https://github.com/torvalds/linux
Revision 95dd77580ccd66a0da96e6d4696945b8cea39431 authored by Eric W. Biederman on 14 March 2018, 23:20:29 UTC, committed by Al Viro on 15 March 2018, 22:48:38 UTC
On nfsv2 and nfsv3 the nfs server can export subsets of the same
filesystem and report the same filesystem identifier, so that the nfs
client can know they are the same filesystem.  The subsets can be from
disjoint directory trees.  The nfsv2 and nfsv3 filesystems provides no
way to find the common root of all directory trees exported form the
server with the same filesystem identifier.

The practical result is that in struct super s_root for nfs s_root is
not necessarily the root of the filesystem.  The nfs mount code sets
s_root to the root of the first subset of the nfs filesystem that the
kernel mounts.

This effects the dcache invalidation code in generic_shutdown_super
currently called shrunk_dcache_for_umount and that code for years
has gone through an additional list of dentries that might be dentry
trees that need to be freed to accomodate nfs.

When I wrote path_connected I did not realize nfs was so special, and
it's hueristic for avoiding calling is_subdir can fail.

The practical case where this fails is when there is a move of a
directory from the subtree exposed by one nfs mount to the subtree
exposed by another nfs mount.  This move can happen either locally or
remotely.  With the remote case requiring that the move directory be cached
before the move and that after the move someone walks the path
to where the move directory now exists and in so doing causes the
already cached directory to be moved in the dcache through the magic
of d_splice_alias.

If someone whose working directory is in the move directory or a
subdirectory and now starts calling .. from the initial mount of nfs
(where s_root == mnt_root), then path_connected as a heuristic will
not bother with the is_subdir check.  As s_root really is not the root
of the nfs filesystem this heuristic is wrong, and the path may
actually not be connected and path_connected can fail.

The is_subdir function might be cheap enough that we can call it
unconditionally.  Verifying that will take some benchmarking and
the result may not be the same on all kernels this fix needs
to be backported to.  So I am avoiding that for now.

Filesystems with snapshots such as nilfs and btrfs do something
similar.  But as the directory tree of the snapshots are disjoint
from one another and from the main directory tree rename won't move
things between them and this problem will not occur.

Cc: stable@vger.kernel.org
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Fixes: 397d425dc26d ("vfs: Test for and handle paths that are unreachable from their mnt_root")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
1 parent 8cc07c8
Raw File
Tip revision: 95dd77580ccd66a0da96e6d4696945b8cea39431 authored by Eric W. Biederman on 14 March 2018, 23:20:29 UTC
fs: Teach path_connected to handle nfs filesystems with multiple roots.
Tip revision: 95dd775
crc32c_generic.c
/*
 * Cryptographic API.
 *
 * CRC32C chksum
 *
 *@Article{castagnoli-crc,
 * author =       { Guy Castagnoli and Stefan Braeuer and Martin Herrman},
 * title =        {{Optimization of Cyclic Redundancy-Check Codes with 24
 *                 and 32 Parity Bits}},
 * journal =      IEEE Transactions on Communication,
 * year =         {1993},
 * volume =       {41},
 * number =       {6},
 * pages =        {},
 * month =        {June},
 *}
 * Used by the iSCSI driver, possibly others, and derived from the
 * the iscsi-crc.c module of the linux-iscsi driver at
 * http://linux-iscsi.sourceforge.net.
 *
 * Following the example of lib/crc32, this function is intended to be
 * flexible and useful for all users.  Modules that currently have their
 * own crc32c, but hopefully may be able to use this one are:
 *  net/sctp (please add all your doco to here if you change to
 *            use this one!)
 *  <endoflist>
 *
 * Copyright (c) 2004 Cisco Systems, Inc.
 * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option)
 * any later version.
 *
 */

#include <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/crc32.h>

#define CHKSUM_BLOCK_SIZE	1
#define CHKSUM_DIGEST_SIZE	4

struct chksum_ctx {
	u32 key;
};

struct chksum_desc_ctx {
	u32 crc;
};

/*
 * Steps through buffer one byte at at time, calculates reflected
 * crc using table.
 */

static int chksum_init(struct shash_desc *desc)
{
	struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);

	ctx->crc = mctx->key;

	return 0;
}

/*
 * Setting the seed allows arbitrary accumulators and flexible XOR policy
 * If your algorithm starts with ~0, then XOR with ~0 before you set
 * the seed.
 */
static int chksum_setkey(struct crypto_shash *tfm, const u8 *key,
			 unsigned int keylen)
{
	struct chksum_ctx *mctx = crypto_shash_ctx(tfm);

	if (keylen != sizeof(mctx->key)) {
		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
		return -EINVAL;
	}
	mctx->key = le32_to_cpu(*(__le32 *)key);
	return 0;
}

static int chksum_update(struct shash_desc *desc, const u8 *data,
			 unsigned int length)
{
	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);

	ctx->crc = __crc32c_le(ctx->crc, data, length);
	return 0;
}

static int chksum_final(struct shash_desc *desc, u8 *out)
{
	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);

	*(__le32 *)out = ~cpu_to_le32p(&ctx->crc);
	return 0;
}

static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out)
{
	*(__le32 *)out = ~cpu_to_le32(__crc32c_le(*crcp, data, len));
	return 0;
}

static int chksum_finup(struct shash_desc *desc, const u8 *data,
			unsigned int len, u8 *out)
{
	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);

	return __chksum_finup(&ctx->crc, data, len, out);
}

static int chksum_digest(struct shash_desc *desc, const u8 *data,
			 unsigned int length, u8 *out)
{
	struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);

	return __chksum_finup(&mctx->key, data, length, out);
}

static int crc32c_cra_init(struct crypto_tfm *tfm)
{
	struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);

	mctx->key = ~0;
	return 0;
}

static struct shash_alg alg = {
	.digestsize		=	CHKSUM_DIGEST_SIZE,
	.setkey			=	chksum_setkey,
	.init		=	chksum_init,
	.update		=	chksum_update,
	.final		=	chksum_final,
	.finup		=	chksum_finup,
	.digest		=	chksum_digest,
	.descsize		=	sizeof(struct chksum_desc_ctx),
	.base			=	{
		.cra_name		=	"crc32c",
		.cra_driver_name	=	"crc32c-generic",
		.cra_priority		=	100,
		.cra_flags		=	CRYPTO_ALG_OPTIONAL_KEY,
		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
		.cra_alignmask		=	3,
		.cra_ctxsize		=	sizeof(struct chksum_ctx),
		.cra_module		=	THIS_MODULE,
		.cra_init		=	crc32c_cra_init,
	}
};

static int __init crc32c_mod_init(void)
{
	return crypto_register_shash(&alg);
}

static void __exit crc32c_mod_fini(void)
{
	crypto_unregister_shash(&alg);
}

module_init(crc32c_mod_init);
module_exit(crc32c_mod_fini);

MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CRYPTO("crc32c");
MODULE_ALIAS_CRYPTO("crc32c-generic");
back to top