From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0C820364047 for ; Tue, 2 Jun 2026 03:02:20 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.132 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780369344; cv=none; b=h+U0CyS+apOeV/6n+x7T0gkwoxfqwtW/ILzzAcARJ4vTy/i2OpMvpnG4SiLXHWpT3c+6F+33OqJlMm1EGrZF0tqDdnge9yFMXZFQSpLWF1fbEhEt1z5ksvqpP2yoA9pVXmIczfEHBJvC0SD6fjzdBC4eh2NuntIwzm/el2Bb+uU= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780369344; c=relaxed/simple; bh=4RzLiTCzMvUR/5e14rnvkALxhDC+tE06t0SKl2HyDvo=; h=Message-ID:Date:MIME-Version:Subject:From:To:Cc:References: In-Reply-To:Content-Type; b=WgzwvfRYs0G2pzEHzkdsT9ODMMly3F6EzwecZI3sN4n+T2tmTKCis5BNfBB6gqJwLBhJZNjlgxgLYjbjRKStdNxg+H5O3q+P7Ivx4DNytWzVBQqwhDJoxF2pOpgO2mKmpjjaF5/2Z9JO0K1qX9cvPBMcITFfCKqhlJd674stHBg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=Cq/khgVa; arc=none smtp.client-ip=115.124.30.132 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="Cq/khgVa" DKIM-Signature:v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1780369333; h=Message-ID:Date:MIME-Version:Subject:From:To:Content-Type; bh=CSTQRXqZkfE0CBpGC79lm3NY6Rv+5Tj1N3miINFndqA=; b=Cq/khgVaah1GWF98/qz7Dp9bc6zeqcZu5WPx71TkMcCkaJ5+LWQA7kLeg3Xsgzmg67cC3dXRej6t1xSqdB4w/RbtQgqgyavMbWW727qml4JNl4+7MxODsfMbyPouY6medeaIPgRDKpBJwbs+Efg/w6tpPJxjJ81krHsK6bmchHU= X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R201e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=maildocker-contentspam033045133197;MF=baolin.wang@linux.alibaba.com;NM=1;PH=DS;RN=27;SR=0;TI=SMTPD_---0X42mreA_1780369330; Received: from 30.166.17.138(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0X42mreA_1780369330 cluster:ay36) by smtp.aliyun-inc.com; Tue, 02 Jun 2026 11:02:11 +0800 Message-ID: <5e4defef-8967-4cdf-9123-07dd9517d637@linux.alibaba.com> Date: Tue, 2 Jun 2026 11:02:10 +0800 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH v5 14/14] mm: thp: always enable mTHP support From: Baolin Wang To: Luiz Capitulino , linux-kernel@vger.kernel.org, linux-mm@kvack.org, david@kernel.org, ziy@nvidia.com, lance.yang@linux.dev Cc: corbet@lwn.net, tsbogend@alpha.franken.de, maddy@linux.ibm.com, mpe@ellerman.id.au, agordeev@linux.ibm.com, gerald.schaefer@linux.ibm.com, hca@linux.ibm.com, gor@linux.ibm.com, x86@kernel.org, tglx@kernel.org, mingo@redhat.com, bp@alien8.de, ira.weiny@intel.com, hughd@google.com, dave.hansen@linux.intel.com, djbw@kernel.org, vishal.l.verma@intel.com, dave.jiang@intel.com, akpm@linux-foundation.org, yintirui@huawei.com, ljs@kernel.org References: <8781a9a0f115705ee11884ed3184b65a1ce39923.1780066530.git.luizcap@redhat.com> <7b3e5fd9-e0d6-4c0d-8656-2649855f4034@linux.alibaba.com> In-Reply-To: <7b3e5fd9-e0d6-4c0d-8656-2649855f4034@linux.alibaba.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit On 6/1/26 8:02 PM, Baolin Wang wrote: > > > On 5/29/26 10:55 PM, Luiz Capitulino wrote: >> If PMD-sized pages are not supported on an architecture (ie. the >> arch implements arch_has_pmd_leaves() and it returns false) then the >> current code disables all THP, including mTHP. >> >> This commit fixes this by allowing mTHP to be always enabled for all >> archs. When PMD-sized pages are not supported, its sysfs entry won't be >> created and their mapping will be disallowed at page-fault time. >> >> Similarly, this commit implements the following changes for shmem in >> shmem_allowable_huge_orders(): >> >>   - Drop the pgtable_has_pmd_leaves() check so that mTHP sizes are >>     considered >>   - Filter out PMD and PUD orders from allowable orders when >>     PMD-sized pages are not supported by the CPU >> >> Signed-off-by: Luiz Capitulino >> --- >>   mm/huge_memory.c | 25 ++++++++++++++++++++----- >>   mm/shmem.c       | 14 +++++++++----- >>   2 files changed, 29 insertions(+), 10 deletions(-) >> >> diff --git a/mm/huge_memory.c b/mm/huge_memory.c >> index 32254febe097..059901a8c6cb 100644 >> --- a/mm/huge_memory.c >> +++ b/mm/huge_memory.c >> @@ -126,6 +126,15 @@ unsigned long __thp_vma_allowable_orders(struct >> vm_area_struct *vma, >>       else >>           supported_orders = THP_ORDERS_ALL_FILE_DEFAULT; >> +    if (!pgtable_has_pmd_leaves()) { >> +        /* >> +         * If the CPU does not support PMD leaves, assume for >> +         * now that it does not support PUD leaves and disable >> +         * both folio orders. >> +         */ >> +        supported_orders &= ~(BIT(PMD_ORDER) | BIT(PUD_ORDER)); >> +    } >> + >>       orders &= supported_orders; >>       if (!orders) >>           return 0; >> @@ -133,7 +142,7 @@ unsigned long __thp_vma_allowable_orders(struct >> vm_area_struct *vma, >>       if (!vma->vm_mm)        /* vdso */ >>           return 0; >> -    if (!pgtable_has_pmd_leaves() || vma_thp_disabled(vma, vm_flags, >> forced_collapse)) >> +    if (vma_thp_disabled(vma, vm_flags, forced_collapse)) >>           return 0; >>       /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ >> @@ -848,7 +857,7 @@ static int __init hugepage_init_sysfs(struct >> kobject **hugepage_kobj) >>        * disable all other sizes. powerpc's PMD_ORDER isn't a compile- >> time >>        * constant so we have to do this here. >>        */ >> -    if (!anon_orders_configured) >> +    if (!anon_orders_configured && pgtable_has_pmd_leaves()) >>           huge_anon_orders_inherit = BIT(PMD_ORDER); >>       *hugepage_kobj = kobject_create_and_add("transparent_hugepage", >> mm_kobj); >> @@ -870,6 +879,15 @@ static int __init hugepage_init_sysfs(struct >> kobject **hugepage_kobj) >>       } >>       orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT; >> +    if (!pgtable_has_pmd_leaves()) { >> +        /* >> +         * If the CPU does not support PMD leaves, assume for >> +         * now that it does not support PUD leaves and disable >> +         * both folio orders. >> +         */ >> +        orders &= ~(BIT(PMD_ORDER) | BIT(PUD_ORDER)); >> +    } >> + >>       order = highest_order(orders); >>       while (orders) { >>           thpsize = thpsize_create(order, *hugepage_kobj); >> @@ -969,9 +987,6 @@ static int __init hugepage_init(void) >>       int err; >>       struct kobject *hugepage_kobj; >> -    if (!pgtable_has_pmd_leaves()) >> -        return -EINVAL; >> - >>       /* >>        * hugepages can't be allocated by the buddy allocator >>        */ >> diff --git a/mm/shmem.c b/mm/shmem.c >> index 079e299ea789..c15dffd0eb41 100644 >> --- a/mm/shmem.c >> +++ b/mm/shmem.c >> @@ -1844,16 +1844,19 @@ unsigned long >> shmem_allowable_huge_orders(struct inode *inode, >>       unsigned long mask = READ_ONCE(huge_shmem_orders_always); >>       unsigned long within_size_orders = >> READ_ONCE(huge_shmem_orders_within_size); >>       vm_flags_t vm_flags = vma ? vma->vm_flags : 0; >> -    unsigned int global_orders; >> +    unsigned int global_orders, disabled_orders = 0; >> -    if (!pgtable_has_pmd_leaves() || (vma && vma_thp_disabled(vma, >> vm_flags, shmem_huge_force))) >> +    if (vma && vma_thp_disabled(vma, vm_flags, shmem_huge_force)) >>           return 0; >> +    if (!pgtable_has_pmd_leaves()) >> +        disabled_orders = BIT(PMD_ORDER); >> + >>       global_orders = shmem_huge_global_enabled(inode, index, write_end, >>                             shmem_huge_force, vma, vm_flags); >>       /* Tmpfs huge pages allocation */ >>       if (!vma || !vma_is_anon_shmem(vma)) >> -        return global_orders; >> +        return global_orders & ~disabled_orders; >>       /* >>        * Following the 'deny' semantics of the top level, force the huge >> @@ -1867,7 +1870,7 @@ unsigned long shmem_allowable_huge_orders(struct >> inode *inode, >>        * means non-PMD sized THP can not override 'huge' mount option >> now. >>        */ >>       if (shmem_huge == SHMEM_HUGE_FORCE) >> -        return READ_ONCE(huge_shmem_orders_inherit); >> +        return READ_ONCE(huge_shmem_orders_inherit) & ~disabled_orders; >>       /* Allow mTHP that will be fully within i_size. */ >>       mask |= shmem_get_orders_within_size(inode, within_size_orders, >> index, 0); >> @@ -1878,6 +1881,7 @@ unsigned long shmem_allowable_huge_orders(struct >> inode *inode, >>       if (global_orders > 0) >>           mask |= READ_ONCE(huge_shmem_orders_inherit); >> +    mask &= ~disabled_orders; >>       return THP_ORDERS_ALL_FILE_DEFAULT & mask; >>   } >> @@ -5461,7 +5465,7 @@ void __init shmem_init(void) >>        * Default to setting PMD-sized THP to inherit the global >> setting and >>        * disable all other multi-size THPs. >>        */ >> -    if (!shmem_orders_configured) >> +    if (!shmem_orders_configured && pgtable_has_pmd_leaves()) >>           huge_shmem_orders_inherit = BIT(HPAGE_PMD_ORDER); >>   #endif >>       return; > > Seems we should also filter the PMD-sized order in shmem_getattr() if > pgtable_has_pmd_leaves() returns false, like I mentioned in the previous > link[1]. > > [1] https://lore.kernel.org/linux-mm/6591a74c-7ef9-4614-9ae9- > cb2fbed86ebf@linux.alibaba.com/ You already did this in patch 7. So LGTM. Reviewed-by: Baolin Wang