From: Michal Wajdeczko <michal.wajdeczko@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Subject: [PATCH 5/5] drm/xe/pf: Adjust scheduling priority based on policy change
Date: Thu, 24 Oct 2024 01:11:52 +0200 [thread overview]
Message-ID: <20241023231152.1815-6-michal.wajdeczko@intel.com> (raw)
In-Reply-To: <20241023231152.1815-1-michal.wajdeczko@intel.com>
Local values of scheduling priorities need to be adjusted when
changing the schedule_if_idle policy as those are related.
Disabling schedule_if_idle policy forces the low priority, and
enabling schedule_if_idle policy forces the normal priority.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
---
drivers/gpu/drm/xe/xe_gt_sriov_pf_policy.c | 25 +++++++++++++++++++---
1 file changed, 22 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_policy.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_policy.c
index fae5be5a2a11..c49983ceac39 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_policy.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_policy.c
@@ -135,14 +135,33 @@ static int pf_update_policy_u32(struct xe_gt *gt, u16 key, u32 *policy, u32 valu
return 0;
}
+static void pf_bulk_reset_priority(struct xe_gt *gt, u32 priority)
+{
+ unsigned int total_vfs = 1 + xe_gt_sriov_pf_get_totalvfs(gt);
+ unsigned int n;
+
+ xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+ lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
+
+ for (n = 0; n < total_vfs; n++)
+ gt->sriov.pf.vfs[n].config.priority = priority;
+}
+
static int pf_provision_sched_if_idle(struct xe_gt *gt, bool enable)
{
+ int err;
+
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
- return pf_update_policy_bool(gt, GUC_KLV_VGT_POLICY_SCHED_IF_IDLE_KEY,
- >->sriov.pf.policy.guc.sched_if_idle,
- enable);
+ err = pf_update_policy_bool(gt, GUC_KLV_VGT_POLICY_SCHED_IF_IDLE_KEY,
+ >->sriov.pf.policy.guc.sched_if_idle,
+ enable);
+
+ if (!err)
+ pf_bulk_reset_priority(gt, enable ? GUC_SCHED_PRIORITY_NORMAL :
+ GUC_SCHED_PRIORITY_LOW);
+ return err;
}
static int pf_reprovision_sched_if_idle(struct xe_gt *gt)
--
2.43.0
next prev parent reply other threads:[~2024-10-23 23:12 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-23 23:11 [PATCH 0/5] PF: Add support for VF scheduling priority Michal Wajdeczko
2024-10-23 23:11 ` [PATCH 1/5] drm/xe/guc: Add VF_CFG_SCHED_PRIORITY_KEY KLV definition Michal Wajdeczko
2024-10-28 15:34 ` Laguna, Lukasz
2024-10-23 23:11 ` [PATCH 2/5] drm/xe/guc: Add VF_CFG_SCHED_PRIORITY to KLV helper Michal Wajdeczko
2024-10-23 23:11 ` [PATCH 3/5] drm/xe/pf: Add functions to configure VF scheduling priority Michal Wajdeczko
2024-10-23 23:11 ` [PATCH 4/5] drm/xe/pf: Allow to control scheduling priority using debugfs Michal Wajdeczko
2024-10-23 23:11 ` Michal Wajdeczko [this message]
2024-10-24 15:30 ` ✓ CI.Patch_applied: success for PF: Add support for VF scheduling priority Patchwork
2024-10-24 15:30 ` ✓ CI.checkpatch: " Patchwork
2024-10-24 15:31 ` ✓ CI.KUnit: " Patchwork
2024-10-24 15:43 ` ✓ CI.Build: " Patchwork
2024-10-24 15:45 ` ✓ CI.Hooks: " Patchwork
2024-10-24 15:46 ` ✓ CI.checksparse: " Patchwork
2024-10-24 16:12 ` ✗ CI.BAT: failure " Patchwork
2024-10-25 18:37 ` ✗ CI.FULL: " Patchwork
2024-10-28 15:51 ` [PATCH 0/5] " Laguna, Lukasz
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=20241023231152.1815-6-michal.wajdeczko@intel.com \
--to=michal.wajdeczko@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