[PATCH] erofs: fix bio->bi_max_vecs behavior change

[PATCH] erofs: fix bio->bi_max_vecs behavior change

[Gao Xiang via Linux-erofs]

From: Gao Xiang <hsiangkao@redhat.com>

Martin reported an issue that directory read could be hung on the
latest -rc kernel with some certain image. The root cause is that
commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
is set as actual allocated vector number rather than the requested
number now.
Let's avoid using .bi_max_vecs completely instead.

Reported-by: Martin DEVERA <devik@eaxlabs.cz>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
Hi Chao,

Could you take some time on reviewing this patchset in advance?
I'd like to upstream this regression fix asap since it has noticable
impact on 5.12-rc kernel.

Thanks,
Gao Xiang

 fs/erofs/data.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index f88851c5c250..fa25d0eab5de 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -231,14 +231,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 		goto submit_bio_retry;
 
 	*last_block = current_block;
-
-	/* shift in advance in case of it followed by too many gaps */
-	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
-		/* err should reassign to 0 after submitting */
-		err = 0;
-		goto submit_bio_out;
-	}
-
 	return bio;
 
 err_out:
@@ -252,7 +244,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* if updated manually, continuous pages has a gap */
 	if (bio)
-submit_bio_out:
 		submit_bio(bio);
 	return err ? ERR_PTR(err) : NULL;
 }
@@ -274,7 +265,8 @@ static int erofs_raw_access_readpage(struct file *file, struct page *page)
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
+	if (bio)
+		submit_bio(bio);
 	return 0;
 }
 
@@ -305,7 +297,6 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		put_page(page);
 	}
 
-	/* the rare case (end in gaps) */
 	if (bio)
 		submit_bio(bio);
 }
-- 
2.20.1

[PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Gao Xiang via Linux-erofs]

From: Gao Xiang <hsiangkao@redhat.com>

Martin reported an issue that directory read could be hung on the
latest -rc kernel with some certain image. The root cause is that
commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
is set as actual allocated vector number rather than the requested
number now.

Let's avoid using .bi_max_vecs completely instead.

Reported-by: Martin DEVERA <devik@eaxlabs.cz>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
change since v1:
 - since bio->bi_max_vecs doesn't record extent blocks anymore,
   introduce a remaining extent block to avoid extent excess.

 fs/erofs/data.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index f88851c5c250..1249e74b3bf0 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -129,6 +129,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 					      struct page *page,
 					      erofs_off_t *last_block,
 					      unsigned int nblocks,
+					      unsigned int *eblks,
 					      bool ra)
 {
 	struct inode *const inode = mapping->host;
@@ -145,8 +146,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* note that for readpage case, bio also equals to NULL */
 	if (bio &&
-	    /* not continuous */
-	    *last_block + 1 != current_block) {
+	    (*last_block + 1 != current_block || !*eblks)) {
 submit_bio_retry:
 		submit_bio(bio);
 		bio = NULL;
@@ -216,7 +216,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
 			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
 
-		bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks));
+		*eblks = bio_max_segs(nblocks);
+		bio = bio_alloc(GFP_NOIO, *eblks);
 
 		bio->bi_end_io = erofs_readendio;
 		bio_set_dev(bio, sb->s_bdev);
@@ -229,16 +230,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 	/* out of the extent or bio is full */
 	if (err < PAGE_SIZE)
 		goto submit_bio_retry;
-
+	--*eblks;
 	*last_block = current_block;
-
-	/* shift in advance in case of it followed by too many gaps */
-	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
-		/* err should reassign to 0 after submitting */
-		err = 0;
-		goto submit_bio_out;
-	}
-
 	return bio;
 
 err_out:
@@ -252,7 +245,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 
 	/* if updated manually, continuous pages has a gap */
 	if (bio)
-submit_bio_out:
 		submit_bio(bio);
 	return err ? ERR_PTR(err) : NULL;
 }
@@ -264,23 +256,26 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
 static int erofs_raw_access_readpage(struct file *file, struct page *page)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio;
 
 	trace_erofs_readpage(page, true);
 
 	bio = erofs_read_raw_page(NULL, page->mapping,
-				  page, &last_block, 1, false);
+				  page, &last_block, 1, &eblks, false);
 
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
+	if (bio)
+		submit_bio(bio);
 	return 0;
 }
 
 static void erofs_raw_access_readahead(struct readahead_control *rac)
 {
 	erofs_off_t last_block;
+	unsigned int eblks;
 	struct bio *bio = NULL;
 	struct page *page;
 
@@ -291,7 +286,7 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		prefetchw(&page->flags);
 
 		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
-				readahead_count(rac), true);
+				readahead_count(rac), &eblks, true);
 
 		/* all the page errors are ignored when readahead */
 		if (IS_ERR(bio)) {
@@ -305,7 +300,6 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
 		put_page(page);
 	}
 
-	/* the rare case (end in gaps) */
 	if (bio)
 		submit_bio(bio);
 }
-- 
2.20.1

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Chao Yu]

On 2021/3/6 12:04, Gao Xiang wrote:
> From: Gao Xiang <hsiangkao@redhat.com>
> 
> Martin reported an issue that directory read could be hung on the
> latest -rc kernel with some certain image. The root cause is that
> commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
> vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
> is set as actual allocated vector number rather than the requested
> number now.
> 
> Let's avoid using .bi_max_vecs completely instead.
> 
> Reported-by: Martin DEVERA <devik@eaxlabs.cz>
> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>

Looks good to me, btw, it needs to Cc stable mailing list?

Reviewed-by: Chao Yu <yuchao0@huawei.com>

Thanks,

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Gao Xiang]

Hi Chao,

On Mon, Mar 08, 2021 at 09:29:30AM +0800, Chao Yu wrote:
> On 2021/3/6 12:04, Gao Xiang wrote:
> > From: Gao Xiang <hsiangkao@redhat.com>
> > 
> > Martin reported an issue that directory read could be hung on the
> > latest -rc kernel with some certain image. The root cause is that
> > commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
> > vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
> > is set as actual allocated vector number rather than the requested
> > number now.
> > 
> > Let's avoid using .bi_max_vecs completely instead.
> > 
> > Reported-by: Martin DEVERA <devik@eaxlabs.cz>
> > Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
> 
> Looks good to me, btw, it needs to Cc stable mailing list?
> 
> Reviewed-by: Chao Yu <yuchao0@huawei.com>
> 

Thanks for your review. <= 5.11 kernels are not impacted.
For now, this only impacts 5.12-rc due to a bio behavior
change (see commit baa2c7c97153). So personally I think
just leave as it is is fine.

Thanks,
Gao Xiang

> Thanks,
> 

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Chao Yu]

On 2021/3/8 10:36, Gao Xiang wrote:
> Hi Chao,
> 
> On Mon, Mar 08, 2021 at 09:29:30AM +0800, Chao Yu wrote:
>> On 2021/3/6 12:04, Gao Xiang wrote:
>>> From: Gao Xiang <hsiangkao@redhat.com>
>>>
>>> Martin reported an issue that directory read could be hung on the
>>> latest -rc kernel with some certain image. The root cause is that
>>> commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
>>> vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
>>> is set as actual allocated vector number rather than the requested
>>> number now.
>>>
>>> Let's avoid using .bi_max_vecs completely instead.
>>>
>>> Reported-by: Martin DEVERA <devik@eaxlabs.cz>
>>> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
>>
>> Looks good to me, btw, it needs to Cc stable mailing list?
>>
>> Reviewed-by: Chao Yu <yuchao0@huawei.com>
>>
> 
> Thanks for your review. <= 5.11 kernels are not impacted.
> For now, this only impacts 5.12-rc due to a bio behavior
> change (see commit baa2c7c97153). So personally I think
> just leave as it is is fine.

Okay, so that's fine if you send pull request before 5.12 formal release. ;)

Thanks,

> 
> Thanks,
> Gao Xiang
> 
>> Thanks,
>>
> 
> .
> 

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Gao Xiang]

On Mon, Mar 08, 2021 at 10:52:19AM +0800, Chao Yu wrote:
> On 2021/3/8 10:36, Gao Xiang wrote:
> > Hi Chao,
> > 
> > On Mon, Mar 08, 2021 at 09:29:30AM +0800, Chao Yu wrote:
> > > On 2021/3/6 12:04, Gao Xiang wrote:
> > > > From: Gao Xiang <hsiangkao@redhat.com>
> > > > 
> > > > Martin reported an issue that directory read could be hung on the
> > > > latest -rc kernel with some certain image. The root cause is that
> > > > commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
> > > > vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
> > > > is set as actual allocated vector number rather than the requested
> > > > number now.
> > > > 
> > > > Let's avoid using .bi_max_vecs completely instead.
> > > > 
> > > > Reported-by: Martin DEVERA <devik@eaxlabs.cz>
> > > > Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
> > > 
> > > Looks good to me, btw, it needs to Cc stable mailing list?
> > > 
> > > Reviewed-by: Chao Yu <yuchao0@huawei.com>
> > > 
> > 
> > Thanks for your review. <= 5.11 kernels are not impacted.
> > For now, this only impacts 5.12-rc due to a bio behavior
> > change (see commit baa2c7c97153). So personally I think
> > just leave as it is is fine.
> 
> Okay, so that's fine if you send pull request before 5.12 formal release. ;)

Yeah, it's an urgent commit and have very negative impact.
I pushed out -fixes branch just now. After leaving in linux-next
for days, will upstream it then asap... :-(

Thanks,
Gao Xiang

> 
> Thanks,
> 
> > 
> > Thanks,
> > Gao Xiang
> > 
> > > Thanks,
> > > 
> > 
> > .
> > 
> 

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Chao Yu]

On 2021/3/6 12:04, Gao Xiang wrote:
> From: Gao Xiang <hsiangkao@redhat.com>
> 
> Martin reported an issue that directory read could be hung on the
> latest -rc kernel with some certain image. The root cause is that
> commit baa2c7c97153 ("block: set .bi_max_vecs as actual allocated
> vector number") changes .bi_max_vecs behavior. bio->bi_max_vecs
> is set as actual allocated vector number rather than the requested
> number now.
> 
> Let's avoid using .bi_max_vecs completely instead.
> 
> Reported-by: Martin DEVERA <devik@eaxlabs.cz>
> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
> ---
> change since v1:
>   - since bio->bi_max_vecs doesn't record extent blocks anymore,
>     introduce a remaining extent block to avoid extent excess.
> 
>   fs/erofs/data.c | 28 +++++++++++-----------------
>   1 file changed, 11 insertions(+), 17 deletions(-)
> 
> diff --git a/fs/erofs/data.c b/fs/erofs/data.c
> index f88851c5c250..1249e74b3bf0 100644
> --- a/fs/erofs/data.c
> +++ b/fs/erofs/data.c
> @@ -129,6 +129,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   					      struct page *page,
>   					      erofs_off_t *last_block,
>   					      unsigned int nblocks,
> +					      unsigned int *eblks,
>   					      bool ra)
>   {
>   	struct inode *const inode = mapping->host;
> @@ -145,8 +146,7 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   
>   	/* note that for readpage case, bio also equals to NULL */
>   	if (bio &&
> -	    /* not continuous */
> -	    *last_block + 1 != current_block) {
> +	    (*last_block + 1 != current_block || !*eblks)) {

Xiang,

I found below function during checking bi_max_vecs usage in f2fs:

/**
  * bio_full - check if the bio is full
  * @bio:        bio to check
  * @len:        length of one segment to be added
  *
  * Return true if @bio is full and one segment with @len bytes can't be
  * added to the bio, otherwise return false
  */
static inline bool bio_full(struct bio *bio, unsigned len)
{
         if (bio->bi_vcnt >= bio->bi_max_vecs)
                 return true;

         if (bio->bi_iter.bi_size > UINT_MAX - len)
                 return true;

         return false;
}

Could you please check that whether it will be better to use bio_full()
rather than using left-space-in-bio maintained by erofs itself? something
like:

if (bio && (bio_full(bio, PAGE_SIZE) ||
	/* not continuous */
	(*last_block + 1 != current_block))

I'm thinking we need to decouple bio detail implementation as much as
possible, to avoid regression whenever bio used/max size definition
updates, though I've no idea how to fix f2fs case.

Let me know if you have other concern.

Thanks,

>   submit_bio_retry:
>   		submit_bio(bio);
>   		bio = NULL;
> @@ -216,7 +216,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
>   			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
>   
> -		bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks));
> +		*eblks = bio_max_segs(nblocks);
> +		bio = bio_alloc(GFP_NOIO, *eblks);
>   
>   		bio->bi_end_io = erofs_readendio;
>   		bio_set_dev(bio, sb->s_bdev);
> @@ -229,16 +230,8 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   	/* out of the extent or bio is full */
>   	if (err < PAGE_SIZE)
>   		goto submit_bio_retry;
> -
> +	--*eblks;
>   	*last_block = current_block;
> -
> -	/* shift in advance in case of it followed by too many gaps */
> -	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
> -		/* err should reassign to 0 after submitting */
> -		err = 0;
> -		goto submit_bio_out;
> -	}
> -
>   	return bio;
>   
>   err_out:
> @@ -252,7 +245,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   
>   	/* if updated manually, continuous pages has a gap */
>   	if (bio)
> -submit_bio_out:
>   		submit_bio(bio);
>   	return err ? ERR_PTR(err) : NULL;
>   }
> @@ -264,23 +256,26 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
>   static int erofs_raw_access_readpage(struct file *file, struct page *page)
>   {
>   	erofs_off_t last_block;
> +	unsigned int eblks;
>   	struct bio *bio;
>   
>   	trace_erofs_readpage(page, true);
>   
>   	bio = erofs_read_raw_page(NULL, page->mapping,
> -				  page, &last_block, 1, false);
> +				  page, &last_block, 1, &eblks, false);
>   
>   	if (IS_ERR(bio))
>   		return PTR_ERR(bio);
>   
> -	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
> +	if (bio)
> +		submit_bio(bio);
>   	return 0;
>   }
>   
>   static void erofs_raw_access_readahead(struct readahead_control *rac)
>   {
>   	erofs_off_t last_block;
> +	unsigned int eblks;
>   	struct bio *bio = NULL;
>   	struct page *page;
>   
> @@ -291,7 +286,7 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
>   		prefetchw(&page->flags);
>   
>   		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
> -				readahead_count(rac), true);
> +				readahead_count(rac), &eblks, true);
>   
>   		/* all the page errors are ignored when readahead */
>   		if (IS_ERR(bio)) {
> @@ -305,7 +300,6 @@ static void erofs_raw_access_readahead(struct readahead_control *rac)
>   		put_page(page);
>   	}
>   
> -	/* the rare case (end in gaps) */
>   	if (bio)
>   		submit_bio(bio);
>   }
> 

Re: [PATCH v2] erofs: fix bio->bi_max_vecs behavior change

[Gao Xiang]

Hi Chao,

On Fri, Mar 19, 2021 at 10:15:18AM +0800, Chao Yu wrote:
> On 2021/3/6 12:04, Gao Xiang wrote:

...

> > +	    (*last_block + 1 != current_block || !*eblks)) {
> 
> Xiang,
> 
> I found below function during checking bi_max_vecs usage in f2fs:
> 
> /**
>  * bio_full - check if the bio is full
>  * @bio:        bio to check
>  * @len:        length of one segment to be added
>  *
>  * Return true if @bio is full and one segment with @len bytes can't be
>  * added to the bio, otherwise return false
>  */
> static inline bool bio_full(struct bio *bio, unsigned len)
> {
>         if (bio->bi_vcnt >= bio->bi_max_vecs)
>                 return true;
> 
>         if (bio->bi_iter.bi_size > UINT_MAX - len)
>                 return true;
> 
>         return false;
> }
> 
> Could you please check that whether it will be better to use bio_full()
> rather than using left-space-in-bio maintained by erofs itself? something
> like:
> 
> if (bio && (bio_full(bio, PAGE_SIZE) ||
> 	/* not continuous */
> 	(*last_block + 1 != current_block))
> 
> I'm thinking we need to decouple bio detail implementation as much as
> possible, to avoid regression whenever bio used/max size definition
> updates, though I've no idea how to fix f2fs case.

Thanks for your suggestion.

Not quite sure I understand the idea... The original problem was that
when EROFS bio_alloc, the number of requested bvec also partially stood
for remaining blocks of the current on-disk extent to limit the read
length. but after that bio behavior change, bi_max_vec could be increased
internally by block layer (e.g. 1 --> 4), so bi_max_vecs is no longer
as what we expect (I mean passed-in). so could cause read request
out-of-bound or hung. That's why I decided to record it manually (never
rely on bio statistics anymore...)

Also btw, AFAIK, Jianan is still investigating to use iomap instead
(mainly resolve tail-packing inline path). And I'm also busy in big
pcluster and LZMA new features for the next cycle. So I think we might
leave it just as is and it would be replaced with iomap in the future.

Thanks,
Gao Xiang

> 
> Let me know if you have other concern.
> 
> Thanks,