[PATCH AUTOSEL 5.0 61/98] libceph: fix breakage caused by multipage bvecs

[PATCH AUTOSEL 5.0 61/98] libceph: fix breakage caused by multipage bvecs

[Sasha Levin]

From: Ilya Dryomov <idryomov@gmail.com>

[ Upstream commit 187df76325af5d9e12ae9daec1510307797e54f0 ]

A bvec can now consist of multiple physically contiguous pages.
This means that bvec_iter_advance() can move to a different page while
staying in the same bvec (i.e. ->bi_bvec_done != 0).

The messenger works in terms of segments which can now be defined as
the smaller of a bvec and a page.  The "more bytes to process in this
segment" condition holds only if bvec_iter_advance() leaves us in the
same bvec _and_ in the same page.  On next bvec (possibly in the same
page) and on next page (possibly in the same bvec) we may need to set
->last_piece.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin (Microsoft) <sashal@kernel.org>
---
 net/ceph/messenger.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 7e71b0df1fbc..3083988ce729 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -840,6 +840,7 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
 	struct ceph_bio_iter *it = &cursor->bio_iter;
+	struct page *page = bio_iter_page(it->bio, it->iter);
 
 	BUG_ON(bytes > cursor->resid);
 	BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
@@ -851,7 +852,8 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 		return false;   /* no more data */
 	}
 
-	if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
+	if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done &&
+		       page == bio_iter_page(it->bio, it->iter)))
 		return false;	/* more bytes to process in this segment */
 
 	if (!it->iter.bi_size) {
@@ -899,6 +901,7 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
 	struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
+	struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter);
 
 	BUG_ON(bytes > cursor->resid);
 	BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
@@ -910,7 +913,8 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
 		return false;   /* no more data */
 	}
 
-	if (!bytes || cursor->bvec_iter.bi_bvec_done)
+	if (!bytes || (cursor->bvec_iter.bi_bvec_done &&
+		       page == bvec_iter_page(bvecs, cursor->bvec_iter)))
 		return false;	/* more bytes to process in this segment */
 
 	BUG_ON(cursor->last_piece);
-- 
2.19.1

[PATCH AUTOSEL 5.0 71/98] ceph: fix use-after-free on symlink traversal

[Sasha Levin]

From: Al Viro <viro@zeniv.linux.org.uk>

[ Upstream commit daf5cc27eed99afdea8d96e71b89ba41f5406ef6 ]

free the symlink body after the same RCU delay we have for freeing the
struct inode itself, so that traversal during RCU pathwalk wouldn't step
into freed memory.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin (Microsoft) <sashal@kernel.org>
---
 fs/ceph/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9d1f34d46627..f7f9e305aaf8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -524,6 +524,7 @@ static void ceph_i_callback(struct rcu_head *head)
 	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	kfree(ci->i_symlink);
 	kmem_cache_free(ceph_inode_cachep, ci);
 }
 
@@ -561,7 +562,6 @@ void ceph_destroy_inode(struct inode *inode)
 		ceph_put_snap_realm(mdsc, realm);
 	}
 
-	kfree(ci->i_symlink);
 	while ((n = rb_first(&ci->i_fragtree)) != NULL) {
 		frag = rb_entry(n, struct ceph_inode_frag, node);
 		rb_erase(n, &ci->i_fragtree);
-- 
2.19.1

Re: [PATCH AUTOSEL 5.0 61/98] libceph: fix breakage caused by multipage bvecs

[Ilya Dryomov]

On Mon, Apr 22, 2019 at 9:44 PM Sasha Levin <sashal@kernel.org> wrote:
>
> From: Ilya Dryomov <idryomov@gmail.com>
>
> [ Upstream commit 187df76325af5d9e12ae9daec1510307797e54f0 ]
>
> A bvec can now consist of multiple physically contiguous pages.
> This means that bvec_iter_advance() can move to a different page while
> staying in the same bvec (i.e. ->bi_bvec_done != 0).
>
> The messenger works in terms of segments which can now be defined as
> the smaller of a bvec and a page.  The "more bytes to process in this
> segment" condition holds only if bvec_iter_advance() leaves us in the
> same bvec _and_ in the same page.  On next bvec (possibly in the same
> page) and on next page (possibly in the same bvec) we may need to set
> ->last_piece.
>
> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
> Signed-off-by: Sasha Levin (Microsoft) <sashal@kernel.org>
> ---
>  net/ceph/messenger.c | 8 ++++++--
>  1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
> index 7e71b0df1fbc..3083988ce729 100644
> --- a/net/ceph/messenger.c
> +++ b/net/ceph/messenger.c
> @@ -840,6 +840,7 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
>                                         size_t bytes)
>  {
>         struct ceph_bio_iter *it = &cursor->bio_iter;
> +       struct page *page = bio_iter_page(it->bio, it->iter);
>
>         BUG_ON(bytes > cursor->resid);
>         BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
> @@ -851,7 +852,8 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
>                 return false;   /* no more data */
>         }
>
> -       if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
> +       if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done &&
> +                      page == bio_iter_page(it->bio, it->iter)))
>                 return false;   /* more bytes to process in this segment */
>
>         if (!it->iter.bi_size) {
> @@ -899,6 +901,7 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
>                                         size_t bytes)
>  {
>         struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
> +       struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter);
>
>         BUG_ON(bytes > cursor->resid);
>         BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
> @@ -910,7 +913,8 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
>                 return false;   /* no more data */
>         }
>
> -       if (!bytes || cursor->bvec_iter.bi_bvec_done)
> +       if (!bytes || (cursor->bvec_iter.bi_bvec_done &&
> +                      page == bvec_iter_page(bvecs, cursor->bvec_iter)))
>                 return false;   /* more bytes to process in this segment */
>
>         BUG_ON(cursor->last_piece);

Same here, shouldn't be needed.

Thanks,

                Ilya

Re: [PATCH AUTOSEL 5.0 61/98] libceph: fix breakage caused by multipage bvecs

[Sasha Levin]

On Tue, Apr 23, 2019 at 10:28:56AM +0200, Ilya Dryomov wrote:
>On Mon, Apr 22, 2019 at 9:44 PM Sasha Levin <sashal@kernel.org> wrote:
>>
>> From: Ilya Dryomov <idryomov@gmail.com>
>>
>> [ Upstream commit 187df76325af5d9e12ae9daec1510307797e54f0 ]
>>
>> A bvec can now consist of multiple physically contiguous pages.
>> This means that bvec_iter_advance() can move to a different page while
>> staying in the same bvec (i.e. ->bi_bvec_done != 0).
>>
>> The messenger works in terms of segments which can now be defined as
>> the smaller of a bvec and a page.  The "more bytes to process in this
>> segment" condition holds only if bvec_iter_advance() leaves us in the
>> same bvec _and_ in the same page.  On next bvec (possibly in the same
>> page) and on next page (possibly in the same bvec) we may need to set
>> ->last_piece.
>>
>> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
>> Signed-off-by: Sasha Levin (Microsoft) <sashal@kernel.org>
>> ---
>>  net/ceph/messenger.c | 8 ++++++--
>>  1 file changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
>> index 7e71b0df1fbc..3083988ce729 100644
>> --- a/net/ceph/messenger.c
>> +++ b/net/ceph/messenger.c
>> @@ -840,6 +840,7 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
>>                                         size_t bytes)
>>  {
>>         struct ceph_bio_iter *it = &cursor->bio_iter;
>> +       struct page *page = bio_iter_page(it->bio, it->iter);
>>
>>         BUG_ON(bytes > cursor->resid);
>>         BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
>> @@ -851,7 +852,8 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
>>                 return false;   /* no more data */
>>         }
>>
>> -       if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
>> +       if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done &&
>> +                      page == bio_iter_page(it->bio, it->iter)))
>>                 return false;   /* more bytes to process in this segment */
>>
>>         if (!it->iter.bi_size) {
>> @@ -899,6 +901,7 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
>>                                         size_t bytes)
>>  {
>>         struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
>> +       struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter);
>>
>>         BUG_ON(bytes > cursor->resid);
>>         BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
>> @@ -910,7 +913,8 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
>>                 return false;   /* no more data */
>>         }
>>
>> -       if (!bytes || cursor->bvec_iter.bi_bvec_done)
>> +       if (!bytes || (cursor->bvec_iter.bi_bvec_done &&
>> +                      page == bvec_iter_page(bvecs, cursor->bvec_iter)))
>>                 return false;   /* more bytes to process in this segment */
>>
>>         BUG_ON(cursor->last_piece);
>
>Same here, shouldn't be needed.

Dropped, thanks!