drm/xe: Add multi_queue_active_lrca debugfs

Add a per-GT debugfs file, multi_queue_active_lrca, that prints, for
every engine supporting multi-queue, the currently active queue ID
(CSMQDEBUG) and the LRCA of the exec queue occupying that slot within
the running multi-queue group.

RING_CURRENT_LRCA only reports the primary queue's LRCA for the group
and does not update to reflect the active queue in multi-queue mode,
which makes it hard to tell which queue is actually running when
debugging multi-queue CSB/context-switch issues. Resolve the active
LRCA by matching the primary LRCA against each queue's group and
picking the queue at the reported active_id position.

v4:
 - Extracted multi_queue_active_lrca into a dedicated
   multi_queue_debugfs_list to prevent debugfs node registration on
   platforms lacking multi-queue support entirely, via
   xe_gt_has_multi_queue() gating. (Tejas)
v3:
 - Use xe_exec_queue_get_lrc() instead of raw pointer dereference to
   safely handle concurrent multi-queue group creation and avoid race
   conditions (Sashiko)
v2:
 - Maintain alphabetical order for includes and
   pf_only_debugfs_list (Tejas)
 - Export and reuse xe_lrc_get_multi_queue_active_queue_id() instead
   of duplicate MMIO read (Tejas)

Bspec: 60321, 73976
Signed-off-by: Varun Gupta <varun.gupta@intel.com>
Link: https://patch.msgid.link/20260908033417.1019602-2-varun.gupta@intel.com
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>

5 files changed, 136 insertions, 3 deletions

diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 361a70234d1f..bb09e70ee44c 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -13,6 +13,7 @@
 #include <drm/drm_managed.h>
 #include <linux/math.h>
 
+#include "regs/xe_engine_regs.h"
 #include "regs/xe_gt_regs.h"
 #include "xe_device.h"
 #include "xe_force_wake.h"
@@ -25,6 +26,7 @@
 #include "xe_gt_stats.h"
 #include "xe_gt_topology.h"
 #include "xe_guc_hwconfig.h"
+#include "xe_guc_submit.h"
 #include "xe_hw_engine.h"
 #include "xe_lrc.h"
 #include "xe_mmio.h"
@@ -130,6 +132,48 @@ static int hw_engines(struct xe_gt *gt, struct drm_printer *p)
 	return 0;
 }
 
+static int multi_queue_active_lrca(struct xe_gt *gt, struct drm_printer *p)
+{
+	struct xe_guc *guc = &gt->uc.guc;
+	struct xe_hw_engine *hwe;
+	enum xe_hw_engine_id id;
+
+	for_each_hw_engine(hwe, gt, id) {
+		u32 cur_lrca, active_id, lrca;
+		unsigned int fw_ref;
+
+		if (!xe_gt_supports_multi_queue(gt, hwe->class))
+			continue;
+
+		/*
+		 * Forcewake is dropped before xe_guc_submit_active_multi_queue_lrca()
+		 * below, which takes guc->submission_state.lock, to avoid holding a
+		 * GT forcewake ref across a mutex acquired elsewhere in the opposite
+		 * order.
+		 */
+		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+		if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
+			drm_printf(p, "%s\tforcewake failed, skipping\n", hwe->name);
+			xe_force_wake_put(gt_to_fw(gt), fw_ref);
+			continue;
+		}
+
+		cur_lrca = xe_mmio_read32(&gt->mmio,
+					  RING_CURRENT_LRCA(hwe->mmio_base));
+		active_id = xe_lrc_get_multi_queue_active_queue_id(hwe);
+
+		xe_force_wake_put(gt_to_fw(gt), fw_ref);
+
+		lrca = xe_guc_submit_active_multi_queue_lrca(guc, hwe, cur_lrca,
+							     active_id);
+
+		drm_printf(p, "%s\tactive_queue_id %u\tcurrent_lrca 0x%08x\tactive_lrca 0x%08x\n",
+			   hwe->name, active_id, cur_lrca, lrca);
+	}
+
+	return 0;
+}
+
 static int steering(struct xe_gt *gt, struct drm_printer *p)
 {
 	xe_gt_mcr_steering_dump(gt, p);
@@ -254,6 +298,11 @@ static const struct drm_info_list pf_only_debugfs_list[] = {
 	{ "steering", .show = xe_gt_debugfs_show_with_rpm, .data = steering },
 };
 
+static const struct drm_info_list multi_queue_debugfs_list[] = {
+	{ "multi_queue_active_lrca",
+		.show = xe_gt_debugfs_show_with_rpm, .data = multi_queue_active_lrca },
+};
+
 static ssize_t write_to_gt_call(const char __user *userbuf, size_t count, loff_t *ppos,
 				void (*call)(struct xe_gt *), struct xe_gt *gt)
 {
@@ -521,6 +570,11 @@ void xe_gt_debugfs_register(struct xe_gt *gt)
 					 ARRAY_SIZE(pf_only_debugfs_list),
 					 root, minor);
 
+	if (!IS_SRIOV_VF(xe) && xe_gt_has_multi_queue(gt))
+		drm_debugfs_create_files(multi_queue_debugfs_list,
+					 ARRAY_SIZE(multi_queue_debugfs_list),
+					 root, minor);
+
 	if (xe_gt_is_main_type(gt) && !IS_DGFX(xe) && !IS_SRIOV_VF(xe))
 		debugfs_create_file("gt_ia_bias", 0600, root, gt, &gt_ia_bias_fops);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index e44d06703020..f3ba8abfc228 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -3882,6 +3882,79 @@ bool xe_guc_has_registered_mlrc_queues(struct xe_guc *guc)
 }
 
 /**
+ * xe_guc_submit_active_multi_queue_lrca() - Resolve the LRCA of the active
+ * queue in the multi-queue group currently running on an engine.
+ * @guc: the &xe_guc managing the exec queues
+ * @hwe: the &xe_hw_engine whose active queue is being resolved
+ * @cur_lrca: value read from RING_CURRENT_LRCA, identifies the running group
+ * @active_id: current Active Queue ID read from CSMQDEBUG (position in group)
+ *
+ * The running group is identified by matching @cur_lrca against the group's
+ * primary LRCA; @active_id then selects the active queue within that group.
+ *
+ * Return: the LRCA of the active queue, or 0 if no matching queue is found.
+ */
+u32 xe_guc_submit_active_multi_queue_lrca(struct xe_guc *guc,
+					  struct xe_hw_engine *hwe,
+					  u32 cur_lrca, u32 active_id)
+{
+	struct xe_exec_queue *q;
+	unsigned long index;
+	u32 lrca = 0;
+
+	/*
+	 * submission_state.lock also protects exec_queue teardown: an exec
+	 * queue is removed from exec_queue_lookup before its group/primary
+	 * are freed, so any q found in the xarray below has a live group
+	 * and primary for as long as we hold the lock.
+	 */
+	guard(mutex)(&guc->submission_state.lock);
+
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		struct xe_exec_queue_group *group = q->multi_queue.group;
+		struct xe_lrc *active_lrc;
+		struct xe_lrc *primary_lrc;
+
+		if (!q->multi_queue.valid || !group || !group->primary)
+			continue;
+		/*
+		 * Multi-queue exec queues are bound to a hw engine class;
+		 * GuC dynamically schedules them onto one of the class's
+		 * physical instances, so there is no fixed queue-to-instance
+		 * mapping to filter on here.
+		 */
+		if (q->class != hwe->class)
+			continue;
+		if (q->multi_queue.pos != active_id)
+			continue;
+		/*
+		 * LRCAs are page-aligned (4K) addresses in GGTT; the low
+		 * bits reported by RING_CURRENT_LRCA are not meaningful, so
+		 * only compare bits [31:12].
+		 */
+		primary_lrc = xe_exec_queue_get_lrc(group->primary, 0);
+		if (!primary_lrc)
+			continue;
+
+		if ((xe_lrc_ggtt_addr(primary_lrc) ^ cur_lrca) & GENMASK(31, 12)) {
+			xe_lrc_put(primary_lrc);
+			continue;
+		}
+
+		active_lrc = xe_exec_queue_get_lrc(q, 0);
+		xe_lrc_put(primary_lrc);
+		if (!active_lrc)
+			continue;
+
+		lrca = xe_lrc_ggtt_addr(active_lrc);
+		xe_lrc_put(active_lrc);
+		break;
+	}
+
+	return lrca;
+}
+
+/**
  * xe_guc_contexts_hwsp_rebase - Re-compute GGTT references within all
  * exec queues registered to given GuC.
  * @guc: the &xe_guc struct instance
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index ccade320dc69..29abf07d8f04 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -11,6 +11,7 @@
 struct drm_printer;
 struct xe_exec_queue;
 struct xe_guc;
+struct xe_hw_engine;
 
 int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids);
 int xe_guc_submit_enable(struct xe_guc *guc);
@@ -55,6 +56,10 @@ void xe_guc_register_vf_exec_queue(struct xe_exec_queue *q, int ctx_type);
 
 bool xe_guc_has_registered_mlrc_queues(struct xe_guc *guc);
 
+u32 xe_guc_submit_active_multi_queue_lrca(struct xe_guc *guc,
+					  struct xe_hw_engine *hwe,
+					  u32 cur_lrca, u32 active_id);
+
 int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 25fe9dbc9141..f1cf1463f1b2 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -2705,7 +2705,7 @@ static u64 get_queue_timestamp(struct xe_hw_engine *hwe)
 				   RING_QUEUE_TIMESTAMP(hwe->mmio_base));
 }
 
-static u32 get_multi_queue_active_queue_id(struct xe_hw_engine *hwe)
+u32 xe_lrc_get_multi_queue_active_queue_id(struct xe_hw_engine *hwe)
 {
 	u32 val = xe_mmio_read32(&hwe->gt->mmio,
 				 RING_CSMQDEBUG(hwe->mmio_base));
@@ -2739,14 +2739,14 @@ static u64 xe_lrc_multi_queue_timestamp(struct xe_lrc *lrc)
 	if (!hwe)
 		return xe_lrc_queue_timestamp(lrc);
 
-	if (get_multi_queue_active_queue_id(hwe) != lrc->multi_queue.pos)
+	if (xe_lrc_get_multi_queue_active_queue_id(hwe) != lrc->multi_queue.pos)
 		return xe_lrc_queue_timestamp(lrc);
 
 	/* queue is active, so store the queue timestamp register */
 	reg_queue_ts = get_queue_timestamp(hwe);
 
 	/* double check queue and primary queue are both still active */
-	if (get_multi_queue_active_queue_id(hwe) != lrc->multi_queue.pos ||
+	if (xe_lrc_get_multi_queue_active_queue_id(hwe) != lrc->multi_queue.pos ||
 	    !context_active(primary_lrc))
 		return xe_lrc_queue_timestamp(lrc);
 
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 7be5e3da8bc8..a8ff4e59a1f4 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -158,6 +158,7 @@ int xe_lrc_lookup_default_reg_value(struct xe_gt *gt,
 u32 *xe_lrc_emit_hwe_state_instructions(struct xe_exec_queue *q, u32 *cs);
 
 void xe_lrc_set_multi_queue_priority(struct xe_lrc *lrc, enum xe_multi_queue_priority priority);
+u32 xe_lrc_get_multi_queue_active_queue_id(struct xe_hw_engine *hwe);
 
 struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc);
 void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot);