Re: [f2fs-dev] [PATCH] f2fs: bio_alloc should never fail

[Chao Yu]

Hi Xiang,

On 2019/10/30 17:15, Gao Xiang wrote:
> Hi Chao,
> 
> On Wed, Oct 30, 2019 at 04:56:17PM +0800, Chao Yu wrote:
>> On 2019/10/30 11:55, Gao Xiang wrote:
>>> remove such useless code and related fault injection.
>>
>> Hi Xiang,
>>
>> Although, there is so many 'nofail' allocation in f2fs, I think we'd better
>> avoid such allocation as much as possible (now for read path, we may allow to
>> fail to allocate bio), I suggest to keep the failure path and bio allocation
>> injection.
>>
>> It looks bio_alloc() will use its own mempool, which may suffer deadlock
>> potentially. So how about changing to use bio_alloc_bioset(, , NULL) instead of
>> bio_alloc()?
> 
> Yes, I noticed the original commit 740432f83560 ("f2fs: handle failed bio allocation"),
> yet I don't find any real call trace clue what happened before.
> 
> As my understanding, if we allocate bios without submit_bio (I mean write path) with
> default bs and gfp_flags GFP_NOIO or GFP_KERNEL, I think it will be slept inside
> mempool rather than return NULL to its caller... Please correct me if I'm wrong...

I'm curious too...

Jaegeuk may know the details.

> 
> I could send another patch with bio_alloc_bioset(, , NULL), I am curious to know the
> original issue and how it solved though...
> 
> For read or flush path, since it will submit_bio and bio_alloc one by one, I think
> mempool will get a page quicker (memory failure path could be longer). But I can
> send a patch just by using bio_alloc_bioset(, , NULL) instead as you suggested later.

You're right, in low memory scenario, allocation with bioset will be faster, as
you mentioned offline, maybe we can add/use a priviate bioset like btrfs did
rather than using global one, however, we'd better check how deadlock happen
with a bioset mempool first ...

Thanks,

> 
> Thanks,
> Gao Xiang
> 
>>
>> Thanks,
>>
>>>
>>> Signed-off-by: Gao Xiang <gaoxiang25@xxxxxxxxxx>
>>> ---
>>>  Documentation/filesystems/f2fs.txt |  1 -
>>>  fs/f2fs/data.c                     |  6 ++----
>>>  fs/f2fs/f2fs.h                     | 21 ---------------------
>>>  fs/f2fs/segment.c                  |  5 +----
>>>  fs/f2fs/super.c                    |  1 -
>>>  5 files changed, 3 insertions(+), 31 deletions(-)
>>>
>>> diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
>>> index 7e1991328473..3477c3e4c08b 100644
>>> --- a/Documentation/filesystems/f2fs.txt
>>> +++ b/Documentation/filesystems/f2fs.txt
>>> @@ -172,7 +172,6 @@ fault_type=%d          Support configuring fault injection type, should be
>>>                         FAULT_KVMALLOC		0x000000002
>>>                         FAULT_PAGE_ALLOC		0x000000004
>>>                         FAULT_PAGE_GET		0x000000008
>>> -                       FAULT_ALLOC_BIO		0x000000010
>>>                         FAULT_ALLOC_NID		0x000000020
>>>                         FAULT_ORPHAN		0x000000040
>>>                         FAULT_BLOCK		0x000000080
>>> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
>>> index 5755e897a5f0..3b88dcb15de6 100644
>>> --- a/fs/f2fs/data.c
>>> +++ b/fs/f2fs/data.c
>>> @@ -288,7 +288,7 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
>>>  	struct f2fs_sb_info *sbi = fio->sbi;
>>>  	struct bio *bio;
>>>  
>>> -	bio = f2fs_bio_alloc(sbi, npages, true);
>>> +	bio = bio_alloc(GFP_NOIO, npages);
>>>  
>>>  	f2fs_target_device(sbi, fio->new_blkaddr, bio);
>>>  	if (is_read_io(fio->op)) {
>>> @@ -682,9 +682,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
>>>  	struct bio_post_read_ctx *ctx;
>>>  	unsigned int post_read_steps = 0;
>>>  
>>> -	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
>>> -	if (!bio)
>>> -		return ERR_PTR(-ENOMEM);
>>> +	bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
>>>  	f2fs_target_device(sbi, blkaddr, bio);
>>>  	bio->bi_end_io = f2fs_read_end_io;
>>>  	bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>>> index 4024790028aa..40012f874be0 100644
>>> --- a/fs/f2fs/f2fs.h
>>> +++ b/fs/f2fs/f2fs.h
>>> @@ -44,7 +44,6 @@ enum {
>>>  	FAULT_KVMALLOC,
>>>  	FAULT_PAGE_ALLOC,
>>>  	FAULT_PAGE_GET,
>>> -	FAULT_ALLOC_BIO,
>>>  	FAULT_ALLOC_NID,
>>>  	FAULT_ORPHAN,
>>>  	FAULT_BLOCK,
>>> @@ -2210,26 +2209,6 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
>>>  	return entry;
>>>  }
>>>  
>>> -static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
>>> -						int npages, bool no_fail)
>>> -{
>>> -	struct bio *bio;
>>> -
>>> -	if (no_fail) {
>>> -		/* No failure on bio allocation */
>>> -		bio = bio_alloc(GFP_NOIO, npages);
>>> -		if (!bio)
>>> -			bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
>>> -		return bio;
>>> -	}
>>> -	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
>>> -		f2fs_show_injection_info(FAULT_ALLOC_BIO);
>>> -		return NULL;
>>> -	}
>>> -
>>> -	return bio_alloc(GFP_KERNEL, npages);
>>> -}
>>> -
>>>  static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
>>>  {
>>>  	if (sbi->gc_mode == GC_URGENT)
>>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>>> index 808709581481..28457c878d0d 100644
>>> --- a/fs/f2fs/segment.c
>>> +++ b/fs/f2fs/segment.c
>>> @@ -552,10 +552,7 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi,
>>>  	struct bio *bio;
>>>  	int ret;
>>>  
>>> -	bio = f2fs_bio_alloc(sbi, 0, false);
>>> -	if (!bio)
>>> -		return -ENOMEM;
>>> -
>>> +	bio = bio_alloc(GFP_KERNEL, 0);
>>>  	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
>>>  	bio_set_dev(bio, bdev);
>>>  	ret = submit_bio_wait(bio);
>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
>>> index 1443cee15863..51945dd27f00 100644
>>> --- a/fs/f2fs/super.c
>>> +++ b/fs/f2fs/super.c
>>> @@ -44,7 +44,6 @@ const char *f2fs_fault_name[FAULT_MAX] = {
>>>  	[FAULT_KVMALLOC]	= "kvmalloc",
>>>  	[FAULT_PAGE_ALLOC]	= "page alloc",
>>>  	[FAULT_PAGE_GET]	= "page get",
>>> -	[FAULT_ALLOC_BIO]	= "alloc bio",
>>>  	[FAULT_ALLOC_NID]	= "alloc nid",
>>>  	[FAULT_ORPHAN]		= "orphan",
>>>  	[FAULT_BLOCK]		= "no more block",
>>>
> .
>