Patch "RDMA/cma: Fix listener leak in rdma_cma_listen_on_all() failure" has been added to the 5.10-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    RDMA/cma: Fix listener leak in rdma_cma_listen_on_all() failure

to the 5.10-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     rdma-cma-fix-listener-leak-in-rdma_cma_listen_on_all.patch
and it can be found in the queue-5.10 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit dea3a6a92c8a41463cb7aa76db9fc707ec2849a3
Author: Tao Liu <thomas.liu@xxxxxxxxx>
Date:   Mon Sep 13 17:33:44 2021 +0800

    RDMA/cma: Fix listener leak in rdma_cma_listen_on_all() failure
    
    [ Upstream commit ca465e1f1f9b38fe916a36f7d80c5d25f2337c81 ]
    
    If cma_listen_on_all() fails it leaves the per-device ID still on the
    listen_list but the state is not set to RDMA_CM_ADDR_BOUND.
    
    When the cmid is eventually destroyed cma_cancel_listens() is not called
    due to the wrong state, however the per-device IDs are still holding the
    refcount preventing the ID from being destroyed, thus deadlocking:
    
     task:rping state:D stack:   0 pid:19605 ppid: 47036 flags:0x00000084
     Call Trace:
      __schedule+0x29a/0x780
      ? free_unref_page_commit+0x9b/0x110
      schedule+0x3c/0xa0
      schedule_timeout+0x215/0x2b0
      ? __flush_work+0x19e/0x1e0
      wait_for_completion+0x8d/0xf0
      _destroy_id+0x144/0x210 [rdma_cm]
      ucma_close_id+0x2b/0x40 [rdma_ucm]
      __destroy_id+0x93/0x2c0 [rdma_ucm]
      ? __xa_erase+0x4a/0xa0
      ucma_destroy_id+0x9a/0x120 [rdma_ucm]
      ucma_write+0xb8/0x130 [rdma_ucm]
      vfs_write+0xb4/0x250
      ksys_write+0xb5/0xd0
      ? syscall_trace_enter.isra.19+0x123/0x190
      do_syscall_64+0x33/0x40
      entry_SYSCALL_64_after_hwframe+0x44/0xa9
    
    Ensure that cma_listen_on_all() atomically unwinds its action under the
    lock during error.
    
    Fixes: c80a0c52d85c ("RDMA/cma: Add missing error handling of listen_id")
    Link: https://lore.kernel.org/r/20210913093344.17230-1-thomas.liu@xxxxxxxxx
    Signed-off-by: Tao Liu <thomas.liu@xxxxxxxxx>
    Reviewed-by: Leon Romanovsky <leonro@xxxxxxxxxx>
    Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 3029e96161b5..8e54184566f7 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1750,15 +1750,16 @@ static void cma_cancel_route(struct rdma_id_private *id_priv)
 	}
 }
 
-static void cma_cancel_listens(struct rdma_id_private *id_priv)
+static void _cma_cancel_listens(struct rdma_id_private *id_priv)
 {
 	struct rdma_id_private *dev_id_priv;
 
+	lockdep_assert_held(&lock);
+
 	/*
 	 * Remove from listen_any_list to prevent added devices from spawning
 	 * additional listen requests.
 	 */
-	mutex_lock(&lock);
 	list_del(&id_priv->list);
 
 	while (!list_empty(&id_priv->listen_list)) {
@@ -1772,6 +1773,12 @@ static void cma_cancel_listens(struct rdma_id_private *id_priv)
 		rdma_destroy_id(&dev_id_priv->id);
 		mutex_lock(&lock);
 	}
+}
+
+static void cma_cancel_listens(struct rdma_id_private *id_priv)
+{
+	mutex_lock(&lock);
+	_cma_cancel_listens(id_priv);
 	mutex_unlock(&lock);
 }
 
@@ -2582,7 +2589,7 @@ static int cma_listen_on_all(struct rdma_id_private *id_priv)
 	return 0;
 
 err_listen:
-	list_del(&id_priv->list);
+	_cma_cancel_listens(id_priv);
 	mutex_unlock(&lock);
 	if (to_destroy)
 		rdma_destroy_id(&to_destroy->id);