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 6EDF3D4335C for ; Fri, 8 Nov 2024 01:07:27 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 0E0FC10E32C; Fri, 8 Nov 2024 01:07:26 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="jJZd4lpb"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.17]) by gabe.freedesktop.org (Postfix) with ESMTPS id B0D7610E139 for ; Fri, 8 Nov 2024 01:07:24 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1731028045; x=1762564045; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=nQMYIohAN0FWNKeW1QgUICRqIBLUnRcAA7wOCLFkcCg=; b=jJZd4lpbxwh9CWECeWfoHl0rRgOugPItSG3FtptD2GJUDCMho8PHpJR4 Ya5B8yxYGckfzjgS/aIN7e714H/RaTBnebNSSFdgIun31bKix1bnvi/km oOOmeabQsNTVnG9zTVkLzNSdyQpjWpa+86WF3Q2a0Dy1spiAPnA5q/MmW Gif3HnygximlImdsssZFIuc8rsaIQyl6OMPXIGztT2bCX6eiENJhS3PGq 2aqF/ybUDl2J/LRSNLT5Lt1QaRXUpDS2pphGOT3cOyB0V0NNZlXyP+gyT ixh0kYKHF+OhPma65N5nTB5zKChWpz8V1WQirQks161z1I41rM3jD0lfq A==; X-CSE-ConnectionGUID: MOLbdBRGRkGb7ydL+N4+cQ== X-CSE-MsgGUID: 9YCnjylyTuiUKmxvXMzGGA== X-IronPort-AV: E=McAfee;i="6700,10204,11249"; a="31009604" X-IronPort-AV: E=Sophos;i="6.12,136,1728975600"; d="scan'208";a="31009604" Received: from fmviesa001.fm.intel.com ([10.60.135.141]) by orvoesa109.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Nov 2024 17:07:25 -0800 X-CSE-ConnectionGUID: NFPJHZMcSZGyiFjArV4YVQ== X-CSE-MsgGUID: R6YHYmxmSdqQHJqxCvOb/A== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.12,136,1728975600"; d="scan'208";a="116191499" Received: from fyang16-desk.jf.intel.com ([10.165.21.214]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Nov 2024 17:07:24 -0800 From: fei.yang@intel.com To: igt-dev@lists.freedesktop.org Cc: Fei Yang Subject: [i-g-t, v2, 3/4] tests/intel/xe_exec_threads: wait for all submissions to complete Date: Thu, 7 Nov 2024 17:10:40 -0800 Message-Id: <20241108011041.2257553-4-fei.yang@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20241108011041.2257553-1-fei.yang@intel.com> References: <20241108011041.2257553-1-fei.yang@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: igt-dev@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Development mailing list for IGT GPU Tools List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: igt-dev-bounces@lists.freedesktop.org Sender: "igt-dev" From: Fei Yang In test_compute_mode, there is an one second sleep waiting for all the submissions to complete, but a hardcode wait is not reliable for test that could have thousands of xe_execs submissions. Instead we should wait for the ufence to make sure the GPU is inactive before unbinding the BO. Signed-off-by: Fei Yang --- tests/intel/xe_exec_threads.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/tests/intel/xe_exec_threads.c b/tests/intel/xe_exec_threads.c index 962957cd7..433f2620a 100644 --- a/tests/intel/xe_exec_threads.c +++ b/tests/intel/xe_exec_threads.c @@ -404,16 +404,32 @@ test_compute_mode(int fd, uint32_t vm, uint64_t addr, uint64_t userptr, } } - j = flags & INVALIDATE ? - (flags & RACE ? n_execs / 2 + 1 : n_execs - 1) : 0; + j = 0; /* wait for all submissions to complete */ + if (flags & INVALIDATE) + /* + * For !RACE cases xe_wait_ufence has been called in above for-loop + * except the last batch of submissions. For RACE cases we will need + * to wait for the second half of the submissions to complete. There + * is a potential race here because the first half submissions might + * have updated the fence in the old physical location while the test + * is remapping the buffer from a different physical location, but the + * wait_ufence only checks the fence from the new location which would + * never be updated. We have to assume the first half of the submissions + * complete before the second half. Will have a follow up patch to fix + * this completely. + */ + j = (flags & RACE) ? (n_execs / 2 + 1) : (((n_execs - 1) & ~0x1f) + 1); + else if (flags & REBIND) + /* + * For REBIND cases xe_wait_ufence has been called in above for-loop + * except the last batch of submissions. + */ + j = ((n_execs - 1) & ~0x1f) + 1; + for (i = j; i < n_execs; i++) xe_wait_ufence(fd, &data[i].exec_sync, USER_FENCE_VALUE, exec_queues[i % n_exec_queues], fence_timeout); - /* Wait for all execs to complete */ - if (flags & INVALIDATE) - sleep(1); - sync[0].addr = to_user_pointer(&data[0].vm_sync); xe_vm_unbind_async(fd, vm, 0, 0, addr, bo_size, sync, 1); xe_wait_ufence(fd, &data[0].vm_sync, USER_FENCE_VALUE, 0, fence_timeout); -- 2.25.1