drm/amdgpu: Add recovery_lock to save bad pages function

Fix race condition failure during UMC UE injection.

Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 08133de21fdd635015e0dae2a4baf46b34a5d539..53b957a5b9a65c806d1834daafda721d79ecbffe 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1935,9 +1935,11 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
        if (!con || !con->eh_data)
                return 0;
 
+       mutex_lock(&con->recovery_lock);
        control = &con->eeprom_control;
        data = con->eh_data;
        save_count = data->count - control->ras_num_recs;
+       mutex_unlock(&con->recovery_lock);
        /* only new entries are saved */
        if (save_count > 0) {
                if (amdgpu_ras_eeprom_append(control,