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
blk-timeout.c
/*
* Functions related to generic timeout handling of requests.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/fault-inject.h>
#include "blk.h"
#include "blk-mq.h"
#ifdef CONFIG_FAIL_IO_TIMEOUT
static DECLARE_FAULT_ATTR(fail_io_timeout);
static int __init setup_fail_io_timeout(char *str)
{
return setup_fault_attr(&fail_io_timeout, str);
}
__setup("fail_io_timeout=", setup_fail_io_timeout);
int blk_should_fake_timeout(struct request_queue *q)
{
if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
return 0;
return should_fail(&fail_io_timeout, 1);
}
static int __init fail_io_timeout_debugfs(void)
{
struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout",
NULL, &fail_io_timeout);
return PTR_ERR_OR_ZERO(dir);
}
late_initcall(fail_io_timeout_debugfs);
ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct gendisk *disk = dev_to_disk(dev);
int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);
return sprintf(buf, "%d\n", set != 0);
}
ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct gendisk *disk = dev_to_disk(dev);
int val;
if (count) {
struct request_queue *q = disk->queue;
char *p = (char *) buf;
val = simple_strtoul(p, &p, 10);
spin_lock_irq(q->queue_lock);
if (val)
queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
else
queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
spin_unlock_irq(q->queue_lock);
}
return count;
}
#endif /* CONFIG_FAIL_IO_TIMEOUT */
/*
* blk_delete_timer - Delete/cancel timer for a given function.
* @req: request that we are canceling timer for
*
*/
void blk_delete_timer(struct request *req)
{
list_del_init(&req->timeout_list);
}
static void blk_rq_timed_out(struct request *req)
{
struct request_queue *q = req->q;
enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
if (q->rq_timed_out_fn)
ret = q->rq_timed_out_fn(req);
switch (ret) {
case BLK_EH_HANDLED:
__blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
blk_add_timer(req);
blk_clear_rq_complete(req);
break;
case BLK_EH_NOT_HANDLED:
/*
* LLD handles this for now but in the future
* we can send a request msg to abort the command
* and we can move more of the generic scsi eh code to
* the blk layer.
*/
break;
default:
printk(KERN_ERR "block: bad eh return: %d\n", ret);
break;
}
}
static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
unsigned int *next_set)
{
if (time_after_eq(jiffies, rq->deadline)) {
list_del_init(&rq->timeout_list);
/*
* Check if we raced with end io completion
*/
if (!blk_mark_rq_complete(rq))
blk_rq_timed_out(rq);
} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
*next_timeout = rq->deadline;
*next_set = 1;
}
}
void blk_timeout_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, timeout_work);
unsigned long flags, next = 0;
struct request *rq, *tmp;
int next_set = 0;
if (blk_queue_enter(q, true))
return;
spin_lock_irqsave(q->queue_lock, flags);
list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
blk_rq_check_expired(rq, &next, &next_set);
if (next_set)
mod_timer(&q->timeout, round_jiffies_up(next));
spin_unlock_irqrestore(q->queue_lock, flags);
blk_queue_exit(q);
}
/**
* blk_abort_request -- Request request recovery for the specified command
* @req: pointer to the request of interest
*
* This function requests that the block layer start recovery for the
* request by deleting the timer and calling the q's timeout function.
* LLDDs who implement their own error recovery MAY ignore the timeout
* event if they generated blk_abort_req. Must hold queue lock.
*/
void blk_abort_request(struct request *req)
{
if (blk_mark_rq_complete(req))
return;
if (req->q->mq_ops) {
blk_mq_rq_timed_out(req, false);
} else {
blk_delete_timer(req);
blk_rq_timed_out(req);
}
}
EXPORT_SYMBOL_GPL(blk_abort_request);
unsigned long blk_rq_timeout(unsigned long timeout)
{
unsigned long maxt;
maxt = round_jiffies_up(jiffies + BLK_MAX_TIMEOUT);
if (time_after(timeout, maxt))
timeout = maxt;
return timeout;
}
/**
* blk_add_timer - Start timeout timer for a single request
* @req: request that is about to start running.
*
* Notes:
* Each request has its own timer, and as it is added to the queue, we
* set up the timer. When the request completes, we cancel the timer.
*/
void blk_add_timer(struct request *req)
{
struct request_queue *q = req->q;
unsigned long expiry;
if (!q->mq_ops)
lockdep_assert_held(q->queue_lock);
/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
if (!q->mq_ops && !q->rq_timed_out_fn)
return;
BUG_ON(!list_empty(&req->timeout_list));
/*
* Some LLDs, like scsi, peek at the timeout to prevent a
* command from being retried forever.
*/
if (!req->timeout)
req->timeout = q->rq_timeout;
req->deadline = jiffies + req->timeout;
/*
* Only the non-mq case needs to add the request to a protected list.
* For the mq case we simply scan the tag map.
*/
if (!q->mq_ops)
list_add_tail(&req->timeout_list, &req->q->timeout_list);
/*
* If the timer isn't already pending or this timeout is earlier
* than an existing one, modify the timer. Round up to next nearest
* second.
*/
expiry = blk_rq_timeout(round_jiffies_up(req->deadline));
if (!timer_pending(&q->timeout) ||
time_before(expiry, q->timeout.expires)) {
unsigned long diff = q->timeout.expires - expiry;
/*
* Due to added timer slack to group timers, the timer
* will often be a little in front of what we asked for.
* So apply some tolerance here too, otherwise we keep
* modifying the timer because expires for value X
* will be X + something.
*/
if (!timer_pending(&q->timeout) || (diff >= HZ / 2))
mod_timer(&q->timeout, expiry);
}
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...