From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: stuart.summers@intel.com, lucas.demarchi@intel.com,
matthew.d.roper@intel.com
Subject: [PATCH 09/12] drm/xe: Add xe_tlb_inval_idle helper
Date: Fri, 31 Oct 2025 18:02:22 -0700 [thread overview]
Message-ID: <20251101010225.3095457-10-matthew.brost@intel.com> (raw)
In-Reply-To: <20251101010225.3095457-1-matthew.brost@intel.com>
Introduce the xe_tlb_inval_idle helper to detect whether any TLB
invalidations are currently in flight. This is used in context-based TLB
invalidations to determine whether dummy TLB invalidations need to be
sent to maintain proper TLB invalidation fence ordering..
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/xe/xe_tlb_inval.c | 26 ++++++++++++++++++++++++++
drivers/gpu/drm/xe/xe_tlb_inval.h | 2 ++
2 files changed, 28 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index 7ee081b94f90..32a0a882343b 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -141,6 +141,7 @@ int xe_gt_tlb_inval_init_early(struct xe_gt *gt)
tlb_inval->xe = xe;
tlb_inval->seqno = 1;
+ tlb_inval->seqno_recv = TLB_INVALIDATION_SEQNO_MAX - 1;
INIT_LIST_HEAD(&tlb_inval->pending_fences);
spin_lock_init(&tlb_inval->pending_lock);
spin_lock_init(&tlb_inval->lock);
@@ -443,3 +444,28 @@ void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
dma_fence_get(&fence->base);
fence->tlb_inval = tlb_inval;
}
+
+/**
+ * xe_tlb_inval_idle() - Initialize TLB invalidation is idle
+ * @tlb_inval: TLB invalidation client
+ *
+ * Check the TLB invalidation seqno to determine if it is idle (i.e., no TLB
+ * invalidations are in flight). Expected to be called in the backend after the
+ * seqno has been bumped, and takes this into account.
+ *
+ * Return: True if TLB invalidation client is idle, False otherwise
+ */
+bool xe_tlb_inval_idle(struct xe_tlb_inval *tlb_inval)
+{
+ int next_recv;
+
+ lockdep_assert_held(&tlb_inval->seqno_lock);
+
+ guard(spinlock_irq)(&tlb_inval->pending_lock);
+
+ next_recv = (tlb_inval->seqno_recv + 2) % TLB_INVALIDATION_SEQNO_MAX;
+ if (!next_recv)
+ next_recv = 1;
+
+ return next_recv == tlb_inval->seqno;
+}
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.h b/drivers/gpu/drm/xe/xe_tlb_inval.h
index 05614915463a..44a6d9177489 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.h
@@ -43,4 +43,6 @@ xe_tlb_inval_fence_wait(struct xe_tlb_inval_fence *fence)
void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno);
+bool xe_tlb_inval_idle(struct xe_tlb_inval *tlb_inval);
+
#endif /* _XE_TLB_INVAL_ */
--
2.34.1
next prev parent reply other threads:[~2025-11-01 1:02 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-01 1:02 [PATCH 00/12] Context based TLB invalidations Matthew Brost
2025-11-01 1:02 ` [PATCH 01/12] drm/xe: Add normalize_invalidation_range Matthew Brost
2025-11-01 1:02 ` [PATCH 02/12] drm/xe: Make usm.asid_to_vm allocation use GFP_NOWAIT Matthew Brost
2025-11-01 1:02 ` [PATCH 03/12] drm/xe: Add xe_device_asid_to_vm helper Matthew Brost
2025-11-01 1:02 ` [PATCH 04/12] drm/xe: Add vm to exec queues association Matthew Brost
2025-11-01 1:02 ` [PATCH 05/12] drm/xe: Taint TLB invalidation seqno lock with GFP_KERNEL Matthew Brost
2025-11-01 1:02 ` [PATCH 06/12] drm/xe: Do not forward invalid TLB invalidation seqnos to upper layers Matthew Brost
2025-11-01 1:02 ` [PATCH 07/12] drm/xe: Rename send_tlb_inval_ppgtt to send_tlb_inval_asid_ppgtt Matthew Brost
2025-11-01 1:02 ` [PATCH 08/12] drm/xe: Add send_tlb_inval_ppgtt helper Matthew Brost
2025-11-01 1:02 ` Matthew Brost [this message]
2025-11-01 1:02 ` [PATCH 10/12] drm/xe: Add exec queue active vfunc Matthew Brost
2025-11-01 1:02 ` [PATCH 11/12] drm/xe: Add context-based invalidation to GuC TLB invalidation backend Matthew Brost
2025-11-01 1:02 ` [PATCH 12/12] drm/xe: Enable context TLB invalidations for CI Matthew Brost
2025-11-01 3:43 ` ✗ CI.checkpatch: warning for Context based TLB invalidations Patchwork
2025-11-01 3:44 ` ✓ CI.KUnit: success " Patchwork
2025-11-01 4:48 ` ✓ Xe.CI.BAT: " Patchwork
2025-11-01 23:44 ` ✓ 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=20251101010225.3095457-10-matthew.brost@intel.com \
--to=matthew.brost@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=lucas.demarchi@intel.com \
--cc=matthew.d.roper@intel.com \
--cc=stuart.summers@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