Revision 7561cea5dbb97fecb952548a0fb74fb105bf4664 authored by Darrick J. Wong on 01 July 2022, 16:08:33 UTC, committed by Darrick J. Wong on 01 July 2022, 16:09:52 UTC
KASAN reported the following use after free bug when running
generic/475:

 XFS (dm-0): Mounting V5 Filesystem
 XFS (dm-0): Starting recovery (logdev: internal)
 XFS (dm-0): Ending recovery (logdev: internal)
 Buffer I/O error on dev dm-0, logical block 20639616, async page read
 Buffer I/O error on dev dm-0, logical block 20639617, async page read
 XFS (dm-0): log I/O error -5
 XFS (dm-0): Filesystem has been shut down due to log error (0x2).
 XFS (dm-0): Unmounting Filesystem
 XFS (dm-0): Please unmount the filesystem and rectify the problem(s).
 ==================================================================
 BUG: KASAN: use-after-free in do_raw_spin_lock+0x246/0x270
 Read of size 4 at addr ffff888109dd84c4 by task 3:1H/136

 CPU: 3 PID: 136 Comm: 3:1H Not tainted 5.19.0-rc4-xfsx #rc4 8e53ab5ad0fddeb31cee5e7063ff9c361915a9c4
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014
 Workqueue: xfs-log/dm-0 xlog_ioend_work [xfs]
 Call Trace:
  <TASK>
  dump_stack_lvl+0x34/0x44
  print_report.cold+0x2b8/0x661
  ? do_raw_spin_lock+0x246/0x270
  kasan_report+0xab/0x120
  ? do_raw_spin_lock+0x246/0x270
  do_raw_spin_lock+0x246/0x270
  ? rwlock_bug.part.0+0x90/0x90
  xlog_force_shutdown+0xf6/0x370 [xfs 4ad76ae0d6add7e8183a553e624c31e9ed567318]
  xlog_ioend_work+0x100/0x190 [xfs 4ad76ae0d6add7e8183a553e624c31e9ed567318]
  process_one_work+0x672/0x1040
  worker_thread+0x59b/0xec0
  ? __kthread_parkme+0xc6/0x1f0
  ? process_one_work+0x1040/0x1040
  ? process_one_work+0x1040/0x1040
  kthread+0x29e/0x340
  ? kthread_complete_and_exit+0x20/0x20
  ret_from_fork+0x1f/0x30
  </TASK>

 Allocated by task 154099:
  kasan_save_stack+0x1e/0x40
  __kasan_kmalloc+0x81/0xa0
  kmem_alloc+0x8d/0x2e0 [xfs]
  xlog_cil_init+0x1f/0x540 [xfs]
  xlog_alloc_log+0xd1e/0x1260 [xfs]
  xfs_log_mount+0xba/0x640 [xfs]
  xfs_mountfs+0xf2b/0x1d00 [xfs]
  xfs_fs_fill_super+0x10af/0x1910 [xfs]
  get_tree_bdev+0x383/0x670
  vfs_get_tree+0x7d/0x240
  path_mount+0xdb7/0x1890
  __x64_sys_mount+0x1fa/0x270
  do_syscall_64+0x2b/0x80
  entry_SYSCALL_64_after_hwframe+0x46/0xb0

 Freed by task 154151:
  kasan_save_stack+0x1e/0x40
  kasan_set_track+0x21/0x30
  kasan_set_free_info+0x20/0x30
  ____kasan_slab_free+0x110/0x190
  slab_free_freelist_hook+0xab/0x180
  kfree+0xbc/0x310
  xlog_dealloc_log+0x1b/0x2b0 [xfs]
  xfs_unmountfs+0x119/0x200 [xfs]
  xfs_fs_put_super+0x6e/0x2e0 [xfs]
  generic_shutdown_super+0x12b/0x3a0
  kill_block_super+0x95/0xd0
  deactivate_locked_super+0x80/0x130
  cleanup_mnt+0x329/0x4d0
  task_work_run+0xc5/0x160
  exit_to_user_mode_prepare+0xd4/0xe0
  syscall_exit_to_user_mode+0x1d/0x40
  entry_SYSCALL_64_after_hwframe+0x46/0xb0

This appears to be a race between the unmount process, which frees the
CIL and waits for in-flight iclog IO; and the iclog IO completion.  When
generic/475 runs, it starts fsstress in the background, waits a few
seconds, and substitutes a dm-error device to simulate a disk falling
out of a machine.  If the fsstress encounters EIO on a pure data write,
it will exit but the filesystem will still be online.

The next thing the test does is unmount the filesystem, which tries to
clean the log, free the CIL, and wait for iclog IO completion.  If an
iclog was being written when the dm-error switch occurred, it can race
with log unmounting as follows:

Thread 1				Thread 2

					xfs_log_unmount
					xfs_log_clean
					xfs_log_quiesce
xlog_ioend_work
<observe error>
xlog_force_shutdown
test_and_set_bit(XLOG_IOERROR)
					xfs_log_force
					<log is shut down, nop>
					xfs_log_umount_write
					<log is shut down, nop>
					xlog_dealloc_log
					xlog_cil_destroy
					<wait for iclogs>
spin_lock(&log->l_cilp->xc_push_lock)
<KABOOM>

Therefore, free the CIL after waiting for the iclogs to complete.  I
/think/ this race has existed for quite a few years now, though I don't
remember the ~2014 era logging code well enough to know if it was a real
threat then or if the actual race was exposed only more recently.

Fixes: ac983517ec59 ("xfs: don't sleep in xlog_cil_force_lsn on shutdown")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
1 parent 8944c6f
Raw File
ctr.c
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * CTR: Counter mode
 *
 * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
 */

#include <crypto/algapi.h>
#include <crypto/ctr.h>
#include <crypto/internal/cipher.h>
#include <crypto/internal/skcipher.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>

struct crypto_rfc3686_ctx {
	struct crypto_skcipher *child;
	u8 nonce[CTR_RFC3686_NONCE_SIZE];
};

struct crypto_rfc3686_req_ctx {
	u8 iv[CTR_RFC3686_BLOCK_SIZE];
	struct skcipher_request subreq CRYPTO_MINALIGN_ATTR;
};

static void crypto_ctr_crypt_final(struct skcipher_walk *walk,
				   struct crypto_cipher *tfm)
{
	unsigned int bsize = crypto_cipher_blocksize(tfm);
	unsigned long alignmask = crypto_cipher_alignmask(tfm);
	u8 *ctrblk = walk->iv;
	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	unsigned int nbytes = walk->nbytes;

	crypto_cipher_encrypt_one(tfm, keystream, ctrblk);
	crypto_xor_cpy(dst, keystream, src, nbytes);

	crypto_inc(ctrblk, bsize);
}

static int crypto_ctr_crypt_segment(struct skcipher_walk *walk,
				    struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		   crypto_cipher_alg(tfm)->cia_encrypt;
	unsigned int bsize = crypto_cipher_blocksize(tfm);
	u8 *ctrblk = walk->iv;
	u8 *src = walk->src.virt.addr;
	u8 *dst = walk->dst.virt.addr;
	unsigned int nbytes = walk->nbytes;

	do {
		/* create keystream */
		fn(crypto_cipher_tfm(tfm), dst, ctrblk);
		crypto_xor(dst, src, bsize);

		/* increment counter in counterblock */
		crypto_inc(ctrblk, bsize);

		src += bsize;
		dst += bsize;
	} while ((nbytes -= bsize) >= bsize);

	return nbytes;
}

static int crypto_ctr_crypt_inplace(struct skcipher_walk *walk,
				    struct crypto_cipher *tfm)
{
	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
		   crypto_cipher_alg(tfm)->cia_encrypt;
	unsigned int bsize = crypto_cipher_blocksize(tfm);
	unsigned long alignmask = crypto_cipher_alignmask(tfm);
	unsigned int nbytes = walk->nbytes;
	u8 *ctrblk = walk->iv;
	u8 *src = walk->src.virt.addr;
	u8 tmp[MAX_CIPHER_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);

	do {
		/* create keystream */
		fn(crypto_cipher_tfm(tfm), keystream, ctrblk);
		crypto_xor(src, keystream, bsize);

		/* increment counter in counterblock */
		crypto_inc(ctrblk, bsize);

		src += bsize;
	} while ((nbytes -= bsize) >= bsize);

	return nbytes;
}

static int crypto_ctr_crypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_cipher *cipher = skcipher_cipher_simple(tfm);
	const unsigned int bsize = crypto_cipher_blocksize(cipher);
	struct skcipher_walk walk;
	unsigned int nbytes;
	int err;

	err = skcipher_walk_virt(&walk, req, false);

	while (walk.nbytes >= bsize) {
		if (walk.src.virt.addr == walk.dst.virt.addr)
			nbytes = crypto_ctr_crypt_inplace(&walk, cipher);
		else
			nbytes = crypto_ctr_crypt_segment(&walk, cipher);

		err = skcipher_walk_done(&walk, nbytes);
	}

	if (walk.nbytes) {
		crypto_ctr_crypt_final(&walk, cipher);
		err = skcipher_walk_done(&walk, 0);
	}

	return err;
}

static int crypto_ctr_create(struct crypto_template *tmpl, struct rtattr **tb)
{
	struct skcipher_instance *inst;
	struct crypto_alg *alg;
	int err;

	inst = skcipher_alloc_instance_simple(tmpl, tb);
	if (IS_ERR(inst))
		return PTR_ERR(inst);

	alg = skcipher_ialg_simple(inst);

	/* Block size must be >= 4 bytes. */
	err = -EINVAL;
	if (alg->cra_blocksize < 4)
		goto out_free_inst;

	/* If this is false we'd fail the alignment of crypto_inc. */
	if (alg->cra_blocksize % 4)
		goto out_free_inst;

	/* CTR mode is a stream cipher. */
	inst->alg.base.cra_blocksize = 1;

	/*
	 * To simplify the implementation, configure the skcipher walk to only
	 * give a partial block at the very end, never earlier.
	 */
	inst->alg.chunksize = alg->cra_blocksize;

	inst->alg.encrypt = crypto_ctr_crypt;
	inst->alg.decrypt = crypto_ctr_crypt;

	err = skcipher_register_instance(tmpl, inst);
	if (err) {
out_free_inst:
		inst->free(inst);
	}

	return err;
}

static int crypto_rfc3686_setkey(struct crypto_skcipher *parent,
				 const u8 *key, unsigned int keylen)
{
	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(parent);
	struct crypto_skcipher *child = ctx->child;

	/* the nonce is stored in bytes at end of key */
	if (keylen < CTR_RFC3686_NONCE_SIZE)
		return -EINVAL;

	memcpy(ctx->nonce, key + (keylen - CTR_RFC3686_NONCE_SIZE),
	       CTR_RFC3686_NONCE_SIZE);

	keylen -= CTR_RFC3686_NONCE_SIZE;

	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
					 CRYPTO_TFM_REQ_MASK);
	return crypto_skcipher_setkey(child, key, keylen);
}

static int crypto_rfc3686_crypt(struct skcipher_request *req)
{
	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
	struct crypto_skcipher *child = ctx->child;
	unsigned long align = crypto_skcipher_alignmask(tfm);
	struct crypto_rfc3686_req_ctx *rctx =
		(void *)PTR_ALIGN((u8 *)skcipher_request_ctx(req), align + 1);
	struct skcipher_request *subreq = &rctx->subreq;
	u8 *iv = rctx->iv;

	/* set up counter block */
	memcpy(iv, ctx->nonce, CTR_RFC3686_NONCE_SIZE);
	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->iv, CTR_RFC3686_IV_SIZE);

	/* initialize counter portion of counter block */
	*(__be32 *)(iv + CTR_RFC3686_NONCE_SIZE + CTR_RFC3686_IV_SIZE) =
		cpu_to_be32(1);

	skcipher_request_set_tfm(subreq, child);
	skcipher_request_set_callback(subreq, req->base.flags,
				      req->base.complete, req->base.data);
	skcipher_request_set_crypt(subreq, req->src, req->dst,
				   req->cryptlen, iv);

	return crypto_skcipher_encrypt(subreq);
}

static int crypto_rfc3686_init_tfm(struct crypto_skcipher *tfm)
{
	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
	struct crypto_skcipher *cipher;
	unsigned long align;
	unsigned int reqsize;

	cipher = crypto_spawn_skcipher(spawn);
	if (IS_ERR(cipher))
		return PTR_ERR(cipher);

	ctx->child = cipher;

	align = crypto_skcipher_alignmask(tfm);
	align &= ~(crypto_tfm_ctx_alignment() - 1);
	reqsize = align + sizeof(struct crypto_rfc3686_req_ctx) +
		  crypto_skcipher_reqsize(cipher);
	crypto_skcipher_set_reqsize(tfm, reqsize);

	return 0;
}

static void crypto_rfc3686_exit_tfm(struct crypto_skcipher *tfm)
{
	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);

	crypto_free_skcipher(ctx->child);
}

static void crypto_rfc3686_free(struct skcipher_instance *inst)
{
	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);

	crypto_drop_skcipher(spawn);
	kfree(inst);
}

static int crypto_rfc3686_create(struct crypto_template *tmpl,
				 struct rtattr **tb)
{
	struct skcipher_instance *inst;
	struct skcipher_alg *alg;
	struct crypto_skcipher_spawn *spawn;
	u32 mask;
	int err;

	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask);
	if (err)
		return err;

	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
	if (!inst)
		return -ENOMEM;

	spawn = skcipher_instance_ctx(inst);

	err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst),
				   crypto_attr_alg_name(tb[1]), 0, mask);
	if (err)
		goto err_free_inst;

	alg = crypto_spawn_skcipher_alg(spawn);

	/* We only support 16-byte blocks. */
	err = -EINVAL;
	if (crypto_skcipher_alg_ivsize(alg) != CTR_RFC3686_BLOCK_SIZE)
		goto err_free_inst;

	/* Not a stream cipher? */
	if (alg->base.cra_blocksize != 1)
		goto err_free_inst;

	err = -ENAMETOOLONG;
	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
		     "rfc3686(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
		goto err_free_inst;
	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
		     "rfc3686(%s)", alg->base.cra_driver_name) >=
	    CRYPTO_MAX_ALG_NAME)
		goto err_free_inst;

	inst->alg.base.cra_priority = alg->base.cra_priority;
	inst->alg.base.cra_blocksize = 1;
	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;

	inst->alg.ivsize = CTR_RFC3686_IV_SIZE;
	inst->alg.chunksize = crypto_skcipher_alg_chunksize(alg);
	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg) +
				CTR_RFC3686_NONCE_SIZE;
	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg) +
				CTR_RFC3686_NONCE_SIZE;

	inst->alg.setkey = crypto_rfc3686_setkey;
	inst->alg.encrypt = crypto_rfc3686_crypt;
	inst->alg.decrypt = crypto_rfc3686_crypt;

	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc3686_ctx);

	inst->alg.init = crypto_rfc3686_init_tfm;
	inst->alg.exit = crypto_rfc3686_exit_tfm;

	inst->free = crypto_rfc3686_free;

	err = skcipher_register_instance(tmpl, inst);
	if (err) {
err_free_inst:
		crypto_rfc3686_free(inst);
	}
	return err;
}

static struct crypto_template crypto_ctr_tmpls[] = {
	{
		.name = "ctr",
		.create = crypto_ctr_create,
		.module = THIS_MODULE,
	}, {
		.name = "rfc3686",
		.create = crypto_rfc3686_create,
		.module = THIS_MODULE,
	},
};

static int __init crypto_ctr_module_init(void)
{
	return crypto_register_templates(crypto_ctr_tmpls,
					 ARRAY_SIZE(crypto_ctr_tmpls));
}

static void __exit crypto_ctr_module_exit(void)
{
	crypto_unregister_templates(crypto_ctr_tmpls,
				    ARRAY_SIZE(crypto_ctr_tmpls));
}

subsys_initcall(crypto_ctr_module_init);
module_exit(crypto_ctr_module_exit);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CTR block cipher mode of operation");
MODULE_ALIAS_CRYPTO("rfc3686");
MODULE_ALIAS_CRYPTO("ctr");
MODULE_IMPORT_NS(CRYPTO_INTERNAL);
back to top