[RFC,15/16] drm/ttm: Use fault-injection to test error paths

Commit Message

Thomas Hellstrom Feb. 15, 2023, 4:14 p.m. UTC

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.

Signed-off-by: Thomas Hellström <[e-mail]>
---
 drivers/gpu/drm/Kconfig        | 10 ++++++++++
 drivers/gpu/drm/ttm/ttm_pool.c | 17 ++++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

Patch

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 1efd33411a92..a78eed9af2c1 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -202,6 +202,16 @@  config DRM_TTM
 	  GPU memory types. Will be enabled automatically if a device driver
 	  uses it.
 
+config DRM_TTM_SHRINK_FAULT_INJECT
+	bool "Enable fault injection during TTM shrinking"
+	depends on DRM_TTM
+	default n
+	help
+	  Inject recoverable failures during TTM shrinking and recovery of
+	  shrunken objects. For DRM driver developers only.
+
+	  If in doubt, choose N.
+
 config DRM_BUDDY
 	tristate
 	depends on DRM
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 319998b4a325..d7c604593689 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -453,6 +453,7 @@  static bool ttm_pool_restore_valid(const struct ttm_pool_tt_restore *restore)
 static int ttm_pool_swapin(struct ttm_pool_tt_restore *restore,
 			   struct ttm_operation_ctx *ctx)
 {
+	static unsigned long __maybe_unused swappedin;
 	unsigned int i, nr = 1 << restore->order;
 	int ret = 0;
 
@@ -468,6 +469,13 @@  static int ttm_pool_swapin(struct ttm_pool_tt_restore *restore,
 			if (swap.val == 0)
 				continue;
 
+			if (IS_ENABLED(CONFIG_DRM_TTM_SHRINK_FAULT_INJECT) &&
+			    ctx->interruptible &&
+			    ++swappedin % 100 == 0) {
+				ret = -EINTR;
+				break;
+			}
+
 			ret = swap_copy_folio(swap, restore->first_page[i], 0,
 					      ctx->interruptible);
 			if (ret)
@@ -905,7 +913,14 @@  long ttm_pool_shrink_tt(struct ttm_pool *pool, struct ttm_tt *ttm)
 	if (current_is_kswapd())
 		alloc_gfp |= __GFP_NOMEMALLOC;
 
-	for (i = 0; i < ttm->num_pages; ++i) {
+	num_pages = ttm->num_pages;
+
+	/* Pretend doing fault injection by shrinking only half of the pages. */
+
+	if (IS_ENABLED(CONFIG_DRM_TTM_SHRINK_FAULT_INJECT))
+		num_pages = DIV_ROUND_UP(num_pages, 2);
+
+	for (i = 0; i < num_pages; ++i) {
 		page = ttm->pages[i];
 		if (unlikely(!page))
 			continue;