From: "Lis, Tomasz" <tomasz.lis@intel.com>
To: Matthew Brost <matthew.brost@intel.com>,
<intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH v6 20/30] drm/xe/vf: Start CTs before resfix VF post migration recovery
Date: Mon, 6 Oct 2025 23:50:41 +0200 [thread overview]
Message-ID: <ee7a0bf0-59d0-4ab6-a5b0-cf93c3d39fe6@intel.com> (raw)
In-Reply-To: <20251006111038.2234860-21-matthew.brost@intel.com>
[-- Attachment #1: Type: text/plain, Size: 7209 bytes --]
On 10/6/2025 1:10 PM, Matthew Brost wrote:
> 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 | 70 +++++++++++++++++++++--------
> drivers/gpu/drm/xe/xe_guc_ct.h | 1 +
> 3 files changed, 60 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 2a988eb3e904..6052c7302cc6 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -1139,6 +1139,11 @@ 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);
> @@ -1190,6 +1195,8 @@ 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 f67575b1ed79..c0d261abf735 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -167,6 +167,7 @@ ct_to_xe(struct xe_guc_ct *ct)
> */
>
> #define CTB_DESC_SIZE ALIGN(sizeof(struct guc_ct_buffer_desc), SZ_2K)
> +#define CTB_H2G_BUFFER_OFFSET (CTB_DESC_SIZE * 2)
We've agreed today to separate the CTB_H2G_BUFFER_OFFSET introduction to
its own patch within this series.
(as in comments for rev4)
-Tomasz
> #define CTB_H2G_BUFFER_SIZE (SZ_4K)
> #define CTB_G2H_BUFFER_SIZE (SZ_128K)
> #define G2H_ROOM_BUFFER_SIZE (CTB_G2H_BUFFER_SIZE / 2)
> @@ -190,7 +191,7 @@ long xe_guc_ct_queue_proc_time_jiffies(struct xe_guc_ct *ct)
>
> static size_t guc_ct_size(void)
> {
> - return 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE +
> + return CTB_H2G_BUFFER_OFFSET + CTB_H2G_BUFFER_SIZE +
> CTB_G2H_BUFFER_SIZE;
> }
>
> @@ -331,7 +332,7 @@ static void guc_ct_ctb_h2g_init(struct xe_device *xe, struct guc_ctb *h2g,
> h2g->desc = *map;
> xe_map_memset(xe, &h2g->desc, 0, 0, sizeof(struct guc_ct_buffer_desc));
>
> - h2g->cmds = IOSYS_MAP_INIT_OFFSET(map, CTB_DESC_SIZE * 2);
> + h2g->cmds = IOSYS_MAP_INIT_OFFSET(map, CTB_H2G_BUFFER_OFFSET);
> }
>
> static void guc_ct_ctb_g2h_init(struct xe_device *xe, struct guc_ctb *g2h,
> @@ -349,7 +350,7 @@ static void guc_ct_ctb_g2h_init(struct xe_device *xe, struct guc_ctb *g2h,
> g2h->desc = IOSYS_MAP_INIT_OFFSET(map, CTB_DESC_SIZE);
> xe_map_memset(xe, &g2h->desc, 0, 0, sizeof(struct guc_ct_buffer_desc));
>
> - g2h->cmds = IOSYS_MAP_INIT_OFFSET(map, CTB_DESC_SIZE * 2 +
> + g2h->cmds = IOSYS_MAP_INIT_OFFSET(map, CTB_H2G_BUFFER_OFFSET +
> CTB_H2G_BUFFER_SIZE);
> }
>
> @@ -360,7 +361,7 @@ static int guc_ct_ctb_h2g_register(struct xe_guc_ct *ct)
> int err;
>
> desc_addr = xe_bo_ggtt_addr(ct->bo);
> - ctb_addr = xe_bo_ggtt_addr(ct->bo) + CTB_DESC_SIZE * 2;
> + ctb_addr = xe_bo_ggtt_addr(ct->bo) + CTB_H2G_BUFFER_OFFSET;
> size = ct->ctbs.h2g.info.size * sizeof(u32);
>
> err = xe_guc_self_cfg64(guc,
> @@ -387,7 +388,7 @@ static int guc_ct_ctb_g2h_register(struct xe_guc_ct *ct)
> int err;
>
> desc_addr = xe_bo_ggtt_addr(ct->bo) + CTB_DESC_SIZE;
> - ctb_addr = xe_bo_ggtt_addr(ct->bo) + CTB_DESC_SIZE * 2 +
> + ctb_addr = xe_bo_ggtt_addr(ct->bo) + CTB_H2G_BUFFER_OFFSET +
> CTB_H2G_BUFFER_SIZE;
> size = ct->ctbs.g2h.info.size * sizeof(u32);
>
> @@ -501,7 +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);
> @@ -509,21 +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);
>
> @@ -555,6 +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..10d05193e51c 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);
[-- Attachment #2: Type: text/html, Size: 7629 bytes --]
next prev parent reply other threads:[~2025-10-06 21:50 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-06 11:10 [PATCH v6 00/30] VF migration redesign Matthew Brost
2025-10-06 11:10 ` [PATCH v6 01/30] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-10-06 21:51 ` Lis, Tomasz
2025-10-06 11:10 ` [PATCH v6 02/30] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-10-06 11:10 ` [PATCH v6 03/30] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-10-06 11:10 ` [PATCH v6 04/30] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-10-06 11:10 ` [PATCH v6 05/30] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-10-06 11:10 ` [PATCH v6 06/30] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-10-06 11:10 ` [PATCH v6 07/30] drm/xe/vf: Add xe_gt_recovery_pending helper Matthew Brost
2025-10-06 13:10 ` Michal Wajdeczko
2025-10-06 11:10 ` [PATCH v6 08/30] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-10-06 11:10 ` [PATCH v6 09/30] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 10/30] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 11/30] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-10-06 14:27 ` Michal Wajdeczko
2025-10-06 14:56 ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 12/30] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-10-06 11:10 ` [PATCH v6 13/30] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 14/30] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-10-06 14:35 ` Michal Wajdeczko
2025-10-06 15:54 ` Matthew Brost
2025-10-06 22:27 ` Lis, Tomasz
2025-10-06 23:07 ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 15/30] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-06 11:10 ` [PATCH v6 16/30] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-10-06 14:51 ` Michal Wajdeczko
2025-10-06 16:02 ` Matthew Brost
2025-10-06 22:21 ` Lis, Tomasz
2025-10-06 22:57 ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 17/30] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 18/30] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-06 11:10 ` [PATCH v6 19/30] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-10-06 11:10 ` [PATCH v6 20/30] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-10-06 21:50 ` Lis, Tomasz [this message]
2025-10-06 11:10 ` [PATCH v6 21/30] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-06 11:10 ` [PATCH v6 22/30] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-06 11:10 ` [PATCH v6 23/30] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-06 15:22 ` Michal Wajdeczko
2025-10-06 21:33 ` Lis, Tomasz
2025-10-06 11:10 ` [PATCH v6 24/30] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 25/30] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-06 11:10 ` [PATCH v6 26/30] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-06 11:10 ` [PATCH v6 27/30] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-10-06 22:24 ` Lucas De Marchi
2025-10-06 22:51 ` Matthew Brost
2025-10-07 17:00 ` Lucas De Marchi
2025-10-07 17:22 ` Matthew Brost
2025-10-07 20:36 ` Lucas De Marchi
2025-10-07 21:18 ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 28/30] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-10-06 11:10 ` [PATCH v6 29/30] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-10-06 11:10 ` [PATCH v6 30/30] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-10-06 11:17 ` ✗ CI.checkpatch: warning for VF migration redesign (rev6) Patchwork
2025-10-06 11:18 ` ✓ CI.KUnit: success " Patchwork
2025-10-06 12:24 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-10-06 14:28 ` ✗ Xe.CI.Full: " Patchwork
2025-10-07 0:20 ` [PATCH v6 00/30] VF migration redesign Niranjana Vishwanathapura
2025-10-07 1:11 ` Matthew Brost
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=ee7a0bf0-59d0-4ab6-a5b0-cf93c3d39fe6@intel.com \
--to=tomasz.lis@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox