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 51FFFC4451A for ; Sat, 11 Jul 2026 02:56:49 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id E829D10F9A9; Sat, 11 Jul 2026 02:56:41 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="NzBxxq3F"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.8]) by gabe.freedesktop.org (Postfix) with ESMTPS id 26F2710E6FE; Sat, 11 Jul 2026 02:56:32 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1783738592; x=1815274592; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=J1YcdAqKuIyiuZspeqa7qmtktzppXeERlakUfbNUKXM=; b=NzBxxq3F+gcRKF47eEQiuUc1ZJzGoIoFmlhIKgtejT6aUN1r0XwFZ13P cgNMtQbWzzd2MAGUlUvHH0yUyUDNii2lLX9FVUoUdR0CxW33Z/DXxXMPs dGHvyyhdOuaxGbEYc2vX8qNh34F151QmAFM/F1/+qo8XmwA42V1R44YQx DY7JWFdI+P4KI/kpjRcOVDpCFI7uqTbTOswalCa0By/GA4F8JLrVMiaSj y5tIXXBc8w8iDKf1hr2bU22EI1HtoH1gLkPi03KBI3C6jV6PNlha3L9Jv f9jB/dicudzDnvAFUutDwuZtH1qc6RZ0unfa1QMr9PK3zus+ZBdMphLei Q==; X-CSE-ConnectionGUID: s1bZKW3EQ5e/Jv8FchTd1Q== X-CSE-MsgGUID: 7zMCsudkS3C2ut2DXSe/eQ== X-IronPort-AV: E=McAfee;i="6800,10657,11841"; a="101986339" X-IronPort-AV: E=Sophos;i="6.25,154,1779174000"; d="scan'208";a="101986339" Received: from fmviesa004.fm.intel.com ([10.60.135.144]) by fmvoesa102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 Jul 2026 19:56:32 -0700 X-CSE-ConnectionGUID: gN9+bWohTD27RwrHoJ61QQ== X-CSE-MsgGUID: R7lxnx79R5iLY0OPROz9aQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.25,154,1779174000"; d="scan'208";a="256987776" Received: from gsse-cloud1.jf.intel.com ([10.54.39.91]) by fmviesa004-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 Jul 2026 19:56:31 -0700 From: Matthew Brost To: intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org Cc: Carlos Santa , Ryan Neph , Christian Koenig , Huang Rui , Matthew Auld , Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , David Airlie , Simona Vetter , linux-kernel@vger.kernel.org, =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Subject: [PATCH v3 24/33] drm/xe: Add defrag profiling tracepoints Date: Fri, 10 Jul 2026 19:56:10 -0700 Message-Id: <20260711025619.2540575-25-matthew.brost@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20260711025619.2540575-1-matthew.brost@intel.com> References: <20260711025619.2540575-1-matthew.brost@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 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" Add two tracepoints to profile the page defragmentation worker: - xe_bo_defrag_worker: emitted on worker entry and exit with the current defrag list count and the bytes processed in the run. - xe_bo_defrag_one: emitted per BO with the run budget, the prealloc fill ratio (got/want) and the lock-held, lock-wait and prealloc durations, plus the bytes consumed and the result. These break down the cost of a defrag attempt into its locked vs unlocked phases, making it possible to confirm that the expensive beneficial-order allocation and cpu cache mode change happen outside the BO dma-resv lock and that the residual lock-held time is copy-bound (with the tail dominated by lock-wait behind active rendering). Cc: Carlos Santa Cc: Ryan Neph Cc: Christian Koenig Cc: Huang Rui Cc: Matthew Auld Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Simona Vetter Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Cc: Thomas Hellström Assisted-by: GitHub_Copilot:claude-opus-4.8 Signed-off-by: Matthew Brost --- v3: - Move the ns-to-us division into TP_fast_assign() to avoid a 64-bit divide in TP_printk() (Sashiko) --- drivers/gpu/drm/xe/xe_bo.c | 18 +++++++++- drivers/gpu/drm/xe/xe_trace_bo.h | 59 ++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 8b89d34f37d4..25e5b72f870c 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1263,7 +1263,9 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo, struct ttm_placement placement; struct ttm_place place; enum ttm_caching tt_caching; - unsigned int order, want = 0; + unsigned int order, want = 0, got = 0; + u64 lock_ns = 0, prealloc_ns = 0, lockwait_ns = 0; + ktime_t t0; int ret = 0; *consumed = 0; @@ -1294,6 +1296,7 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo, /* Phase 2: preallocate outside the lock; */ if (want) { + t0 = ktime_get(); ret = ttm_pool_prealloc_fill(pool, tt_caching, &pp, want); if (ret || !pp.count) { ret = ret ?: -ENOMEM; @@ -1301,12 +1304,16 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo, XE_GT_STATS_ID_DEFRAG_FAILED_COUNT, 1); goto out_err; } + prealloc_ns = ktime_to_ns(ktime_sub(ktime_get(), t0)); } /* * Phase 3: re-take the lock, re-check, and validate using the prealloc. */ + t0 = ktime_get(); xe_bo_lock(bo, false); + lockwait_ns = ktime_to_ns(ktime_sub(ktime_get(), t0)); + t0 = ktime_get(); if (!xe_bo_needs_defrag(bo)) { xe_bo_defrag_remove(bo); @@ -1362,9 +1369,13 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo, unlock: xe_bo_unlock(bo); + lock_ns = ktime_to_ns(ktime_sub(ktime_get(), t0)); + got = pp.used; out_err: ttm_pool_prealloc_fini(pool, &pp); out: + trace_xe_bo_defrag_one(bo, budget, want, got, lock_ns, prealloc_ns, + lockwait_ns, *consumed, ret); return ret; } @@ -1396,6 +1407,9 @@ static void xe_bo_defrag_worker(struct work_struct *w) return; } + trace_xe_bo_defrag_worker(xe, 0, atomic_read(&xe->mem.defrag.count), + true); + /* * Process at most XE_BO_DEFRAG_SIZE_LIMIT bytes of newly (re)allocated * backing per run rather than draining the whole list in one go. Only @@ -1503,6 +1517,8 @@ static void xe_bo_defrag_worker(struct work_struct *w) xe_pm_runtime_put(xe); drm_dev_exit(idx); + trace_xe_bo_defrag_worker(xe, defrag_bytes, + atomic_read(&xe->mem.defrag.count), false); } static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h index 86323cf3be2c..b159d37d39a1 100644 --- a/drivers/gpu/drm/xe/xe_trace_bo.h +++ b/drivers/gpu/drm/xe/xe_trace_bo.h @@ -85,6 +85,65 @@ TRACE_EVENT(xe_bo_move, __get_str(new_placement_name), __get_str(device_id)) ); +TRACE_EVENT(xe_bo_defrag_worker, + TP_PROTO(struct xe_device *xe, u64 defrag_bytes, int count, + bool enter), + TP_ARGS(xe, defrag_bytes, count, enter), + TP_STRUCT__entry( + __string(dev, dev_name(xe->drm.dev)) + __field(u64, defrag_bytes) + __field(int, count) + __field(bool, enter) + ), + TP_fast_assign( + __assign_str(dev); + __entry->defrag_bytes = defrag_bytes; + __entry->count = count; + __entry->enter = enter; + ), + TP_printk("dev=%s %s defrag_bytes=%llu count=%d", + __get_str(dev), __entry->enter ? "enter" : "exit", + __entry->defrag_bytes, __entry->count) +); + +TRACE_EVENT(xe_bo_defrag_one, + TP_PROTO(struct xe_bo *bo, u64 budget, unsigned int prealloc_want, + unsigned int prealloc_got, u64 lock_ns, u64 prealloc_ns, + u64 lockwait_ns, u64 consumed, int ret), + TP_ARGS(bo, budget, prealloc_want, prealloc_got, lock_ns, + prealloc_ns, lockwait_ns, consumed, ret), + TP_STRUCT__entry( + __string(dev, __dev_name_bo(bo)) + __field(size_t, size) + __field(u64, budget) + __field(unsigned int, prealloc_want) + __field(unsigned int, prealloc_got) + __field(u64, lock_us) + __field(u64, prealloc_us) + __field(u64, lockwait_us) + __field(u64, consumed) + __field(int, ret) + ), + TP_fast_assign( + __assign_str(dev); + __entry->size = xe_bo_size(bo); + __entry->budget = budget; + __entry->prealloc_want = prealloc_want; + __entry->prealloc_got = prealloc_got; + __entry->lock_us = div_u64(lock_ns, 1000); + __entry->prealloc_us = div_u64(prealloc_ns, 1000); + __entry->lockwait_us = div_u64(lockwait_ns, 1000); + __entry->consumed = consumed; + __entry->ret = ret; + ), + TP_printk("dev=%s size=%zu budget=%llu prealloc=%u/%u lock_us=%llu lockwait_us=%llu prealloc_us=%llu consumed=%llu ret=%d", + __get_str(dev), __entry->size, __entry->budget, + __entry->prealloc_got, __entry->prealloc_want, + __entry->lock_us, __entry->lockwait_us, + __entry->prealloc_us, __entry->consumed, + __entry->ret) +); + DECLARE_EVENT_CLASS(xe_vma, TP_PROTO(struct xe_vma *vma), TP_ARGS(vma), -- 2.34.1