Revision 32db864d33c21fd70a217ba53cb7224889354ffb authored by Nikolay Aleksandrov on 30 August 2017, 09:48:59 UTC, committed by David S. Miller on 30 August 2017, 22:26:11 UTC
If sch_hhf fails in its ->init() function (either due to wrong
user-space arguments as below or memory alloc failure of hh_flows) it
will do a null pointer deref of q->hh_flows in its ->destroy() function.

To reproduce the crash:
$ tc qdisc add dev eth0 root hhf quantum 2000000 non_hh_weight 10000000

Crash log:
[  690.654882] BUG: unable to handle kernel NULL pointer dereference at (null)
[  690.655565] IP: hhf_destroy+0x48/0xbc
[  690.655944] PGD 37345067
[  690.655948] P4D 37345067
[  690.656252] PUD 58402067
[  690.656554] PMD 0
[  690.656857]
[  690.657362] Oops: 0000 [#1] SMP
[  690.657696] Modules linked in:
[  690.658032] CPU: 3 PID: 920 Comm: tc Not tainted 4.13.0-rc6+ #57
[  690.658525] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[  690.659255] task: ffff880058578000 task.stack: ffff88005acbc000
[  690.659747] RIP: 0010:hhf_destroy+0x48/0xbc
[  690.660146] RSP: 0018:ffff88005acbf9e0 EFLAGS: 00010246
[  690.660601] RAX: 0000000000000000 RBX: 0000000000000020 RCX: 0000000000000000
[  690.661155] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffff821f63f0
[  690.661710] RBP: ffff88005acbfa08 R08: ffffffff81b10a90 R09: 0000000000000000
[  690.662267] R10: 00000000f42b7019 R11: ffff880058578000 R12: 00000000ffffffea
[  690.662820] R13: ffff8800372f6400 R14: 0000000000000000 R15: 0000000000000000
[  690.663769] FS:  00007f8ae5e8b740(0000) GS:ffff88005d980000(0000) knlGS:0000000000000000
[  690.667069] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  690.667965] CR2: 0000000000000000 CR3: 0000000058523000 CR4: 00000000000406e0
[  690.668918] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  690.669945] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  690.671003] Call Trace:
[  690.671743]  qdisc_create+0x377/0x3fd
[  690.672534]  tc_modify_qdisc+0x4d2/0x4fd
[  690.673324]  rtnetlink_rcv_msg+0x188/0x197
[  690.674204]  ? rcu_read_unlock+0x3e/0x5f
[  690.675091]  ? rtnl_newlink+0x729/0x729
[  690.675877]  netlink_rcv_skb+0x6c/0xce
[  690.676648]  rtnetlink_rcv+0x23/0x2a
[  690.677405]  netlink_unicast+0x103/0x181
[  690.678179]  netlink_sendmsg+0x326/0x337
[  690.678958]  sock_sendmsg_nosec+0x14/0x3f
[  690.679743]  sock_sendmsg+0x29/0x2e
[  690.680506]  ___sys_sendmsg+0x209/0x28b
[  690.681283]  ? __handle_mm_fault+0xc7d/0xdb1
[  690.681915]  ? check_chain_key+0xb0/0xfd
[  690.682449]  __sys_sendmsg+0x45/0x63
[  690.682954]  ? __sys_sendmsg+0x45/0x63
[  690.683471]  SyS_sendmsg+0x19/0x1b
[  690.683974]  entry_SYSCALL_64_fastpath+0x23/0xc2
[  690.684516] RIP: 0033:0x7f8ae529d690
[  690.685016] RSP: 002b:00007fff26d2d6b8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  690.685931] RAX: ffffffffffffffda RBX: ffffffff810d278c RCX: 00007f8ae529d690
[  690.686573] RDX: 0000000000000000 RSI: 00007fff26d2d700 RDI: 0000000000000003
[  690.687047] RBP: ffff88005acbff98 R08: 0000000000000001 R09: 0000000000000000
[  690.687519] R10: 00007fff26d2d480 R11: 0000000000000246 R12: 0000000000000002
[  690.687996] R13: 0000000001258070 R14: 0000000000000001 R15: 0000000000000000
[  690.688475]  ? trace_hardirqs_off_caller+0xa7/0xcf
[  690.688887] Code: 00 00 e8 2a 02 ae ff 49 8b bc 1d 60 02 00 00 48 83
c3 08 e8 19 02 ae ff 48 83 fb 20 75 dc 45 31 f6 4d 89 f7 4d 03 bd 20 02
00 00 <49> 8b 07 49 39 c7 75 24 49 83 c6 10 49 81 fe 00 40 00 00 75 e1
[  690.690200] RIP: hhf_destroy+0x48/0xbc RSP: ffff88005acbf9e0
[  690.690636] CR2: 0000000000000000

Fixes: 87b60cfacf9f ("net_sched: fix error recovery at qdisc creation")
Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent e89d469
Raw File
bsg-lib.c
/*
 *  BSG helper library
 *
 *  Copyright (C) 2008   James Smart, Emulex Corporation
 *  Copyright (C) 2011   Red Hat, Inc.  All rights reserved.
 *  Copyright (C) 2011   Mike Christie
 *
 *  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.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/scatterlist.h>
#include <linux/bsg-lib.h>
#include <linux/export.h>
#include <scsi/scsi_cmnd.h>

/**
 * bsg_destroy_job - routine to teardown/delete a bsg job
 * @job: bsg_job that is to be torn down
 */
static void bsg_destroy_job(struct kref *kref)
{
	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
	struct request *rq = job->req;

	blk_end_request_all(rq, BLK_STS_OK);

	put_device(job->dev);	/* release reference for the request */

	kfree(job->request_payload.sg_list);
	kfree(job->reply_payload.sg_list);
	kfree(job);
}

void bsg_job_put(struct bsg_job *job)
{
	kref_put(&job->kref, bsg_destroy_job);
}
EXPORT_SYMBOL_GPL(bsg_job_put);

int bsg_job_get(struct bsg_job *job)
{
	return kref_get_unless_zero(&job->kref);
}
EXPORT_SYMBOL_GPL(bsg_job_get);

/**
 * bsg_job_done - completion routine for bsg requests
 * @job: bsg_job that is complete
 * @result: job reply result
 * @reply_payload_rcv_len: length of payload recvd
 *
 * The LLD should call this when the bsg job has completed.
 */
void bsg_job_done(struct bsg_job *job, int result,
		  unsigned int reply_payload_rcv_len)
{
	struct request *req = job->req;
	struct request *rsp = req->next_rq;
	struct scsi_request *rq = scsi_req(req);
	int err;

	err = scsi_req(job->req)->result = result;
	if (err < 0)
		/* we're only returning the result field in the reply */
		rq->sense_len = sizeof(u32);
	else
		rq->sense_len = job->reply_len;
	/* we assume all request payload was transferred, residual == 0 */
	rq->resid_len = 0;

	if (rsp) {
		WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len);

		/* set reply (bidi) residual */
		scsi_req(rsp)->resid_len -=
			min(reply_payload_rcv_len, scsi_req(rsp)->resid_len);
	}
	blk_complete_request(req);
}
EXPORT_SYMBOL_GPL(bsg_job_done);

/**
 * bsg_softirq_done - softirq done routine for destroying the bsg requests
 * @rq: BSG request that holds the job to be destroyed
 */
static void bsg_softirq_done(struct request *rq)
{
	struct bsg_job *job = rq->special;

	bsg_job_put(job);
}

static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
{
	size_t sz = (sizeof(struct scatterlist) * req->nr_phys_segments);

	BUG_ON(!req->nr_phys_segments);

	buf->sg_list = kzalloc(sz, GFP_KERNEL);
	if (!buf->sg_list)
		return -ENOMEM;
	sg_init_table(buf->sg_list, req->nr_phys_segments);
	scsi_req(req)->resid_len = blk_rq_bytes(req);
	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
	buf->payload_len = blk_rq_bytes(req);
	return 0;
}

/**
 * bsg_create_job - create the bsg_job structure for the bsg request
 * @dev: device that is being sent the bsg request
 * @req: BSG request that needs a job structure
 */
static int bsg_create_job(struct device *dev, struct request *req)
{
	struct request *rsp = req->next_rq;
	struct request_queue *q = req->q;
	struct scsi_request *rq = scsi_req(req);
	struct bsg_job *job;
	int ret;

	BUG_ON(req->special);

	job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL);
	if (!job)
		return -ENOMEM;

	req->special = job;
	job->req = req;
	if (q->bsg_job_size)
		job->dd_data = (void *)&job[1];
	job->request = rq->cmd;
	job->request_len = rq->cmd_len;
	job->reply = rq->sense;
	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
						 * allocated */
	if (req->bio) {
		ret = bsg_map_buffer(&job->request_payload, req);
		if (ret)
			goto failjob_rls_job;
	}
	if (rsp && rsp->bio) {
		ret = bsg_map_buffer(&job->reply_payload, rsp);
		if (ret)
			goto failjob_rls_rqst_payload;
	}
	job->dev = dev;
	/* take a reference for the request */
	get_device(job->dev);
	kref_init(&job->kref);
	return 0;

failjob_rls_rqst_payload:
	kfree(job->request_payload.sg_list);
failjob_rls_job:
	kfree(job);
	return -ENOMEM;
}

/**
 * bsg_request_fn - generic handler for bsg requests
 * @q: request queue to manage
 *
 * On error the create_bsg_job function should return a -Exyz error value
 * that will be set to ->result.
 *
 * Drivers/subsys should pass this to the queue init function.
 */
static void bsg_request_fn(struct request_queue *q)
	__releases(q->queue_lock)
	__acquires(q->queue_lock)
{
	struct device *dev = q->queuedata;
	struct request *req;
	struct bsg_job *job;
	int ret;

	if (!get_device(dev))
		return;

	while (1) {
		req = blk_fetch_request(q);
		if (!req)
			break;
		spin_unlock_irq(q->queue_lock);

		ret = bsg_create_job(dev, req);
		if (ret) {
			scsi_req(req)->result = ret;
			blk_end_request_all(req, BLK_STS_OK);
			spin_lock_irq(q->queue_lock);
			continue;
		}

		job = req->special;
		ret = q->bsg_job_fn(job);
		spin_lock_irq(q->queue_lock);
		if (ret)
			break;
	}

	spin_unlock_irq(q->queue_lock);
	put_device(dev);
	spin_lock_irq(q->queue_lock);
}

/**
 * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
 * @dev: device to attach bsg device to
 * @name: device to give bsg device
 * @job_fn: bsg job handler
 * @dd_job_size: size of LLD data needed for each job
 */
struct request_queue *bsg_setup_queue(struct device *dev, char *name,
		bsg_job_fn *job_fn, int dd_job_size)
{
	struct request_queue *q;
	int ret;

	q = blk_alloc_queue(GFP_KERNEL);
	if (!q)
		return ERR_PTR(-ENOMEM);
	q->cmd_size = sizeof(struct scsi_request);
	q->request_fn = bsg_request_fn;

	ret = blk_init_allocated_queue(q);
	if (ret)
		goto out_cleanup_queue;

	q->queuedata = dev;
	q->bsg_job_size = dd_job_size;
	q->bsg_job_fn = job_fn;
	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
	blk_queue_softirq_done(q, bsg_softirq_done);
	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);

	ret = bsg_register_queue(q, dev, name, NULL);
	if (ret) {
		printk(KERN_ERR "%s: bsg interface failed to "
		       "initialize - register queue\n", dev->kobj.name);
		goto out_cleanup_queue;
	}

	return q;
out_cleanup_queue:
	blk_cleanup_queue(q);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(bsg_setup_queue);
back to top