drm/xe/client: add missing bo locking in show_meminfo()

bo_meminfo() wants to inspect bo state like tt and the ttm resource,
however this state can change at any point leading to stuff like NPD and
UAF, if the bo lock is not held. Grab the bo lock when calling
bo_meminfo(), ensuring we drop any spinlocks first. In the case of
object_idr we now also need to hold a ref.

v2 (MattB)
  - Also add xe_bo_assert_held()

Fixes: 0845233388f8 ("drm/xe: Implement fdinfo memory stats printing")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240911155527.178910-6-matthew.auld@intel.com
(cherry picked from commit 4f63d712fa104c3ebefcb289d1e733e86d8698c7)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index badfa045ead808ec5d3b10db1b780e5050e73d2d..95a05c5bc897a74868d07be5d22da3161cb54417 100644 (file)
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
+#include "xe_assert.h"
 #include "xe_bo.h"
 #include "xe_bo_types.h"
 #include "xe_device_types.h"
@@ -151,10 +152,13 @@ void xe_drm_client_add_bo(struct xe_drm_client *client,
  */
 void xe_drm_client_remove_bo(struct xe_bo *bo)
 {
+       struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev);
        struct xe_drm_client *client = bo->client;
 
+       xe_assert(xe, !kref_read(&bo->ttm.base.refcount));
+
        spin_lock(&client->bos_lock);
-       list_del(&bo->client_link);
+       list_del_init(&bo->client_link);
        spin_unlock(&client->bos_lock);
 
        xe_drm_client_put(client);
@@ -166,6 +170,8 @@ static void bo_meminfo(struct xe_bo *bo,
        u64 sz = bo->size;
        u32 mem_type;
 
+       xe_bo_assert_held(bo);
+
        if (bo->placement.placement)
                mem_type = bo->placement.placement->mem_type;
        else
@@ -207,7 +213,20 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
        idr_for_each_entry(&file->object_idr, obj, id) {
                struct xe_bo *bo = gem_to_xe_bo(obj);
 
-               bo_meminfo(bo, stats);
+               if (dma_resv_trylock(bo->ttm.base.resv)) {
+                       bo_meminfo(bo, stats);
+                       xe_bo_unlock(bo);
+               } else {
+                       xe_bo_get(bo);
+                       spin_unlock(&file->table_lock);
+
+                       xe_bo_lock(bo, false);
+                       bo_meminfo(bo, stats);
+                       xe_bo_unlock(bo);
+
+                       xe_bo_put(bo);
+                       spin_lock(&file->table_lock);
+               }
        }
        spin_unlock(&file->table_lock);
 
@@ -217,7 +236,21 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
                if (!kref_get_unless_zero(&bo->ttm.base.refcount))
                        continue;
 
-               bo_meminfo(bo, stats);
+               if (dma_resv_trylock(bo->ttm.base.resv)) {
+                       bo_meminfo(bo, stats);
+                       xe_bo_unlock(bo);
+               } else {
+                       spin_unlock(&client->bos_lock);
+
+                       xe_bo_lock(bo, false);
+                       bo_meminfo(bo, stats);
+                       xe_bo_unlock(bo);
+
+                       spin_lock(&client->bos_lock);
+                       /* The bo ref will prevent this bo from being removed from the list */
+                       xe_assert(xef->xe, !list_empty(&bo->client_link));
+               }
+
                xe_bo_put_deferred(bo, &deferred);
        }
        spin_unlock(&client->bos_lock);