Date:   Fri, 20 Apr 2018 15:25:53 +0800
From:   Chao Yu <yuchao0@...wei.com>
To:     Jaegeuk Kim <jaegeuk@...nel.org>
CC:     <linux-f2fs-devel@...ts.sourceforge.net>,
        <linux-kernel@...r.kernel.org>, <chao@...nel.org>
Subject: Re: [PATCH 5/5] f2fs: fix to avoid race during access gc_thread
 pointer

On 2018/4/20 11:54, Jaegeuk Kim wrote:
> On 04/20, Chao Yu wrote:
>> On 2018/4/20 11:19, Jaegeuk Kim wrote:
>>> On 04/18, Chao Yu wrote:
>>>> Thread A			Thread B		Thread C
>>>> - f2fs_remount
>>>>  - stop_gc_thread
>>>> 				- f2fs_sbi_store
>>>> 							- issue_discard_thread
>>>>    sbi->gc_thread = NULL;
>>>> 				  sbi->gc_thread->gc_wake = 1
>>>> 							  access sbi->gc_thread->gc_urgent
>>>
>>> Do we simply need a lock for this?
>>
>> Code will be more complicated for handling existed and new coming fields with
>> the sbi->gc_thread pointer, and causing unneeded lock overhead, right?
>>
>> So let's just allocate memory during fill_super?
> 
> No, the case is when stopping the thread. We can keep the gc_thread and indicate
> its state as "disabled". Then, we need to handle other paths with the state?

After this patch, we use f2fs_gc_kthread.f2fs_gc_task to indicate whether GC
thread is existed, so you mean if we do that change, we also need to add a lock,
and access/update other fields in f2fs_gc_kthread after we check
f2fs_gc_kthread.f2fs_gc_task with a lock, right?

Like:

f2fs_sbi_store:

	if (!strcmp(a->attr.name, "gc_urgent") && t == 1) {
		gc_context_lock()
		if (GC_I(sbi)->f2fs_gc_task) {
			GC_I(sbi)->gc_wake = 1;
			...
		}
		gc_context_unlock()

Do you mean that?

Thanks,

> 
>>
>> Thanks,
>>
>>>
>>>>
>>>> Previously, we allocate memory for sbi->gc_thread based on background
>>>> gc thread mount option, the memory can be released if we turn off
>>>> that mount option, but still there are several places access gc_thread
>>>> pointer without considering race condition, result in NULL point
>>>> dereference.
>>>>
>>>> In order to fix this issue, keep gc_thread structure valid in sbi all
>>>> the time instead of alloc/free it dynamically.
>>>>
>>>> Signed-off-by: Chao Yu <yuchao0@...wei.com>
>>>> ---
>>>>  fs/f2fs/debug.c   |  3 +--
>>>>  fs/f2fs/f2fs.h    |  7 +++++++
>>>>  fs/f2fs/gc.c      | 58 +++++++++++++++++++++++++++++++++----------------------
>>>>  fs/f2fs/segment.c |  4 ++--
>>>>  fs/f2fs/super.c   | 13 +++++++++++--
>>>>  fs/f2fs/sysfs.c   |  8 ++++----
>>>>  6 files changed, 60 insertions(+), 33 deletions(-)
>>>>
>>>> diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
>>>> index 715beb85e9db..7bb036a3bb81 100644
>>>> --- a/fs/f2fs/debug.c
>>>> +++ b/fs/f2fs/debug.c
>>>> @@ -223,8 +223,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
>>>>  	si->cache_mem = 0;
>>>>  
>>>>  	/* build gc */
>>>> -	if (sbi->gc_thread)
>>>> -		si->cache_mem += sizeof(struct f2fs_gc_kthread);
>>>> +	si->cache_mem += sizeof(struct f2fs_gc_kthread);
>>>>  
>>>>  	/* build merge flush thread */
>>>>  	if (SM_I(sbi)->fcc_info)
>>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>>>> index 567c6bb57ae3..c553f63199e8 100644
>>>> --- a/fs/f2fs/f2fs.h
>>>> +++ b/fs/f2fs/f2fs.h
>>>> @@ -1412,6 +1412,11 @@ static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi)
>>>>  	return (struct sit_info *)(SM_I(sbi)->sit_info);
>>>>  }
>>>>  
>>>> +static inline struct f2fs_gc_kthread *GC_I(struct f2fs_sb_info *sbi)
>>>> +{
>>>> +	return (struct f2fs_gc_kthread *)(sbi->gc_thread);
>>>> +}
>>>> +
>>>>  static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi)
>>>>  {
>>>>  	return (struct free_segmap_info *)(SM_I(sbi)->free_info);
>>>> @@ -2954,6 +2959,8 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
>>>>  /*
>>>>   * gc.c
>>>>   */
>>>> +int init_gc_context(struct f2fs_sb_info *sbi);
>>>> +void destroy_gc_context(struct f2fs_sb_info * sbi);
>>>>  int start_gc_thread(struct f2fs_sb_info *sbi);
>>>>  void stop_gc_thread(struct f2fs_sb_info *sbi);
>>>>  block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
>>>> diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
>>>> index da89ca16a55d..7d310e454b77 100644
>>>> --- a/fs/f2fs/gc.c
>>>> +++ b/fs/f2fs/gc.c
>>>> @@ -26,8 +26,8 @@
>>>>  static int gc_thread_func(void *data)
>>>>  {
>>>>  	struct f2fs_sb_info *sbi = data;
>>>> -	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
>>>> -	wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
>>>> +	struct f2fs_gc_kthread *gc_th = GC_I(sbi);
>>>> +	wait_queue_head_t *wq = &gc_th->gc_wait_queue_head;
>>>>  	unsigned int wait_ms;
>>>>  
>>>>  	wait_ms = gc_th->min_sleep_time;
>>>> @@ -114,17 +114,15 @@ static int gc_thread_func(void *data)
>>>>  	return 0;
>>>>  }
>>>>  
>>>> -int start_gc_thread(struct f2fs_sb_info *sbi)
>>>> +int init_gc_context(struct f2fs_sb_info *sbi)
>>>>  {
>>>>  	struct f2fs_gc_kthread *gc_th;
>>>> -	dev_t dev = sbi->sb->s_bdev->bd_dev;
>>>> -	int err = 0;
>>>>  
>>>>  	gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
>>>> -	if (!gc_th) {
>>>> -		err = -ENOMEM;
>>>> -		goto out;
>>>> -	}
>>>> +	if (!gc_th)
>>>> +		return -ENOMEM;
>>>> +
>>>> +	gc_th->f2fs_gc_task = NULL;
>>>>  
>>>>  	gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
>>>>  	gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
>>>> @@ -139,26 +137,41 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
>>>>  	gc_th->atomic_file[FG_GC] = 0;
>>>>  
>>>>  	sbi->gc_thread = gc_th;
>>>> -	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
>>>> -	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
>>>> +
>>>> +	return 0;
>>>> +}
>>>> +
>>>> +void destroy_gc_context(struct f2fs_sb_info *sbi)
>>>> +{
>>>> +	kfree(GC_I(sbi));
>>>> +	sbi->gc_thread = NULL;
>>>> +}
>>>> +
>>>> +int start_gc_thread(struct f2fs_sb_info *sbi)
>>>> +{
>>>> +	struct f2fs_gc_kthread *gc_th = GC_I(sbi);
>>>> +	dev_t dev = sbi->sb->s_bdev->bd_dev;
>>>> +	int err = 0;
>>>> +
>>>> +	init_waitqueue_head(&gc_th->gc_wait_queue_head);
>>>> +	gc_th->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
>>>>  			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
>>>>  	if (IS_ERR(gc_th->f2fs_gc_task)) {
>>>>  		err = PTR_ERR(gc_th->f2fs_gc_task);
>>>> -		kfree(gc_th);
>>>> -		sbi->gc_thread = NULL;
>>>> +		gc_th->f2fs_gc_task = NULL;
>>>>  	}
>>>> -out:
>>>> +
>>>>  	return err;
>>>>  }
>>>>  
>>>>  void stop_gc_thread(struct f2fs_sb_info *sbi)
>>>>  {
>>>> -	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
>>>> -	if (!gc_th)
>>>> -		return;
>>>> -	kthread_stop(gc_th->f2fs_gc_task);
>>>> -	kfree(gc_th);
>>>> -	sbi->gc_thread = NULL;
>>>> +	struct f2fs_gc_kthread *gc_th = GC_I(sbi);
>>>> +
>>>> +	if (gc_th->f2fs_gc_task) {
>>>> +		kthread_stop(gc_th->f2fs_gc_task);
>>>> +		gc_th->f2fs_gc_task = NULL;
>>>> +	}
>>>>  }
>>>>  
>>>>  static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type)
>>>> @@ -190,15 +203,14 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
>>>>  		p->max_search = dirty_i->nr_dirty[type];
>>>>  		p->ofs_unit = 1;
>>>>  	} else {
>>>> -		p->gc_mode = select_gc_type(sbi->gc_thread, gc_type);
>>>> +		p->gc_mode = select_gc_type(GC_I(sbi), gc_type);
>>>>  		p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
>>>>  		p->max_search = dirty_i->nr_dirty[DIRTY];
>>>>  		p->ofs_unit = sbi->segs_per_sec;
>>>>  	}
>>>>  
>>>>  	/* we need to check every dirty segments in the FG_GC case */
>>>> -	if (gc_type != FG_GC &&
>>>> -			(sbi->gc_thread && !sbi->gc_thread->gc_urgent) &&
>>>> +	if (gc_type != FG_GC && !GC_I(sbi)->gc_urgent &&
>>>>  			p->max_search > sbi->max_victim_search)
>>>>  		p->max_search = sbi->max_victim_search;
>>>>  
>>>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>>>> index 831cefa088bc..c869ce54be4d 100644
>>>> --- a/fs/f2fs/segment.c
>>>> +++ b/fs/f2fs/segment.c
>>>> @@ -177,7 +177,7 @@ bool need_SSR(struct f2fs_sb_info *sbi)
>>>>  
>>>>  	if (test_opt(sbi, LFS))
>>>>  		return false;
>>>> -	if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
>>>> +	if (GC_I(sbi)->gc_urgent)
>>>>  		return true;
>>>>  
>>>>  	return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
>>>> @@ -1422,7 +1422,7 @@ static int issue_discard_thread(void *data)
>>>>  		if (dcc->discard_wake)
>>>>  			dcc->discard_wake = 0;
>>>>  
>>>> -		if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
>>>> +		if (GC_I(sbi)->gc_urgent)
>>>>  			init_discard_policy(&dpolicy, DPOLICY_FORCE, 1);
>>>>  
>>>>  		sb_start_intwrite(sbi->sb);
>>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
>>>> index d01c11f5e9c1..f3a5f463496f 100644
>>>> --- a/fs/f2fs/super.c
>>>> +++ b/fs/f2fs/super.c
>>>> @@ -1012,6 +1012,8 @@ static void f2fs_put_super(struct super_block *sb)
>>>>  		write_checkpoint(sbi, &cpc);
>>>>  	}
>>>>  
>>>> +	destroy_gc_context(sbi);
>>>> +
>>>>  	/* write_checkpoint can update stat informaion */
>>>>  	f2fs_destroy_stats(sbi);
>>>>  
>>>> @@ -1044,6 +1046,7 @@ static void f2fs_put_super(struct super_block *sb)
>>>>  	kfree(sbi->raw_super);
>>>>  
>>>>  	destroy_device_list(sbi);
>>>> +	destroy_gc_context(sbi);
>>>>  	mempool_destroy(sbi->write_io_dummy);
>>>>  #ifdef CONFIG_QUOTA
>>>>  	for (i = 0; i < MAXQUOTAS; i++)
>>>> @@ -1476,11 +1479,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
>>>>  	 * option. Also sync the filesystem.
>>>>  	 */
>>>>  	if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) {
>>>> -		if (sbi->gc_thread) {
>>>> +		if (GC_I(sbi)->f2fs_gc_task) {
>>>>  			stop_gc_thread(sbi);
>>>>  			need_restart_gc = true;
>>>>  		}
>>>> -	} else if (!sbi->gc_thread) {
>>>> +	} else if (!GC_I(sbi)->f2fs_gc_task) {
>>>>  		err = start_gc_thread(sbi);
>>>>  		if (err)
>>>>  			goto restore_opts;
>>>> @@ -2771,6 +2774,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
>>>>  		goto free_meta_inode;
>>>>  	}
>>>>  
>>>> +	err = init_gc_context(sbi);
>>>> +	if (err)
>>>> +		goto free_checkpoint;
>>>> +
>>>>  	/* Initialize device list */
>>>>  	err = f2fs_scan_devices(sbi);
>>>>  	if (err) {
>>>> @@ -2981,6 +2988,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
>>>>  	destroy_segment_manager(sbi);
>>>>  free_devices:
>>>>  	destroy_device_list(sbi);
>>>> +	destroy_gc_context(sbi);
>>>> +free_checkpoint:
>>>>  	kfree(sbi->ckpt);
>>>>  free_meta_inode:
>>>>  	make_bad_inode(sbi->meta_inode);
>>>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
>>>> index 2c53de9251be..fb3cd477d985 100644
>>>> --- a/fs/f2fs/sysfs.c
>>>> +++ b/fs/f2fs/sysfs.c
>>>> @@ -46,7 +46,7 @@ struct f2fs_attr {
>>>>  static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
>>>>  {
>>>>  	if (struct_type == GC_THREAD)
>>>> -		return (unsigned char *)sbi->gc_thread;
>>>> +		return (unsigned char *)GC_I(sbi);
>>>>  	else if (struct_type == SM_INFO)
>>>>  		return (unsigned char *)SM_I(sbi);
>>>>  	else if (struct_type == DCC_INFO)
>>>> @@ -252,9 +252,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
>>>>  
>>>>  	if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
>>>>  		f2fs_reset_iostat(sbi);
>>>> -	if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) {
>>>> -		sbi->gc_thread->gc_wake = 1;
>>>> -		wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head);
>>>> +	if (!strcmp(a->attr.name, "gc_urgent") && t == 1) {
>>>> +		GC_I(sbi)->gc_wake = 1;
>>>> +		wake_up_interruptible_all(&GC_I(sbi)->gc_wait_queue_head);
>>>>  		wake_up_discard_thread(sbi, true);
>>>>  	}
>>>>  
>>>> -- 
>>>> 2.15.0.55.gc2ece9dc4de6
>>>
>>> .
>>>
> 
> .
> 

Powered by blists - more mailing lists