From: Raag Jadav <raag.jadav@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: matthew.brost@intel.com, rodrigo.vivi@intel.com,
thomas.hellstrom@linux.intel.com, riana.tauro@intel.com,
michal.wajdeczko@intel.com, matthew.d.roper@intel.com,
michal.winiarski@intel.com, matthew.auld@intel.com,
dev@lankhorst.se, jani.nikula@intel.com, lukasz.laguna@intel.com,
lukas@wunner.de, daniele.ceraolospurio@intel.com,
badal.nilawar@intel.com, Raag Jadav <raag.jadav@intel.com>
Subject: [PATCH v10 02/10] drm/xe/guc_submit: Introduce guc_exec_queue_reinit_kernel()
Date: Fri, 21 Aug 2026 16:53:24 +0530 [thread overview]
Message-ID: <20260821112436.545405-3-raag.jadav@intel.com> (raw)
In-Reply-To: <20260821112436.545405-1-raag.jadav@intel.com>
In preparation of usecases which require re-initializing GuC submission
after PCIe FLR, introduce guc_exec_queue_reinit_kernel() helper. This will
restore kernel queues which might have been killed before PCIe FLR.
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Tested-by: Lukasz Laguna <lukasz.laguna@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
---
v4: Teardown exec queues instead of mangling scheduler pending list (Matthew Brost)
v5: Re-initialize kernel queues through submission backend (Matthew Brost)
v8: Introduce xe_sched_reinit() (Daniele)
Maintain timeout per scheduler instance (Daniele)
s/reinit/reinit_kernel (Daniele)
v9: Move drm_sched_is_stopped() assert to xe_sched_reinit() (Daniele)
---
drivers/gpu/drm/xe/xe_exec_queue_types.h | 2 ++
drivers/gpu/drm/xe/xe_execlist.c | 6 ++++++
drivers/gpu/drm/xe/xe_gpu_scheduler.c | 17 +++++++++++++++++
drivers/gpu/drm/xe/xe_gpu_scheduler.h | 1 +
drivers/gpu/drm/xe/xe_gpu_scheduler_types.h | 5 +++++
drivers/gpu/drm/xe/xe_guc_submit.c | 9 +++++++++
6 files changed, 40 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 95f75d61a647..3b5bcd08f624 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -297,6 +297,8 @@ struct xe_exec_queue {
struct xe_exec_queue_ops {
/** @init: Initialize exec queue for submission backend */
int (*init)(struct xe_exec_queue *q);
+ /** @reinit_kernel: Re-initialize kernel queue for submission backend */
+ void (*reinit_kernel)(struct xe_exec_queue *q);
/** @kill: Kill inflight submissions for backend */
void (*kill)(struct xe_exec_queue *q);
/** @fini: Undoes the init() for submission backend */
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index cc33ae80e8cf..fba0d2850905 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -403,6 +403,11 @@ static void execlist_exec_queue_destroy_async(struct work_struct *w)
xe_exec_queue_fini(q);
}
+static void execlist_exec_queue_reinit_kernel(struct xe_exec_queue *q)
+{
+ /* NIY */
+}
+
static void execlist_exec_queue_kill(struct xe_exec_queue *q)
{
/* NIY */
@@ -460,6 +465,7 @@ static bool execlist_exec_queue_reset_status(struct xe_exec_queue *q)
static const struct xe_exec_queue_ops execlist_exec_queue_ops = {
.init = execlist_exec_queue_init,
+ .reinit_kernel = execlist_exec_queue_reinit_kernel,
.kill = execlist_exec_queue_kill,
.fini = execlist_exec_queue_fini,
.destroy = execlist_exec_queue_destroy,
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.c b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
index 67d8ce368486..e85bc4077809 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.c
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
@@ -3,7 +3,10 @@
* Copyright © 2023 Intel Corporation
*/
+#include "xe_assert.h"
+#include "xe_exec_queue_types.h"
#include "xe_gpu_scheduler.h"
+#include "xe_guc_exec_queue_types.h"
static void xe_sched_process_msg_queue(struct xe_gpu_scheduler *sched)
{
@@ -76,6 +79,7 @@ int xe_sched_init(struct xe_gpu_scheduler *sched,
};
sched->ops = xe_ops;
+ sched->timeout = timeout;
spin_lock_init(&sched->msg_lock);
INIT_LIST_HEAD(&sched->msgs);
INIT_WORK(&sched->work_process_msg, xe_sched_process_msg_work);
@@ -83,6 +87,19 @@ int xe_sched_init(struct xe_gpu_scheduler *sched,
return drm_sched_init(&sched->base, &args);
}
+void xe_sched_reinit(struct xe_gpu_scheduler *sched)
+{
+ struct xe_guc_exec_queue *ge = container_of(sched, struct xe_guc_exec_queue, sched);
+
+ xe_gt_assert(ge->q->gt, drm_sched_is_stopped(&sched->base));
+
+ /*
+ * TODO: Implement drm_sched_reinit() instead of requiring the
+ * driver to restore individual fields.
+ */
+ sched->base.timeout = sched->timeout;
+}
+
void xe_sched_fini(struct xe_gpu_scheduler *sched)
{
xe_sched_submission_stop(sched);
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 664c2db56af3..22e24b4b7171 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -17,6 +17,7 @@ int xe_sched_init(struct xe_gpu_scheduler *sched,
long timeout, struct workqueue_struct *timeout_wq,
atomic_t *score, const char *name,
struct device *dev);
+void xe_sched_reinit(struct xe_gpu_scheduler *sched);
void xe_sched_fini(struct xe_gpu_scheduler *sched);
void xe_sched_submission_start(struct xe_gpu_scheduler *sched);
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler_types.h b/drivers/gpu/drm/xe/xe_gpu_scheduler_types.h
index 63d9bf92583c..e73fdacca164 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler_types.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler_types.h
@@ -51,6 +51,11 @@ struct xe_gpu_scheduler {
spinlock_t msg_lock;
/** @work_process_msg: processes messages */
struct work_struct work_process_msg;
+ /**
+ * @timeout: timeout for the scheduler instance, to be restored
+ * during exec queue re-initialization
+ */
+ long timeout;
};
#define xe_sched_entity drm_sched_entity
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 99d8c807ff05..f7519e55b610 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2130,6 +2130,14 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
return err;
}
+static void guc_exec_queue_reinit_kernel(struct xe_exec_queue *q)
+{
+ xe_gt_assert(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL);
+
+ atomic_set(&q->guc->state, 0);
+ xe_sched_reinit(&q->guc->sched);
+}
+
static void guc_exec_queue_kill(struct xe_exec_queue *q)
{
trace_xe_exec_queue_kill(q);
@@ -2597,6 +2605,7 @@ static bool guc_exec_queue_reset_status(struct xe_exec_queue *q)
*/
static const struct xe_exec_queue_ops guc_exec_queue_ops = {
.init = guc_exec_queue_init,
+ .reinit_kernel = guc_exec_queue_reinit_kernel,
.kill = guc_exec_queue_kill,
.fini = guc_exec_queue_fini,
.destroy = guc_exec_queue_destroy,
--
2.43.0
next prev parent reply other threads:[~2026-08-21 11:25 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-21 11:23 [PATCH v10 00/10] Introduce Xe PCIe FLR Raag Jadav
2026-08-21 11:23 ` [PATCH v10 01/10] drm/xe/uc_fw: Allow re-initializing firmware Raag Jadav
2026-08-21 11:41 ` sashiko-bot
2026-08-21 11:23 ` Raag Jadav [this message]
2026-08-21 11:52 ` [PATCH v10 02/10] drm/xe/guc_submit: Introduce guc_exec_queue_reinit_kernel() sashiko-bot
2026-08-21 11:23 ` [PATCH v10 03/10] drm/xe/gt: Introduce FLR helpers Raag Jadav
2026-08-26 9:39 ` Tauro, Riana
2026-08-21 11:23 ` [PATCH v10 04/10] drm/xe/bo_evict: Introduce xe_bo_restore_map() Raag Jadav
2026-08-21 11:23 ` [PATCH v10 05/10] drm/xe/exec_queue: Introduce xe_exec_queue_reinit() Raag Jadav
2026-08-21 11:43 ` sashiko-bot
2026-08-21 11:23 ` [PATCH v10 06/10] drm/xe/migrate: Introduce xe_migrate_reinit() Raag Jadav
2026-08-21 11:39 ` sashiko-bot
2026-08-21 11:23 ` [PATCH v10 07/10] drm/xe/pm: Introduce xe_device_suspend/resume() Raag Jadav
2026-08-21 11:43 ` sashiko-bot
2026-08-24 18:22 ` Rodrigo Vivi
2026-08-26 7:01 ` Raag Jadav
2026-08-21 11:23 ` [PATCH v10 08/10] drm/xe: Introduce temporary device wedging Raag Jadav
2026-08-21 11:37 ` sashiko-bot
2026-08-24 14:30 ` Laguna, Lukasz
2026-08-24 16:08 ` Raag Jadav
2026-08-24 18:29 ` Rodrigo Vivi
2026-08-25 7:41 ` Raag Jadav
2026-08-21 11:23 ` [PATCH v10 09/10] drm/xe/pci: Introduce PCIe Function Level Reset Raag Jadav
2026-08-21 11:39 ` sashiko-bot
2026-08-25 10:06 ` Laguna, Lukasz
2026-08-26 9:01 ` Raag Jadav
2026-08-26 9:52 ` Tauro, Riana
2026-08-26 11:38 ` Raag Jadav
2026-08-21 11:23 ` [PATCH v10 10/10] drm/xe/doc: Wire up PCI Error Handling Raag Jadav
2026-08-21 11:31 ` ✗ CI.checkpatch: warning for Introduce Xe PCIe FLR (rev10) Patchwork
2026-08-21 11:33 ` ✓ CI.KUnit: success " Patchwork
2026-08-21 12:37 ` ✓ Xe.CI.BAT: " Patchwork
2026-08-21 14:38 ` ✓ Xe.CI.FULL: " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260821112436.545405-3-raag.jadav@intel.com \
--to=raag.jadav@intel.com \
--cc=badal.nilawar@intel.com \
--cc=daniele.ceraolospurio@intel.com \
--cc=dev@lankhorst.se \
--cc=intel-xe@lists.freedesktop.org \
--cc=jani.nikula@intel.com \
--cc=lukas@wunner.de \
--cc=lukasz.laguna@intel.com \
--cc=matthew.auld@intel.com \
--cc=matthew.brost@intel.com \
--cc=matthew.d.roper@intel.com \
--cc=michal.wajdeczko@intel.com \
--cc=michal.winiarski@intel.com \
--cc=riana.tauro@intel.com \
--cc=rodrigo.vivi@intel.com \
--cc=thomas.hellstrom@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.