linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Michal Hocko <mhocko@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, Mel Gorman <mgorman@suse.de>,
	Vlastimil Babka <vbabka@suse.cz>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Jerome Glisse <jglisse@redhat.com>,
	Reza Arbab <arbab@linux.vnet.ibm.com>,
	Yasuaki Ishimatsu <yasu.isimatu@gmail.com>,
	qiuxishi@huawei.com, Kani Toshimitsu <toshi.kani@hpe.com>,
	slaoub@gmail.com, Joonsoo Kim <js1304@gmail.com>,
	Andi Kleen <ak@linux.intel.com>,
	David Rientjes <rientjes@google.com>,
	Daniel Kiper <daniel.kiper@oracle.com>,
	Igor Mammedov <imammedo@redhat.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Michal Hocko <mhocko@suse.com>
Subject: [PATCH 05/14] mm, memory_hotplug: split up register_one_node
Date: Mon, 15 May 2017 10:58:18 +0200	[thread overview]
Message-ID: <20170515085827.16474-6-mhocko@kernel.org> (raw)
In-Reply-To: <20170515085827.16474-1-mhocko@kernel.org>

From: Michal Hocko <mhocko@suse.com>

Memory hotplug (add_memory_resource) has to reinitialize node
infrastructure if the node is offline (one which went through the
complete add_memory(); remove_memory() cycle). That involves node
registration to the kobj infrastructure (register_node), the proper
association with cpus (register_cpu_under_node) and finally creation of
node<->memblock symlinks (link_mem_sections).

The last part requires to know node_start_pfn and node_spanned_pages
which we currently have but a leter patch will postpone this
initialization to the onlining phase which happens later. In fact we do
not need to rely on the early pgdat initialization even now because the
currently hot added pfn range is currently known.

Split register_one_node into core which does all the common work for
the boot time NUMA initialization and the hotplug (__register_one_node).
register_one_node keeps the full initialization while hotplug calls
__register_one_node and manually calls link_mem_sections for the proper
range.

This shouldn't introduce any functional change.

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
 drivers/base/node.c  | 51 ++++++++++++++++++++-------------------------------
 include/linux/node.h | 35 ++++++++++++++++++++++++++++++++++-
 mm/memory_hotplug.c  | 17 ++++++++++++++++-
 3 files changed, 70 insertions(+), 33 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 06294d69779b..dff5b53f7905 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -461,10 +461,9 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 	return 0;
 }
 
-static int link_mem_sections(int nid)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 {
-	unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
-	unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages;
+	unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn;
 	struct memory_block *mem_blk = NULL;
 	int err = 0;
@@ -552,10 +551,7 @@ static int node_memory_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif	/* CONFIG_HUGETLBFS */
-#else	/* !CONFIG_MEMORY_HOTPLUG_SPARSE */
-
-static int link_mem_sections(int nid) { return 0; }
-#endif	/* CONFIG_MEMORY_HOTPLUG_SPARSE */
+#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
 #if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
     !defined(CONFIG_HUGETLBFS)
@@ -569,39 +565,32 @@ static void init_node_hugetlb_work(int nid) { }
 
 #endif
 
-int register_one_node(int nid)
+int __register_one_node(int nid)
 {
-	int error = 0;
+	int p_node = parent_node(nid);
+	struct node *parent = NULL;
+	int error;
 	int cpu;
 
-	if (node_online(nid)) {
-		int p_node = parent_node(nid);
-		struct node *parent = NULL;
-
-		if (p_node != nid)
-			parent = node_devices[p_node];
-
-		node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
-		if (!node_devices[nid])
-			return -ENOMEM;
-
-		error = register_node(node_devices[nid], nid, parent);
+	if (p_node != nid)
+		parent = node_devices[p_node];
 
-		/* link cpu under this node */
-		for_each_present_cpu(cpu) {
-			if (cpu_to_node(cpu) == nid)
-				register_cpu_under_node(cpu, nid);
-		}
+	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!node_devices[nid])
+		return -ENOMEM;
 
-		/* link memory sections under this node */
-		error = link_mem_sections(nid);
+	error = register_node(node_devices[nid], nid, parent);
 
-		/* initialize work queue for memory hot plug */
-		init_node_hugetlb_work(nid);
+	/* link cpu under this node */
+	for_each_present_cpu(cpu) {
+		if (cpu_to_node(cpu) == nid)
+			register_cpu_under_node(cpu, nid);
 	}
 
-	return error;
+	/* initialize work queue for memory hot plug */
+	init_node_hugetlb_work(nid);
 
+	return error;
 }
 
 void unregister_one_node(int nid)
diff --git a/include/linux/node.h b/include/linux/node.h
index 2115ad5d6f19..d1751beb462c 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -30,9 +30,38 @@ struct memory_block;
 extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
+extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages);
+#else
+static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+{
+	return 0;
+}
+#endif
+
 extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
-extern int register_one_node(int nid);
+/* Core of the node registration - only memory hotplug should use this */
+extern int __register_one_node(int nid);
+
+/* Registers an online node */
+static inline int register_one_node(int nid)
+{
+	int error = 0;
+
+	if (node_online(nid)) {
+		struct pglist_data *pgdat = NODE_DATA(nid);
+
+		error = __register_one_node(nid);
+		if (error)
+			return error;
+		/* link memory sections under this node */
+		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages);
+	}
+
+	return error;
+}
+
 extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
@@ -46,6 +75,10 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
 					 node_registration_func_t unregister);
 #endif
 #else
+static inline int __register_one_node(int nid)
+{
+	return 0;
+}
 static inline int register_one_node(int nid)
 {
 	return 0;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a95120c56a9a..05796ee974f7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1392,7 +1392,22 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
 	node_set_online(nid);
 
 	if (new_node) {
-		ret = register_one_node(nid);
+		unsigned long start_pfn = start >> PAGE_SHIFT;
+		unsigned long nr_pages = size >> PAGE_SHIFT;
+
+		ret = __register_one_node(nid);
+		if (ret)
+			goto register_fail;
+
+		/*
+		 * link memory sections under this node. This is already
+		 * done when creatig memory section in register_new_memory
+		 * but that depends to have the node registered so offline
+		 * nodes have to go through register_node.
+		 * TODO clean up this mess.
+		 */
+		ret = link_mem_sections(nid, start_pfn, nr_pages);
+register_fail:
 		/*
 		 * If sysfs file of new node can't create, cpu on the node
 		 * can't be hot-added. There is no rollback way now.
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2017-05-15  9:00 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-15  8:58 [PATCH -v4 0/14] mm: make movable onlining suck less Michal Hocko
2017-05-15  8:58 ` [PATCH 01/14] mm: remove return value from init_currently_empty_zone Michal Hocko
2017-05-15  8:58 ` [PATCH 02/14] mm, memory_hotplug: use node instead of zone in can_online_high_movable Michal Hocko
2017-05-15  8:58 ` [PATCH 03/14] mm: drop page_initialized check from get_nid_for_pfn Michal Hocko
2017-05-15  8:58 ` [PATCH 04/14] mm, memory_hotplug: get rid of is_zone_device_section Michal Hocko
2017-06-10  9:56   ` Wei Yang
2017-06-10 14:58     ` Wei Yang
2017-06-12  6:49       ` Michal Hocko
2017-06-14  6:17         ` Wei Yang
2017-06-14  6:12     ` Wei Yang
2017-06-14  6:32       ` Michal Hocko
2017-06-14  9:12         ` Wei Yang
2017-06-14  9:24           ` Michal Hocko
2017-06-15  1:02             ` Wei Yang
2017-05-15  8:58 ` Michal Hocko [this message]
2017-05-15  8:58 ` [PATCH 06/14] mm, memory_hotplug: consider offline memblocks removable Michal Hocko
2017-05-15  8:58 ` [PATCH 07/14] mm: consider zone which is not fully populated to have holes Michal Hocko
2017-05-18 16:14   ` Vlastimil Babka
2017-05-18 16:42     ` Michal Hocko
2017-05-19  7:21       ` Vlastimil Babka
2017-05-15  8:58 ` [PATCH 08/14] mm, compaction: skip over holes in __reset_isolation_suitable Michal Hocko
2017-05-19  7:23   ` Vlastimil Babka
2017-05-15  8:58 ` [PATCH 09/14] mm: __first_valid_page skip over offline pages Michal Hocko
2017-05-19  8:05   ` Vlastimil Babka
2017-05-15  8:58 ` [PATCH 10/14] mm, vmstat: skip reporting offline pages in pagetypeinfo Michal Hocko
2017-05-19  8:17   ` Vlastimil Babka
2017-05-15  8:58 ` [PATCH 11/14] mm, memory_hotplug: do not associate hotadded memory to zones until online Michal Hocko
2017-05-19  8:56   ` Vlastimil Babka
2017-06-16  4:20   ` Wei Yang
2017-06-16  8:05     ` Michal Hocko
2017-06-16  8:11   ` Wei Yang
2017-06-16  8:45     ` Michal Hocko
2017-06-16  9:11       ` Wei Yang
2017-06-25  0:14   ` Wei Yang
2017-06-26  5:38     ` Michal Hocko
2017-05-15  8:58 ` [PATCH 12/14] mm, memory_hotplug: replace for_device by want_memblock in arch_add_memory Michal Hocko
2017-05-15  8:58 ` [PATCH 13/14] mm, memory_hotplug: fix the section mismatch warning Michal Hocko
2017-05-15  8:58 ` [PATCH 14/14] mm, memory_hotplug: remove unused cruft after memory hotplug rework Michal Hocko
2017-06-09  9:51 ` [PATCH -v4 0/14] mm: make movable onlining suck less Wei Yang
2017-06-09 10:49   ` Michal Hocko
2017-06-10  2:20     ` Wei Yang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170515085827.16474-6-mhocko@kernel.org \
    --to=mhocko@kernel.org \
    --cc=aarcange@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=arbab@linux.vnet.ibm.com \
    --cc=daniel.kiper@oracle.com \
    --cc=imammedo@redhat.com \
    --cc=jglisse@redhat.com \
    --cc=js1304@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=qiuxishi@huawei.com \
    --cc=rientjes@google.com \
    --cc=slaoub@gmail.com \
    --cc=toshi.kani@hpe.com \
    --cc=vbabka@suse.cz \
    --cc=vkuznets@redhat.com \
    --cc=yasu.isimatu@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).