Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v10] drm/xe/uc: Add stop on hardware initialization error
@ 2025-12-05 18:06 Zhanjun Dong
  2025-12-05 21:25 ` ✓ CI.KUnit: success for drm/xe/uc: Add stop on hardware initialization error (rev10) Patchwork
                   ` (3 more replies)
  0 siblings, 4 replies; 6+ messages in thread
From: Zhanjun Dong @ 2025-12-05 18:06 UTC (permalink / raw)
  To: intel-xe; +Cc: matthew.brost, Zhanjun Dong

On hardware init fail, the hardware might no longer response, add uc stop
to clean up. At driver unload, all exec_queue items need to be freeed,
change xe_guc_submit_pause_abort to free all contexts.

This will fix memory leak issue like:
[  189.997904] [drm:drm_mm_takedown] *ERROR* node [00f0f000 + 00007000]: inserted at
                drm_mm_insert_node_in_range+0x2c0/0x510
                __xe_ggtt_insert_bo_at+0x167/0x540 [xe]
                xe_ggtt_insert_bo+0x1a/0x30 [xe]
                __xe_bo_create_locked+0x1f3/0x930 [xe]
                xe_bo_create_pin_map_at_aligned+0x59/0x1f0 [xe]
                xe_bo_create_pin_map_at_novm+0xae/0x140 [xe]
                xe_bo_create_pin_map_novm+0x23/0x40 [xe]
                xe_lrc_create+0x1e4/0x17c0 [xe]
                xe_exec_queue_create+0x38a/0x6a0 [xe]
                xe_gt_record_default_lrcs+0x117/0x8b0 [xe]
                xe_uc_load_hw+0xa2/0x290 [xe]
                xe_gt_init+0x357/0xab0 [xe]
                xe_device_probe+0x403/0xa30 [xe]
                xe_pci_probe+0x39a/0x610 [xe]
                local_pci_probe+0x47/0xb0
                pci_device_probe+0xf3/0x260
                really_probe+0xf1/0x3b0
                __driver_probe_device+0x8c/0x180
                device_driver_attach+0x57/0xd0
                bind_store+0x77/0xd0
                drv_attr_store+0x24/0x50
                sysfs_kf_write+0x4d/0x80
                kernfs_fop_write_iter+0x188/0x240
                vfs_write+0x280/0x540
                ksys_write+0x6f/0xf0
                __x64_sys_write+0x19/0x30
                x64_sys_call+0x2171/0x25a0
                do_syscall_64+0x93/0xb80
                entry_SYSCALL_64_after_hwframe+0x7
and:
[  189.973775] xe 0000:00:02.0: [drm] *ERROR* Tile0: GT1: GUC ID manager unclean (1/65535)
[  189.981731] xe 0000:00:02.0: [drm] Tile0: GT1: 	total 65535
[  189.981733] xe 0000:00:02.0: [drm] Tile0: GT1: 	used 1
[  189.981734] xe 0000:00:02.0: [drm] Tile0: GT1: 	range 2..2 (1)

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5466
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5530
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
---
v10:Add submit initialized helper function (Matthew)
    Call xe_uc_reset_prepare rather than set flag directly (Matthew)
v9: Rebase and keep xe_guc_submit_pause_abort name unchanged
v8: Fix __mutex_lock warning
v7: Clear all queue items by guc_submit_fini/xe_guc_submit_pause_abort (Matthew)
v6: As huc not involved in vf_uc_load_hw, roll back to guc sanitize
v5: Move stop flag set in guc_fini_hw
    Change to uc_sanitize in uc init path
v4: Add memory leak fix
    Switch to xe_uc_stop
v3: Switch to xe_guc_stop
v2: Switch to xe_guc_ct_stop
---
 drivers/gpu/drm/xe/xe_guc.c        |  6 ++++++
 drivers/gpu/drm/xe/xe_guc_submit.c | 12 ++++++++----
 drivers/gpu/drm/xe/xe_guc_submit.h |  1 +
 drivers/gpu/drm/xe/xe_uc.c         |  8 ++++++--
 4 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index f0407bab9a0c..3dcf078e111f 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -662,6 +662,12 @@ static void guc_fini_hw(void *arg)
 	struct xe_guc *guc = arg;
 	struct xe_gt *gt = guc_to_gt(guc);
 
+	if (xe_guc_submit_initialized(guc)) {
+		xe_guc_reset_prepare(guc);
+		xe_guc_stop(guc);
+		xe_guc_submit_pause_abort(guc);
+	}
+
 	xe_with_force_wake(fw_ref, gt_to_fw(gt), XE_FORCEWAKE_ALL)
 		xe_uc_sanitize_reset(&guc_to_gt(guc)->uc);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index f3f2c8556a66..34c6e8a03013 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -425,6 +425,11 @@ void xe_guc_submit_disable(struct xe_guc *guc)
 	guc->submission_state.enabled = false;
 }
 
+bool xe_guc_submit_initialized(struct xe_guc *guc)
+{
+	return guc->submission_state.initialized;
+}
+
 static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa_count)
 {
 	int i;
@@ -992,7 +997,7 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 	 * If device is being wedged even before submission_state is
 	 * initialized, there's nothing to do here.
 	 */
-	if (!guc->submission_state.initialized)
+	if (!xe_guc_submit_initialized(guc))
 		return;
 
 	err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
@@ -1994,7 +1999,7 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 	if (xe_gt_WARN_ON(guc_to_gt(guc), vf_recovery(guc)))
 		return 0;
 
-	if (!guc->submission_state.initialized)
+	if (!xe_guc_submit_initialized(guc))
 		return 0;
 
 	/*
@@ -2418,8 +2423,7 @@ void xe_guc_submit_pause_abort(struct xe_guc *guc)
 			continue;
 
 		xe_sched_submission_start(sched);
-		if (exec_queue_killed_or_banned_or_wedged(q))
-			xe_guc_exec_queue_trigger_cleanup(q);
+		guc_exec_queue_kill(q);
 	}
 	mutex_unlock(&guc->submission_state.lock);
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 100a7891b918..9308da2bd104 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -15,6 +15,7 @@ struct xe_guc;
 int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids);
 int xe_guc_submit_enable(struct xe_guc *guc);
 void xe_guc_submit_disable(struct xe_guc *guc);
+bool xe_guc_submit_initialized(struct xe_guc *guc);
 
 int xe_guc_submit_reset_prepare(struct xe_guc *guc);
 void xe_guc_submit_reset_wait(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index 157520ea1783..60430d56c79c 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -173,7 +173,9 @@ static int vf_uc_load_hw(struct xe_uc *uc)
 	return 0;
 
 err_out:
-	xe_guc_sanitize(&uc->guc);
+	xe_uc_reset_prepare(uc);
+	xe_uc_stop(uc);
+	xe_uc_sanitize(uc);
 	return err;
 }
 
@@ -231,7 +233,9 @@ int xe_uc_load_hw(struct xe_uc *uc)
 	return 0;
 
 err_out:
-	xe_guc_sanitize(&uc->guc);
+	xe_uc_reset_prepare(uc);
+	xe_uc_stop(uc);
+	xe_uc_sanitize(uc);
 	return ret;
 }
 
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 6+ messages in thread
end of thread, other threads:[~2025-12-12 22:03 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-12-05 18:06 [PATCH v10] drm/xe/uc: Add stop on hardware initialization error Zhanjun Dong
2025-12-05 21:25 ` ✓ CI.KUnit: success for drm/xe/uc: Add stop on hardware initialization error (rev10) Patchwork
2025-12-05 21:59 ` ✓ Xe.CI.BAT: " Patchwork
2025-12-06  8:00 ` ✗ Xe.CI.Full: failure " Patchwork
2025-12-08 12:58 ` [PATCH v10] drm/xe/uc: Add stop on hardware initialization error Rodrigo Vivi
2025-12-12 22:01   ` Matthew Brost

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox