From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 4C6A1C55838 for ; Thu, 6 Aug 2026 03:32:13 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id AE81C10E167; Thu, 6 Aug 2026 03:32:12 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="SNWdZ9uK"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.16]) by gabe.freedesktop.org (Postfix) with ESMTPS id 48CE610E167 for ; Thu, 6 Aug 2026 03:32:11 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1785987132; x=1817523132; h=from:to:subject:date:message-id:mime-version: content-transfer-encoding; bh=E7vSKRBdi4cEEOLJ4MAAilIEacdR0dZCCjG1uwvhh7Q=; b=SNWdZ9uK1Z03Z5OOjnN0mNaZy+V/uEr/B1RHP/q9c4UU9iRmQkCFJoMK zD0BSF9umJbj5gUzZTe5r4C8L6rcR7QjdVz1sHo1RJXATRYp7w3cfGc1X Dahc9o0IRfRr4doLEyn6e0tl+UJAQCLBLouwhvpl1maOAJRAI+MEpD8FJ mDdBKOqN1EvVaJ9VmFs6/MmzsqFyurapTjxaYzOXH2NdnRMuDJQh8BUxQ 8KftVDVNjUcULOQsH6BApgE9w2e3vY5hln3lQWm216ZRwHyswOJTVNMA3 rZ7KdulOyDfq2nu1Du5mPDHjyRqPt+uk0meQMu+bZUeoqLCj764YvBW0x w==; X-CSE-ConnectionGUID: fC9rI1VOSWOMRqPSNZoLkA== X-CSE-MsgGUID: 99ygEadiQcyXci2YNi2ofA== X-IronPort-AV: E=McAfee;i="6800,10657,11866"; a="86776660" X-IronPort-AV: E=Sophos;i="6.25,207,1779174000"; d="scan'208";a="86776660" Received: from orviesa002.jf.intel.com ([10.64.159.142]) by orvoesa108.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 05 Aug 2026 20:32:11 -0700 X-CSE-ConnectionGUID: KDMcyLmqR8ereSEG+tZUrg== X-CSE-MsgGUID: N64YanpER320TXLUUfxJlA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.25,207,1779174000"; d="scan'208";a="291905081" Received: from gsse-cloud1.jf.intel.com ([10.54.39.91]) by orviesa002-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 05 Aug 2026 20:32:11 -0700 From: Matthew Brost To: intel-xe@lists.freedesktop.org Subject: [PATCH] drm/xe: Skip GT TLB invalidation when VM has no queues mapped Date: Wed, 5 Aug 2026 20:32:05 -0700 Message-Id: <20260806033205.3858054-1-matthew.brost@intel.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" If no exec queues from a VM are mapped on a GT, issuing a PPGTT TLB invalidation for that GT can require an rc6 wake which is expensive. Skip the media TLB invalidation when the VM has no exec queues mapped on it. If TLB invalidations are already in-flight on that GT we can't break fence ordering, so issue a dummy GGTT invalidation instead to maintain seqno ordering. This optimization is particularly impactful for SVM workloads which may or may not use the media GT. Average TLB invalidation time drops from ~75us to ~18us in such benchmarks on certain BMG parts - the improvement varies based on platform. Signed-off-by: Matthew Brost --- v2: - Make GT generic rather than just media GT (Thomas) - Fix accounting bug in empty vs non-empty (CI) --- drivers/gpu/drm/xe/xe_guc_tlb_inval.c | 20 ++++++++++++++++++-- drivers/gpu/drm/xe/xe_vm.c | 12 ++---------- 2 files changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c index 046d0655122f..ab04b87cf1c3 100644 --- a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c +++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c @@ -205,11 +205,27 @@ static int send_tlb_inval_asid_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno, struct drm_suballoc *prl_sa) { struct xe_guc *guc = tlb_inval->private; + struct xe_device *xe = guc_to_xe(guc); + struct xe_vm *vm; + int err, id = guc_to_gt(guc)->info.id; lockdep_assert_held(&tlb_inval->seqno_lock); - return send_tlb_inval_ppgtt(guc, seqno, start, end, asid, - XE_GUC_TLB_INVAL_PAGE_SELECTIVE, prl_sa); + vm = xe_device_asid_to_vm(xe, asid); + if (IS_ERR(vm)) + return PTR_ERR(vm); + + down_read(&vm->exec_queues.lock); + if (!vm->exec_queues.count[id] && xe_tlb_inval_idle(tlb_inval)) + err = -ECANCELED; + else + err = send_tlb_inval_ppgtt(guc, seqno, start, end, asid, + XE_GUC_TLB_INVAL_PAGE_SELECTIVE, + prl_sa); + up_read(&vm->exec_queues.lock); + xe_vm_put(vm); + + return err; } static int send_tlb_inval_ctx_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno, diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 9e0176861cb6..e2667200462c 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -4946,8 +4946,7 @@ int xe_vm_alloc_cpu_addr_mirror_vma(struct xe_vm *vm, uint64_t start, uint64_t r * @vm: The VM. * @q: The exec_queue * - * Add exec queue to VM, skipped if the device does not have context based TLB - * invalidations. + * Add exec queue to VM. */ void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) { @@ -4961,9 +4960,6 @@ void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) xe_assert(xe, vm->xef); xe_assert(xe, vm == q->vm); - if (!xe->info.has_ctx_tlb_inval) - return; - down_write(&vm->exec_queues.lock); list_add(&q->vm_exec_queue_link, &vm->exec_queues.list[q->gt->info.id]); ++vm->exec_queues.count[q->gt->info.id]; @@ -4975,14 +4971,10 @@ void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) * @vm: The VM. * @q: The exec_queue * - * Remove exec queue from VM, skipped if the device does not have context based - * TLB invalidations. + * Remove exec queue from VM. */ void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) { - if (!vm->xe->info.has_ctx_tlb_inval) - return; - down_write(&vm->exec_queues.lock); if (!list_empty(&q->vm_exec_queue_link)) { list_del(&q->vm_exec_queue_link); -- 2.34.1