linux-kernel - Re: [PATCH] io_uring: fix deferred req iovec leak

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 6 Feb 2020 20:16:30 +0300
From:   Pavel Begunkov <asml.silence@...il.com>
To:     Jens Axboe <axboe@...nel.dk>, io-uring@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] io_uring: fix deferred req iovec leak

On 06/02/2020 20:04, Pavel Begunkov wrote:
> On 06/02/2020 19:51, Pavel Begunkov wrote:
>> After defer, a request will be prepared, that includes allocating iovec
>> if needed, and then submitted through io_wq_submit_work() but not custom
>> handler (e.g. io_rw_async()/io_sendrecv_async()). However, it'll leak
>> iovec, as it's in io-wq and the code goes as follows:
>>
>> io_read() {
>> 	if (!io_wq_current_is_worker())
>> 		kfree(iovec);
>> }
>>
>> Put all deallocation logic in io_{read,write,send,recv}(), which will
>> leave the memory, if going async with -EAGAIN.
>>
> Interestingly, this will fail badly if it returns -EAGAIN from io-wq context.
> Apparently, I need to do v2.
> 
Or not...
Jens, can you please explain what's with the -EAGAIN handling in
io_wq_submit_work()? Checking the code, it seems neither of
read/write/recv/send can return -EAGAIN from async context (i.e.
force_nonblock=false). Are there other ops that can do it?


>> It also fixes a leak after failed io_alloc_async_ctx() in
>> io_{recv,send}_msg().
>>
>> Signed-off-by: Pavel Begunkov <asml.silence@...il.com>
>> ---
>>  fs/io_uring.c | 47 ++++++++++++-----------------------------------
>>  1 file changed, 12 insertions(+), 35 deletions(-)
>>
>> diff --git a/fs/io_uring.c b/fs/io_uring.c
>> index bff7a03e873f..ce3dbd2b1b5c 100644
>> --- a/fs/io_uring.c
>> +++ b/fs/io_uring.c
>> @@ -2143,17 +2143,6 @@ static int io_alloc_async_ctx(struct io_kiocb *req)
>>  	return req->io == NULL;
>>  }
>>  
>> -static void io_rw_async(struct io_wq_work **workptr)
>> -{
>> -	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
>> -	struct iovec *iov = NULL;
>> -
>> -	if (req->io->rw.iov != req->io->rw.fast_iov)
>> -		iov = req->io->rw.iov;
>> -	io_wq_submit_work(workptr);
>> -	kfree(iov);
>> -}
>> -
>>  static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
>>  			     struct iovec *iovec, struct iovec *fast_iov,
>>  			     struct iov_iter *iter)
>> @@ -2166,7 +2155,6 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
>>  
>>  		io_req_map_rw(req, io_size, iovec, fast_iov, iter);
>>  	}
>> -	req->work.func = io_rw_async;
>>  	return 0;
>>  }
>>  
>> @@ -2253,8 +2241,7 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
>>  		}
>>  	}
>>  out_free:
>> -	if (!io_wq_current_is_worker())
>> -		kfree(iovec);
>> +	kfree(iovec);
>>  	return ret;
>>  }
>>  
>> @@ -2359,8 +2346,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
>>  		}
>>  	}
>>  out_free:
>> -	if (!io_wq_current_is_worker())
>> -		kfree(iovec);
>> +	kfree(iovec);
>>  	return ret;
>>  }
>>  
>> @@ -2955,19 +2941,6 @@ static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt,
>>  	return 0;
>>  }
>>  
>> -#if defined(CONFIG_NET)
>> -static void io_sendrecv_async(struct io_wq_work **workptr)
>> -{
>> -	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
>> -	struct iovec *iov = NULL;
>> -
>> -	if (req->io->rw.iov != req->io->rw.fast_iov)
>> -		iov = req->io->msg.iov;
>> -	io_wq_submit_work(workptr);
>> -	kfree(iov);
>> -}
>> -#endif
>> -
>>  static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>>  {
>>  #if defined(CONFIG_NET)
>> @@ -3036,17 +3009,19 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
>>  		if (force_nonblock && ret == -EAGAIN) {
>>  			if (req->io)
>>  				return -EAGAIN;
>> -			if (io_alloc_async_ctx(req))
>> +			if (io_alloc_async_ctx(req)) {
>> +				if (kmsg && kmsg->iov != kmsg->fast_iov)
>> +					kfree(kmsg->iov);
>>  				return -ENOMEM;
>> +			}
>>  			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
>> -			req->work.func = io_sendrecv_async;
>>  			return -EAGAIN;
>>  		}
>>  		if (ret == -ERESTARTSYS)
>>  			ret = -EINTR;
>>  	}
>>  
>> -	if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
>> +	if (kmsg && kmsg->iov != kmsg->fast_iov)
>>  		kfree(kmsg->iov);
>>  	io_cqring_add_event(req, ret);
>>  	if (ret < 0)
>> @@ -3180,17 +3155,19 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
>>  		if (force_nonblock && ret == -EAGAIN) {
>>  			if (req->io)
>>  				return -EAGAIN;
>> -			if (io_alloc_async_ctx(req))
>> +			if (io_alloc_async_ctx(req)) {
>> +				if (kmsg && kmsg->iov != kmsg->fast_iov)
>> +					kfree(kmsg->iov);
>>  				return -ENOMEM;
>> +			}
>>  			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
>> -			req->work.func = io_sendrecv_async;
>>  			return -EAGAIN;
>>  		}
>>  		if (ret == -ERESTARTSYS)
>>  			ret = -EINTR;
>>  	}
>>  
>> -	if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
>> +	if (kmsg && kmsg->iov != kmsg->fast_iov)
>>  		kfree(kmsg->iov);
>>  	io_cqring_add_event(req, ret);
>>  	if (ret < 0)
>>
> 

-- 
Pavel Begunkov



Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)