Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Daniel Jordan <daniel.m.jordan@oracle.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Herbert Xu <herbert@gondor.apana.org.au>,
        Steffen Klassert <steffen.klassert@secunet.com>
Cc:     Alex Williamson <alex.williamson@redhat.com>,
        Alexander Duyck <alexander.h.duyck@linux.intel.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        David Hildenbrand <david@redhat.com>,
        Jason Gunthorpe <jgg@ziepe.ca>,
        Jonathan Corbet <corbet@lwn.net>,
        Josh Triplett <josh@joshtriplett.org>,
        Kirill Tkhai <ktkhai@virtuozzo.com>,
        Michal Hocko <mhocko@kernel.org>, Pavel Machek <pavel@ucw.cz>,
        Pavel Tatashin <pasha.tatashin@soleen.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Randy Dunlap <rdunlap@infradead.org>,
        Robert Elliott <elliott@hpe.com>,
        Shile Zhang <shile.zhang@linux.alibaba.com>,
        Steven Sistare <steven.sistare@oracle.com>,
        Tejun Heo <tj@kernel.org>, Zi Yan <ziy@nvidia.com>,
        linux-crypto@vger.kernel.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, linux-s390@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org,
        Daniel Jordan <daniel.m.jordan@oracle.com>
Subject: [PATCH v3 7/8] mm: make deferred init's max threads arch-specific
Date:   Wed, 27 May 2020 13:36:07 -0400
Message-Id: <20200527173608.2885243-8-daniel.m.jordan@oracle.com>
In-Reply-To: <20200527173608.2885243-1-daniel.m.jordan@oracle.com>
References: <20200527173608.2885243-1-daniel.m.jordan@oracle.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-crypto-owner@vger.kernel.org
Precedence: bulk

Using padata during deferred init has only been tested on x86, so for
now limit it to this architecture.

If another arch wants this, it can find the max thread limit that's best
for it and override deferred_page_init_max_threads().

Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Tested-by: Josh Triplett <josh@joshtriplett.org>
---
 arch/x86/mm/init_64.c    | 12 ++++++++++++
 include/linux/memblock.h |  3 +++
 mm/page_alloc.c          | 13 ++++++++-----
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 8b5f73f5e207c..2d749ec12ea8a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1260,6 +1260,18 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
+{
+	/*
+	 * More CPUs always led to greater speedups on tested systems, up to
+	 * all the nodes' CPUs.  Use all since the system is otherwise idle
+	 * now.
+	 */
+	return max_t(int, cpumask_weight(node_cpumask), 1);
+}
+#endif
+
 int kernel_set_to_readonly;
 
 void mark_rodata_ro(void)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 6bc37a731d27b..2b289df44194f 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -275,6 +275,9 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 #define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \
 	for (; i != U64_MAX;					  \
 	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
+
+int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
+
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1d47016849531..329fd1a809c59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1835,6 +1835,13 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 	}
 }
 
+/* An arch may override for more concurrency. */
+__weak int __init
+deferred_page_init_max_threads(const struct cpumask *node_cpumask)
+{
+	return 1;
+}
+
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
 {
@@ -1883,11 +1890,7 @@ static int __init deferred_init_memmap(void *data)
 						 first_init_pfn))
 		goto zone_empty;
 
-	/*
-	 * More CPUs always led to greater speedups on tested systems, up to
-	 * all the nodes' CPUs.  Use all since the system is otherwise idle now.
-	 */
-	max_threads = max(cpumask_weight(cpumask), 1u);
+	max_threads = deferred_page_init_max_threads(cpumask);
 
 	while (spfn < epfn) {
 		unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
-- 
2.26.2