drm/ttm: Use fault-injection to test error paths

Use fault-injection to test partial TTM swapout and interrupted swapin.
Return -EINTR for swapin to test the callers ability to handle and
restart the swapin, and on swapout perform a partial swapout to test that
the swapin and release_shrunken functionality.

v8:
- Use the core fault-injection system.
v9:
- Fix compliation failure for !CONFIG_FAULT_INJECTION

Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/intel-xe/20250305092220.123405-4-thomas.hellstrom@linux.intel.com

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index ffb7abf52bab7a2dd075010a13a2a248900b70b7..83b10706ba896b31e30f4d179db114b7164ff88a 100644 (file)
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -48,6 +48,13 @@
 
 #include "ttm_module.h"
 
+#ifdef CONFIG_FAULT_INJECTION
+#include <linux/fault-inject.h>
+static DECLARE_FAULT_ATTR(backup_fault_inject);
+#else
+#define should_fail(...) false
+#endif
+
 /**
  * struct ttm_pool_dma - Helper object for coherent DMA mappings
  *
@@ -514,6 +521,12 @@ static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore,
                if (ttm_backup_page_ptr_is_handle(p)) {
                        unsigned long handle = ttm_backup_page_ptr_to_handle(p);
 
+                       if (IS_ENABLED(CONFIG_FAULT_INJECTION) && ctx->interruptible &&
+                           should_fail(&backup_fault_inject, 1)) {
+                               ret = -EINTR;
+                               break;
+                       }
+
                        if (handle == 0) {
                                restore->restored_pages++;
                                continue;
@@ -1007,7 +1020,13 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 
        alloc_gfp = GFP_KERNEL | __GFP_HIGH | __GFP_NOWARN | __GFP_RETRY_MAYFAIL;
 
-       for (i = 0; i < tt->num_pages; ++i) {
+       num_pages = tt->num_pages;
+
+       /* Pretend doing fault injection by shrinking only half of the pages. */
+       if (IS_ENABLED(CONFIG_FAULT_INJECTION) && should_fail(&backup_fault_inject, 1))
+               num_pages = DIV_ROUND_UP(num_pages, 2);
+
+       for (i = 0; i < num_pages; ++i) {
                s64 shandle;
 
                page = tt->pages[i];
@@ -1293,6 +1312,10 @@ int ttm_pool_mgr_init(unsigned long num_pages)
                            &ttm_pool_debugfs_globals_fops);
        debugfs_create_file("page_pool_shrink", 0400, ttm_debugfs_root, NULL,
                            &ttm_pool_debugfs_shrink_fops);
+#ifdef CONFIG_FAULT_INJECTION
+       fault_create_debugfs_attr("backup_fault_inject", ttm_debugfs_root,
+                                 &backup_fault_inject);
+#endif
 #endif
 
        mm_shrinker = shrinker_alloc(0, "drm-ttm_pool");