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]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id B66EBC61DBD for ; Fri, 28 Aug 2026 07:11:43 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id A3CC76B0088; Fri, 28 Aug 2026 03:11:42 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id A14136B008A; Fri, 28 Aug 2026 03:11:42 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 951C66B008C; Fri, 28 Aug 2026 03:11:42 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0017.hostedemail.com [216.40.44.17]) by kanga.kvack.org (Postfix) with ESMTP id 696E56B0088 for ; Fri, 28 Aug 2026 03:11:42 -0400 (EDT) Received: from smtpin24.hostedemail.com (lb01a-stub [10.200.18.249]) by unirelay07.hostedemail.com (Postfix) with ESMTP id DEB5016027A for ; Fri, 28 Aug 2026 07:11:41 +0000 (UTC) X-FDA: 85149808002.24.783ED67 Received: from tor.source.kernel.org (tor.source.kernel.org [172.105.4.254]) by imf19.hostedemail.com (Postfix) with ESMTP id 58A951A0008 for ; Fri, 28 Aug 2026 07:11:40 +0000 (UTC) Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=kernel.org header.s=k20260515 header.b=LQO7tg5L; spf=pass (imf19.hostedemail.com: domain of ljs@kernel.org designates 172.105.4.254 as permitted sender) smtp.mailfrom=ljs@kernel.org; dmarc=pass (policy=quarantine) header.from=kernel.org ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1787901100; 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=Nlvtq8RrY4Qv1BwWlfkIuckX4fyEMKpcHNCZEpNZD1g=; b=eBgxB37rBK3NpOui5OzU+Qk/G3V/kclQiY3pdPgwBczPdb6TWo/svK9qancEbEEjcsaHoA RX65kF31iuhqU5auqkIF2LRHlhdQZ0C10e0JiJdWRQ2DhC83JmHVO+gVZrQLYnX1LDDs2U 0LqNjYbnV/KgKuINW/kGynESv5gJ3xg= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=kernel.org header.s=k20260515 header.b=LQO7tg5L; spf=pass (imf19.hostedemail.com: domain of ljs@kernel.org designates 172.105.4.254 as permitted sender) smtp.mailfrom=ljs@kernel.org; dmarc=pass (policy=quarantine) header.from=kernel.org ARC-Seal: i=1; a=rsa-sha256; d=hostedemail.com; s=arc-20220608; cv=none; t=1787901100; b=OcxjhLQ+w9WIJPg/oMisNRXZiicgfmSLJ1PySid/QTSl1lNTWMY++tQY2y+1olhA1RNDja mrz4pnOei9r+4wgGDwKBKkPetIz1lAQHa694v+1/nlLrAHfPhmz9hVlWN8+PR8rRn+zSV2 DNku2+Cf2T7EafrCd7JKV1bB7pg+gQ4= Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) by tor.source.kernel.org (Postfix) with ESMTP id 1F3EF60232; Fri, 28 Aug 2026 07:11:39 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id AA3981F000E9; Fri, 28 Aug 2026 07:11:34 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787901098; bh=Nlvtq8RrY4Qv1BwWlfkIuckX4fyEMKpcHNCZEpNZD1g=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=LQO7tg5LJMeiaUlf4a5H7/JysPrXdJg6wWW6gAPJHdrP//LipPDnv3j2P+z5oJifu ttdApyw0xT3NW4RHj9q26RZUz/UY38/m1vrm3PQ369Ezl/ttVkOK/4rKaNz2cb7DNA ORPvN9x+XNb4nzBNb6MKiwqb7laHIaP+jTiLbOnePwZjZSL056DXh8Xfi/kKU7eG57 lPkXI6PjMfTVH8laDKmUwoRCM/hnw6jjRHTRiOitxxUN5ysdv7HeEnUa479ld34MbZ ons+fV7jS1m7b9RDaYPkBMqqyMkJEqOUKDuI5NPgIHP0iKT4O6WtjPHivhePxqiadR rNbRhQ9ePvwag== Date: Fri, 28 Aug 2026 08:11:32 +0100 From: "Lorenzo Stoakes (ARM)" To: Zi Yan Cc: Andrew Morton , David Hildenbrand , Baolin Wang , "Liam R. Howlett" , Nico Pache , Ryan Roberts , Dev Jain , Barry Song , Lance Yang , Usama Arif , Peter Xu , Jason Gunthorpe , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Cedric Le Goater , Saravanan D , stable@vger.kernel.org Subject: Re: [PATCH] mm/huge_memory: bypass THP tuneables for huge pfnmap mappings Message-ID: References: <20260827-hugepfn-allowable-orders-v1-1-94819c8807c8@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-Stat-Signature: wk9o5eij9imoc6ahp6m3unnfx46woihc X-Rspamd-Server: rspam09 X-Rspamd-Queue-Id: 58A951A0008 X-Rspam-User: X-HE-Tag: 1787901100-618305 X-HE-Meta: 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 JM/F2F+r 4dV5mpYuRNjsCUpUW5VrSupsSC3ukJKMPgcx4apzd7uu46++gWxfBwOB/oF/X6G9xYRYJxLApVYKwgQI2ey1dUzVXdVznvfsG6GtNHeiH+6r4zuNJ4Qvyl30KIdU8eC/FxD6dd2CpU6TSyv4wUsAl/KATG8H5Y4ngDTcp7j2PZvxGzm9x1waMvLifB+iNW3gwvYNcJ5wLWwUmTs5/XCm0iMPQxlM4garwkz0/FVY5ldG9NB9pVi3McLbaaimqkQpBe/Iu5TnAr8uAc7wYxETAxUpAX8ws6LK+4/XP5vtv+/lIisqsTDo6r+z4JaBqZdjzxitJ9M4sHM1OgzZ2r5Nd8iHh4YuCI9VM90vdTaoP/A8I9CTxmYjv/I2n1w== Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: On Thu, Aug 27, 2026 at 10:52:24PM -0400, Zi Yan wrote: > On Thu Aug 27, 2026 at 3:55 PM EDT, Lorenzo Stoakes (ARM) wrote: > > The sysfs THP tuneables at /sys/kernel/mm/transparent_huge_pages/ rather > > confusingly only control the behaviour of THP in some instances. > > > > They are not applicable to MADV_COLLAPSE operations, nor to DAX mappings. > > > > Long-term, THP is predicated upon compaction being able to obtain large > > folios to populate THP ranges. > > > > However, vm_normal_folio() returns NULL for PFN map mappings, thus their > > reference count is maintained by the driver, not core mm. > > > > As a consequence, the folios are not subject to reclaim nor compaction, so > > are not truly part of the THP mechanism at all. > > > > However, since commit 5dd40721f147 ("mm: allow THP orders for PFNMAPs") > > introduced the ability to establish huge PFN maps, they have been subject > > to THP tuneables. > > > > This is incorrect - if a huge PFN map is available (defined by > > vma->vm_ops->huge_fault being non-NULL for a VMA_PFNMAP_BIT VMA), then it > > should be mapped huge upon fault-in. > > > > Correct this by explicitly checking for this while ensuring that smaps > > continues to accurately report THPeligible statistics. > > > > While here, abstract the entire file-backed THP check in > > vma_can_map_huge_file(), with sensible separation of logic into helper > > functions. > > > > Note that drm_gem_shmem_mmap() and panthor_gem_mmap() establish huge PFN > > maps of shmem folios, however they are marked unevictable in > > drm_gem_get_pages(), and in any case would fail the reference check in > > __remove_mapping() even if they weren't. > > > > Failing to map huge PFN maps has resulted in significant real-world > > performance degradation, see links for details. > > > > Reported-by: Cedric Le Goater > > Closes: https://lore.kernel.org/linux-mm/20260805055544.1568534-1-clg@redhat.com/ > > Reported-by: Saravanan D > > Closes: https://lore.kernel.org/linux-mm/20260821070520.25759-1-saravanand@crusoe.ai/ > > Fixes: 5dd40721f147 ("mm: allow THP orders for PFNMAPs") > > Cc: stable@vger.kernel.org > > Signed-off-by: Lorenzo Stoakes (ARM) > > --- > > mm/huge_memory.c | 86 +++++++++++++++++++++++++++++++++++++++++--------------- > > 1 file changed, 64 insertions(+), 22 deletions(-) > > I checked the code logic and find everything matches except the intended > pfnmap check for the fix. > > Reviewed-by: Zi Yan Thanks! :) > > Some nits on the function names below, but feel free to ignore. > > > > > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > > index afbb5974bd22..4bf7b670586d 100644 > > --- a/mm/huge_memory.c > > +++ b/mm/huge_memory.c > > @@ -92,7 +92,7 @@ unsigned long huge_anon_orders_madvise __read_mostly; > > unsigned long huge_anon_orders_inherit __read_mostly; > > static bool anon_orders_configured __initdata; > > > > -static inline bool file_thp_enabled(struct vm_area_struct *vma) > > +static inline bool file_thp_enabled(const struct vm_area_struct *vma) > > { > > struct inode *inode; > > > > @@ -118,6 +118,67 @@ static bool vma_is_special_huge(const struct vm_area_struct *vma) > > return vma_test_any(vma, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT); > > } > > > > +static bool vma_bypass_thp_tuneables_file(const struct vm_area_struct *vma, > > + enum tva_type type) > > +{ > > + const bool has_huge_fault = vma->vm_ops->huge_fault; > > + > > + /* MADV_COLLAPSE ignores tuneables. */ > > + if (type == TVA_FORCED_COLLAPSE) > > + return true; > > + /* Huge PFN mappings are uncompactable so the policy doesn't apply. */ > > + if (vma_test(vma, VMA_PFNMAP_BIT) && has_huge_fault) > > + return true; > > + return false; > > +} > > + > > +static bool vma_thp_tuneables_allow_file(vm_flags_t vm_flags) > > +{ > > + /* THP=always? */ > > + if (hugepage_global_always()) > > + return true; > > + /* THP=madvise and marked MADV_HUGEPAGE? */ > > + if (hugepage_global_enabled() && (vm_flags & VM_HUGEPAGE)) > > + return true; > > + return false; > > +} > > + > > +static bool vma_check_thp_tuneables_file(const struct vm_area_struct *vma, > > + vm_flags_t vm_flags, enum tva_type type) > > +{ > > + return vma_bypass_thp_tuneables_file(vma, type) || > > + vma_thp_tuneables_allow_file(vm_flags); > > Naming is hard, but Yes :) > 1. is vma_allow_thp_tuneables_file() better? Then all three helpers are > vma + a verb + thp_tuneables_file(). That's a good idea! Much better thanks. > > 2. is vma_file_ a better prefix than putting file at the end? Yeah, it's an annoying one as kinda want to say 'file-backed VMA' but I think you're right vma_xxx_file() -> vma_file_xxx() is better. Andrew - could you fix that up in place? Obviously if there's further feedback I can respin as well. > > > Another idea is to put all checks in one function and just add some comments > on bypassing ones and allowed ones. > > > +} > > + > > +static bool vma_can_map_huge_file(const struct vm_area_struct *vma, > > + vm_flags_t vm_flags, enum tva_type type) > > +{ > > + const bool has_huge_fault = vma->vm_ops->huge_fault; > > + > > + /* > > + * Enforce THP collapse requirements as necessary. Anonymous vmas > > + * were already handled in thp_vma_allowable_orders(). > > + */ > > + if (!vma_check_thp_tuneables_file(vma, vm_flags, type)) > > + return false; > > + > > + switch (type) { > > + case TVA_PAGEFAULT: > > + /* > > + * Trust that ->huge_fault() handlers know what they are doing > > + * in fault path. > > + */ > > + return has_huge_fault; > > + case TVA_SMAPS: > > + if (has_huge_fault) > > + return true; > > + fallthrough; > > + default: > > + /* Only regular file is valid in collapse path. */ > > + return file_thp_enabled(vma); > > + } > > +} > > + > > unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, > > vm_flags_t vm_flags, > > enum tva_type type, > > @@ -190,27 +251,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, > > vma, vma_start_pgoff(vma), 0, > > forced_collapse); > > > > - if (!vma_is_anonymous(vma)) { > > - /* > > - * Enforce THP collapse requirements as necessary. Anonymous vmas > > - * were already handled in thp_vma_allowable_orders(). > > - */ > > - if (!forced_collapse && > > - (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) && > > - !hugepage_global_always()))) > > - return 0; > > - > > - /* > > - * Trust that ->huge_fault() handlers know what they are doing > > - * in fault path. > > - */ > > - if (((in_pf || smaps)) && vma->vm_ops->huge_fault) > > - return orders; > > - /* Only regular file is valid in collapse path */ > > - if (((!in_pf || smaps)) && file_thp_enabled(vma)) > > - return orders; > > - return 0; > > - } > > + if (!vma_is_anonymous(vma)) > > + return vma_can_map_huge_file(vma, vm_flags, type) ? orders : 0; > > > > if (vma_is_temporary_stack(vma)) > > return 0; > > > > The rest looks great to me. Thanks. Thanks! > > > -- > Best Regards, > Yan, Zi > -- Cheers, Lorenzo