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 X-Spam-Level: X-Spam-Status: No, score=-6.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5E00CC43331 for ; Tue, 31 Mar 2020 23:29:26 +0000 (UTC) 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 mail.kernel.org (Postfix) with ESMTPS id 3755B206DB for ; Tue, 31 Mar 2020 23:29:26 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 3755B206DB Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=intel.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=intel-gfx-bounces@lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id B44C26E8A3; Tue, 31 Mar 2020 23:29:25 +0000 (UTC) Received: from mga18.intel.com (mga18.intel.com [134.134.136.126]) by gabe.freedesktop.org (Postfix) with ESMTPS id E64E96E8A3 for ; Tue, 31 Mar 2020 23:29:24 +0000 (UTC) IronPort-SDR: i0pQGxP6b5BKTm4QPeAcGQ0vrBSWcyIfVV/ywcCMfFo8dksFZ+gMFr5fQMKJ8J83SJ5E+XJp53 Junt4quVceww== X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by orsmga106.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 31 Mar 2020 16:29:24 -0700 IronPort-SDR: Ia7Q2AWj15jKdWEnirTz8/g3dllpZXPr08cvBcKPOX54eQA9Hhp//Qebg20iAiC6gGor+uA9mc Fqc6OiME5nSQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.72,329,1580803200"; d="scan'208";a="448866975" Received: from adixit-mobl.amr.corp.intel.com (HELO adixit-arch.intel.com) ([10.212.195.197]) by fmsmga005.fm.intel.com with ESMTP; 31 Mar 2020 16:29:23 -0700 Date: Tue, 31 Mar 2020 16:29:23 -0700 Message-ID: <87v9mk85nw.wl-ashutosh.dixit@intel.com> From: "Dixit, Ashutosh" To: Lionel Landwerlin In-Reply-To: References: <20200331052222.76525-1-ashutosh.dixit@intel.com> User-Agent: Wanderlust/2.15.9 (Almost Unreal) SEMI-EPG/1.14.7 (Harue) FLIM/1.14.9 (=?ISO-8859-4?Q?Goj=F2?=) APEL/10.8 EasyPG/1.0.0 Emacs/26 (x86_64-pc-linux-gnu) MULE/6.0 (HANACHIRUSATO) MIME-Version: 1.0 (generated by SEMI-EPG 1.14.7 - "Harue") Subject: Re: [Intel-gfx] [PATCH] drm/i915/perf: Do not clear pollin for small user read buffers X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: intel-gfx@lists.freedesktop.org Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" On Tue, 31 Mar 2020 00:34:10 -0700, Lionel Landwerlin wrote: > > On 31/03/2020 08:22, Ashutosh Dixit wrote: > > It is wrong to block the user thread in the next poll when OA data is > > already available which could not fit in the user buffer provided in > > the previous read. In several cases the exact user buffer size is not > > known. Blocking user space in poll can lead to data loss when the > > buffer size used is smaller than the available data. > > > > This change fixes this issue and allows user space to read all OA data > > even when using a buffer size smaller than the available data using > > multiple non-blocking reads rather than staying blocked in poll till > > the next timer interrupt. > > > > v2: Fix ret value for blocking reads (Umesh) > > v3: Mistake during patch send (Ashutosh) > > v4: Remove -EAGAIN from comment (Umesh) > > v5: Improve condition for clearing pollin and return (Lionel) > > > > Cc: Umesh Nerlige Ramappa > > Cc: Lionel Landwerlin > > Signed-off-by: Ashutosh Dixit > > I forgot to mention this needs to be Cc: stable. I will Cc stable or send them the patch after it's finalized, hope that will be ok? > > Still one nit below which should make the remaining function a bit simpler. > > Thanks for your time. > > -Lionel > > > > --- > > drivers/gpu/drm/i915/i915_perf.c | 62 +++++++------------------------- > > 1 file changed, 13 insertions(+), 49 deletions(-) > > > > diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c > > index c74ebac50015..9c21f28f89a7 100644 > > --- a/drivers/gpu/drm/i915/i915_perf.c > > +++ b/drivers/gpu/drm/i915/i915_perf.c > > @@ -2914,49 +2914,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce, > > gen8_update_reg_state_unlocked(ce, stream); > > } > > -/** > > - * i915_perf_read_locked - &i915_perf_stream_ops->read with error normalisation > > - * @stream: An i915 perf stream > > - * @file: An i915 perf stream file > > - * @buf: destination buffer given by userspace > > - * @count: the number of bytes userspace wants to read > > - * @ppos: (inout) file seek position (unused) > > - * > > - * Besides wrapping &i915_perf_stream_ops->read this provides a common place to > > - * ensure that if we've successfully copied any data then reporting that takes > > - * precedence over any internal error status, so the data isn't lost. > > - * > > - * For example ret will be -ENOSPC whenever there is more buffered data than > > - * can be copied to userspace, but that's only interesting if we weren't able > > - * to copy some data because it implies the userspace buffer is too small to > > - * receive a single record (and we never split records). > > - * > > - * Another case with ret == -EFAULT is more of a grey area since it would seem > > - * like bad form for userspace to ask us to overrun its buffer, but the user > > - * knows best: > > - * > > - * http://yarchive.net/comp/linux/partial_reads_writes.html > > - * > > - * Returns: The number of bytes copied or a negative error code on failure. > > - */ > > -static ssize_t i915_perf_read_locked(struct i915_perf_stream *stream, > > - struct file *file, > > - char __user *buf, > > - size_t count, > > - loff_t *ppos) > > -{ > > - /* Note we keep the offset (aka bytes read) separate from any > > - * error status so that the final check for whether we return > > - * the bytes read with a higher precedence than any error (see > > - * comment below) doesn't need to be handled/duplicated in > > - * stream->ops->read() implementations. > > - */ > > - size_t offset = 0; > > - int ret = stream->ops->read(stream, buf, count, &offset); > > - > > - return offset ?: (ret ?: -EAGAIN); > > -} > > - > > /** > > * i915_perf_read - handles read() FOP for i915 perf stream FDs > > * @file: An i915 perf stream file > > @@ -2982,7 +2939,8 @@ static ssize_t i915_perf_read(struct file *file, > > { > > struct i915_perf_stream *stream = file->private_data; > > struct i915_perf *perf = stream->perf; > > - ssize_t ret; > > + size_t offset = 0; > > + int __ret; > > /* To ensure it's handled consistently we simply treat all reads of > > a > > * disabled stream as an error. In particular it might otherwise lead > > @@ -2992,6 +2950,8 @@ static ssize_t i915_perf_read(struct file *file, > > return -EIO; > > if (!(file->f_flags & O_NONBLOCK)) { > > + ssize_t ret; > > + > > /* There's the small chance of false positives from > > * stream->ops->wait_unlocked. > > * > > @@ -3005,13 +2965,13 @@ static ssize_t i915_perf_read(struct file *file, > > return ret; > > mutex_lock(&perf->lock); > > - ret = i915_perf_read_locked(stream, file, > > - buf, count, ppos); > > + __ret = stream->ops->read(stream, buf, count, &offset); > > > I think you can keep using ret and just change the loop to while (ret >= 0) > (which means no failure). > > You will get -ENOSPC when the whole buffer is filled or some other error > which should trigger stream closure. Sorry, but I did not follow you here. Are you saying even when we have data to return (offset > 0) you want to go back and block (in the wait_unlocked())? I am not sure if that will be acceptable, I'd think the expectation would be to return data at the rate of the OA timer. > Finally you can 0 if nothing was written but there was nothing to read and > that keeps the read going. Here I really lost you. Are you talking about -ENOSPC returning after blocking multiple times and then resetting the error to 0 somehow? Could you please look at v6 and let me know what you think? I have eliminated the second ret variable by changing the do-while loop to "do { } while (!offset && !ret);" and thus mostly retain the original logic. Thanks! -- Ashutosh > > > > + ret = offset ?: (__ret ?: -EAGAIN); > > mutex_unlock(&perf->lock); > > } while (ret == -EAGAIN); > > } else { > > mutex_lock(&perf->lock); > > - ret = i915_perf_read_locked(stream, file, buf, count, ppos); > > + __ret = stream->ops->read(stream, buf, count, &offset); > > mutex_unlock(&perf->lock); > > } > > @@ -3022,11 +2982,15 @@ static ssize_t i915_perf_read(struct file > > *file, > > * and read() returning -EAGAIN. Clearing the oa.pollin state here > > * effectively ensures we back off until the next hrtimer callback > > * before reporting another EPOLLIN event. > > + * The exception to this is if ops->read() returned -ENOSPC which means > > + * that more OA data is available than could fit in the user provided > > + * buffer. In this case we want the next poll() call to not block. > > */ > > - if (ret >= 0 || ret == -EAGAIN) > > + if (__ret != -ENOSPC) > > stream->pollin = false; > > - return ret; > > + /* Possible values for __ret are 0, -EFAULT, -ENOSPC, -EIO, ... */ > > + return offset ?: (__ret ?: -EAGAIN); > > } > > static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer > > *hrtimer) > > _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx