UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

RDMA/cma: Fix deadlock on &lock in rdma_cma_listen_on_all() error unwind 

rdma_detroy_id() cannot be called under &lock - we must instead keep the
error'd ID around until &lock can be released, then destroy it.

This is complicated by the usual way listen IDs are destroyed through
cma_process_remove() which can run at any time and will asynchronously
destroy the same ID.

Remove the ID from visiblity of cma_process_remove() before going down the
destroy path outside the locking.

Fixes: c80a0c52d8 ("RDMA/cma: Add missing error handling of listen_id")
Link: https://lore.kernel.org/r/20201118133756.GK244516@ziepe.ca
Reported-by: syzbot+1bc48bf7f78253f664a9@syzkaller.appspotmail.com
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This commit is contained in:
Jason Gunthorpe 2020-11-18 09:33:23 -04:00
parent 6f6e2dcbb8
commit dd37d2f59e
1 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
drivers/infiniband/core/cma.c
View File

@ -2496,7 +2496,8 @@ static int cma_listen_handler(struct rdma_cm_id *id,
} }
static int cma_listen_on_dev(struct rdma_id_private *id_priv, static int cma_listen_on_dev(struct rdma_id_private *id_priv,
struct cma_device *cma_dev) struct cma_device *cma_dev,
struct rdma_id_private **to_destroy)
{ {
struct rdma_id_private *dev_id_priv; struct rdma_id_private *dev_id_priv;
struct net *net = id_priv->id.route.addr.dev_addr.net; struct net *net = id_priv->id.route.addr.dev_addr.net;
@ -2504,6 +2505,7 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
lockdep_assert_held(&lock); lockdep_assert_held(&lock);
*to_destroy = NULL;
if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
return 0; return 0;
@ -2518,7 +2520,6 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
rdma_addr_size(cma_src_addr(id_priv))); rdma_addr_size(cma_src_addr(id_priv)));
_cma_attach_to_dev(dev_id_priv, cma_dev); _cma_attach_to_dev(dev_id_priv, cma_dev);
list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
cma_id_get(id_priv); cma_id_get(id_priv);
dev_id_priv->internal_id = 1; dev_id_priv->internal_id = 1;
dev_id_priv->afonly = id_priv->afonly; dev_id_priv->afonly = id_priv->afonly;
@ -2528,32 +2529,40 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog);
if (ret) if (ret)
goto err_listen; goto err_listen;
list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
return 0; return 0;
err_listen: err_listen:
list_del(&id_priv->listen_list); /* Caller must destroy this after releasing lock */
*to_destroy = dev_id_priv;
dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret);
rdma_destroy_id(&dev_id_priv->id);
return ret; return ret;
} }
static int cma_listen_on_all(struct rdma_id_private *id_priv) static int cma_listen_on_all(struct rdma_id_private *id_priv)
{ {
struct rdma_id_private *to_destroy;
struct cma_device *cma_dev; struct cma_device *cma_dev;
int ret; int ret;
mutex_lock(&lock); mutex_lock(&lock);
list_add_tail(&id_priv->list, &listen_any_list); list_add_tail(&id_priv->list, &listen_any_list);
list_for_each_entry(cma_dev, &dev_list, list) { list_for_each_entry(cma_dev, &dev_list, list) {
ret = cma_listen_on_dev(id_priv, cma_dev); ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy);
if (ret) if (ret) {
/* Prevent racing with cma_process_remove() */
if (to_destroy)
list_del_init(&to_destroy->list);
goto err_listen; goto err_listen;
} }
}
mutex_unlock(&lock); mutex_unlock(&lock);
return 0; return 0;
err_listen: err_listen:
list_del(&id_priv->list); list_del(&id_priv->list);
mutex_unlock(&lock); mutex_unlock(&lock);
if (to_destroy)
rdma_destroy_id(&to_destroy->id);
return ret; return ret;
} }
@ -4855,6 +4864,7 @@ static void cma_process_remove(struct cma_device *cma_dev)
static int cma_add_one(struct ib_device *device) static int cma_add_one(struct ib_device *device)
{ {
struct rdma_id_private *to_destroy;
struct cma_device *cma_dev; struct cma_device *cma_dev;
struct rdma_id_private *id_priv; struct rdma_id_private *id_priv;
unsigned int i; unsigned int i;
@ -4902,7 +4912,7 @@ static int cma_add_one(struct ib_device *device)
mutex_lock(&lock); mutex_lock(&lock);
list_add_tail(&cma_dev->list, &dev_list); list_add_tail(&cma_dev->list, &dev_list);
list_for_each_entry(id_priv, &listen_any_list, list) { list_for_each_entry(id_priv, &listen_any_list, list) {
ret = cma_listen_on_dev(id_priv, cma_dev); ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy);
if (ret) if (ret)
goto free_listen; goto free_listen;
} }
@ -4915,6 +4925,7 @@ free_listen:
list_del(&cma_dev->list); list_del(&cma_dev->list);
mutex_unlock(&lock); mutex_unlock(&lock);
/* cma_process_remove() will delete to_destroy */
cma_process_remove(cma_dev); cma_process_remove(cma_dev);
kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_roce_tos);
free_gid_type: free_gid_type: