From: Matthew Brost <matthew.brost@intel.com>
To: "Lis, Tomasz" <tomasz.lis@intel.com>
Cc: <intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH v2 14/34] drm/xe/vf: Remove memory allocations from VF post migration recovery
Date: Thu, 25 Sep 2025 18:43:40 -0700 [thread overview]
Message-ID: <aNXvzPBKizZjBxzn@lstrano-desk.jf.intel.com> (raw)
In-Reply-To: <60a52da8-6949-4c51-b7a1-16c71e4b4fe6@intel.com>
On Fri, Sep 26, 2025 at 03:35:33AM +0200, Lis, Tomasz wrote:
>
> On 9/24/2025 3:15 AM, Matthew Brost wrote:
> > VF post migration recovery is the path of dma-fence signaling / reclaim,
> > avoid memory allocations in this path.
> >
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > ---
> > drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 29 ++++++++++++++---------
> > drivers/gpu/drm/xe/xe_gt_sriov_vf.h | 2 +-
> > drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h | 2 ++
> > drivers/gpu/drm/xe/xe_sriov.c | 8 +++++--
> > drivers/gpu/drm/xe/xe_sriov_vf.c | 14 ++++++++---
> > drivers/gpu/drm/xe/xe_sriov_vf.h | 2 +-
> > 6 files changed, 39 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 cfb71b749e52..8304c26c076e 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> > @@ -1214,17 +1214,13 @@ static size_t post_migration_scratch_size(struct xe_device *xe)
> > static int vf_post_migration_fixups(struct xe_gt *gt)
> > {
> > + void *buf = gt->sriov.vf.migration.lrc_wa_bb;
>
> can we just call it 'scratch', or 'recovery_scratch'? The current use is
> limited to lrc, but besides temp buffer for WAs it also stores MEMIRQ regs.
>
> This name makes it look like something more important than it is, and does
> not describe all uses.
>
> Besides that name, LGTM.
Yes, that is a better name. Will change.
Matt
>
> -Tomasz
>
> > s64 shift;
> > - void *buf;
> > int err;
> > - buf = kmalloc(post_migration_scratch_size(gt_to_xe(gt)), GFP_ATOMIC);
> > - if (!buf)
> > - return -ENOMEM;
> > -
> > err = xe_gt_sriov_vf_query_config(gt);
> > if (err)
> > - goto out;
> > + return err;
> > shift = xe_gt_sriov_vf_ggtt_shift(gt);
> > if (shift) {
> > @@ -1232,12 +1228,10 @@ static int vf_post_migration_fixups(struct xe_gt *gt)
> > xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
> > err = xe_guc_contexts_hwsp_rebase(>->uc.guc, buf);
> > if (err)
> > - goto out;
> > + return err;
> > }
> > -out:
> > - kfree(buf);
> > - return err;
> > + return 0;
> > }
> > static void vf_post_migration_kickstart(struct xe_gt *gt)
> > @@ -1314,15 +1308,28 @@ static void migration_worker_func(struct work_struct *w)
> > /**
> > * xe_gt_sriov_vf_migration_init_early() - VF post migration init early
> > * @gt: the &xe_gt
> > + *
> > + * Return 0 on success, errno on failure
> > */
> > -void xe_gt_sriov_vf_migration_init_early(struct xe_gt *gt)
> > +int xe_gt_sriov_vf_migration_init_early(struct xe_gt *gt)
> > {
> > + void *buf;
> > +
> > + buf = drmm_kmalloc(>_to_xe(gt)->drm,
> > + post_migration_scratch_size(gt_to_xe(gt)),
> > + GFP_KERNEL);
> > + if (!buf)
> > + return -ENOMEM;
> > +
> > + gt->sriov.vf.migration.lrc_wa_bb = buf;
> > init_rwsem(>->sriov.vf.self_config.lock);
> > spin_lock_init(>->sriov.vf.migration.lock);
> > INIT_WORK(>->sriov.vf.migration.worker, migration_worker_func);
> > if (!xe_sriov_vf_migration_supported(gt_to_xe(gt)))
> > xe_gt_sriov_info(gt, "migration not supported by this module version\n");
> > +
> > + return 0;
> > }
> > /**
> > diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> > index 2ac6775b52f0..195dbebe941e 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> > @@ -23,7 +23,7 @@ int xe_gt_sriov_vf_connect(struct xe_gt *gt);
> > int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt);
> > void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
> > -void xe_gt_sriov_vf_migration_init_early(struct xe_gt *gt);
> > +int xe_gt_sriov_vf_migration_init_early(struct xe_gt *gt);
> > bool xe_gt_sriov_vf_recovery_inprogress(struct xe_gt *gt);
> > u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt);
> > diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> > index 53680a2f188a..496b657119de 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> > @@ -58,6 +58,8 @@ struct xe_gt_sriov_vf_migration {
> > struct work_struct worker;
> > /** @lock: Protects recovery_queued */
> > spinlock_t lock;
> > + /** @lrc_wa_bb: Scratch memory for LRC WA BB in recovery */
> > + void *lrc_wa_bb;
> > /** @recovery_queued: VF post migration recovery in queued */
> > bool recovery_queued;
> > /** @recovery_inprogress: VF post migration recovery in progress */
> > diff --git a/drivers/gpu/drm/xe/xe_sriov.c b/drivers/gpu/drm/xe/xe_sriov.c
> > index 7d2d6de2aabf..358a35c80d5a 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov.c
> > +++ b/drivers/gpu/drm/xe/xe_sriov.c
> > @@ -116,8 +116,12 @@ int xe_sriov_init(struct xe_device *xe)
> > return err;
> > }
> > - if (IS_SRIOV_VF(xe))
> > - xe_sriov_vf_init_early(xe);
> > + if (IS_SRIOV_VF(xe)) {
> > + int err = xe_sriov_vf_init_early(xe);
> > +
> > + if (err)
> > + return err;
> > + }
> > xe_assert(xe, !xe->sriov.wq);
> > xe->sriov.wq = alloc_workqueue("xe-sriov-wq", 0, 0);
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
> > index 7d91553c4acc..e622a7c562c4 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov_vf.c
> > +++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
> > @@ -180,16 +180,24 @@ static void vf_migration_init_early(struct xe_device *xe)
> > /**
> > * xe_sriov_vf_init_early - Initialize SR-IOV VF specific data.
> > * @xe: the &xe_device to initialize
> > + *
> > + * Return: 0 on success or a negative error code on failure.
> > */
> > -void xe_sriov_vf_init_early(struct xe_device *xe)
> > +int xe_sriov_vf_init_early(struct xe_device *xe)
> > {
> > struct xe_gt *gt;
> > unsigned int id;
> > + int err;
> > - for_each_gt(gt, xe, id)
> > - xe_gt_sriov_vf_migration_init_early(gt);
> > + for_each_gt(gt, xe, id) {
> > + err = xe_gt_sriov_vf_migration_init_early(gt);
> > + if (err)
> > + return err;
> > + }
> > vf_migration_init_early(xe);
> > +
> > + return 0;
> > }
> > /**
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.h b/drivers/gpu/drm/xe/xe_sriov_vf.h
> > index 4df95266b261..13969c6910ce 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov_vf.h
> > +++ b/drivers/gpu/drm/xe/xe_sriov_vf.h
> > @@ -11,7 +11,7 @@
> > struct dentry;
> > struct xe_device;
> > -void xe_sriov_vf_init_early(struct xe_device *xe);
> > +int xe_sriov_vf_init_early(struct xe_device *xe);
> > int xe_sriov_vf_init_late(struct xe_device *xe);
> > bool xe_sriov_vf_migration_supported(struct xe_device *xe);
> > void xe_sriov_vf_debugfs_register(struct xe_device *xe, struct dentry *root);
next prev parent reply other threads:[~2025-09-26 1:43 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-24 1:15 [PATCH v2 00/34] VF migration redesign Matthew Brost
2025-09-24 1:15 ` [PATCH v2 01/34] drm/xe/vf: Lock querying GGTT config during driver init Matthew Brost
2025-09-24 9:29 ` Michal Wajdeczko
2025-09-24 20:23 ` Matthew Brost
2025-09-30 0:42 ` Lis, Tomasz
2025-09-24 1:15 ` [PATCH v2 02/34] Revert "drm/xe/vf: Rebase exec queue parallel commands during migration recovery" Matthew Brost
2025-09-24 9:32 ` Michal Wajdeczko
2025-09-24 20:17 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 03/34] Revert "drm/xe/vf: Post migration, repopulate ring area for pending request" Matthew Brost
2025-09-24 1:15 ` [PATCH v2 04/34] Revert "drm/xe/vf: Fixup CTB send buffer messages after migration" Matthew Brost
2025-09-24 1:15 ` [PATCH v2 05/34] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-09-24 1:15 ` [PATCH v2 06/34] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-09-24 1:15 ` [PATCH v2 07/34] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-09-24 1:15 ` [PATCH v2 08/34] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-09-24 15:14 ` Lis, Tomasz
2025-09-25 16:12 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 09/34] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-09-24 14:23 ` Lis, Tomasz
2025-09-24 18:01 ` Lucas De Marchi
2025-09-25 20:25 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 10/34] drm/xe/guc: Document GuC submission backend Matthew Brost
2025-09-24 9:35 ` Michal Wajdeczko
2025-09-24 20:20 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 11/34] drm/xe/vf: Add xe_gt_sriov_vf_recovery_inprogress helper Matthew Brost
2025-09-24 10:14 ` Michal Wajdeczko
2025-09-24 19:39 ` Matthew Brost
2025-09-24 20:12 ` Michal Wajdeczko
2025-09-24 20:30 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 12/34] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-09-24 10:49 ` Michal Wajdeczko
2025-09-24 19:50 ` Matthew Brost
2025-09-24 20:21 ` Michal Wajdeczko
2025-09-24 20:35 ` Matthew Brost
2025-09-25 16:27 ` Lis, Tomasz
2025-09-25 16:56 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 13/34] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-09-24 11:00 ` Michal Wajdeczko
2025-09-24 20:01 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 14/34] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-09-26 1:35 ` Lis, Tomasz
2025-09-26 1:43 ` Matthew Brost [this message]
2025-09-24 1:15 ` [PATCH v2 15/34] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-09-26 2:33 ` Lis, Tomasz
2025-09-26 19:09 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 16/34] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-09-26 15:40 ` Lis, Tomasz
2025-09-26 19:13 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 17/34] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-09-27 2:59 ` Lis, Tomasz
2025-09-27 22:33 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 18/34] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-09-25 19:06 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 19/34] drm/xe/vf: Extra debug on GGTT shift Matthew Brost
2025-09-27 3:16 ` Lis, Tomasz
2025-09-27 11:06 ` Michal Wajdeczko
2025-09-27 22:56 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 20/34] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-09-24 11:15 ` Michal Wajdeczko
2025-09-24 20:16 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 21/34] drm/xe/vf: Stop and flush CTs in VF post migration recovery Matthew Brost
2025-09-24 11:21 ` Michal Wajdeczko
2025-09-24 20:12 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 22/34] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-09-27 3:43 ` Lis, Tomasz
2025-09-27 22:29 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 23/34] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-09-27 11:21 ` Lis, Tomasz
2025-09-24 1:15 ` [PATCH v2 24/34] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-09-24 11:50 ` Michal Wajdeczko
2025-09-24 20:10 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 25/34] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-09-27 11:54 ` Lis, Tomasz
2025-09-27 22:38 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 26/34] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-09-27 13:33 ` Lis, Tomasz
2025-09-27 23:11 ` Matthew Brost
2025-09-24 1:15 ` [PATCH v2 27/34] drm/xe: Move queue init before LRC creation Matthew Brost
2025-09-24 1:15 ` [PATCH v2 28/34] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-09-24 1:15 ` [PATCH v2 29/34] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-09-24 1:15 ` [PATCH v2 30/34] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-09-24 1:15 ` [PATCH v2 31/34] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-09-24 1:15 ` [PATCH v2 32/34] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-09-24 1:16 ` [PATCH v2 33/34] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-09-24 4:04 ` K V P, Satyanarayana
2025-09-24 6:32 ` Matthew Brost
2025-09-24 6:36 ` K V P, Satyanarayana
2025-09-24 1:16 ` [PATCH v2 34/34] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-09-24 1:29 ` ✓ CI.KUnit: success for VF migration redesign (rev2) Patchwork
2025-09-24 2:14 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-09-24 7:37 ` ✗ 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=aNXvzPBKizZjBxzn@lstrano-desk.jf.intel.com \
--to=matthew.brost@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=tomasz.lis@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