[PATCH V2] accel/amdxdna: Prevent PM resume deadlock in hwctx_sync_debug_bo()

[Lizhi Hou]

amdxdna_hwctx_sync_debug_bo() invokes the hardware
hwctx_sync_debug_bo() callback while holding xdna->dev_lock.

The callback may call amdxdna_cmd_submit(), which in turn calls
amdxdna_pm_resume_get(). If the device is suspended,
amdxdna_pm_resume_get() may synchronously execute
amdxdna_pm_resume(), which also acquires xdna->dev_lock, resulting
in a deadlock.

Avoid the deadlock by calling amdxdna_pm_resume_get() before holding
xdna->dev_lock.

Fixes: 7ea046838021 ("accel/amdxdna: Support firmware debug buffer")
Signed-off-by: Lizhi Hou <lizhi....@amd.com>
---
V2:
  Fix jumping forward over the guard(mutex) declaration.
 
 drivers/accel/amdxdna/amdxdna_ctx.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c 
b/drivers/accel/amdxdna/amdxdna_ctx.c
index ff6c3e8e5a15..2f3dfb155d1d 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.c
+++ b/drivers/accel/amdxdna/amdxdna_ctx.c
@@ -386,16 +386,25 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client 
*client, u32 debug_bo_hdl)
        if (!gobj)
                return -EINVAL;
 
+       ret = amdxdna_pm_resume_get(xdna);
+       if (ret) {
+               XDNA_ERR(xdna, "Resume failed, ret %d", ret);
+               goto put_obj;
+       }
+
        abo = to_xdna_obj(gobj);
-       guard(mutex)(&xdna->dev_lock);
+       mutex_lock(&xdna->dev_lock);
        hwctx = xa_load(&client->hwctx_xa, abo->assigned_hwctx);
        if (!hwctx) {
                ret = -EINVAL;
-               goto put_obj;
+               goto unlock;
        }
 
        ret = xdna->dev_info->ops->hwctx_sync_debug_bo(hwctx, debug_bo_hdl);
 
+unlock:
+       mutex_unlock(&xdna->dev_lock);
+       amdxdna_pm_suspend_put(xdna);
 put_obj:
        drm_gem_object_put(gobj);
        return ret;
-- 
2.34.1