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 B3EA8C3ABBE for ; Thu, 8 May 2025 07:43:13 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 7A3F16B0089; Thu, 8 May 2025 03:43:12 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 750236B008A; Thu, 8 May 2025 03:43:12 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 61BBF6B008C; Thu, 8 May 2025 03:43:12 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id 442256B0089 for ; Thu, 8 May 2025 03:43:12 -0400 (EDT) Received: from smtpin16.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay04.hostedemail.com (Postfix) with ESMTP id 4EB5B1A0E43 for ; Thu, 8 May 2025 07:43:12 +0000 (UTC) X-FDA: 83418949824.16.B23EDC3 Received: from mail-vk1-f169.google.com (mail-vk1-f169.google.com [209.85.221.169]) by imf03.hostedemail.com (Postfix) with ESMTP id 706A220003 for ; Thu, 8 May 2025 07:43:10 +0000 (UTC) Authentication-Results: imf03.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=VkVAcNms; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (imf03.hostedemail.com: domain of 21cnbao@gmail.com designates 209.85.221.169 as permitted sender) smtp.mailfrom=21cnbao@gmail.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1746690190; a=rsa-sha256; cv=none; b=eEL3LaaonFaQ0WaLUMrTaVuBK5S/HPCC/ffgU+/pXTR9JmQ+dje5y8ixkLdEIEPnRyeekr iil6TgKDT5npd4d17e2CfBNsXCS0W060gO6yROn2H5etCDmbNbQ0Ao5HzrKREB2Z4xjbKJ CKpUfkqdYZToaxONEPzdjLf+k5Wn9VE= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1746690190; 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:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=/5+KEBtT2aBtAcU9qUPvo+iC2dk60rp413TigGZQUQQ=; b=EVkgsDKKKpCUnxaZq3BS47LoWuiTA/CO4VKJQImCCOSSTHgui/dugh9fTp71k5HmIzg8JV o0jaDvszMNxhRGqo+wlwYClUr3uzvjR+OUIlBlRczgg4u+uYreuMZO7kB2cwRV8Jt1gWWD iTEdYyr+HXKAINN6pjbFFTLIDfC8nxE= ARC-Authentication-Results: i=1; imf03.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=VkVAcNms; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (imf03.hostedemail.com: domain of 21cnbao@gmail.com designates 209.85.221.169 as permitted sender) smtp.mailfrom=21cnbao@gmail.com Received: by mail-vk1-f169.google.com with SMTP id 71dfb90a1353d-52934f4fb23so534752e0c.1 for ; Thu, 08 May 2025 00:43:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1746690189; x=1747294989; darn=kvack.org; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=/5+KEBtT2aBtAcU9qUPvo+iC2dk60rp413TigGZQUQQ=; b=VkVAcNmsrG1eufy9Uq9R7FScT/zzTPnxa65fJ3jL2NL6jFg7vYfFVC1xxKHS8lxuG1 8GtzEvOWyEzcDkmMmo+sVvTliAfJ6iag5EpF9Px9MttQiTZUgH/f0uYcnk6OY6e6DUZu y1PPku/YsPOpZ0PP7+OnB3k9APpdo8fBBF0UbYV73EmnwUUI1IVjUdFXX+Tnb4ET8jNH RrTQ7mG9INpo11Vj+rXT7bsLQImmDrxaKeqFJyQt/XfKWND4XMk+I6CnYWDuZQWIHJTk ptAF9kBhsgrUXm3dKz1Wr2PJDWosw3ioRRw3UP8xmnHFDA2+4rTzn+1HHIHHkB0AcPWW xp9w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1746690189; x=1747294989; h=content-transfer-encoding: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=/5+KEBtT2aBtAcU9qUPvo+iC2dk60rp413TigGZQUQQ=; b=OZV8/jn7rus/EfR8ORSQGncRD7JlOODOZDojhcPy2F+LmGCgV/5yQygleo5fEyd6O8 R9upNUOeG8+jwugStRPGnQ/lhxPsrMEGbMxB53PGIp2JP86vVvTupbmU4x8gVYvotQmk 2u3gPGUFiaBWD2wwuxAVhd0UISmd2b6kJ1InLEr7uHGWaBNQYii81DeoYXUoevNPwWyO FnCZw8X8ts/FOgZKkHVQxIkVhWPLUPP28aSWTFdquBdX/fMXzmAI7SIjUEQH8cU5LK9X xUCbfYl357Enr7u+hgbziYVqzb/Uyuy9nLyGNqHdqKtstVorJSmZK0NFu53EVRwln7P7 fE8w== X-Forwarded-Encrypted: i=1; AJvYcCXVuWaz6sywTJscpFUm1rdoRzWsUCOgEhqm1JixzNB6ZW9uHp9hw/rWQuNFDNWQELh2jhXuUHJTog==@kvack.org X-Gm-Message-State: AOJu0YwqK7UZefQoutmGyR7IRTL93jV+VZNZ4B/xU+MB+lHtqzMoXhwt kZcCBqXGBE5RPGxuzzwTDxc/S3HLp0ptvBDeXxPzFR/HnjMYgRGX28Cn4nG6cPomHnxzAZ01Yqo 1R2AoBZAWeNMqJB7SdedFoBOICCY= X-Gm-Gg: ASbGnctk1mTijroU3dhkEiit/YrqNKZlRLcjhqlF2V0UazQvQd/BpmO7ykl92j5bUHO haQnG3E99svOPN89y/Uvy4FnJkVBuE4CT/S6R2Xc822Wwt/5kD8NzMu+fkokIMIsfbTdY+vKYZy 8e16EV+iAk4y775wwiD40/Yw== X-Google-Smtp-Source: AGHT+IF7FWWXPxXOzLHYQKMnXVAoo5udvCIuu3X6taFvK22+XbMCcckbKjoLMt4SURdp+f1isPMZgS+Ysji5V4+Nfl0= X-Received: by 2002:a05:6122:1e06:b0:529:1a6a:cc2f with SMTP id 71dfb90a1353d-52c37a8bcd2mr4989998e0c.7.1746690189473; Thu, 08 May 2025 00:43:09 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Barry Song <21cnbao@gmail.com> Date: Thu, 8 May 2025 19:42:58 +1200 X-Gm-Features: ATxdqUFV5fNeTsnqzRFZ9aw0PQBuboIh4qamDRWp2kWChzFg5jO55dnGwi3pWkE Message-ID: Subject: Re: [PATCH v2] mm: mincore: use pte_batch_bint() to batch process large folios To: Baolin Wang Cc: akpm@linux-foundation.org, david@redhat.com, ryan.roberts@arm.com, dev.jain@arm.com, ziy@nvidia.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Rspamd-Server: rspam06 X-Rspamd-Queue-Id: 706A220003 X-Stat-Signature: o3tm94tipwtiq9wq1km6y9y1sjaeb1bi X-Rspam-User: X-HE-Tag: 1746690190-539264 X-HE-Meta: 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 4kfkMZuL 8+ZOONdUQz/gFOMWBpnIenuf9CGjpuUyYQPl0fjzNXm8mYNWXIzzKOaDKOCS0fzf8/fNHHhnj/a3acFcC60NFPonq8V5n8a+/27fcj9rc41sFbDASnJvHXrwvXRMxTk6OZ8Z/Pa5iysQeVqtecP9hC3Ymf1uARtw0eYeAjJA/sAbzDVuCi7BrfEOTwWm0Jb72Gzmmg66HMlhXA5z4H2/FoubUeTuOM2bNoKMNPpNDCdcL7N8eoLOcUlWouY5FMnuaGQXvg2DNEsWw1oPx9k00ZREe2wNZseDCbjPWGurvJcd7O0b9UL214PUVf2/NTh6RKuXE6IB4tbANC0cPhTuZ/J0UcC633NRTU8xEJ/pt9/7/ywsREkDmxGS0ahCRU5jCV74S73/8tTl/kSKeIbrtvUu1nVrGqii4tUJOTzLBSVo3B/s= 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: On Thu, May 8, 2025 at 4:09=E2=80=AFPM Baolin Wang wrote: > > When I tested the mincore() syscall, I observed that it takes longer with > 64K mTHP enabled on my Arm64 server. The reason is the mincore_pte_range(= ) > still checks each PTE individually, even when the PTEs are contiguous, > which is not efficient. > > Thus we can use pte_batch_hint() to get the batch number of the present > contiguous PTEs, which can improve the performance. I tested the mincore(= ) > syscall with 1G anonymous memory populated with 64K mTHP, and observed an > obvious performance improvement: > > w/o patch w/ patch changes > 6022us 549us +91% > > Moreover, I also tested mincore() with disabling mTHP/THP, and did not > see any obvious regression for base pages. > > Signed-off-by: Baolin Wang > --- > Changes from v1: > - Change to use pte_batch_hint() to get the batch number, per Ryan. > > Note: I observed the min_t() can introduce a slight performance regressio= n > for base pages, so I change to add a batch size check for base pages, > which can resolve the performance regression issue. > --- > mm/mincore.c | 19 ++++++++++++++----- > 1 file changed, 14 insertions(+), 5 deletions(-) > > diff --git a/mm/mincore.c b/mm/mincore.c > index 832f29f46767..2e6a9123305e 100644 > --- a/mm/mincore.c > +++ b/mm/mincore.c > @@ -21,6 +21,7 @@ > > #include > #include "swap.h" > +#include "internal.h" > > static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned lon= g addr, > unsigned long end, struct mm_walk *walk) > @@ -105,6 +106,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned lon= g addr, unsigned long end, > pte_t *ptep; > unsigned char *vec =3D walk->private; > int nr =3D (end - addr) >> PAGE_SHIFT; > + int step, i; > > ptl =3D pmd_trans_huge_lock(pmd, vma); > if (ptl) { > @@ -118,16 +120,23 @@ static int mincore_pte_range(pmd_t *pmd, unsigned l= ong addr, unsigned long end, > walk->action =3D ACTION_AGAIN; > return 0; > } > - for (; addr !=3D end; ptep++, addr +=3D PAGE_SIZE) { > + for (; addr !=3D end; ptep +=3D step, addr +=3D step * PAGE_SIZE)= { > pte_t pte =3D ptep_get(ptep); > > + step =3D 1; > /* We need to do cache lookup too for pte markers */ > if (pte_none_mostly(pte)) > __mincore_unmapped_range(addr, addr + PAGE_SIZE, > vma, vec); > - else if (pte_present(pte)) > - *vec =3D 1; > - else { /* pte is a swap entry */ > + else if (pte_present(pte)) { > + unsigned int batch =3D pte_batch_hint(ptep, pte); > + > + if (batch > 1) > + step =3D min_t(unsigned int, batch, nr); Not quite sure if nr should be (end - addr) / PAGE_SIZE as nr is always the initial value. For example, nr =3D 50, and we have scanned 48 PTEs, then we have 2 ptes left. No? > + > + for (i =3D 0; i < step; i++) > + vec[i] =3D 1; > + } else { /* pte is a swap entry */ > swp_entry_t entry =3D pte_to_swp_entry(pte); > > if (non_swap_entry(entry)) { > @@ -146,7 +155,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned lon= g addr, unsigned long end, > #endif > } > } > - vec++; > + vec +=3D step; > } > pte_unmap_unlock(ptep - 1, ptl); > out: > -- > 2.43.5 > Thanks Barry