(cc, ti, salt,
crypto_ahash_digestsize(hash_tfm));
if (IS_ERR(essiv_tfm)) {
crypt_iv_essiv_dtr(cc);
return PTR_ERR(essiv_tfm);
}
cc->iv_private = essiv_tfm;
return 0;
bad:
if (hash_tfm && !IS_ERR(hash_tfm))
crypto_free_ahash(hash_tfm);
kfree(salt);
return err;
}
static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
struct crypto_cipher *essiv_tfm = cc->iv_private;
memset(iv, 0, cc->iv_size);
*(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);
crypto_cipher_encrypt_one(essiv_tfm, iv, iv);
return 0;
}
static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
const char *opts)
{
unsigned bs = crypto_skcipher_blocksize(any_tfm(cc));
int log = ilog2(bs);
/* we need to calculate how far we must shift the sector count
* to get the cipher block count, we use this shift in _gen */
if (1 << log != bs) {
ti->error = "cypher blocksize is not a power of 2";
return -EINVAL;
}
if (log > 9) {
ti->error = "cypher blocksize is > 512";
return -EINVAL;
}
cc->iv_gen_private.benbi.shift = 9 - log;
return 0;
}
static void crypt_iv_benbi_dtr(struct crypt_config *cc)
{
}
static int crypt_iv_benbi_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
__be64 val;
memset(iv, 0, cc->iv_size - sizeof(u64)); /* rest is cleared below */
val = cpu_to_be64(((u64)dmreq->iv_sector << cc->iv_gen_private.benbi.shift) + 1);
put_unaligned(val, (__be64 *)(iv + cc->iv_size - sizeof(u64)));
return 0;
}
static int crypt_iv_null_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
memset(iv, 0, cc->iv_size);
return 0;
}
static void crypt_iv_lmk_dtr(struct crypt_config *cc)
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
if (lmk->hash_tfm && !IS_ERR(lmk->hash_tfm))
crypto_free_shash(lmk->hash_tfm);
lmk->hash_tfm = NULL;
kzfree(lmk->seed);
lmk->seed = NULL;
}
static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti,
const char *opts)
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(lmk->hash_tfm)) {
ti->error = "Error initializing LMK hash";
return PTR_ERR(lmk->hash_tfm);
}
/* No seed in LMK version 2 */
if (cc->key_parts == cc->tfms_count) {
lmk->seed = NULL;
return 0;
}
lmk->seed = kzalloc(LMK_SEED_SIZE, GFP_KERNEL);
if (!lmk->seed) {
crypt_iv_lmk_dtr(cc);
ti->error = "Error kmallocing seed storage in LMK";
return -ENOMEM;
}
return 0;
}
static int crypt_iv_lmk_init(struct crypt_config *cc)
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
int subkey_size = cc->key_size / cc->key_parts;
/* LMK seed is on the position of LMK_KEYS + 1 key */
if (lmk->seed)
memcpy(lmk->seed, cc->key + (cc->tfms_count * subkey_size),
crypto_shash_digestsize(lmk->hash_tfm));
return 0;
}
static int crypt_iv_lmk_wipe(struct crypt_config *cc)
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
if (lmk->seed)
memset(lmk->seed, 0, LMK_SEED_SIZE);
return 0;
}
static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq,
u8 *data)
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
SHASH_DESC_ON_STACK(desc, lmk->hash_tfm);
struct md5_state md5state;
__le32 buf[4];
int i, r;
desc->tfm = lmk->hash_tfm;
desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
r = crypto_shash_init(desc);
if (r)
return r;
if (lmk->seed) {
r = crypto_shash_update(desc, lmk->seed, LMK_SEED_SIZE);
if (r)
return r;
}
/* Sector is always 512B, block size 16, add data of blocks 1-31 */
r = crypto_shash_update(desc, data + 16, 16 * 31);
if (r)
return r;
/* Sector is cropped to 56 bits here */
buf[0] = cpu_to_le32(dmreq->iv_sector & 0xFFFFFFFF);
buf[1] = cpu_to_le32((((u64)dmreq->iv_sector >> 32) & 0x00FFFFFF) | 0x80000000);
buf[2] = cpu_to_le32(4024);
buf[3] = 0;
r = crypto_shash_update(desc, (u8 *)buf, sizeof(buf));
if (r)
return r;
/* No MD5 padding here */
r = crypto_shash_export(desc, &md5state);
if (r)
return r;
for (i = 0; i < MD5_HASH_WORDS; i++)
__cpu_to_le32s(&md5state.hash[i]);
memcpy(iv, &md5state.hash, cc->iv_size);
return 0;
}
static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
u8 *src;
int r = 0;
if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
src = kmap_atomic(sg_page(&dmreq->sg_in));
r = crypt_iv_lmk_one(cc, iv, dmreq, src + dmreq->sg_in.offset);
kunmap_atomic(src);
} else
memset(iv, 0, cc->iv_size);
return r;
}
static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
u8 *dst;
int r;
if (bio_data_dir(dmreq->ctx->bio_in) == WRITE)
return 0;
dst = kmap_atomic(sg_page(&dmreq->sg_out));
r = crypt_iv_lmk_one(cc, iv, dmreq, dst + dmreq->sg_out.offset);
/* Tweak the first block of plaintext sector */
if (!r)
crypto_xor(dst + dmreq->sg_out.offset, iv, cc->iv_size);
kunmap_atomic(dst);
return r;
}
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
static void crypt_iv_tcw_dtr(struct crypt_config *cc)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
kzfree(tcw->iv_seed);
tcw->iv_seed = NULL;
kzfree(tcw->whitening);
tcw->whitening = NULL;
if (tcw->crc32_tfm && !IS_ERR(tcw->crc32_tfm))
crypto_free_shash(tcw->crc32_tfm);
tcw->crc32_tfm = NULL;
}
static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti,
const char *opts)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
if (cc->key_size <= (cc->iv_size + TCW_WHITENING_SIZE)) {
ti->error = "Wrong key size for TCW";
return -EINVAL;
}
tcw->crc32_tfm = crypto_alloc_shash("crc32", 0, 0);
if (IS_ERR(tcw->crc32_tfm)) {
ti->error = "Error initializing CRC32 in TCW";
return PTR_ERR(tcw->crc32_tfm);
}
tcw->iv_seed = kzalloc(cc->iv_size, GFP_KERNEL);
tcw->whitening = kzalloc(TCW_WHITENING_SIZE, GFP_KERNEL);
if (!tcw->iv_seed || !tcw->whitening) {
crypt_iv_tcw_dtr(cc);
ti->error = "Error allocating seed storage in TCW";
return -ENOMEM;
}
return 0;
}
static int crypt_iv_tcw_init(struct crypt_config *cc)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
int key_offset = cc->key_size - cc->iv_size - TCW_WHITENING_SIZE;
memcpy(tcw->iv_seed, &cc->key[key_offset], cc->iv_size);
memcpy(tcw->whitening, &cc->key[key_offset + cc->iv_size],
TCW_WHITENING_SIZE);
return 0;
}
static int crypt_iv_tcw_wipe(struct crypt_config *cc)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
memset(tcw->iv_seed, 0, cc->iv_size);
memset(tcw->whitening, 0, TCW_WHITENING_SIZE);
return 0;
}
static int crypt_iv_tcw_whitening(struct crypt_config *cc,
struct dm_crypt_request *dmreq,
u8 *data)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
u8 buf[TCW_WHITENING_SIZE];
SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm);
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
int i, r;
/* xor whitening with sector number */
memcpy(buf, tcw->whitening, TCW_WHITENING_SIZE);
crypto_xor(buf, (u8 *)&sector, 8);
crypto_xor(&buf[8], (u8 *)&sector, 8);
/* calculate crc32 for every 32bit part and xor it */
desc->tfm = tcw->crc32_tfm;
desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
for (i = 0; i < 4; i++) {
r = crypto_shash_init(desc);
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
if (r)
goto out;
r = crypto_shash_update(desc, &buf[i * 4], 4);
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
if (r)
goto out;
r = crypto_shash_final(desc, &buf[i * 4]);
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
if (r)
goto out;
}
crypto_xor(&buf[0], &buf[12], 4);
crypto_xor(&buf[4], &buf[8], 4);
/* apply whitening (8 bytes) to whole sector */
for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++)
crypto_xor(data + i * 8, buf, 8);
out:
memzero_explicit(buf, sizeof(buf));
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
return r;
}
static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
u8 *src;
int r = 0;
/* Remove whitening from ciphertext */
if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) {
src = kmap_atomic(sg_page(&dmreq->sg_in));
r = crypt_iv_tcw_whitening(cc, dmreq, src + dmreq->sg_in.offset);
kunmap_atomic(src);
}
/* Calculate IV */
memcpy(iv, tcw->iv_seed, cc->iv_size);
crypto_xor(iv, (u8 *)&sector, 8);
if (cc->iv_size > 8)
crypto_xor(&iv[8], (u8 *)&sector, cc->iv_size - 8);
return r;
}
static int crypt_iv_tcw_post(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
u8 *dst;
int r;
if (bio_data_dir(dmreq->ctx->bio_in) != WRITE)
return 0;
/* Apply whitening on ciphertext */
dst = kmap_atomic(sg_page(&dmreq->sg_out));
r = crypt_iv_tcw_whitening(cc, dmreq, dst + dmreq->sg_out.offset);
kunmap_atomic(dst);
return r;
}
static struct crypt_iv_operations crypt_iv_plain_ops = {
.generator = crypt_iv_plain_gen
};
static struct crypt_iv_operations crypt_iv_plain64_ops = {
.generator = crypt_iv_plain64_gen
};
static struct crypt_iv_operations crypt_iv_essiv_ops = {
.ctr = crypt_iv_essiv_ctr,
.dtr = crypt_iv_essiv_dtr,
.init = crypt_iv_essiv_init,
.wipe = crypt_iv_essiv_wipe,
.generator = crypt_iv_essiv_gen
};
static struct crypt_iv_operations crypt_iv_benbi_ops = {
.ctr = crypt_iv_benbi_ctr,
.dtr = crypt_iv_benbi_dtr,
.generator = crypt_iv_benbi_gen
};
static struct crypt_iv_operations crypt_iv_null_ops = {
.generator = crypt_iv_null_gen
};
static struct crypt_iv_operations crypt_iv_lmk_ops = {
.ctr = crypt_iv_lmk_ctr,
.dtr = crypt_iv_lmk_dtr,
.init = crypt_iv_lmk_init,
.wipe = crypt_iv_lmk_wipe,
.generator = crypt_iv_lmk_gen,
.post = crypt_iv_lmk_post
};
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
static struct crypt_iv_operations crypt_iv_tcw_ops = {
.ctr = crypt_iv_tcw_ctr,
.dtr = crypt_iv_tcw_dtr,
.init = crypt_iv_tcw_init,
.wipe = crypt_iv_tcw_wipe,
.generator = crypt_iv_tcw_gen,
.post = crypt_iv_tcw_post
};
static void crypt_convert_init(struct crypt_config *cc,
struct convert_context *ctx,
struct bio *bio_out, struct bio *bio_in,
sector_t sector)
{
ctx->bio_in = bio_in;
ctx->bio_out = bio_out;
if (bio_in)
ctx->iter_in = bio_in->bi_iter;
if (bio_out)
ctx->iter_out = bio_out->bi_iter;
ctx->cc_sector = sector + cc->iv_offset;
init_completion(&ctx->restart);
}
static struct dm_crypt_request *dmreq_of_req(struct crypt_config *cc,
struct skcipher_request *req)
{
return (struct dm_crypt_request *)((char *)req + cc->dmreq_start);
}
static struct skcipher_request *req_of_dmreq(struct crypt_config *cc,
struct dm_crypt_request *dmreq)
{
return (struct skcipher_request *)((char *)dmreq - cc->dmreq_start);
}
static u8 *iv_of_dmreq(struct crypt_config *cc,
struct dm_crypt_request *dmreq)
{
return (u8 *)ALIGN((unsigned long)(dmreq + 1),
crypto_skcipher_alignmask(any_tfm(cc)) + 1);
}
static int crypt_convert_block(struct crypt_config *cc,
struct convert_context *ctx,
struct skcipher_request *req)
{
struct bio_vec bv_in = bio_iter_iovec(ctx->bio_in, ctx->iter_in);
struct bio_vec bv_out = bio_iter_iovec(ctx->bio_out, ctx->iter_out);
struct dm_crypt_request *dmreq;
u8 *iv;
int r;
dmreq = dmreq_of_req(cc, req);
iv = iv_of_dmreq(cc, dmreq);
dmreq->iv_sector = ctx->cc_sector;
dmreq->ctx = ctx;
sg_init_table(&dmreq->sg_in, 1);
sg_set_page(&dmreq->sg_in, bv_in.bv_page, 1 << SECTOR_SHIFT,
bv_in.bv_offset);
sg_init_table(&dmreq->sg_out, 1);
sg_set_page(&dmreq->sg_out, bv_out.bv_page, 1 << SECTOR_SHIFT,
bv_out.bv_offset);
bio_advance_iter(ctx->bio_in, &ctx->iter_in, 1 << SECTOR_SHIFT);
bio_advance_iter(ctx->bio_out, &ctx->iter_out, 1 << SECTOR_SHIFT);
if (cc->iv_gen_ops) {
r = cc->iv_gen_ops->generator(cc, iv, dmreq);
if (r < 0)
return r;
}
skcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out,
1 << SECTOR_SHIFT, iv);
if (bio_data_dir(ctx->bio_in) == WRITE)
r = crypto_skcipher_encrypt(req);
else
r = crypto_skcipher_decrypt(req);
if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
r = cc->iv_gen_ops->post(cc, iv, dmreq);
return r;
}
static void kcryptd_async_done(struct crypto_async_request *async_req,
int error);
static void crypt_alloc_req(struct crypt_config *cc,
struct convert_context *ctx)
{
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
if (!ctx->req)
ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
skcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
/*
* Use REQ_MAY_BACKLOG so a cipher driver internally backlogs
* requests if driver request queue is full.
*/
skcipher_request_set_callback(ctx->req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
kcryptd_async_done, dmreq_of_req(cc, ctx->req));
}
static void crypt_free_req(struct crypt_config *cc,
struct skcipher_request *req, struct bio *base_bio)
{
struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
if ((struct skcipher_request *)(io + 1) != req)
mempool_free(req, cc->req_pool);
}
/*
* Encrypt / decrypt data from one bio to another one (can be the same one)
*/
static int crypt_convert(struct crypt_config *cc,
struct convert_context *ctx)
{
int r;
atomic_set(&ctx->cc_pending, 1);
while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
crypt_alloc_req(cc, ctx);
atomic_inc(&ctx->cc_pending);
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
r = crypt_convert_block(cc, ctx, ctx->req);
switch (r) {
/*
* The request was queued by a crypto driver
* but the driver request queue is full, let's wait.
*/
case -EBUSY:
wait_for_completion(&ctx->restart);
reinit_completion(&ctx->restart);
/* fall through */
/*
* The request is queued and processed asynchronously,
* completion function kcryptd_async_done() will be called.
*/
Revert "dm crypt: fix deadlock when async crypto algorithm returns -EBUSY" This reverts Linux 4.1-rc1 commit 0618764cb25f6fa9fb31152995de42a8a0496475. The problem which that commit attempts to fix actually lies in the Freescale CAAM crypto driver not dm-crypt. dm-crypt uses CRYPTO_TFM_REQ_MAY_BACKLOG. This means the the crypto driver should internally backlog requests which arrive when the queue is full and process them later. Until the crypto hw's queue becomes full, the driver returns -EINPROGRESS. When the crypto hw's queue if full, the driver returns -EBUSY, and if CRYPTO_TFM_REQ_MAY_BACKLOG is set, is expected to backlog the request and process it when the hardware has queue space. At the point when the driver takes the request from the backlog and starts processing it, it calls the completion function with a status of -EINPROGRESS. The completion function is called (for a second time, in the case of backlogged requests) with a status/err of 0 when a request is done. Crypto drivers for hardware without hardware queueing use the helpers, crypto_init_queue(), crypto_enqueue_request(), crypto_dequeue_request() and crypto_get_backlog() helpers to implement this behaviour correctly, while others implement this behaviour without these helpers (ccp, for example). dm-crypt (before the patch that needs reverting) uses this API correctly. It queues up as many requests as the hw queues will allow (i.e. as long as it gets back -EINPROGRESS from the request function). Then, when it sees at least one backlogged request (gets -EBUSY), it waits till that backlogged request is handled (completion gets called with -EINPROGRESS), and then continues. The references to af_alg_wait_for_completion() and af_alg_complete() in that commit's commit message are irrelevant because those functions only handle one request at a time, unlink dm-crypt. The problem is that the Freescale CAAM driver, which that commit describes as having being tested with, fails to implement the backlogging behaviour correctly. In cam_jr_enqueue(), if the hardware queue is full, it simply returns -EBUSY without backlogging the request. What the observed deadlock was is not described in the commit message but it is obviously the wait_for_completion() in crypto_convert() where dm-crypto would wait for the completion being called with -EINPROGRESS in the case of backlogged requests. This completion will never be completed due to the bug in the CAAM driver. Commit 0618764cb25 incorrectly made dm-crypt wait for every request, even when the driver/hardware queues are not full, which means that dm-crypt will never see -EBUSY. This means that that commit will cause a performance regression on all crypto drivers which implement the API correctly. Revert it. Correct backlog handling should be implemented in the CAAM driver instead. Cc'ing stable purely because commit 0618764cb25 did. If for some reason a stable@ kernel did pick up commit 0618764cb25 it should get reverted. Signed-off-by: Rabin Vincent <rabin.vincent@axis.com> Reviewed-by: Horia Geanta <horia.geanta@freescale.com> Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-05-05 13:15:56 +00:00
case -EINPROGRESS:
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
ctx->req = NULL;
ctx->cc_sector++;
continue;
/*
* The request was already processed (synchronously).
*/
case 0:
atomic_dec(&ctx->cc_pending);
ctx->cc_sector++;
cond_resched();
continue;
/* There was an error while processing the request. */
default:
atomic_dec(&ctx->cc_pending);
return r;
}
}
return 0;
}
static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
/*
* Generate a new unfragmented bio with the given size
dm crypt: constrain crypt device's max_segment_size to PAGE_SIZE Setting the dm-crypt device's max_segment_size to PAGE_SIZE is an unfortunate constraint that is required to avoid the potential for exceeding dm-crypt's underlying device's max_segments limits -- due to crypt_alloc_buffer() possibly allocating pages for the encryption bio that are not as physically contiguous as the original bio. It is interesting to note that this problem was already fixed back in 2007 via commit 91e106259 ("dm crypt: use bio_add_page"). But Linux 4.0 commit cf2f1abfb ("dm crypt: don't allocate pages for a partial request") regressed dm-crypt back to _not_ using bio_add_page(). But given dm-crypt's cpu parallelization changes all depend on commit cf2f1abfb's abandoning of the more complex io fragments processing that dm-crypt previously had we cannot easily go back to using bio_add_page(). So all said the cleanest way to resolve this issue is to fix dm-crypt to properly constrain the original bios entering dm-crypt so the encryption bios that dm-crypt generates from the original bios are always compatible with the underlying device's max_segments queue limits. It should be noted that technically Linux 4.3 does _not_ need this fix because of the block core's new late bio-splitting capability. But, it is reasoned, there is little to be gained by having the block core split the encrypted bio that is composed of PAGE_SIZE segments. That said, in the future we may revert this change. Fixes: cf2f1abfb ("dm crypt: don't allocate pages for a partial request") Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=104421 Suggested-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.0+
2015-09-10 01:34:51 +00:00
* This should never violate the device limitations (but only because
* max_segment_size is being constrained to PAGE_SIZE).
*
* This function may be called concurrently. If we allocate from the mempool
* concurrently, there is a possibility of deadlock. For example, if we have
* mempool of 256 pages, two processes, each wanting 256, pages allocate from
* the mempool concurrently, it may deadlock in a situation where both processes
* have allocated 128 pages and the mempool is exhausted.
*
* In order to avoid this scenario we allocate the pages under a mutex.
*
* In order to not degrade performance with excessive locking, we try
* non-blocking allocations without a mutex first but on failure we fallback
* to blocking allocations with a mutex.
*/
static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
unsigned i, len, remaining_size;
struct page *page;
struct bio_vec *bvec;
retry:
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
mutex_lock(&cc->bio_alloc_lock);
clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
if (!clone)
goto return_clone;
clone_init(io, clone);
remaining_size = size;
for (i = 0; i < nr_iovecs; i++) {
page = mempool_alloc(cc->page_pool, gfp_mask);
if (!page) {
crypt_free_buffer_pages(cc, clone);
bio_put(clone);
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
gfp_mask |= __GFP_DIRECT_RECLAIM;
goto retry;
}
len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
bvec = &clone->bi_io_vec[clone->bi_vcnt++];
bvec->bv_page = page;
bvec->bv_len = len;
bvec->bv_offset = 0;
clone->bi_iter.bi_size += len;
remaining_size -= len;
}
return_clone:
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
mutex_unlock(&cc->bio_alloc_lock);
return clone;
}
static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
{
unsigned int i;
struct bio_vec *bv;
bio_for_each_segment_all(bv, clone, i) {
BUG_ON(!bv->bv_page);
mempool_free(bv->bv_page, cc->page_pool);
bv->bv_page = NULL;
}
}
static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
struct bio *bio, sector_t sector)
{
io->cc = cc;
io->base_bio = bio;
io->sector = sector;
io->error = 0;
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
io->ctx.req = NULL;
atomic_set(&io->io_pending, 0);
}
static void crypt_inc_pending(struct dm_crypt_io *io)
{
atomic_inc(&io->io_pending);
}
/*
* One of the bios was finished. Check for completion of
* the whole request and correctly clean up the buffer.
*/
static void crypt_dec_pending(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
struct bio *base_bio = io->base_bio;
int error = io->error;
if (!atomic_dec_and_test(&io->io_pending))
return;
dm crypt: fix cpu hotplug crash by removing per-cpu structure The DM crypt target used per-cpu structures to hold pointers to a ablkcipher_request structure. The code assumed that the work item keeps executing on a single CPU, so it didn't use synchronization when accessing this structure. If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online, the work item could be moved to another CPU. This causes dm-crypt crashes, like the following, because the code starts using an incorrect ablkcipher_request: smpboot: CPU 7 is now offline BUG: unable to handle kernel NULL pointer dereference at 0000000000000130 IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt] ... Call Trace: [<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt] [<ffffffff81062060>] ? finish_task_switch+0x40/0xc0 [<ffffffff81052a28>] ? process_one_work+0x168/0x470 [<ffffffff8105366b>] ? worker_thread+0x10b/0x390 [<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290 [<ffffffff81058d9f>] ? kthread+0xaf/0xc0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 [<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0 [<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120 Fix this bug by removing the per-cpu definition. The structure ablkcipher_request is accessed via a pointer from convert_context. Consequently, if the work item is rescheduled to a different CPU, the thread still uses the same ablkcipher_request. This change may undermine performance improvements intended by commit c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In practice no performance difference was observed on recent hardware. But regardless, correctness is more important than performance. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org
2014-02-20 23:01:01 +00:00
if (io->ctx.req)
crypt_free_req(cc, io->ctx.req, base_bio);
base_bio->bi_error = error;
bio_endio(base_bio);
}
/*
* kcryptd/kcryptd_io:
*
* Needed because it would be very unwise to do decryption in an
* interrupt context.
*
* kcryptd performs the actual encryption or decryption.
*
* kcryptd_io performs the IO submission.
*
* They must be separated as otherwise the final stages could be
* starved by new requests which can block in the first stages due
* to memory allocation.
*
* The work is done per CPU global for all dm-crypt instances.
* They should not depend on each other and do not block.
*/
static void crypt_endio(struct bio *clone)
{
struct dm_crypt_io *io = clone->bi_private;
struct crypt_config *cc = io->cc;
unsigned rw = bio_data_dir(clone);
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-10 23:05:18 +00:00
int error;
/*
* free the processed pages
*/
if (rw == WRITE)
crypt_free_buffer_pages(cc, clone);
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-10 23:05:18 +00:00
error = clone->bi_error;
bio_put(clone);
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-10 23:05:18 +00:00
if (rw == READ && !error) {
kcryptd_queue_crypt(io);
return;
}
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-10 23:05:18 +00:00
if (unlikely(error))
io->error = error;
crypt_dec_pending(io);
}
static void clone_init(struct dm_crypt_io *io, struct bio *clone)
{
struct crypt_config *cc = io->cc;
clone->bi_private = io;
clone->bi_end_io = crypt_endio;
clone->bi_bdev = cc->dev->bdev;
bio_set_op_attrs(clone, bio_op(io->base_bio), io->base_bio->bi_rw);
}
static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
/*
* We need the original biovec array in order to decrypt
* the whole bio data *afterwards* -- thanks to immutable
* biovecs we don't need to worry about the block layer
* modifying the biovec array; so leverage bio_clone_fast().
*/
clone = bio_clone_fast(io->base_bio, gfp, cc->bs);
if (!clone)
return 1;
crypt_inc_pending(io);
clone_init(io, clone);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
clone->bi_iter.bi_sector = cc->start + io->sector;
generic_make_request(clone);
return 0;
}
static void kcryptd_io_read_work(struct work_struct *work)
{
struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
crypt_inc_pending(io);
if (kcryptd_io_read(io, GFP_NOIO))
io->error = -ENOMEM;
crypt_dec_pending(io);
}
static void kcryptd_queue_read(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
INIT_WORK(&io->work, kcryptd_io_read_work);
queue_work(cc->io_queue, &io->work);
}
static void kcryptd_io_write(struct dm_crypt_io *io)
{
struct bio *clone = io->ctx.bio_out;
generic_make_request(clone);
}
#define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node)
static int dmcrypt_write(void *data)
{
struct crypt_config *cc = data;
struct dm_crypt_io *io;
while (1) {
struct rb_root write_tree;
struct blk_plug plug;
DECLARE_WAITQUEUE(wait, current);
spin_lock_irq(&cc->write_thread_wait.lock);
continue_locked:
if (!RB_EMPTY_ROOT(&cc->write_tree))
goto pop_from_list;
dm crypt: fix a possible hang due to race condition on exit A kernel thread executes __set_current_state(TASK_INTERRUPTIBLE), __add_wait_queue, spin_unlock_irq and then tests kthread_should_stop(). It is possible that the processor reorders memory accesses so that kthread_should_stop() is executed before __set_current_state(). If such reordering happens, there is a possible race on thread termination: CPU 0: calls kthread_should_stop() it tests KTHREAD_SHOULD_STOP bit, returns false CPU 1: calls kthread_stop(cc->write_thread) sets the KTHREAD_SHOULD_STOP bit calls wake_up_process on the kernel thread, that sets the thread state to TASK_RUNNING CPU 0: sets __set_current_state(TASK_INTERRUPTIBLE) spin_unlock_irq(&cc->write_thread_wait.lock) schedule() - and the process is stuck and never terminates, because the state is TASK_INTERRUPTIBLE and wake_up_process on CPU 1 already terminated Fix this race condition by using a new flag DM_CRYPT_EXIT_THREAD to signal that the kernel thread should exit. The flag is set and tested while holding cc->write_thread_wait.lock, so there is no possibility of racy access to the flag. Also, remove the unnecessary set_task_state(current, TASK_RUNNING) following the schedule() call. When the process was woken up, its state was already set to TASK_RUNNING. Other kernel code also doesn't set the state to TASK_RUNNING following schedule() (for example, do_wait_for_common in completion.c doesn't do it). Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-11-19 12:36:50 +00:00
if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) {
spin_unlock_irq(&cc->write_thread_wait.lock);
break;
}
__set_current_state(TASK_INTERRUPTIBLE);
__add_wait_queue(&cc->write_thread_wait, &wait);
spin_unlock_irq(&cc->write_thread_wait.lock);
schedule();
spin_lock_irq(&cc->write_thread_wait.lock);
__remove_wait_queue(&cc->write_thread_wait, &wait);
goto continue_locked;
pop_from_list:
write_tree = cc->write_tree;
cc->write_tree = RB_ROOT;
spin_unlock_irq(&cc->write_thread_wait.lock);
BUG_ON(rb_parent(write_tree.rb_node));
/*
* Note: we cannot walk the tree here with rb_next because
* the structures may be freed when kcryptd_io_write is called.
*/
blk_start_plug(&plug);
do {
io = crypt_io_from_node(rb_first(&write_tree));
rb_erase(&io->rb_node, &write_tree);
kcryptd_io_write(io);
} while (!RB_EMPTY_ROOT(&write_tree));
blk_finish_plug(&plug);
}
return 0;
}
static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
{
struct bio *clone = io->ctx.bio_out;
struct crypt_config *cc = io->cc;
unsigned long flags;
sector_t sector;
struct rb_node **rbp, *parent;
if (unlikely(io->error < 0)) {
crypt_free_buffer_pages(cc, clone);
bio_put(clone);
crypt_dec_pending(io);
return;
}
/* crypt_convert should have filled the clone bio */
BUG_ON(io->ctx.iter_out.bi_size);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
clone->bi_iter.bi_sector = cc->start + io->sector;
if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) {
generic_make_request(clone);
return;
}
spin_lock_irqsave(&cc->write_thread_wait.lock, flags);
rbp = &cc->write_tree.rb_node;
parent = NULL;
sector = io->sector;
while (*rbp) {
parent = *rbp;
if (sector < crypt_io_from_node(parent)->sector)
rbp = &(*rbp)->rb_left;
else
rbp = &(*rbp)->rb_right;
}
rb_link_node(&io->rb_node, parent, rbp);
rb_insert_color(&io->rb_node, &cc->write_tree);
wake_up_locked(&cc->write_thread_wait);
spin_unlock_irqrestore(&cc->write_thread_wait.lock, flags);
}
static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
int crypt_finished;
sector_t sector = io->sector;
int r;
/*
* Prevent io from disappearing until this function completes.
*/
crypt_inc_pending(io);
crypt_convert_init(cc, &io->ctx, NULL, io->base_bio, sector);
clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
if (unlikely(!clone)) {
io->error = -EIO;
goto dec;
}
io->ctx.bio_out = clone;
io->ctx.iter_out = clone->bi_iter;
sector += bio_sectors(clone);
crypt_inc_pending(io);
r = crypt_convert(cc, &io->ctx);
if (r)
io->error = -EIO;
crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
/* Encryption was already finished, submit io now */
if (crypt_finished) {
kcryptd_crypt_write_io_submit(io, 0);
io->sector = sector;
}
dec:
crypt_dec_pending(io);
}
static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
{
crypt_dec_pending(io);
}
static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
int r = 0;
crypt_inc_pending(io);
crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
io->sector);
r = crypt_convert(cc, &io->ctx);
if (r < 0)
io->error = -EIO;
if (atomic_dec_and_test(&io->ctx.cc_pending))
kcryptd_crypt_read_done(io);
crypt_dec_pending(io);
}
static void kcryptd_async_done(struct crypto_async_request *async_req,
int error)
{
struct dm_crypt_request *dmreq = async_req->data;
struct convert_context *ctx = dmreq->ctx;
struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx);
struct crypt_config *cc = io->cc;
/*
* A request from crypto driver backlog is going to be processed now,
* finish the completion and continue in crypt_convert().
* (Callback will be called for the second time for this request.)
*/
Revert "dm crypt: fix deadlock when async crypto algorithm returns -EBUSY" This reverts Linux 4.1-rc1 commit 0618764cb25f6fa9fb31152995de42a8a0496475. The problem which that commit attempts to fix actually lies in the Freescale CAAM crypto driver not dm-crypt. dm-crypt uses CRYPTO_TFM_REQ_MAY_BACKLOG. This means the the crypto driver should internally backlog requests which arrive when the queue is full and process them later. Until the crypto hw's queue becomes full, the driver returns -EINPROGRESS. When the crypto hw's queue if full, the driver returns -EBUSY, and if CRYPTO_TFM_REQ_MAY_BACKLOG is set, is expected to backlog the request and process it when the hardware has queue space. At the point when the driver takes the request from the backlog and starts processing it, it calls the completion function with a status of -EINPROGRESS. The completion function is called (for a second time, in the case of backlogged requests) with a status/err of 0 when a request is done. Crypto drivers for hardware without hardware queueing use the helpers, crypto_init_queue(), crypto_enqueue_request(), crypto_dequeue_request() and crypto_get_backlog() helpers to implement this behaviour correctly, while others implement this behaviour without these helpers (ccp, for example). dm-crypt (before the patch that needs reverting) uses this API correctly. It queues up as many requests as the hw queues will allow (i.e. as long as it gets back -EINPROGRESS from the request function). Then, when it sees at least one backlogged request (gets -EBUSY), it waits till that backlogged request is handled (completion gets called with -EINPROGRESS), and then continues. The references to af_alg_wait_for_completion() and af_alg_complete() in that commit's commit message are irrelevant because those functions only handle one request at a time, unlink dm-crypt. The problem is that the Freescale CAAM driver, which that commit describes as having being tested with, fails to implement the backlogging behaviour correctly. In cam_jr_enqueue(), if the hardware queue is full, it simply returns -EBUSY without backlogging the request. What the observed deadlock was is not described in the commit message but it is obviously the wait_for_completion() in crypto_convert() where dm-crypto would wait for the completion being called with -EINPROGRESS in the case of backlogged requests. This completion will never be completed due to the bug in the CAAM driver. Commit 0618764cb25 incorrectly made dm-crypt wait for every request, even when the driver/hardware queues are not full, which means that dm-crypt will never see -EBUSY. This means that that commit will cause a performance regression on all crypto drivers which implement the API correctly. Revert it. Correct backlog handling should be implemented in the CAAM driver instead. Cc'ing stable purely because commit 0618764cb25 did. If for some reason a stable@ kernel did pick up commit 0618764cb25 it should get reverted. Signed-off-by: Rabin Vincent <rabin.vincent@axis.com> Reviewed-by: Horia Geanta <horia.geanta@freescale.com> Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-05-05 13:15:56 +00:00
if (error == -EINPROGRESS) {
complete(&ctx->restart);
return;
Revert "dm crypt: fix deadlock when async crypto algorithm returns -EBUSY" This reverts Linux 4.1-rc1 commit 0618764cb25f6fa9fb31152995de42a8a0496475. The problem which that commit attempts to fix actually lies in the Freescale CAAM crypto driver not dm-crypt. dm-crypt uses CRYPTO_TFM_REQ_MAY_BACKLOG. This means the the crypto driver should internally backlog requests which arrive when the queue is full and process them later. Until the crypto hw's queue becomes full, the driver returns -EINPROGRESS. When the crypto hw's queue if full, the driver returns -EBUSY, and if CRYPTO_TFM_REQ_MAY_BACKLOG is set, is expected to backlog the request and process it when the hardware has queue space. At the point when the driver takes the request from the backlog and starts processing it, it calls the completion function with a status of -EINPROGRESS. The completion function is called (for a second time, in the case of backlogged requests) with a status/err of 0 when a request is done. Crypto drivers for hardware without hardware queueing use the helpers, crypto_init_queue(), crypto_enqueue_request(), crypto_dequeue_request() and crypto_get_backlog() helpers to implement this behaviour correctly, while others implement this behaviour without these helpers (ccp, for example). dm-crypt (before the patch that needs reverting) uses this API correctly. It queues up as many requests as the hw queues will allow (i.e. as long as it gets back -EINPROGRESS from the request function). Then, when it sees at least one backlogged request (gets -EBUSY), it waits till that backlogged request is handled (completion gets called with -EINPROGRESS), and then continues. The references to af_alg_wait_for_completion() and af_alg_complete() in that commit's commit message are irrelevant because those functions only handle one request at a time, unlink dm-crypt. The problem is that the Freescale CAAM driver, which that commit describes as having being tested with, fails to implement the backlogging behaviour correctly. In cam_jr_enqueue(), if the hardware queue is full, it simply returns -EBUSY without backlogging the request. What the observed deadlock was is not described in the commit message but it is obviously the wait_for_completion() in crypto_convert() where dm-crypto would wait for the completion being called with -EINPROGRESS in the case of backlogged requests. This completion will never be completed due to the bug in the CAAM driver. Commit 0618764cb25 incorrectly made dm-crypt wait for every request, even when the driver/hardware queues are not full, which means that dm-crypt will never see -EBUSY. This means that that commit will cause a performance regression on all crypto drivers which implement the API correctly. Revert it. Correct backlog handling should be implemented in the CAAM driver instead. Cc'ing stable purely because commit 0618764cb25 did. If for some reason a stable@ kernel did pick up commit 0618764cb25 it should get reverted. Signed-off-by: Rabin Vincent <rabin.vincent@axis.com> Reviewed-by: Horia Geanta <horia.geanta@freescale.com> Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-05-05 13:15:56 +00:00
}
if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post)
error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq);
if (error < 0)
io->error = -EIO;
crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
if (!atomic_dec_and_test(&ctx->cc_pending))
Revert "dm crypt: fix deadlock when async crypto algorithm returns -EBUSY" This reverts Linux 4.1-rc1 commit 0618764cb25f6fa9fb31152995de42a8a0496475. The problem which that commit attempts to fix actually lies in the Freescale CAAM crypto driver not dm-crypt. dm-crypt uses CRYPTO_TFM_REQ_MAY_BACKLOG. This means the the crypto driver should internally backlog requests which arrive when the queue is full and process them later. Until the crypto hw's queue becomes full, the driver returns -EINPROGRESS. When the crypto hw's queue if full, the driver returns -EBUSY, and if CRYPTO_TFM_REQ_MAY_BACKLOG is set, is expected to backlog the request and process it when the hardware has queue space. At the point when the driver takes the request from the backlog and starts processing it, it calls the completion function with a status of -EINPROGRESS. The completion function is called (for a second time, in the case of backlogged requests) with a status/err of 0 when a request is done. Crypto drivers for hardware without hardware queueing use the helpers, crypto_init_queue(), crypto_enqueue_request(), crypto_dequeue_request() and crypto_get_backlog() helpers to implement this behaviour correctly, while others implement this behaviour without these helpers (ccp, for example). dm-crypt (before the patch that needs reverting) uses this API correctly. It queues up as many requests as the hw queues will allow (i.e. as long as it gets back -EINPROGRESS from the request function). Then, when it sees at least one backlogged request (gets -EBUSY), it waits till that backlogged request is handled (completion gets called with -EINPROGRESS), and then continues. The references to af_alg_wait_for_completion() and af_alg_complete() in that commit's commit message are irrelevant because those functions only handle one request at a time, unlink dm-crypt. The problem is that the Freescale CAAM driver, which that commit describes as having being tested with, fails to implement the backlogging behaviour correctly. In cam_jr_enqueue(), if the hardware queue is full, it simply returns -EBUSY without backlogging the request. What the observed deadlock was is not described in the commit message but it is obviously the wait_for_completion() in crypto_convert() where dm-crypto would wait for the completion being called with -EINPROGRESS in the case of backlogged requests. This completion will never be completed due to the bug in the CAAM driver. Commit 0618764cb25 incorrectly made dm-crypt wait for every request, even when the driver/hardware queues are not full, which means that dm-crypt will never see -EBUSY. This means that that commit will cause a performance regression on all crypto drivers which implement the API correctly. Revert it. Correct backlog handling should be implemented in the CAAM driver instead. Cc'ing stable purely because commit 0618764cb25 did. If for some reason a stable@ kernel did pick up commit 0618764cb25 it should get reverted. Signed-off-by: Rabin Vincent <rabin.vincent@axis.com> Reviewed-by: Horia Geanta <horia.geanta@freescale.com> Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-05-05 13:15:56 +00:00
return;
if (bio_data_dir(io->base_bio) == READ)
kcryptd_crypt_read_done(io);
else
kcryptd_crypt_write_io_submit(io, 1);
}
static void kcryptd_crypt(struct work_struct *work)
{
struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
if (bio_data_dir(io->base_bio) == READ)
kcryptd_crypt_read_convert(io);
else
kcryptd_crypt_write_convert(io);
}
static void kcryptd_queue_crypt(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
INIT_WORK(&io->work, kcryptd_crypt);
queue_work(cc->crypt_queue, &io->work);
}
/*
* Decode key from its hex representation
*/
static int crypt_decode_key(u8 *key, char *hex, unsigned int size)
{
char buffer[3];
unsigned int i;
buffer[2] = '\0';
for (i = 0; i < size; i++) {
buffer[0] = *hex++;
buffer[1] = *hex++;
if (kstrtou8(buffer, 16, &key[i]))
return -EINVAL;
}
if (*hex != '\0')
return -EINVAL;
return 0;
}
static void crypt_free_tfms(struct crypt_config *cc)
{
unsigned i;
if (!cc->tfms)
return;
for (i = 0; i < cc->tfms_count; i++)
if (cc->tfms[i] && !IS_ERR(cc->tfms[i])) {
crypto_free_skcipher(cc->tfms[i]);
cc->tfms[i] = NULL;
}
kfree(cc->tfms);
cc->tfms = NULL;
}
static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode)
{
unsigned i;
int err;
cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
GFP_KERNEL);
if (!cc->tfms)
return -ENOMEM;
for (i = 0; i < cc->tfms_count; i++) {
cc->tfms[i] = crypto_alloc_skcipher(ciphermode, 0, 0);
if (IS_ERR(cc->tfms[i])) {
err = PTR_ERR(cc->tfms[i]);
crypt_free_tfms(cc);
return err;
}
}
return 0;
}
static int crypt_setkey_allcpus(struct crypt_config *cc)
{
unsigned subkey_size;
int err = 0, i, r;
/* Ignore extra keys (which are used for IV etc) */
subkey_size = (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count);
for (i = 0; i < cc->tfms_count; i++) {
r = crypto_skcipher_setkey(cc->tfms[i],
cc->key + (i * subkey_size),
subkey_size);
if (r)
err = r;
}
return err;
}
static int crypt_set_key(struct crypt_config *cc, char *key)
{
int r = -EINVAL;
int key_string_len = strlen(key);
/* The key size may not be changed. */
if (cc->key_size != (key_string_len >> 1))
goto out;
/* Hyphen (which gives a key_size of zero) means there is no key. */
if (!cc->key_size && strcmp(key, "-"))
goto out;
if (cc->key_size && crypt_decode_key(cc->key, key, cc->key_size) < 0)
goto out;
set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
r = crypt_setkey_allcpus(cc);
out:
/* Hex key string not needed after here, so wipe it. */
memset(key, '0', key_string_len);
return r;
}
static int crypt_wipe_key(struct crypt_config *cc)
{
clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
memset(&cc->key, 0, cc->key_size * sizeof(u8));
return crypt_setkey_allcpus(cc);
}
static void crypt_dtr(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
ti->private = NULL;
if (!cc)
return;
dm crypt: fix a possible hang due to race condition on exit A kernel thread executes __set_current_state(TASK_INTERRUPTIBLE), __add_wait_queue, spin_unlock_irq and then tests kthread_should_stop(). It is possible that the processor reorders memory accesses so that kthread_should_stop() is executed before __set_current_state(). If such reordering happens, there is a possible race on thread termination: CPU 0: calls kthread_should_stop() it tests KTHREAD_SHOULD_STOP bit, returns false CPU 1: calls kthread_stop(cc->write_thread) sets the KTHREAD_SHOULD_STOP bit calls wake_up_process on the kernel thread, that sets the thread state to TASK_RUNNING CPU 0: sets __set_current_state(TASK_INTERRUPTIBLE) spin_unlock_irq(&cc->write_thread_wait.lock) schedule() - and the process is stuck and never terminates, because the state is TASK_INTERRUPTIBLE and wake_up_process on CPU 1 already terminated Fix this race condition by using a new flag DM_CRYPT_EXIT_THREAD to signal that the kernel thread should exit. The flag is set and tested while holding cc->write_thread_wait.lock, so there is no possibility of racy access to the flag. Also, remove the unnecessary set_task_state(current, TASK_RUNNING) following the schedule() call. When the process was woken up, its state was already set to TASK_RUNNING. Other kernel code also doesn't set the state to TASK_RUNNING following schedule() (for example, do_wait_for_common in completion.c doesn't do it). Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-11-19 12:36:50 +00:00
if (cc->write_thread) {
spin_lock_irq(&cc->write_thread_wait.lock);
set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags);
wake_up_locked(&cc->write_thread_wait);
spin_unlock_irq(&cc->write_thread_wait.lock);
kthread_stop(cc->write_thread);
dm crypt: fix a possible hang due to race condition on exit A kernel thread executes __set_current_state(TASK_INTERRUPTIBLE), __add_wait_queue, spin_unlock_irq and then tests kthread_should_stop(). It is possible that the processor reorders memory accesses so that kthread_should_stop() is executed before __set_current_state(). If such reordering happens, there is a possible race on thread termination: CPU 0: calls kthread_should_stop() it tests KTHREAD_SHOULD_STOP bit, returns false CPU 1: calls kthread_stop(cc->write_thread) sets the KTHREAD_SHOULD_STOP bit calls wake_up_process on the kernel thread, that sets the thread state to TASK_RUNNING CPU 0: sets __set_current_state(TASK_INTERRUPTIBLE) spin_unlock_irq(&cc->write_thread_wait.lock) schedule() - and the process is stuck and never terminates, because the state is TASK_INTERRUPTIBLE and wake_up_process on CPU 1 already terminated Fix this race condition by using a new flag DM_CRYPT_EXIT_THREAD to signal that the kernel thread should exit. The flag is set and tested while holding cc->write_thread_wait.lock, so there is no possibility of racy access to the flag. Also, remove the unnecessary set_task_state(current, TASK_RUNNING) following the schedule() call. When the process was woken up, its state was already set to TASK_RUNNING. Other kernel code also doesn't set the state to TASK_RUNNING following schedule() (for example, do_wait_for_common in completion.c doesn't do it). Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-11-19 12:36:50 +00:00
}
if (cc->io_queue)
destroy_workqueue(cc->io_queue);
if (cc->crypt_queue)
destroy_workqueue(cc->crypt_queue);
crypt_free_tfms(cc);
if (cc->bs)
bioset_free(cc->bs);
mempool_destroy(cc->page_pool);
mempool_destroy(cc->req_pool);
if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
cc->iv_gen_ops->dtr(cc);
if (cc->dev)
dm_put_device(ti, cc->dev);
kzfree(cc->cipher);
kzfree(cc->cipher_string);
/* Must zero key material before freeing */
kzfree(cc);
}
static int crypt_ctr_cipher(struct dm_target *ti,
char *cipher_in, char *key)
{
struct crypt_config *cc = ti->private;
char *tmp, *cipher, *chainmode, *ivmode, *ivopts, *keycount;
char *cipher_api = NULL;
int ret = -EINVAL;
char dummy;
/* Convert to crypto api definition? */
if (strchr(cipher_in, '(')) {
ti->error = "Bad cipher specification";
return -EINVAL;
}
cc->cipher_string = kstrdup(cipher_in, GFP_KERNEL);
if (!cc->cipher_string)
goto bad_mem;
/*
* Legacy dm-crypt cipher specification
* cipher[:keycount]-mode-iv:ivopts
*/
tmp = cipher_in;
keycount = strsep(&tmp, "-");
cipher = strsep(&keycount, ":");
if (!keycount)
cc->tfms_count = 1;
else if (sscanf(keycount, "%u%c", &cc->tfms_count, &dummy) != 1 ||
!is_power_of_2(cc->tfms_count)) {
ti->error = "Bad cipher key count specification";
return -EINVAL;
}
cc->key_parts = cc->tfms_count;
cc->key_extra_size = 0;
cc->cipher = kstrdup(cipher, GFP_KERNEL);
if (!cc->cipher)
goto bad_mem;
chainmode = strsep(&tmp, "-");
ivopts = strsep(&tmp, "-");
ivmode = strsep(&ivopts, ":");
if (tmp)
DMWARN("Ignoring unexpected additional cipher options");
/*
* For compatibility with the original dm-crypt mapping format, if
* only the cipher name is supplied, use cbc-plain.
*/
if (!chainmode || (!strcmp(chainmode, "plain") && !ivmode)) {
chainmode = "cbc";
ivmode = "plain";
}
if (strcmp(chainmode, "ecb") && !ivmode) {
ti->error = "IV mechanism required";
return -EINVAL;
}
cipher_api = kmalloc(CRYPTO_MAX_ALG_NAME, GFP_KERNEL);
if (!cipher_api)
goto bad_mem;
ret = snprintf(cipher_api, CRYPTO_MAX_ALG_NAME,
"%s(%s)", chainmode, cipher);
if (ret < 0) {
kfree(cipher_api);
goto bad_mem;
}
/* Allocate cipher */
ret = crypt_alloc_tfms(cc, cipher_api);
if (ret < 0) {
ti->error = "Error allocating crypto tfm";
goto bad;
}
/* Initialize IV */
cc->iv_size = crypto_skcipher_ivsize(any_tfm(cc));
if (cc->iv_size)
/* at least a 64 bit sector number should fit in our buffer */
cc->iv_size = max(cc->iv_size,
(unsigned int)(sizeof(u64) / sizeof(u8)));
else if (ivmode) {
DMWARN("Selected cipher does not support IVs");
ivmode = NULL;
}
/* Choose ivmode, see comments at iv code. */
if (ivmode == NULL)
cc->iv_gen_ops = NULL;
else if (strcmp(ivmode, "plain") == 0)
cc->iv_gen_ops = &crypt_iv_plain_ops;
else if (strcmp(ivmode, "plain64") == 0)
cc->iv_gen_ops = &crypt_iv_plain64_ops;
else if (strcmp(ivmode, "essiv") == 0)
cc->iv_gen_ops = &crypt_iv_essiv_ops;
else if (strcmp(ivmode, "benbi") == 0)
cc->iv_gen_ops = &crypt_iv_benbi_ops;
else if (strcmp(ivmode, "null") == 0)
cc->iv_gen_ops = &crypt_iv_null_ops;
else if (strcmp(ivmode, "lmk") == 0) {
cc->iv_gen_ops = &crypt_iv_lmk_ops;
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
/*
* Version 2 and 3 is recognised according
* to length of provided multi-key string.
* If present (version 3), last key is used as IV seed.
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
* All keys (including IV seed) are always the same size.
*/
if (cc->key_size % cc->key_parts) {
cc->key_parts++;
cc->key_extra_size = cc->key_size / cc->key_parts;
}
dm crypt: add TCW IV mode for old CBC TCRYPT containers dm-crypt can already activate TCRYPT (TrueCrypt compatible) containers in LRW or XTS block encryption mode. TCRYPT containers prior to version 4.1 use CBC mode with some additional tweaks, this patch adds support for these containers. This new mode is implemented using special IV generator named TCW (TrueCrypt IV with whitening). TCW IV only supports containers that are encrypted with one cipher (Tested with AES, Twofish, Serpent, CAST5 and TripleDES). While this mode is legacy and is known to be vulnerable to some watermarking attacks (e.g. revealing of hidden disk existence) it can still be useful to activate old containers without using 3rd party software or for independent forensic analysis of such containers. (Both the userspace and kernel code is an independent implementation based on the format documentation and it completely avoids use of original source code.) The TCW IV generator uses two additional keys: Kw (whitening seed, size is always 16 bytes - TCW_WHITENING_SIZE) and Kiv (IV seed, size is always the IV size of the selected cipher). These keys are concatenated at the end of the main encryption key provided in mapping table. While whitening is completely independent from IV, it is implemented inside IV generator for simplification. The whitening value is always 16 bytes long and is calculated per sector from provided Kw as initial seed, xored with sector number and mixed with CRC32 algorithm. Resulting value is xored with ciphertext sector content. IV is calculated from the provided Kiv as initial IV seed and xored with sector number. Detailed calculation can be found in the Truecrypt documentation for version < 4.1 and will also be described on dm-crypt site, see: http://code.google.com/p/cryptsetup/wiki/DMCrypt The experimental support for activation of these containers is already present in git devel brach of cryptsetup. Signed-off-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2013-10-28 22:21:04 +00:00
} else if (strcmp(ivmode, "tcw") == 0) {
cc->iv_gen_ops = &crypt_iv_tcw_ops;
cc->key_parts += 2; /* IV + whitening */
cc->key_extra_size = cc->iv_size + TCW_WHITENING_SIZE;
} else {
ret = -EINVAL;
ti->error = "Invalid IV mode";
goto bad;
}
/* Initialize and set key */
ret = crypt_set_key(cc, key);
if (ret < 0) {
ti->error = "Error decoding and setting key";
goto bad;
}
/* Allocate IV */
if (cc->iv_gen_ops && cc->iv_gen_ops->ctr) {
ret = cc->iv_gen_ops->ctr(cc, ti, ivopts);
if (ret < 0) {
ti->error = "Error creating IV";
goto bad;
}
}
/* Initialize IV (set keys for ESSIV etc) */
if (cc->iv_gen_ops && cc->iv_gen_ops->init) {
ret = cc->iv_gen_ops->init(cc);
if (ret < 0) {
ti->error = "Error initialising IV";
goto bad;
}
}
ret = 0;
bad:
kfree(cipher_api);
return ret;
bad_mem:
ti->error = "Cannot allocate cipher strings";
return -ENOMEM;
}
/*
* Construct an encryption mapping:
* <cipher> <key> <iv_offset> <dev_path> <start>
*/
static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct crypt_config *cc;
unsigned int key_size, opt_params;
unsigned long long tmpll;
int ret;
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
size_t iv_size_padding;
struct dm_arg_set as;
const char *opt_string;
char dummy;
static struct dm_arg _args[] = {
{0, 3, "Invalid number of feature args"},
};
if (argc < 5) {
ti->error = "Not enough arguments";
return -EINVAL;
}
key_size = strlen(argv[1]) >> 1;
cc = kzalloc(sizeof(*cc) + key_size * sizeof(u8), GFP_KERNEL);
if (!cc) {
ti->error = "Cannot allocate encryption context";
return -ENOMEM;
}
cc->key_size = key_size;
ti->private = cc;
ret = crypt_ctr_cipher(ti, argv[0], argv[1]);
if (ret < 0)
goto bad;
cc->dmreq_start = sizeof(struct skcipher_request);
cc->dmreq_start += crypto_skcipher_reqsize(any_tfm(cc));
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
if (crypto_skcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
/* Allocate the padding exactly */
iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
& crypto_skcipher_alignmask(any_tfm(cc));
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
} else {
/*
* If the cipher requires greater alignment than kmalloc
* alignment, we don't know the exact position of the
* initialization vector. We must assume worst case.
*/
iv_size_padding = crypto_skcipher_alignmask(any_tfm(cc));
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
}
ret = -ENOMEM;
cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
if (!cc->req_pool) {
ti->error = "Cannot allocate crypt request mempool";
goto bad;
}
cc->per_bio_data_size = ti->per_io_data_size =
dm crypt: fix access beyond the end of allocated space The DM crypt target accesses memory beyond allocated space resulting in a crash on 32 bit x86 systems. This bug is very old (it dates back to 2.6.25 commit 3a7f6c990ad04 "dm crypt: use async crypto"). However, this bug was masked by the fact that kmalloc rounds the size up to the next power of two. This bug wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio data"). By switching to using per-bio data there was no longer any padding beyond the end of a dm-crypt allocated memory block. To minimize allocation overhead dm-crypt puts several structures into one block allocated with kmalloc. The block holds struct ablkcipher_request, cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))), struct dm_crypt_request and an initialization vector. The variable dmreq_start is set to offset of struct dm_crypt_request within this memory block. dm-crypt allocates the block with this size: cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size. When accessing the initialization vector, dm-crypt uses the function iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1). dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request structure. However, when dm-crypt accesses the initialization vector, it takes a pointer to the end of dm_crypt_request, aligns it, and then uses it as the initialization vector. If the end of dm_crypt_request is not aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the alignment causes the initialization vector to point beyond the allocated space. Fix this bug by calculating the variable iv_size_padding and adding it to the allocated size. Also correct the alignment of dm_crypt_request. struct dm_crypt_request is specific to dm-crypt (it isn't used by the crypto subsystem at all), so it is aligned on __alignof__(struct dm_crypt_request). Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is aligned as if the block was allocated with kmalloc. Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl> Tested-by: Milan Broz <gmazyland@gmail.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-28 15:09:31 +00:00
ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start +
sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
ARCH_KMALLOC_MINALIGN);
cc->page_pool = mempool_create_page_pool(BIO_MAX_PAGES, 0);
if (!cc->page_pool) {
ti->error = "Cannot allocate page mempool";
goto bad;
}
cc->bs = bioset_create(MIN_IOS, 0);
if (!cc->bs) {
ti->error = "Cannot allocate crypt bioset";
goto bad;
}
mutex_init(&cc->bio_alloc_lock);
ret = -EINVAL;
if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid iv_offset sector";
goto bad;
}
cc->iv_offset = tmpll;
ret = dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev);
if (ret) {
ti->error = "Device lookup failed";
goto bad;
}
ret = -EINVAL;
if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid device sector";
goto bad;
}
cc->start = tmpll;
argv += 5;
argc -= 5;
/* Optional parameters */
if (argc) {
as.argc = argc;
as.argv = argv;
ret = dm_read_arg_group(_args, &as, &opt_params, &ti->error);
if (ret)
goto bad;
ret = -EINVAL;
while (opt_params--) {
opt_string = dm_shift_arg(&as);
if (!opt_string) {
ti->error = "Not enough feature arguments";
goto bad;
}
if (!strcasecmp(opt_string, "allow_discards"))
ti->num_discard_bios = 1;
else if (!strcasecmp(opt_string, "same_cpu_crypt"))
set_bit(DM_CRYPT_SAME_CPU, &cc->flags);
else if (!strcasecmp(opt_string, "submit_from_crypt_cpus"))
set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
else {
ti->error = "Invalid feature arguments";
goto bad;
}
}
}
ret = -ENOMEM;
cc->io_queue = alloc_workqueue("kcryptd_io", WQ_MEM_RECLAIM, 1);
if (!cc->io_queue) {
ti->error = "Couldn't create kcryptd io queue";
goto bad;
}
if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1);
else
cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
num_online_cpus());
if (!cc->crypt_queue) {
ti->error = "Couldn't create kcryptd queue";
goto bad;
}
init_waitqueue_head(&cc->write_thread_wait);
cc->write_tree = RB_ROOT;
cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write");
if (IS_ERR(cc->write_thread)) {
ret = PTR_ERR(cc->write_thread);
cc->write_thread = NULL;
ti->error = "Couldn't spawn write thread";
goto bad;
}
wake_up_process(cc->write_thread);
ti->num_flush_bios = 1;
ti->discard_zeroes_data_unsupported = true;
return 0;
bad:
crypt_dtr(ti);
return ret;
}
static int crypt_map(struct dm_target *ti, struct bio *bio)
{
struct dm_crypt_io *io;
struct crypt_config *cc = ti->private;
/*
* If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues.
* - for REQ_PREFLUSH device-mapper core ensures that no IO is in-flight
* - for REQ_OP_DISCARD caller must use flush if IO ordering matters
*/
if (unlikely(bio->bi_rw & REQ_PREFLUSH ||
bio_op(bio) == REQ_OP_DISCARD)) {
bio->bi_bdev = cc->dev->bdev;
if (bio_sectors(bio))
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector = cc->start +
dm_target_offset(ti, bio->bi_iter.bi_sector);
return DM_MAPIO_REMAPPED;
}
io = dm_per_bio_data(bio, cc->per_bio_data_size);
crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
io->ctx.req = (struct skcipher_request *)(io + 1);
if (bio_data_dir(io->base_bio) == READ) {
if (kcryptd_io_read(io, GFP_NOWAIT))
kcryptd_queue_read(io);
} else
kcryptd_queue_crypt(io);
return DM_MAPIO_SUBMITTED;
}
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-01 22:45:44 +00:00
static void crypt_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct crypt_config *cc = ti->private;
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-01 22:45:44 +00:00
unsigned i, sz = 0;
int num_feature_args = 0;
switch (type) {
case STATUSTYPE_INFO:
result[0] = '\0';
break;
case STATUSTYPE_TABLE:
DMEMIT("%s ", cc->cipher_string);
dm: fix truncated status strings Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2013-03-01 22:45:44 +00:00
if (cc->key_size > 0)
for (i = 0; i < cc->key_size; i++)
DMEMIT("%02x", cc->key[i]);
else
DMEMIT("-");
DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset,
cc->dev->name, (unsigned long long)cc->start);
num_feature_args += !!ti->num_discard_bios;
num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags);
num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
if (num_feature_args) {
DMEMIT(" %d", num_feature_args);
if (ti->num_discard_bios)
DMEMIT(" allow_discards");
if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
DMEMIT(" same_cpu_crypt");
if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags))
DMEMIT(" submit_from_crypt_cpus");
}
break;
}
}
static void crypt_postsuspend(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
set_bit(DM_CRYPT_SUSPENDED, &cc->flags);
}
static int crypt_preresume(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
if (!test_bit(DM_CRYPT_KEY_VALID, &cc->flags)) {
DMERR("aborting resume - crypt key is not set.");
return -EAGAIN;
}
return 0;
}
static void crypt_resume(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
clear_bit(DM_CRYPT_SUSPENDED, &cc->flags);
}
/* Message interface
* key set <key>
* key wipe
*/
static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
{
struct crypt_config *cc = ti->private;
int ret = -EINVAL;
if (argc < 2)
goto error;
if (!strcasecmp(argv[0], "key")) {
if (!test_bit(DM_CRYPT_SUSPENDED, &cc->flags)) {
DMWARN("not suspended during key manipulation.");
return -EINVAL;
}
if (argc == 3 && !strcasecmp(argv[1], "set")) {
ret = crypt_set_key(cc, argv[2]);
if (ret)
return ret;
if (cc->iv_gen_ops && cc->iv_gen_ops->init)
ret = cc->iv_gen_ops->init(cc);
return ret;
}
if (argc == 2 && !strcasecmp(argv[1], "wipe")) {
if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) {
ret = cc->iv_gen_ops->wipe(cc);
if (ret)
return ret;
}
return crypt_wipe_key(cc);
}
}
error:
DMWARN("unrecognised message received.");
return -EINVAL;
}
static int crypt_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct crypt_config *cc = ti->private;
return fn(ti, cc->dev, cc->start, ti->len, data);
}
dm crypt: constrain crypt device's max_segment_size to PAGE_SIZE Setting the dm-crypt device's max_segment_size to PAGE_SIZE is an unfortunate constraint that is required to avoid the potential for exceeding dm-crypt's underlying device's max_segments limits -- due to crypt_alloc_buffer() possibly allocating pages for the encryption bio that are not as physically contiguous as the original bio. It is interesting to note that this problem was already fixed back in 2007 via commit 91e106259 ("dm crypt: use bio_add_page"). But Linux 4.0 commit cf2f1abfb ("dm crypt: don't allocate pages for a partial request") regressed dm-crypt back to _not_ using bio_add_page(). But given dm-crypt's cpu parallelization changes all depend on commit cf2f1abfb's abandoning of the more complex io fragments processing that dm-crypt previously had we cannot easily go back to using bio_add_page(). So all said the cleanest way to resolve this issue is to fix dm-crypt to properly constrain the original bios entering dm-crypt so the encryption bios that dm-crypt generates from the original bios are always compatible with the underlying device's max_segments queue limits. It should be noted that technically Linux 4.3 does _not_ need this fix because of the block core's new late bio-splitting capability. But, it is reasoned, there is little to be gained by having the block core split the encrypted bio that is composed of PAGE_SIZE segments. That said, in the future we may revert this change. Fixes: cf2f1abfb ("dm crypt: don't allocate pages for a partial request") Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=104421 Suggested-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.0+
2015-09-10 01:34:51 +00:00
static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
/*
* Unfortunate constraint that is required to avoid the potential
* for exceeding underlying device's max_segments limits -- due to
* crypt_alloc_buffer() possibly allocating pages for the encryption
* bio that are not as physically contiguous as the original bio.
*/
limits->max_segment_size = PAGE_SIZE;
}
static struct target_type crypt_target = {
.name = "crypt",
dm crypt: constrain crypt device's max_segment_size to PAGE_SIZE Setting the dm-crypt device's max_segment_size to PAGE_SIZE is an unfortunate constraint that is required to avoid the potential for exceeding dm-crypt's underlying device's max_segments limits -- due to crypt_alloc_buffer() possibly allocating pages for the encryption bio that are not as physically contiguous as the original bio. It is interesting to note that this problem was already fixed back in 2007 via commit 91e106259 ("dm crypt: use bio_add_page"). But Linux 4.0 commit cf2f1abfb ("dm crypt: don't allocate pages for a partial request") regressed dm-crypt back to _not_ using bio_add_page(). But given dm-crypt's cpu parallelization changes all depend on commit cf2f1abfb's abandoning of the more complex io fragments processing that dm-crypt previously had we cannot easily go back to using bio_add_page(). So all said the cleanest way to resolve this issue is to fix dm-crypt to properly constrain the original bios entering dm-crypt so the encryption bios that dm-crypt generates from the original bios are always compatible with the underlying device's max_segments queue limits. It should be noted that technically Linux 4.3 does _not_ need this fix because of the block core's new late bio-splitting capability. But, it is reasoned, there is little to be gained by having the block core split the encrypted bio that is composed of PAGE_SIZE segments. That said, in the future we may revert this change. Fixes: cf2f1abfb ("dm crypt: don't allocate pages for a partial request") Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=104421 Suggested-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.0+
2015-09-10 01:34:51 +00:00
.version = {1, 14, 1},
.module = THIS_MODULE,
.ctr = crypt_ctr,
.dtr = crypt_dtr,
.map = crypt_map,
.status = crypt_status,
.postsuspend = crypt_postsuspend,
.preresume = crypt_preresume,
.resume = crypt_resume,
.message = crypt_message,
.iterate_devices = crypt_iterate_devices,
dm crypt: constrain crypt device's max_segment_size to PAGE_SIZE Setting the dm-crypt device's max_segment_size to PAGE_SIZE is an unfortunate constraint that is required to avoid the potential for exceeding dm-crypt's underlying device's max_segments limits -- due to crypt_alloc_buffer() possibly allocating pages for the encryption bio that are not as physically contiguous as the original bio. It is interesting to note that this problem was already fixed back in 2007 via commit 91e106259 ("dm crypt: use bio_add_page"). But Linux 4.0 commit cf2f1abfb ("dm crypt: don't allocate pages for a partial request") regressed dm-crypt back to _not_ using bio_add_page(). But given dm-crypt's cpu parallelization changes all depend on commit cf2f1abfb's abandoning of the more complex io fragments processing that dm-crypt previously had we cannot easily go back to using bio_add_page(). So all said the cleanest way to resolve this issue is to fix dm-crypt to properly constrain the original bios entering dm-crypt so the encryption bios that dm-crypt generates from the original bios are always compatible with the underlying device's max_segments queue limits. It should be noted that technically Linux 4.3 does _not_ need this fix because of the block core's new late bio-splitting capability. But, it is reasoned, there is little to be gained by having the block core split the encrypted bio that is composed of PAGE_SIZE segments. That said, in the future we may revert this change. Fixes: cf2f1abfb ("dm crypt: don't allocate pages for a partial request") Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=104421 Suggested-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.0+
2015-09-10 01:34:51 +00:00
.io_hints = crypt_io_hints,
};
static int __init dm_crypt_init(void)
{
int r;
r = dm_register_target(&crypt_target);
if (r < 0)
DMERR("register failed %d", r);
return r;
}
static void __exit dm_crypt_exit(void)
{
dm_unregister_target(&crypt_target);
}
module_init(dm_crypt_init);
module_exit(dm_crypt_exit);
MODULE_AUTHOR("Jana Saout <jana@saout.de>");
MODULE_DESCRIPTION(DM_NAME " target for transparent encryption / decryption");
MODULE_LICENSE("GPL");