Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node:

    BUG: unable to handle kernel paging request at ffffc90008963690
    IP: __wake_up_bit+0x20/0x70
    Oops: 0000 [#1] SMP
    CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80
    Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015
    task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000
    RIP: 0010:[<ffffffff810dff80>]  [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
    RSP: 0018:ffff880017b97be8  EFLAGS: 00010246
    RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9
    RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648
    RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000
    R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800
    R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000
    FS:  00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0
    Call Trace:
      unlock_page+0x6d/0x70
      generic_write_end+0x53/0xb0
      xfs_vm_write_end+0x29/0x80 [xfs]
      generic_perform_write+0x10a/0x1e0
      xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs]
      xfs_file_write_iter+0x79/0x120 [xfs]
      __vfs_write+0xd4/0x110
      vfs_write+0xac/0x1c0
      SyS_write+0x58/0xd0
      system_call_fastpath+0x12/0x76
    Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48
    RIP  [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
     RSP <ffff880017b97be8>
    CR2: ffffc90008963690

Reproduce method (re-add a node)::
  Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic)

This seems an use-after-free problem, and the root cause is
zone->wait_table was not set to *NULL* after free it in
try_offline_node.

When hot re-add a node, we will reuse the pgdat of it, so does the zone
struct, and when add pages to the target zone, it will init the zone
first (including the wait_table) if the zone is not initialized.  The
judgement of zone initialized is based on zone->wait_table:

	static inline bool zone_is_initialized(struct zone *zone)
	{
		return !!zone->wait_table;
	}

so if we do not set the zone->wait_table to *NULL* after free it, the
memory hotplug routine will skip the init of new zone when hot re-add
the node, and the wait_table still points to the freed memory, then we
will access the invalid address when trying to wake up the waiting
people after the i/o operation with the page is done, such as mentioned
above.

Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com>
Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5879ae5
Raw File
ahash.c
/*
 * Asynchronous Cryptographic Hash operations.
 *
 * This is the asynchronous version of hash.c with notification of
 * completion via a callback.
 *
 * Copyright (c) 2008 Loc Ho <lho@amcc.com>
 *
 * 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 <crypto/scatterwalk.h>
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/cryptouser.h>
#include <net/netlink.h>

#include "internal.h"

struct ahash_request_priv {
	crypto_completion_t complete;
	void *data;
	u8 *result;
	void *ubuf[] CRYPTO_MINALIGN_ATTR;
};

static inline struct ahash_alg *crypto_ahash_alg(struct crypto_ahash *hash)
{
	return container_of(crypto_hash_alg_common(hash), struct ahash_alg,
			    halg);
}

static int hash_walk_next(struct crypto_hash_walk *walk)
{
	unsigned int alignmask = walk->alignmask;
	unsigned int offset = walk->offset;
	unsigned int nbytes = min(walk->entrylen,
				  ((unsigned int)(PAGE_SIZE)) - offset);

	if (walk->flags & CRYPTO_ALG_ASYNC)
		walk->data = kmap(walk->pg);
	else
		walk->data = kmap_atomic(walk->pg);
	walk->data += offset;

	if (offset & alignmask) {
		unsigned int unaligned = alignmask + 1 - (offset & alignmask);

		if (nbytes > unaligned)
			nbytes = unaligned;
	}

	walk->entrylen -= nbytes;
	return nbytes;
}

static int hash_walk_new_entry(struct crypto_hash_walk *walk)
{
	struct scatterlist *sg;

	sg = walk->sg;
	walk->pg = sg_page(sg);
	walk->offset = sg->offset;
	walk->entrylen = sg->length;

	if (walk->entrylen > walk->total)
		walk->entrylen = walk->total;
	walk->total -= walk->entrylen;

	return hash_walk_next(walk);
}

int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err)
{
	unsigned int alignmask = walk->alignmask;
	unsigned int nbytes = walk->entrylen;

	walk->data -= walk->offset;

	if (nbytes && walk->offset & alignmask && !err) {
		walk->offset = ALIGN(walk->offset, alignmask + 1);
		walk->data += walk->offset;

		nbytes = min(nbytes,
			     ((unsigned int)(PAGE_SIZE)) - walk->offset);
		walk->entrylen -= nbytes;

		return nbytes;
	}

	if (walk->flags & CRYPTO_ALG_ASYNC)
		kunmap(walk->pg);
	else {
		kunmap_atomic(walk->data);
		/*
		 * The may sleep test only makes sense for sync users.
		 * Async users don't need to sleep here anyway.
		 */
		crypto_yield(walk->flags);
	}

	if (err)
		return err;

	if (nbytes) {
		walk->offset = 0;
		walk->pg++;
		return hash_walk_next(walk);
	}

	if (!walk->total)
		return 0;

	walk->sg = sg_next(walk->sg);

	return hash_walk_new_entry(walk);
}
EXPORT_SYMBOL_GPL(crypto_hash_walk_done);

int crypto_hash_walk_first(struct ahash_request *req,
			   struct crypto_hash_walk *walk)
{
	walk->total = req->nbytes;

	if (!walk->total) {
		walk->entrylen = 0;
		return 0;
	}

	walk->alignmask = crypto_ahash_alignmask(crypto_ahash_reqtfm(req));
	walk->sg = req->src;
	walk->flags = req->base.flags & CRYPTO_TFM_REQ_MASK;

	return hash_walk_new_entry(walk);
}
EXPORT_SYMBOL_GPL(crypto_hash_walk_first);

int crypto_ahash_walk_first(struct ahash_request *req,
			    struct crypto_hash_walk *walk)
{
	walk->total = req->nbytes;

	if (!walk->total) {
		walk->entrylen = 0;
		return 0;
	}

	walk->alignmask = crypto_ahash_alignmask(crypto_ahash_reqtfm(req));
	walk->sg = req->src;
	walk->flags = req->base.flags & CRYPTO_TFM_REQ_MASK;
	walk->flags |= CRYPTO_ALG_ASYNC;

	BUILD_BUG_ON(CRYPTO_TFM_REQ_MASK & CRYPTO_ALG_ASYNC);

	return hash_walk_new_entry(walk);
}
EXPORT_SYMBOL_GPL(crypto_ahash_walk_first);

int crypto_hash_walk_first_compat(struct hash_desc *hdesc,
				  struct crypto_hash_walk *walk,
				  struct scatterlist *sg, unsigned int len)
{
	walk->total = len;

	if (!walk->total) {
		walk->entrylen = 0;
		return 0;
	}

	walk->alignmask = crypto_hash_alignmask(hdesc->tfm);
	walk->sg = sg;
	walk->flags = hdesc->flags & CRYPTO_TFM_REQ_MASK;

	return hash_walk_new_entry(walk);
}

static int ahash_setkey_unaligned(struct crypto_ahash *tfm, const u8 *key,
				unsigned int keylen)
{
	unsigned long alignmask = crypto_ahash_alignmask(tfm);
	int ret;
	u8 *buffer, *alignbuffer;
	unsigned long absize;

	absize = keylen + alignmask;
	buffer = kmalloc(absize, GFP_KERNEL);
	if (!buffer)
		return -ENOMEM;

	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
	memcpy(alignbuffer, key, keylen);
	ret = tfm->setkey(tfm, alignbuffer, keylen);
	kzfree(buffer);
	return ret;
}

int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
			unsigned int keylen)
{
	unsigned long alignmask = crypto_ahash_alignmask(tfm);

	if ((unsigned long)key & alignmask)
		return ahash_setkey_unaligned(tfm, key, keylen);

	return tfm->setkey(tfm, key, keylen);
}
EXPORT_SYMBOL_GPL(crypto_ahash_setkey);

static int ahash_nosetkey(struct crypto_ahash *tfm, const u8 *key,
			  unsigned int keylen)
{
	return -ENOSYS;
}

static inline unsigned int ahash_align_buffer_size(unsigned len,
						   unsigned long mask)
{
	return len + (mask & ~(crypto_tfm_ctx_alignment() - 1));
}

static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
{
	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
	unsigned long alignmask = crypto_ahash_alignmask(tfm);
	unsigned int ds = crypto_ahash_digestsize(tfm);
	struct ahash_request_priv *priv;

	priv = kmalloc(sizeof(*priv) + ahash_align_buffer_size(ds, alignmask),
		       (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
		       GFP_KERNEL : GFP_ATOMIC);
	if (!priv)
		return -ENOMEM;

	/*
	 * WARNING: Voodoo programming below!
	 *
	 * The code below is obscure and hard to understand, thus explanation
	 * is necessary. See include/crypto/hash.h and include/linux/crypto.h
	 * to understand the layout of structures used here!
	 *
	 * The code here will replace portions of the ORIGINAL request with
	 * pointers to new code and buffers so the hashing operation can store
	 * the result in aligned buffer. We will call the modified request
	 * an ADJUSTED request.
	 *
	 * The newly mangled request will look as such:
	 *
	 * req {
	 *   .result        = ADJUSTED[new aligned buffer]
	 *   .base.complete = ADJUSTED[pointer to completion function]
	 *   .base.data     = ADJUSTED[*req (pointer to self)]
	 *   .priv          = ADJUSTED[new priv] {
	 *           .result   = ORIGINAL(result)
	 *           .complete = ORIGINAL(base.complete)
	 *           .data     = ORIGINAL(base.data)
	 *   }
	 */

	priv->result = req->result;
	priv->complete = req->base.complete;
	priv->data = req->base.data;
	/*
	 * WARNING: We do not backup req->priv here! The req->priv
	 *          is for internal use of the Crypto API and the
	 *          user must _NOT_ _EVER_ depend on it's content!
	 */

	req->result = PTR_ALIGN((u8 *)priv->ubuf, alignmask + 1);
	req->base.complete = cplt;
	req->base.data = req;
	req->priv = priv;

	return 0;
}

static void ahash_restore_req(struct ahash_request *req)
{
	struct ahash_request_priv *priv = req->priv;

	/* Restore the original crypto request. */
	req->result = priv->result;
	req->base.complete = priv->complete;
	req->base.data = priv->data;
	req->priv = NULL;

	/* Free the req->priv.priv from the ADJUSTED request. */
	kzfree(priv);
}

static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
{
	struct ahash_request_priv *priv = req->priv;

	if (err == -EINPROGRESS)
		return;

	if (!err)
		memcpy(priv->result, req->result,
		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));

	ahash_restore_req(req);
}

static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
{
	struct ahash_request *areq = req->data;

	/*
	 * Restore the original request, see ahash_op_unaligned() for what
	 * goes where.
	 *
	 * The "struct ahash_request *req" here is in fact the "req.base"
	 * from the ADJUSTED request from ahash_op_unaligned(), thus as it
	 * is a pointer to self, it is also the ADJUSTED "req" .
	 */

	/* First copy req->result into req->priv.result */
	ahash_op_unaligned_finish(areq, err);

	/* Complete the ORIGINAL request. */
	areq->base.complete(&areq->base, err);
}

static int ahash_op_unaligned(struct ahash_request *req,
			      int (*op)(struct ahash_request *))
{
	int err;

	err = ahash_save_req(req, ahash_op_unaligned_done);
	if (err)
		return err;

	err = op(req);
	ahash_op_unaligned_finish(req, err);

	return err;
}

static int crypto_ahash_op(struct ahash_request *req,
			   int (*op)(struct ahash_request *))
{
	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
	unsigned long alignmask = crypto_ahash_alignmask(tfm);

	if ((unsigned long)req->result & alignmask)
		return ahash_op_unaligned(req, op);

	return op(req);
}

int crypto_ahash_final(struct ahash_request *req)
{
	return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->final);
}
EXPORT_SYMBOL_GPL(crypto_ahash_final);

int crypto_ahash_finup(struct ahash_request *req)
{
	return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->finup);
}
EXPORT_SYMBOL_GPL(crypto_ahash_finup);

int crypto_ahash_digest(struct ahash_request *req)
{
	return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->digest);
}
EXPORT_SYMBOL_GPL(crypto_ahash_digest);

static void ahash_def_finup_finish2(struct ahash_request *req, int err)
{
	struct ahash_request_priv *priv = req->priv;

	if (err == -EINPROGRESS)
		return;

	if (!err)
		memcpy(priv->result, req->result,
		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));

	ahash_restore_req(req);
}

static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
{
	struct ahash_request *areq = req->data;

	ahash_def_finup_finish2(areq, err);

	areq->base.complete(&areq->base, err);
}

static int ahash_def_finup_finish1(struct ahash_request *req, int err)
{
	if (err)
		goto out;

	req->base.complete = ahash_def_finup_done2;
	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
	err = crypto_ahash_reqtfm(req)->final(req);

out:
	ahash_def_finup_finish2(req, err);
	return err;
}

static void ahash_def_finup_done1(struct crypto_async_request *req, int err)
{
	struct ahash_request *areq = req->data;

	err = ahash_def_finup_finish1(areq, err);

	areq->base.complete(&areq->base, err);
}

static int ahash_def_finup(struct ahash_request *req)
{
	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
	int err;

	err = ahash_save_req(req, ahash_def_finup_done1);
	if (err)
		return err;

	err = tfm->update(req);
	return ahash_def_finup_finish1(req, err);
}

static int ahash_no_export(struct ahash_request *req, void *out)
{
	return -ENOSYS;
}

static int ahash_no_import(struct ahash_request *req, const void *in)
{
	return -ENOSYS;
}

static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
{
	struct crypto_ahash *hash = __crypto_ahash_cast(tfm);
	struct ahash_alg *alg = crypto_ahash_alg(hash);

	hash->setkey = ahash_nosetkey;
	hash->export = ahash_no_export;
	hash->import = ahash_no_import;

	if (tfm->__crt_alg->cra_type != &crypto_ahash_type)
		return crypto_init_shash_ops_async(tfm);

	hash->init = alg->init;
	hash->update = alg->update;
	hash->final = alg->final;
	hash->finup = alg->finup ?: ahash_def_finup;
	hash->digest = alg->digest;

	if (alg->setkey)
		hash->setkey = alg->setkey;
	if (alg->export)
		hash->export = alg->export;
	if (alg->import)
		hash->import = alg->import;

	return 0;
}

static unsigned int crypto_ahash_extsize(struct crypto_alg *alg)
{
	if (alg->cra_type == &crypto_ahash_type)
		return alg->cra_ctxsize;

	return sizeof(struct crypto_shash *);
}

#ifdef CONFIG_NET
static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
{
	struct crypto_report_hash rhash;

	strncpy(rhash.type, "ahash", sizeof(rhash.type));

	rhash.blocksize = alg->cra_blocksize;
	rhash.digestsize = __crypto_hash_alg_common(alg)->digestsize;

	if (nla_put(skb, CRYPTOCFGA_REPORT_HASH,
		    sizeof(struct crypto_report_hash), &rhash))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -EMSGSIZE;
}
#else
static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
{
	return -ENOSYS;
}
#endif

static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg)
	__attribute__ ((unused));
static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg)
{
	seq_printf(m, "type         : ahash\n");
	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
					     "yes" : "no");
	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
	seq_printf(m, "digestsize   : %u\n",
		   __crypto_hash_alg_common(alg)->digestsize);
}

const struct crypto_type crypto_ahash_type = {
	.extsize = crypto_ahash_extsize,
	.init_tfm = crypto_ahash_init_tfm,
#ifdef CONFIG_PROC_FS
	.show = crypto_ahash_show,
#endif
	.report = crypto_ahash_report,
	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
	.maskset = CRYPTO_ALG_TYPE_AHASH_MASK,
	.type = CRYPTO_ALG_TYPE_AHASH,
	.tfmsize = offsetof(struct crypto_ahash, base),
};
EXPORT_SYMBOL_GPL(crypto_ahash_type);

struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type,
					u32 mask)
{
	return crypto_alloc_tfm(alg_name, &crypto_ahash_type, type, mask);
}
EXPORT_SYMBOL_GPL(crypto_alloc_ahash);

static int ahash_prepare_alg(struct ahash_alg *alg)
{
	struct crypto_alg *base = &alg->halg.base;

	if (alg->halg.digestsize > PAGE_SIZE / 8 ||
	    alg->halg.statesize > PAGE_SIZE / 8)
		return -EINVAL;

	base->cra_type = &crypto_ahash_type;
	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
	base->cra_flags |= CRYPTO_ALG_TYPE_AHASH;

	return 0;
}

int crypto_register_ahash(struct ahash_alg *alg)
{
	struct crypto_alg *base = &alg->halg.base;
	int err;

	err = ahash_prepare_alg(alg);
	if (err)
		return err;

	return crypto_register_alg(base);
}
EXPORT_SYMBOL_GPL(crypto_register_ahash);

int crypto_unregister_ahash(struct ahash_alg *alg)
{
	return crypto_unregister_alg(&alg->halg.base);
}
EXPORT_SYMBOL_GPL(crypto_unregister_ahash);

int ahash_register_instance(struct crypto_template *tmpl,
			    struct ahash_instance *inst)
{
	int err;

	err = ahash_prepare_alg(&inst->alg);
	if (err)
		return err;

	return crypto_register_instance(tmpl, ahash_crypto_instance(inst));
}
EXPORT_SYMBOL_GPL(ahash_register_instance);

void ahash_free_instance(struct crypto_instance *inst)
{
	crypto_drop_spawn(crypto_instance_ctx(inst));
	kfree(ahash_instance(inst));
}
EXPORT_SYMBOL_GPL(ahash_free_instance);

int crypto_init_ahash_spawn(struct crypto_ahash_spawn *spawn,
			    struct hash_alg_common *alg,
			    struct crypto_instance *inst)
{
	return crypto_init_spawn2(&spawn->base, &alg->base, inst,
				  &crypto_ahash_type);
}
EXPORT_SYMBOL_GPL(crypto_init_ahash_spawn);

struct hash_alg_common *ahash_attr_alg(struct rtattr *rta, u32 type, u32 mask)
{
	struct crypto_alg *alg;

	alg = crypto_attr_alg2(rta, &crypto_ahash_type, type, mask);
	return IS_ERR(alg) ? ERR_CAST(alg) : __crypto_hash_alg_common(alg);
}
EXPORT_SYMBOL_GPL(ahash_attr_alg);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Asynchronous cryptographic hash type");
back to top