From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v3 26/36] drm/xe/vf: Start CTs before resfix VF post migration recovery
Date: Sun, 28 Sep 2025 19:55:32 -0700 [thread overview]
Message-ID: <20250929025542.1486303-27-matthew.brost@intel.com> (raw)
In-Reply-To: <20250929025542.1486303-1-matthew.brost@intel.com>
Before `resfix`, all CTs stuck in the H2G queue need to be squashed, as
they may contain stale or invalid data.
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)
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 | 1 +
3 files changed, 54 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 35de8977c6d0..cb3e9f6e83fa 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -1214,6 +1214,11 @@ 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);
@@ -1265,6 +1270,8 @@ 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 fd6e731c0395..25efc1f813ce 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -500,7 +500,7 @@ 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);
@@ -508,21 +508,28 @@ 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_DESC_SIZE * 2, 0,
+ CTB_H2G_BUFFER_SIZE);
+ }
guc_ct_change_state(ct, XE_GUC_CT_STATE_ENABLED);
@@ -554,6 +561,32 @@ 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 0a88f4e447fa..b1cba250c51c 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);
--
2.34.1
next prev parent reply other threads:[~2025-09-29 2:56 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-29 2:55 [PATCH v3 00/36] VF migration redesign Matthew Brost
2025-09-29 2:55 ` [PATCH v3 01/36] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-09-30 2:06 ` Lis, Tomasz
2025-09-30 22:53 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 02/36] drm/xe/vf: Lock querying GGTT config during driver init Matthew Brost
2025-09-29 7:42 ` Michal Wajdeczko
2025-09-29 12:15 ` Matthew Brost
2025-09-30 0:42 ` Lis, Tomasz
2025-09-30 10:25 ` Michal Wajdeczko
2025-09-29 8:13 ` Ville Syrjälä
2025-09-30 13:22 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 03/36] Revert "drm/xe/vf: Rebase exec queue parallel commands during migration recovery" Matthew Brost
2025-09-30 15:22 ` Michal Wajdeczko
2025-09-29 2:55 ` [PATCH v3 04/36] Revert "drm/xe/vf: Post migration, repopulate ring area for pending request" Matthew Brost
2025-09-30 15:24 ` Michal Wajdeczko
2025-09-29 2:55 ` [PATCH v3 05/36] Revert "drm/xe/vf: Fixup CTB send buffer messages after migration" Matthew Brost
2025-09-30 15:27 ` Michal Wajdeczko
2025-09-29 2:55 ` [PATCH v3 06/36] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-09-29 2:55 ` [PATCH v3 07/36] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-09-29 2:55 ` [PATCH v3 08/36] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-09-29 2:55 ` [PATCH v3 09/36] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-09-30 2:38 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 10/36] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-09-29 2:55 ` [PATCH v3 11/36] drm/xe/guc: Document GuC submission backend Matthew Brost
2025-09-30 3:28 ` Lis, Tomasz
2025-09-30 6:30 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 12/36] drm/xe/vf: Add xe_gt_recovery_inprogress helper Matthew Brost
2025-09-29 8:04 ` Michal Wajdeczko
2025-09-29 8:52 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 13/36] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-09-30 14:47 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 14/36] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-09-29 8:17 ` Michal Wajdeczko
2025-09-29 2:55 ` [PATCH v3 15/36] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-09-30 15:00 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 16/36] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-09-29 8:44 ` Michal Wajdeczko
2025-09-29 12:31 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 17/36] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-09-30 16:24 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 18/36] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-09-29 9:17 ` Michal Wajdeczko
2025-09-29 12:50 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 19/36] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-09-29 2:55 ` [PATCH v3 20/36] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-01 13:45 ` Lis, Tomasz
2025-10-01 13:56 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 21/36] drm/xe/vf: Extra debug on GGTT shift Matthew Brost
2025-09-29 2:55 ` [PATCH v3 22/36] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-09-29 2:55 ` [PATCH v3 23/36] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-09-29 21:31 ` Michal Wajdeczko
2025-09-29 2:55 ` [PATCH v3 24/36] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-01 13:53 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 25/36] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-09-29 2:55 ` Matthew Brost [this message]
2025-09-29 21:49 ` [PATCH v3 26/36] drm/xe/vf: Start CTs before resfix " Michal Wajdeczko
2025-09-30 6:26 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 27/36] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-01 14:06 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 28/36] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-01 14:37 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 29/36] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-02 0:44 ` Lis, Tomasz
2025-10-02 7:36 ` Matthew Brost
2025-10-02 14:54 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 30/36] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-10-02 1:02 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 31/36] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-02 1:09 ` Lis, Tomasz
2025-10-02 6:12 ` Matthew Brost
2025-09-29 2:55 ` [PATCH v3 32/36] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-02 1:25 ` Lis, Tomasz
2025-09-29 2:55 ` [PATCH v3 33/36] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-09-29 2:55 ` [PATCH v3 34/36] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-09-29 2:55 ` [PATCH v3 35/36] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-09-29 2:55 ` [PATCH v3 36/36] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-09-29 15:17 ` K V P, Satyanarayana
2025-09-30 12:39 ` Matthew Brost
2025-09-30 13:38 ` Michal Wajdeczko
2025-09-30 14:39 ` Matthew Brost
2025-09-29 3:06 ` ✗ CI.checkpatch: warning for VF migration redesign (rev3) Patchwork
2025-09-29 3:08 ` ✓ CI.KUnit: success " Patchwork
2025-09-29 6:28 ` ✗ Xe.CI.Full: failure " 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=20250929025542.1486303-27-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