From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v7 22/32] drm/xe/vf: Start CTs before resfix VF post migration recovery
Date: Tue, 7 Oct 2025 04:26:31 -0700 [thread overview]
Message-ID: <20251007112641.2669655-23-matthew.brost@intel.com> (raw)
In-Reply-To: <20251007112641.2669655-1-matthew.brost@intel.com>
Before RESFIX_DONE, all CTs stuck in the H2G queue need to be squashed,
as they may contain actions which contain invalid GGTT references or are
unnecessary after HW change.
Starting the CTs clears all H2Gs in the queue. Any lost H2Gs are
resubmitted by the GuC submission state machine.
v3:
- Don't mess with head / tail values (Michal)
v4:
- Don't mess with broke (Michal)
- Add CTB_H2G_BUFFER_OFFSET (Michal)
v5:
- Adjust commit message (Tomasz)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 7 ++++
drivers/gpu/drm/xe/xe_guc_ct.c | 59 ++++++++++++++++++++++-------
drivers/gpu/drm/xe/xe_guc_ct.h | 3 +-
3 files changed, 55 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 1575ffaaaf52..675bb0d43343 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -1128,6 +1128,11 @@ static int vf_post_migration_fixups(struct xe_gt *gt)
return 0;
}
+static void vf_post_migration_rearm(struct xe_gt *gt)
+{
+ xe_guc_ct_restart(>->uc.guc.ct);
+}
+
static void vf_post_migration_kickstart(struct xe_gt *gt)
{
xe_guc_submit_unpause(>->uc.guc);
@@ -1179,6 +1184,8 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
if (err)
goto fail;
+ vf_post_migration_rearm(gt);
+
err = vf_post_migration_notify_resfix_done(gt);
if (err && err != -EAGAIN)
goto fail;
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 503cf5cb5d33..d0666d6d12f8 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -502,7 +502,7 @@ static void ct_exit_safe_mode(struct xe_guc_ct *ct)
xe_gt_dbg(ct_to_gt(ct), "GuC CT safe-mode disabled\n");
}
-int xe_guc_ct_enable(struct xe_guc_ct *ct)
+static int __xe_guc_ct_start(struct xe_guc_ct *ct, bool needs_register)
{
struct xe_device *xe = ct_to_xe(ct);
struct xe_gt *gt = ct_to_gt(ct);
@@ -510,21 +510,28 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
xe_gt_assert(gt, !xe_guc_ct_enabled(ct));
- xe_map_memset(xe, &ct->bo->vmap, 0, 0, xe_bo_size(ct->bo));
- guc_ct_ctb_h2g_init(xe, &ct->ctbs.h2g, &ct->bo->vmap);
- guc_ct_ctb_g2h_init(xe, &ct->ctbs.g2h, &ct->bo->vmap);
+ if (needs_register) {
+ xe_map_memset(xe, &ct->bo->vmap, 0, 0, xe_bo_size(ct->bo));
+ guc_ct_ctb_h2g_init(xe, &ct->ctbs.h2g, &ct->bo->vmap);
+ guc_ct_ctb_g2h_init(xe, &ct->ctbs.g2h, &ct->bo->vmap);
- err = guc_ct_ctb_h2g_register(ct);
- if (err)
- goto err_out;
+ err = guc_ct_ctb_h2g_register(ct);
+ if (err)
+ goto err_out;
- err = guc_ct_ctb_g2h_register(ct);
- if (err)
- goto err_out;
+ err = guc_ct_ctb_g2h_register(ct);
+ if (err)
+ goto err_out;
- err = guc_ct_control_toggle(ct, true);
- if (err)
- goto err_out;
+ err = guc_ct_control_toggle(ct, true);
+ if (err)
+ goto err_out;
+ } else {
+ ct->ctbs.h2g.info.broken = false;
+ ct->ctbs.g2h.info.broken = false;
+ xe_map_memset(xe, &ct->bo->vmap, CTB_H2G_BUFFER_OFFSET, 0,
+ CTB_H2G_BUFFER_SIZE);
+ }
guc_ct_change_state(ct, XE_GUC_CT_STATE_ENABLED);
@@ -556,6 +563,32 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
return err;
}
+/**
+ * xe_guc_ct_restart() - Restart GuC CT
+ * @ct: the &xe_guc_ct
+ *
+ * Restart GuC CT to an empty state without issuing a CT register MMIO command.
+ *
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int xe_guc_ct_restart(struct xe_guc_ct *ct)
+{
+ return __xe_guc_ct_start(ct, false);
+}
+
+/**
+ * xe_guc_ct_enable() - Enable GuC CT
+ * @ct: the &xe_guc_ct
+ *
+ * Enable GuC CT to an empty state and issue a CT register MMIO command.
+ *
+ * Return: 0 on success, or a negative errno on failure.
+ */
+int xe_guc_ct_enable(struct xe_guc_ct *ct)
+{
+ return __xe_guc_ct_start(ct, true);
+}
+
static void stop_g2h_handler(struct xe_guc_ct *ct)
{
cancel_work_sync(&ct->g2h_worker);
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 02eaa452b400..ca1ce2b3c354 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct.h
@@ -15,6 +15,7 @@ int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct);
int xe_guc_ct_init(struct xe_guc_ct *ct);
int xe_guc_ct_init_post_hwconfig(struct xe_guc_ct *ct);
int xe_guc_ct_enable(struct xe_guc_ct *ct);
+int xe_guc_ct_restart(struct xe_guc_ct *ct);
void xe_guc_ct_disable(struct xe_guc_ct *ct);
void xe_guc_ct_stop(struct xe_guc_ct *ct);
void xe_guc_ct_flush_and_stop(struct xe_guc_ct *ct);
@@ -75,7 +76,7 @@ long xe_guc_ct_queue_proc_time_jiffies(struct xe_guc_ct *ct);
/**
* xe_guc_ct_wake_waiters() - GuC CT wake up waiters
- * @guc: GuC CT object
+ * @ct: GuC CT object
*/
static inline void xe_guc_ct_wake_waiters(struct xe_guc_ct *ct)
{
--
2.34.1
next prev parent reply other threads:[~2025-10-07 11:26 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-07 11:26 [PATCH v7 00/32] VF migration redesign Matthew Brost
2025-10-07 11:26 ` [PATCH v7 01/32] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-10-07 11:26 ` [PATCH v7 02/32] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-10-07 11:26 ` [PATCH v7 03/32] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-10-07 11:26 ` [PATCH v7 04/32] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-10-07 11:26 ` [PATCH v7 05/32] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-10-07 12:29 ` Matthew Auld
2025-10-07 13:00 ` Matthew Brost
2025-10-07 11:26 ` [PATCH v7 06/32] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-10-07 11:26 ` [PATCH v7 07/32] drm/xe/vf: Add xe_gt_recovery_pending helper Matthew Brost
2025-10-07 11:26 ` [PATCH v7 08/32] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-10-07 11:26 ` [PATCH v7 09/32] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-10-07 11:26 ` [PATCH v7 10/32] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-10-07 11:26 ` [PATCH v7 11/32] drm/xe: Move GGTT lock init to alloc Matthew Brost
2025-10-07 11:47 ` Michal Wajdeczko
2025-10-07 12:53 ` Matthew Brost
2025-10-07 11:26 ` [PATCH v7 12/32] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-10-07 13:03 ` Michal Wajdeczko
2025-10-07 11:26 ` [PATCH v7 13/32] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-10-07 11:26 ` [PATCH v7 14/32] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-10-07 11:26 ` [PATCH v7 15/32] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-10-07 11:26 ` [PATCH v7 16/32] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-07 11:26 ` [PATCH v7 17/32] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-10-07 11:26 ` [PATCH v7 18/32] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-10-07 11:26 ` [PATCH v7 19/32] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-07 11:26 ` [PATCH v7 20/32] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-10-07 11:26 ` [PATCH v7 21/32] drm/xe: Add CTB_H2G_BUFFER_OFFSET define Matthew Brost
2025-10-07 11:26 ` Matthew Brost [this message]
2025-10-07 11:26 ` [PATCH v7 23/32] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-07 11:26 ` [PATCH v7 24/32] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-07 11:26 ` [PATCH v7 25/32] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-07 11:26 ` [PATCH v7 26/32] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-10-07 11:26 ` [PATCH v7 27/32] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-07 11:26 ` [PATCH v7 28/32] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-07 11:26 ` [PATCH v7 29/32] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-10-07 11:26 ` [PATCH v7 30/32] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-10-07 11:26 ` [PATCH v7 31/32] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-10-07 11:26 ` [PATCH v7 32/32] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-10-07 11:38 ` ✗ CI.checkpatch: warning for VF migration redesign (rev7) Patchwork
2025-10-07 11:39 ` ✓ CI.KUnit: success " Patchwork
2025-10-07 12:26 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-10-07 14:23 ` ✗ 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=20251007112641.2669655-23-matthew.brost@intel.com \
--to=matthew.brost@intel.com \
--cc=intel-xe@lists.freedesktop.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox