[PATCH v2 7/9] drm/ttm: Use fault-injection to test error paths

[Thomas Hellström]

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.

Cc: Christian König <christian.koenig at amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram at amd.com>
Cc: <dri-devel at lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
---
 drivers/gpu/drm/Kconfig        | 10 ++++++++++
 drivers/gpu/drm/ttm/ttm_pool.c | 17 ++++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 959b19a04101..032f069235d5 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -258,6 +258,16 @@ config DRM_GPUVM
 	  GPU-VM representation providing helpers to manage a GPUs virtual
 	  address space
 
+config DRM_TTM_BACKUP_FAULT_INJECT
+	bool "Enable fault injection during TTM backup"
+	depends on DRM_TTM
+	default n
+	help
+	  Inject recoverable failures during TTM backup and recovery of
+	  backed-up 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 38e50cf81b0a..d32a1f2e5e50 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -431,6 +431,7 @@ static int ttm_pool_restore_tt(struct ttm_pool_tt_restore *restore,
 			       struct ttm_backup *backup,
 			       struct ttm_operation_ctx *ctx)
 {
+	static unsigned long __maybe_unused swappedin;
 	unsigned int i, nr = 1 << restore->order;
 	int ret = 0;
 
@@ -446,6 +447,13 @@ static int ttm_pool_restore_tt(struct ttm_pool_tt_restore *restore,
 			if (handle == 0)
 				continue;
 
+			if (IS_ENABLED(CONFIG_DRM_TTM_BACKUP_FAULT_INJECT) &&
+			    ctx->interruptible &&
+			    ++swappedin % 100 == 0) {
+				ret = -EINTR;
+				break;
+			}
+
 			ret = backup->ops->copy_backed_up_page
 				(backup, restore->first_page[i],
 				 handle, ctx->interruptible);
@@ -892,7 +900,14 @@ long ttm_pool_backup_tt(struct ttm_pool *pool, struct ttm_tt *ttm, bool purge,
 
 	alloc_gfp = GFP_KERNEL | __GFP_HIGH | __GFP_NOWARN | __GFP_RETRY_MAYFAIL;
 
-	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_BACKUP_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;
-- 
2.44.0