From: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
To: Matthew Brost <matthew.brost@intel.com>
Cc: intel-xe@lists.freedesktop.org
Subject: Re: [PATCH v3 02/36] drm/xe/vf: Lock querying GGTT config during driver init
Date: Mon, 29 Sep 2025 11:13:03 +0300 [thread overview]
Message-ID: <aNo_jwo80N-3WEDv@intel.com> (raw)
In-Reply-To: <20250929025542.1486303-3-matthew.brost@intel.com>
On Sun, Sep 28, 2025 at 07:55:08PM -0700, Matthew Brost wrote:
> From: Tomasz Lis <tomasz.lis@intel.com>
>
> Protect access to GGTT config as this is non-static information.
>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> ---
> drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 96 ++++++++++++++++++-----
> drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h | 3 +
> drivers/gpu/drm/xe/xe_sriov_vf.c | 6 ++
> 3 files changed, 84 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 0461d5513487..016c867e5e2b 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -440,18 +440,21 @@ static int vf_get_ggtt_info(struct xe_gt *gt)
>
> xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
>
> + down_write(&config->lock);
> +
> err = guc_action_query_single_klv64(guc, GUC_KLV_VF_CFG_GGTT_START_KEY, &start);
> if (unlikely(err))
> - return err;
> + goto out;
>
> err = guc_action_query_single_klv64(guc, GUC_KLV_VF_CFG_GGTT_SIZE_KEY, &size);
> if (unlikely(err))
> - return err;
> + goto out;
>
> if (config->ggtt_size && config->ggtt_size != size) {
> xe_gt_sriov_err(gt, "Unexpected GGTT reassignment: %lluK != %lluK\n",
> size / SZ_1K, config->ggtt_size / SZ_1K);
> - return -EREMCHG;
> + err = -EREMCHG;
> + goto out;
> }
>
> xe_gt_sriov_dbg_verbose(gt, "GGTT %#llx-%#llx = %lluK\n",
> @@ -460,8 +463,11 @@ static int vf_get_ggtt_info(struct xe_gt *gt)
> config->ggtt_shift = start - (s64)config->ggtt_base;
> config->ggtt_base = start;
> config->ggtt_size = size;
> + err = config->ggtt_size ? 0 : -ENODATA;
>
> - return config->ggtt_size ? 0 : -ENODATA;
> +out:
> + up_write(&config->lock);
> + return err;
> }
>
> static int vf_get_lmem_info(struct xe_gt *gt)
> @@ -474,22 +480,28 @@ static int vf_get_lmem_info(struct xe_gt *gt)
>
> xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
>
> + down_write(&config->lock);
> +
> err = guc_action_query_single_klv64(guc, GUC_KLV_VF_CFG_LMEM_SIZE_KEY, &size);
> if (unlikely(err))
> - return err;
> + goto out;
>
> if (config->lmem_size && config->lmem_size != size) {
> xe_gt_sriov_err(gt, "Unexpected LMEM reassignment: %lluM != %lluM\n",
> size / SZ_1M, config->lmem_size / SZ_1M);
> - return -EREMCHG;
> + err = -EREMCHG;
> + goto out;
> }
>
> string_get_size(size, 1, STRING_UNITS_2, size_str, sizeof(size_str));
> xe_gt_sriov_dbg_verbose(gt, "LMEM %lluM %s\n", size / SZ_1M, size_str);
>
> config->lmem_size = size;
> + err = config->lmem_size ? 0 : -ENODATA;
>
> - return config->lmem_size ? 0 : -ENODATA;
> +out:
> + up_write(&config->lock);
> + return err;
> }
>
> static int vf_get_submission_cfg(struct xe_gt *gt)
> @@ -501,23 +513,27 @@ static int vf_get_submission_cfg(struct xe_gt *gt)
>
> xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
>
> + down_write(&config->lock);
> +
> err = guc_action_query_single_klv32(guc, GUC_KLV_VF_CFG_NUM_CONTEXTS_KEY, &num_ctxs);
> if (unlikely(err))
> - return err;
> + goto out;
>
> err = guc_action_query_single_klv32(guc, GUC_KLV_VF_CFG_NUM_DOORBELLS_KEY, &num_dbs);
> if (unlikely(err))
> - return err;
> + goto out;
>
> if (config->num_ctxs && config->num_ctxs != num_ctxs) {
> xe_gt_sriov_err(gt, "Unexpected CTXs reassignment: %u != %u\n",
> num_ctxs, config->num_ctxs);
> - return -EREMCHG;
> + err = -EREMCHG;
> + goto out;
> }
> if (config->num_dbs && config->num_dbs != num_dbs) {
> xe_gt_sriov_err(gt, "Unexpected DBs reassignment: %u != %u\n",
> num_dbs, config->num_dbs);
> - return -EREMCHG;
> + err = -EREMCHG;
> + goto out;
> }
>
> xe_gt_sriov_dbg_verbose(gt, "CTXs %u DBs %u\n", num_ctxs, num_dbs);
> @@ -525,7 +541,11 @@ static int vf_get_submission_cfg(struct xe_gt *gt)
> config->num_ctxs = num_ctxs;
> config->num_dbs = num_dbs;
>
> - return config->num_ctxs ? 0 : -ENODATA;
> + err = config->num_ctxs ? 0 : -ENODATA;
> +
> +out:
> + up_write(&config->lock);
> + return err;
> }
>
> static void vf_cache_gmdid(struct xe_gt *gt)
> @@ -579,11 +599,18 @@ int xe_gt_sriov_vf_query_config(struct xe_gt *gt)
> */
> u16 xe_gt_sriov_vf_guc_ids(struct xe_gt *gt)
> {
> + struct xe_gt_sriov_vf_selfconfig *config = >->sriov.vf.self_config;
> + u16 val;
> +
> xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
> xe_gt_assert(gt, gt->sriov.vf.guc_version.major);
> - xe_gt_assert(gt, gt->sriov.vf.self_config.num_ctxs);
>
> - return gt->sriov.vf.self_config.num_ctxs;
> + down_read(&config->lock);
> + xe_gt_assert(gt, config->num_ctxs);
> + val = config->num_ctxs;
> + up_read(&config->lock);
> +
> + return val;
> }
>
> /**
> @@ -596,11 +623,18 @@ u16 xe_gt_sriov_vf_guc_ids(struct xe_gt *gt)
> */
> u64 xe_gt_sriov_vf_lmem(struct xe_gt *gt)
> {
> + struct xe_gt_sriov_vf_selfconfig *config = >->sriov.vf.self_config;
> + u64 val;
> +
> xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
> xe_gt_assert(gt, gt->sriov.vf.guc_version.major);
> - xe_gt_assert(gt, gt->sriov.vf.self_config.lmem_size);
>
> - return gt->sriov.vf.self_config.lmem_size;
> + down_read(&config->lock);
> + xe_gt_assert(gt, config->lmem_size);
> + val = config->lmem_size;
> + up_read(&config->lock);
Why is someone mutating this sort of information at runtime?
Sounds pretty crazy to me.
--
Ville Syrjälä
Intel
next prev parent reply other threads:[~2025-09-29 8:13 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 [this message]
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 ` [PATCH v3 26/36] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-09-29 21:49 ` 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=aNo_jwo80N-3WEDv@intel.com \
--to=ville.syrjala@linux.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