drm/xe/lrc: Allow to add user commands mid context switch

Like done for post-context-restore commands, allow to add commands from
configfs in the middle of context restore. Since currently the indirect
ctx hardcodes the offset to CTX_INDIRECT_CTX_OFFSET_DEFAULT, this is
executed in the very beginning of engine context restore.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250916-wa-bb-cmds-v5-6-306bddbc15da@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

3 files changed, 56 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 9a30dc958c35..90bc5a4b5da7 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -898,6 +898,21 @@ bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev)
 }
 
 /**
+ * xe_configfs_get_ctx_restore_mid_bb - get configfs ctx_restore_mid_bb setting
+ * @pdev: pci device
+ * @class: hw engine class
+ * @cs: pointer to the bb to use - only valid during probe
+ *
+ * Return: Number of dwords used in the mid_ctx_restore setting in configfs
+ */
+u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev,
+				       enum xe_engine_class class,
+				       const u32 **cs)
+{
+	return 0;
+}
+
+/**
  * xe_configfs_get_ctx_restore_post_bb - get configfs ctx_restore_post_bb setting
  * @pdev: pci device
  * @class: hw engine class
diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h
index eff2645b5f59..c61e0e47ed94 100644
--- a/drivers/gpu/drm/xe/xe_configfs.h
+++ b/drivers/gpu/drm/xe/xe_configfs.h
@@ -19,6 +19,8 @@ void xe_configfs_check_device(struct pci_dev *pdev);
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev);
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
 bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev);
+u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class,
+				       const u32 **cs);
 u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class,
 					const u32 **cs);
 #else
@@ -28,6 +30,8 @@ static inline void xe_configfs_check_device(struct pci_dev *pdev) { }
 static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; }
 static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; }
 static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
+static inline u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class,
+						     const u32 **cs) { return 0; }
 static inline u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class,
 						      const u32 **cs) { return 0; }
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 0ab99c210d88..47e9df775072 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -77,11 +77,17 @@ lrc_to_xe(struct xe_lrc *lrc)
 static bool
 gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class)
 {
+	struct xe_device *xe = gt_to_xe(gt);
+
 	if (XE_GT_WA(gt, 16010904313) &&
 	    (class == XE_ENGINE_CLASS_RENDER ||
 	     class == XE_ENGINE_CLASS_COMPUTE))
 		return true;
 
+	if (xe_configfs_get_ctx_restore_mid_bb(to_pci_dev(xe->drm.dev),
+					       class, NULL))
+		return true;
+
 	return false;
 }
 
@@ -1133,6 +1139,35 @@ static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc,
 	return cmd - batch;
 }
 
+static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc,
+						 struct xe_hw_engine *hwe,
+						 u32 *batch, size_t max_len)
+{
+	struct xe_device *xe = gt_to_xe(lrc->gt);
+	const u32 *user_batch;
+	u32 *cmd = batch;
+	u32 count;
+
+	count = xe_configfs_get_ctx_restore_mid_bb(to_pci_dev(xe->drm.dev),
+						   hwe->class, &user_batch);
+	if (!count)
+		return 0;
+
+	if (count > max_len)
+		return -ENOSPC;
+
+	/*
+	 * This should be used only for tests and validation. Taint the kernel
+	 * as anything could be submitted directly in context switches
+	 */
+	add_taint(TAINT_TEST, LOCKDEP_STILL_OK);
+
+	memcpy(cmd, user_batch, count * sizeof(u32));
+	cmd += count;
+
+	return cmd - batch;
+}
+
 static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 					       struct xe_hw_engine *hwe,
 					       u32 *batch, size_t max_len)
@@ -1283,8 +1318,10 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
 	static const struct bo_setup rcs_funcs[] = {
 		{ .setup = setup_timestamp_wa },
+		{ .setup = setup_configfs_mid_ctx_restore_bb },
 	};
 	static const struct bo_setup xcs_funcs[] = {
+		{ .setup = setup_configfs_mid_ctx_restore_bb },
 	};
 	struct bo_setup_state state = {
 		.lrc = lrc,