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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id EB5D1C83F26 for ; Mon, 28 Jul 2025 21:59:39 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 525406B0088; Mon, 28 Jul 2025 17:59:39 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 4FD496B0089; Mon, 28 Jul 2025 17:59:39 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 3ED086B008A; Mon, 28 Jul 2025 17:59:39 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0014.hostedemail.com [216.40.44.14]) by kanga.kvack.org (Postfix) with ESMTP id 2BC1A6B0088 for ; Mon, 28 Jul 2025 17:59:39 -0400 (EDT) Received: from smtpin18.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay07.hostedemail.com (Postfix) with ESMTP id 661EC160477 for ; Mon, 28 Jul 2025 21:59:38 +0000 (UTC) X-FDA: 83715040836.18.95A8E77 Received: from mail-ed1-f44.google.com (mail-ed1-f44.google.com [209.85.208.44]) by imf21.hostedemail.com (Postfix) with ESMTP id 5CFCC1C0009 for ; Mon, 28 Jul 2025 21:59:36 +0000 (UTC) Authentication-Results: imf21.hostedemail.com; dkim=pass header.d=kowalczyk-ws.20230601.gappssmtp.com header.s=20230601 header.b="bpjIPqe/"; spf=pass (imf21.hostedemail.com: domain of patryk@kowalczyk.ws designates 209.85.208.44 as permitted sender) smtp.mailfrom=patryk@kowalczyk.ws; dmarc=none ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1753739976; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=ZFQq9BS1AZDnONWjFjq6WhnDJjmdicQEDZuU+ciJV44=; b=M0L8K+qf4tH2eOVnjj8q33kWhBvo5JwOaDVA6Xv5LM9FvTWUUwQXmeH+dvAb97sEqh5lIL WGUv/G9NR5zX7/Ha7ocb7tF9KaOI2RktAW8eUb3i8Ei55SzXaSFT2920H2vfAw7kak9s3f xH7M8dmWEDfXYFXeWZcATr7giVmJkmE= ARC-Authentication-Results: i=1; imf21.hostedemail.com; dkim=pass header.d=kowalczyk-ws.20230601.gappssmtp.com header.s=20230601 header.b="bpjIPqe/"; spf=pass (imf21.hostedemail.com: domain of patryk@kowalczyk.ws designates 209.85.208.44 as permitted sender) smtp.mailfrom=patryk@kowalczyk.ws; dmarc=none ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1753739976; a=rsa-sha256; cv=none; b=csKNE70VJaBa1Ccj/awNVyIjqKa//yQuJ4aSrf0rIJ1KOqhlG3nVRIcIchA8VTeJ1DG85+ pVRQo3/GJ0ZhG6e8GUEujsZr/djoTm+paGSgChQIQniYR+cPAHICivQum/irp+8odptPBl pMqoszQKAPkELYpCZD9EkErFQLFcLcc= Received: by mail-ed1-f44.google.com with SMTP id 4fb4d7f45d1cf-6153a19dddfso2580408a12.1 for ; Mon, 28 Jul 2025 14:59:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kowalczyk-ws.20230601.gappssmtp.com; s=20230601; t=1753739974; x=1754344774; darn=kvack.org; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=ZFQq9BS1AZDnONWjFjq6WhnDJjmdicQEDZuU+ciJV44=; b=bpjIPqe/zr+Wu6zs+sKqLl8SxBm+Z/8q82sN1p4SdYdQFmzVuVuF7UCCd19nife+IK T6DiMywXbhfwDT0FxElelAgF6Pa98x+Dfb0L3qogBAodc2buECAYgs7JOOgT9S7rqbkw poeUMh7SxfQAjLUjPtg3rMMdpcCcl44avQ+wpsvylTF/l8vwsnuy6qZqUhLNs+j3XWUb bJ4CTxhESNf1Xa6iLHYUnvU5pWQQ8o9mEy6wkPEqLb2E/MupRCyYpUgYf8SK86HMraZg cLWz638DJgybBjMZ01dPm1fTDRE5RkI/2d3xIfoldkKnBX7hrvqK1RnnQmCwUUx47Zkf 96SQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1753739974; x=1754344774; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=ZFQq9BS1AZDnONWjFjq6WhnDJjmdicQEDZuU+ciJV44=; b=jojHs5LvXet+wG+ql58tu55KmxwAinRx+ApQvHHQfpLQd2YUnXYeV3N/N0vnr9KJMy dJ60MLWEuaxXgWl7LXZqMgvjmRnJaGS72IG7mz2VJXMvwjqje8fqmkjSqbjvMxk9sRPH tNxqORGyk/1g7GMwJKF15Oqof/qrejHAJ89v0zqOdM9PKdHRQl/0KHMgrJw5hTBXgk+L NUWIOqkb3jsOx6r+L5OiolZtdO7Zq9VV34IxUMryEPBVOiAFCzUl3/j+SaePARN13GGJ upF+XeoI7JHEX1gZ31/pTpeOQnJHg5Z/BcCMmAnZVaogdd9a7rogQFLtuH5MO4k1xJTb nvkw== X-Forwarded-Encrypted: i=1; AJvYcCUhtxy7m2yxWDQ7nveDNLnQmaqrEOLl2kNHwaQHrangjtNAH90qLSx57FBe5gMcaFpktUIyFHmnjQ==@kvack.org X-Gm-Message-State: AOJu0YzzlXKw5fBxsZ3gTL3leAK1K528T7P0SblRG37Sd9ZFIkTB5ANa e73sHWuxLuqdGLncLrdRj8tLXcsEiJhgoIN7qmmwAYfqWWo8rJTNZivd3KXO2mBIO+NPMqN57tn /MfGQC+gzIqdpIcvNVOjVZ93q1XY0WMfzBDCN19Pb X-Gm-Gg: ASbGncvb8WCKiNbifLsmH1NGNIkxPZUMWBvVTosZQnZn51IuVgFBCX/yvKT+zZNpylZ iK3G0pfK+l2VkqQHRZrreiRv6dznQVAjez9xmfBm8wQcVGnm1HdFE4WYgrEwzUnQ6s1TCeFKBBs 32d3Rh5hoJ7HYGZcxlB0dxzlgC7AqXKL0MI6b32yp6l8rtnurtfhmlce+5DrpzdOnE79fGJ0+W1 YXl X-Google-Smtp-Source: AGHT+IEceYjA6cxsSRdCMNyewOG3XPoHrKBCUR9gGBeKUYS35hxGkLKlNk7w2IS6opzkPla6j9Fi8GgCrh0dEXg1zB0= X-Received: by 2002:a05:6402:4602:20b0:615:539b:7adc with SMTP id 4fb4d7f45d1cf-615539b93d1mr2691395a12.27.1753739974395; Mon, 28 Jul 2025 14:59:34 -0700 (PDT) MIME-Version: 1.0 References: <0d734549d5ed073c80b11601da3abdd5223e1889.1753689802.git.baolin.wang@linux.alibaba.com> <20250728144424.208d58d5a95057ee7081ccd8@linux-foundation.org> In-Reply-To: <20250728144424.208d58d5a95057ee7081ccd8@linux-foundation.org> From: Patryk Kowalczyk Date: Mon, 28 Jul 2025 23:59:22 +0200 X-Gm-Features: Ac12FXwwsiS4JI_-ICJdYNU4HPVvMiegzl4Qe4w16nBmZCl8pKBLj0t9-vRLQHg Message-ID: Subject: Re: [PATCH] mm: shmem: fix the shmem large folio allocation for the i915 driver To: Andrew Morton Cc: Baolin Wang , hughd@google.com, ville.syrjala@linux.intel.com, david@redhat.com, willy@infradead.org, maarten.lankhorst@linux.intel.com, mripard@kernel.org, tzimmermann@suse.de, airlied@gmail.com, simona@ffwll.ch, jani.nikula@linux.intel.com, joonas.lahtinen@linux.intel.com, rodrigo.vivi@intel.com, tursulin@ursulin.net, christian.koenig@amd.com, ray.huang@amd.com, matthew.auld@intel.com, matthew.brost@intel.com, dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org Content-Type: multipart/alternative; boundary="00000000000033d963063b0468cf" X-Rspam-User: X-Rspamd-Queue-Id: 5CFCC1C0009 X-Rspamd-Server: rspam06 X-Stat-Signature: jxwsxkte1wm8r36umayk3xc5zhfcdfhh X-HE-Tag: 1753739976-693123 X-HE-Meta: U2FsdGVkX1/CN6p0l6r4Dkm6cz5RlkF0fjRXbNJAgH6W3sM2JVCQDn8On5o0Muqe1NCUZ6e9FvaglRelVusxNYFC+y1KEQBUpmyj5HG66ir+vVRn3L2BEitRsE5Lgpi9QQaU8yV7wnWNoK6LwgyhTFludiBXWUa+NIsu2zmddgYADCULBN6f2PHkRzZMJrPAxiIL3jScs/O5F6S4/aroG/1+b+Zch4j85DilNwoYRUeK2R5G3mzzvmpjsud5pAhxa1wjAjUZnxgmpIEFC+yaUBKlOsSeWxzr76+dILNGKZpuU5J9QEJqKaCcxeBoO6oiv7O0C57rWpVhl+GZaOZPfqmI1KGSRQdOWBMrYw7T5J84tAxOzHDuk9kw0ueSrmBaFDbKRyFJGUnkcfZ+7QH+fuBJuUin25kqBmhuQVsylrFYdyMjZMF9hcyHz2QaEanKTVKnN9Ah3Ld/EXbousuK529bGbyIVj7R5NBipDwGaP64KA6MHSb7iWT0lmkjbd3yWC7CHJi3Yige6ETaK8gj9M6rHE8kWQBQYxcBcwvBw+Ud8cMYxXrYMprV5RB9Fx0UeDQiSKswWYdZslP1eZ7Olc4xyVplZNwDYoRJPaQQlYIDZgFnLopP9PnzSflfhmgivLxwpDihsd08TRf7DyqXAtUBmKxIftq1LZeK19H2zHCndpXxgbB9AIp2dknspu04UPYz9bcIzUDBPWVfI4oPoqqQ5dIn9EnOcbcqfPFHaAteDqiwE3ob1n36wAu5YVOaTX8809T+m/5tv3wHqcdxSZBtbhqcDiRKPpNFmgsqlHqIC+xllMQSLMgj4HmUyoEGhK72vk4VLkLwR08G8UTmHjItP2giTNMVMVjRZkl25fyr4NwRKfDqJ9LMdF6f5gUd6+uScuw/8W5xiTdWNTaazTolQEJNIB17STikigUCjwWYGBJmAV3YZbTa5x+ItS/XN9RZCubWj5AzMG6tvsk P55vGezk 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 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: --00000000000033d963063b0468cf Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Hi, In my tests, the performance drop ranges from a few percent up to 13% in Unigine Superposition under heavy memory usage on the CPU Core Ultra 155H with the Xe 128 EU GPU. Other users have reported performance impact up to 30% on certain workloads= . Please find more in the regressions reports: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14645 https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13845 I believe the change should be backported to all active kernel branches after version 6.12. best regards, Patryk pon., 28 lip 2025 o 23:44 Andrew Morton napisa=C5=82(a): > On Mon, 28 Jul 2025 16:03:53 +0800 Baolin Wang < > baolin.wang@linux.alibaba.com> wrote: > > > After commit acd7ccb284b8 ("mm: shmem: add large folio support for > tmpfs"), > > we extend the 'huge=3D' option to allow any sized large folios for tmpf= s, > > which means tmpfs will allow getting a highest order hint based on the > size > > of write() and fallocate() paths, and then will try each allowable larg= e > order. > > > > However, when the i915 driver allocates shmem memory, it doesn't provid= e > hint > > information about the size of the large folio to be allocated, resultin= g > in > > the inability to allocate PMD-sized shmem, which in turn affects GPU > performance. > > > > To fix this issue, add the 'end' information for shmem_read_folio_gfp() > to help > > allocate PMD-sized large folios. Additionally, use the maximum > allocation chunk > > (via mapping_max_folio_size()) to determine the size of the large folio= s > to > > allocate in the i915 driver. > > What is the magnitude of the performance change? > > > Fixes: acd7ccb284b8 ("mm: shmem: add large folio support for tmpfs") > > Reported-by: Patryk Kowalczyk > > Reported-by: Ville Syrj=C3=A4l=C3=A4 > > Tested-by: Patryk Kowalczyk > > This isn't a regression fix, is it? acd7ccb284b8 adds a new feature > and we have now found a flaw in it. > > Still, we could bend the rules a little bit and backport this, depends > on how significant the runtime effect is. > --00000000000033d963063b0468cf Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi,=C2=A0
In my tests, the performance drop= ranges from a few percent up to 13% in Unigine Superposition
und= er heavy memory usage on the CPU Core Ultra 155H with the Xe 128 EU GPU.=C2= =A0
Other users have reported performance impact up to 30% on cer= tain workloads.
Please find more=C2=A0 in the regressions reports= :



pon., 28 lip 2025 o 2= 3:44=C2=A0Andrew Morton <ak= pm@linux-foundation.org> napisa=C5=82(a):
On Mon, 28 Jul 2025 16:03:53 +0800 Baolin = Wang <baolin.wang@linux.alibaba.com> wrote:

> After commit acd7ccb284b8 ("mm: shmem: add large folio support fo= r tmpfs"),
> we extend the 'huge=3D' option to allow any sized large folios= for tmpfs,
> which means tmpfs will allow getting a highest order hint based on the= size
> of write() and fallocate() paths, and then will try each allowable lar= ge order.
>
> However, when the i915 driver allocates shmem memory, it doesn't p= rovide hint
> information about the size of the large folio to be allocated, resulti= ng in
> the inability to allocate PMD-sized shmem, which in turn affects GPU p= erformance.
>
> To fix this issue, add the 'end' information for shmem_read_fo= lio_gfp()=C2=A0 to help
> allocate PMD-sized large folios. Additionally, use the maximum allocat= ion chunk
> (via mapping_max_folio_size()) to determine the size of the large foli= os to
> allocate in the i915 driver.

What is the magnitude of the performance change?

> Fixes: acd7ccb284b8 ("mm: shmem: add large folio support for tmpf= s")
> Reported-by: Patryk Kowalczyk <patryk@kowalczyk.ws>
> Reported-by: Ville Syrj=C3=A4l=C3=A4 <ville.syrjala@linux.intel.com>=
> Tested-by: Patryk Kowalczyk <patryk@kowalczyk.ws>

This isn't a regression fix, is it?=C2=A0 acd7ccb284b8 adds a new featu= re
and we have now found a flaw in it.

Still, we could bend the rules a little bit and backport this, depends
on how significant the runtime effect is.
--00000000000033d963063b0468cf--