x86/mm/numa: Clean up numa_clear_kernel_node_hotplug()

So we fixed an overflow bug in numa_clear_kernel_node_hotplug():

  2b54ab3c66d4 ("x86/mm/numa: Fix memory corruption on 32-bit NUMA kernels")

... and the bug was indirectly caused by poor coding style,
such as using start/end local variables unnecessarily, which
lost the physaddr_t type.

So make the code more readable and try to fully comment all
the thinking behind the logic.

No change in functionality.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Chen Tang <imtangchen@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Taku Izumi <izumi.taku@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: y14sg1 <y14sg1@comcast.net>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 42 insertions, 23 deletions

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index d04f8094bc23..ede4506abb18 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -465,46 +465,65 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+/*
+ * Mark all currently memblock-reserved physical memory (which covers the
+ * kernel's own memory ranges) as hot-unswappable.
+ */
 static void __init numa_clear_kernel_node_hotplug(void)
 {
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	phys_addr_t start, end;
-	struct memblock_region *r;
+	nodemask_t reserved_nodemask = NODE_MASK_NONE;
+	struct memblock_region *mb_region;
+	int i;
 
 	/*
+	 * We have to do some preprocessing of memblock regions, to
+	 * make them suitable for reservation.
+	 *
 	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
+	 * used by the kernel, but those regions are not split up
+	 * along node boundaries yet, and don't necessarily have their
+	 * node ID set yet either.
+	 *
+	 * So iterate over all memory known to the x86 architecture,
+	 * and use those ranges to set the nid in memblock.reserved.
+	 * This will split up the memblock regions along node
+	 * boundaries and will set the node IDs as well.
 	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		struct numa_memblk *mb = numa_meminfo.blk + i;
 
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
+		memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid);
 	}
 
 	/*
-	 * Mark all kernel nodes.
+	 * Now go over all reserved memblock regions, to construct a
+	 * node mask of all kernel reserved memory areas.
 	 *
-	 * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
-	 * may not include all the memblock.reserved memory ranges because
-	 * trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
+	 * [ Note, when booting with mem=nn[kMG] or in a kdump kernel,
+	 *   numa_meminfo might not include all memblock.reserved
+	 *   memory ranges, because quirks such as trim_snb_memory()
+	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, r)
-		if (r->nid != MAX_NUMNODES)
-			node_set(r->nid, numa_kernel_nodes);
+	for_each_memblock(reserved, mb_region) {
+		if (mb_region->nid != MAX_NUMNODES)
+			node_set(mb_region->nid, reserved_nodemask);
+	}
 
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	/*
+	 * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory
+	 * belonging to the reserved node mask.
+	 *
+	 * Note that this will include memory regions that reside
+	 * on nodes that contain kernel memory - entire nodes
+	 * become hot-unpluggable:
+	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
+		struct numa_memblk *mb = numa_meminfo.blk + i;
 
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
+		if (!node_isset(mb->nid, reserved_nodemask))
+			continue;
 
-		memblock_clear_hotplug(start, end - start);
+		memblock_clear_hotplug(mb->start, mb->end - mb->start);
 	}
 }