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
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:
/* Can we use req->errors here? */
__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_rq_timed_out_timer(unsigned long data)
{
struct request_queue *q = (struct request_queue *) data;
unsigned long flags, next = 0;
struct request *rq, *tmp;
int next_set = 0;
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_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;
blk_delete_timer(req);
if (req->q->mq_ops)
blk_mq_rq_timed_out(req, false);
else
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 (req->cmd_flags & REQ_NO_TIMEOUT)
return;
/* 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;
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 ...