[PATCH] x86-64: Fix fake numa for x86_64 machines with big IO hole

This patch resolves the issue of running with numa=fake=X on kernel command
line on x86_64 machines that have big IO hole.  While calculating the size
of each node now we look at the total hole size in that range.

Previously there were nodes that only had IO holes in them causing kernel
boot problems.  We now use the NODE_MIN_SIZE (64MB) as the minimum size of
memory that any node must have.  We reduce the number of allocated nodes if
the number of nodes specified on kernel command line results in any node
getting memory smaller than NODE_MIN_SIZE.

This change allows the extra memory to be incremented in NODE_MIN_SIZE
granule and uniformly distribute among as many nodes (called big nodes) as
possible.

[akpm@osdl.org: build fix]
Signed-off-by: David Rientjes <reintjes@google.com>
Signed-off-by: Paul Menage <menage@google.com>
Signed-off-by: Rohit Seth <rohitseth@google.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>

1 files changed, 31 insertions, 0 deletions

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 9d67955bbc31..4651fd22b213 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -191,6 +191,37 @@ unsigned long __init e820_end_of_ram(void)
 }
 
 /*
+ * Find the hole size in the range.
+ */
+unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
+{
+	unsigned long ram = 0;
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		unsigned long last, addr;
+
+		if (ei->type != E820_RAM ||
+		    ei->addr+ei->size <= start ||
+		    ei->addr >= end)
+			continue;
+
+		addr = round_up(ei->addr, PAGE_SIZE);
+		if (addr < start)
+			addr = start;
+
+		last = round_down(ei->addr + ei->size, PAGE_SIZE);
+		if (last >= end)
+			last = end;
+
+		if (last > addr)
+			ram += last - addr;
+	}
+	return ((end - start) - ram);
+}
+
+/*
  * Mark e820 reserved areas as busy for the resource manager.
  */
 void __init e820_reserve_resources(void)