From nobody Thu Dec 25 10:30:03 2025 Received: from out-177.mta1.migadu.com (out-177.mta1.migadu.com [95.215.58.177]) (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 6F8E228DC3 for ; Thu, 18 Jan 2024 12:39:38 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.177 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705581580; cv=none; b=tEWZiFS/FsM1t/eMJIkcSVJS+qx+V6HZlh6DdNmCcjjwM6VZMaGejPzUwGxdabHiUiFT9ERNH9GlHyg94JatoI4ZyjlVyicXLcLklWg++LqiZKFFDtXLkPw/REeM/ipllzZNl8ZIlM8tvmXBlpQSkHOqeI0qcAWTpmRomt7C4YQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705581580; c=relaxed/simple; bh=RXho9gcWShyEgzc6VWxyMJAoRzTXkb0OAPzJWwFdVNk=; h=X-Report-Abuse:DKIM-Signature:From:To:Cc:Subject:Date:Message-Id: In-Reply-To:References:MIME-Version:Content-Transfer-Encoding: X-Migadu-Flow; b=JBxx7x0p4aVNQeJO2eSpJ6FqDQfAXhcZD9ZQYBfdBb4WLKURle13XASBLy8RdQ9x1G47lgX2EozL/dqo7pz8G2SIcQXwMDtMcWxXUbG3Pf/nlTDbgmJoOolYY4f0ABLTNcrvl8RdmH26dLPGbju8ToYqpyN9AZ4DSNnzfZoBuxU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=X9AMrKwC; arc=none smtp.client-ip=95.215.58.177 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="X9AMrKwC" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1705581576; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=1NWoU3oNLKXdGAS21M0bC7+FD15GTIkL0kQlYQf/mAw=; b=X9AMrKwCFkauV1DKTVIEE+qGM2FG1NTvSzWTmV79baKdAnr8JOXd0UzWf4lXz9eRSwPsmJ xUlRA/NNXsMhUd+q5AubG2ApMlLTNXk5xLpCNocAJIIsPrKSI0L4SkGbNsxx3zBpI/B7Hw DoLUtRX1d5mdreKgoItEtz++Kk7gaXI= From: Gang Li To: David Hildenbrand , David Rientjes , Mike Kravetz , Muchun Song , Andrew Morton , Tim Chen Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, ligang.bdlg@bytedance.com, Gang Li Subject: [PATCH v4 6/7] hugetlb: parallelize 2M hugetlb allocation and initialization Date: Thu, 18 Jan 2024 20:39:10 +0800 Message-Id: <20240118123911.88833-7-gang.li@linux.dev> In-Reply-To: <20240118123911.88833-1-gang.li@linux.dev> References: <20240118123911.88833-1-gang.li@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Content-Type: text/plain; charset="utf-8" By distributing both the allocation and the initialization tasks across multiple threads, the initialization of 2M hugetlb will be faster, thereby improving the boot speed. Here are some test results: test no patch(ms) patched(ms) saved ------------------- -------------- ------------- -------- 256c2t(4 node) 2M 3336 1051 68.52% 128c1t(2 node) 2M 1943 716 63.15% Signed-off-by: Gang Li Tested-by: David Rientjes --- mm/hugetlb.c | 70 ++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 52 insertions(+), 18 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index effe5539e545..9b348ba418f5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -35,6 +35,7 @@ #include #include #include +#include =20 #include #include @@ -3510,43 +3511,76 @@ static void __init hugetlb_hstate_alloc_pages_errch= eck(unsigned long allocated, } } =20 -static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstat= e *h) +static void __init hugetlb_alloc_node(unsigned long start, unsigned long e= nd, void *arg) { - unsigned long i; + struct hstate *h =3D (struct hstate *)arg; + int i, num =3D end - start; + nodemask_t node_alloc_noretry; + unsigned long flags; + int next_node =3D 0; =20 - for (i =3D 0; i < h->max_huge_pages; ++i) { - if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) + /* Bit mask controlling how hard we retry per-node allocations.*/ + nodes_clear(node_alloc_noretry); + + for (i =3D 0; i < num; ++i) { + struct folio *folio =3D alloc_pool_huge_folio(h, &node_states[N_MEMORY], + &node_alloc_noretry, &next_node); + if (!folio) break; + spin_lock_irqsave(&hugetlb_lock, flags); + __prep_account_new_huge_page(h, folio_nid(folio)); + enqueue_hugetlb_folio(h, folio); + spin_unlock_irqrestore(&hugetlb_lock, flags); cond_resched(); } +} =20 - return i; +static void __init hugetlb_vmemmap_optimize_node(unsigned long start, unsi= gned long end, void *arg) +{ + struct hstate *h =3D (struct hstate *)arg; + int nid =3D start; + + hugetlb_vmemmap_optimize_folios(h, &h->hugepage_freelists[nid]); } =20 -static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) +static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstat= e *h) { unsigned long i; - struct folio *folio; - LIST_HEAD(folio_list); - nodemask_t node_alloc_noretry; - - /* Bit mask controlling how hard we retry per-node allocations.*/ - nodes_clear(node_alloc_noretry); =20 for (i =3D 0; i < h->max_huge_pages; ++i) { - folio =3D alloc_pool_huge_folio(h, &node_states[N_MEMORY], - &node_alloc_noretry); - if (!folio) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; - list_add(&folio->lru, &folio_list); cond_resched(); } =20 - prep_and_add_allocated_folios(h, &folio_list); - return i; } =20 +static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) +{ + struct padata_mt_job job =3D { + .fn_arg =3D h, + .align =3D 1, + .numa_aware =3D true + }; + + job.thread_fn =3D hugetlb_alloc_node; + job.start =3D 0; + job.size =3D h->max_huge_pages; + job.min_chunk =3D h->max_huge_pages / num_node_state(N_MEMORY) / 2; + job.max_threads =3D num_node_state(N_MEMORY) * 2; + padata_do_multithreaded(&job); + + job.thread_fn =3D hugetlb_vmemmap_optimize_node; + job.start =3D 0; + job.size =3D num_node_state(N_MEMORY); + job.min_chunk =3D 1; + job.max_threads =3D num_node_state(N_MEMORY); + padata_do_multithreaded(&job); + + return h->nr_huge_pages; +} + /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. --=20 2.20.1