| 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
| ||
|
Message-ID: <YUFldgfRYrJyxFtz@T590>
Date: Wed, 15 Sep 2021 11:16:06 +0800
From: Ming Lei <ming.lei@...hat.com>
To: "yukuai (C)" <yukuai3@...wei.com>
Cc: axboe@...nel.dk, josef@...icpanda.com, hch@...radead.org,
linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
nbd@...er.debian.org, yi.zhang@...wei.com
Subject: Re: [PATCH v5 5/6] nbd: convert to use blk_mq_find_and_get_req()
On Wed, Sep 15, 2021 at 09:54:09AM +0800, yukuai (C) wrote:
> On 2021/09/14 22:37, Ming Lei wrote:
> > On Tue, Sep 14, 2021 at 05:19:31PM +0800, yukuai (C) wrote:
> > > On 在 2021/09/14 15:46, Ming Lei wrote:
> > >
> > > > If the above can happen, blk_mq_find_and_get_req() may not fix it too, just
> > > > wondering why not take the following simpler way for avoiding the UAF?
> > > >
> > > > diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> > > > index 5170a630778d..dfa5cce71f66 100644
> > > > --- a/drivers/block/nbd.c
> > > > +++ b/drivers/block/nbd.c
> > > > @@ -795,9 +795,13 @@ static void recv_work(struct work_struct *work)
> > > > work);
> > > > struct nbd_device *nbd = args->nbd;
> > > > struct nbd_config *config = nbd->config;
> > > > + struct request_queue *q = nbd->disk->queue;
> > > > struct nbd_cmd *cmd;
> > > > struct request *rq;
> > > > + if (!percpu_ref_tryget(&q->q_usage_counter))
> > > > + return;
> > > > +
> > > > while (1) {
> > > > cmd = nbd_read_stat(nbd, args->index);
> > > > if (IS_ERR(cmd)) {
> > > > @@ -813,6 +817,7 @@ static void recv_work(struct work_struct *work)
> > > > if (likely(!blk_should_fake_timeout(rq->q)))
> > > > blk_mq_complete_request(rq);
> > > > }
> > > > + blk_queue_exit(q);
> > > > nbd_config_put(nbd);
> > > > atomic_dec(&config->recv_threads);
> > > > wake_up(&config->recv_wq);
> > > >
> > >
> > > Hi, Ming
> > >
> > > This apporch is wrong.
> > >
> > > If blk_mq_freeze_queue() is called, and nbd is waiting for all
> > > request to complete. percpu_ref_tryget() will fail here, and deadlock
> > > will occur because request can't complete in recv_work().
> >
> > No, percpu_ref_tryget() won't fail until ->q_usage_counter is zero, when
> > it is perfectly fine to do nothing in recv_work().
> >
>
> Hi Ming
>
> This apporch is a good idea, however we should not get q_usage_counter
> in reccv_work(), because It will block freeze queue.
>
> How about get q_usage_counter in nbd_read_stat(), and put in error path
> or after request completion?
OK, looks I missed that nbd_read_stat() needs to wait for incoming reply
first, so how about the following change by partitioning nbd_read_stat()
into nbd_read_reply() and nbd_handle_reply()?
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 5170a630778d..477fe057fc93 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -683,38 +683,47 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
return 0;
}
-/* NULL returned = something went wrong, inform userspace */
-static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
+static int nbd_read_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
{
- struct nbd_config *config = nbd->config;
int result;
- struct nbd_reply reply;
- struct nbd_cmd *cmd;
- struct request *req = NULL;
- u64 handle;
- u16 hwq;
- u32 tag;
- struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
+ struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)};
struct iov_iter to;
- int ret = 0;
- reply.magic = 0;
+ reply->magic = 0;
iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply));
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
- if (result <= 0) {
- if (!nbd_disconnected(config))
+ if (result < 0) {
+ if (!nbd_disconnected(nbd->config))
dev_err(disk_to_dev(nbd->disk),
"Receive control failed (result %d)\n", result);
- return ERR_PTR(result);
+ return result;
}
- if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
+ if (ntohl(reply->magic) != NBD_REPLY_MAGIC) {
dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
- (unsigned long)ntohl(reply.magic));
- return ERR_PTR(-EPROTO);
+ (unsigned long)ntohl(reply->magic));
+ return -EPROTO;
}
- memcpy(&handle, reply.handle, sizeof(handle));
+ return 0;
+}
+
+/* NULL returned = something went wrong, inform userspace */
+static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
+{
+ struct nbd_config *config = nbd->config;
+ int result;
+ struct nbd_cmd *cmd;
+ struct request *req = NULL;
+ u64 handle;
+ u16 hwq;
+ u32 tag;
+ struct iov_iter to;
+ int ret = 0;
+
+ memcpy(&handle, reply->handle, sizeof(handle));
tag = nbd_handle_to_tag(handle);
hwq = blk_mq_unique_tag_to_hwq(tag);
if (hwq < nbd->tag_set.nr_hw_queues)
@@ -747,9 +756,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
ret = -ENOENT;
goto out;
}
- if (ntohl(reply.error)) {
+ if (ntohl(reply->error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
- ntohl(reply.error));
+ ntohl(reply->error));
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -795,24 +804,36 @@ static void recv_work(struct work_struct *work)
work);
struct nbd_device *nbd = args->nbd;
struct nbd_config *config = nbd->config;
+ struct request_queue *q = nbd->disk->queue;
+ struct nbd_sock *nsock;
struct nbd_cmd *cmd;
struct request *rq;
while (1) {
- cmd = nbd_read_stat(nbd, args->index);
- if (IS_ERR(cmd)) {
- struct nbd_sock *nsock = config->socks[args->index];
+ struct nbd_reply reply;
- mutex_lock(&nsock->tx_lock);
- nbd_mark_nsock_dead(nbd, nsock, 1);
- mutex_unlock(&nsock->tx_lock);
+ if (nbd_read_reply(nbd, args->index, &reply))
break;
- }
+ if (!percpu_ref_tryget(&q->q_usage_counter))
+ break;
+
+ cmd = nbd_handle_reply(nbd, args->index, &reply);
+ if (IS_ERR(cmd)) {
+ blk_queue_exit(q);
+ break;
+ }
rq = blk_mq_rq_from_pdu(cmd);
if (likely(!blk_should_fake_timeout(rq->q)))
blk_mq_complete_request(rq);
+ blk_queue_exit(q);
}
+
+ nsock = config->socks[args->index];
+ mutex_lock(&nsock->tx_lock);
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+
nbd_config_put(nbd);
atomic_dec(&config->recv_threads);
wake_up(&config->recv_wq);
Thanks,
Ming
Powered by blists - more mailing lists