[PATCH] x86_64: Tell VM about holes in nodes

Some nodes can have large holes on x86-64.

This fixes problems with the VM allowing too many dirty pages because it
overestimates the number of available RAM in a node.  In extreme cases you
can end up with all RAM filled with dirty pages which can lead to deadlocks
and other nasty behaviour.

This patch just tells the VM about the known holes from e820.  Reserved
(like the kernel text or mem_map) is still not taken into account, but that
should be only a few percent error now.

Small detail is that the flat setup uses the NUMA free_area_init_node() now
too because it offers more flexibility.

(akpm: lotsa thanks to Martin for working this problem out)

Cc: Martin Bligh <mbligh@mbligh.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 34 insertions, 0 deletions

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 6ded3a50dfe6..b548dea4e5b9 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -185,6 +185,40 @@ unsigned long __init e820_end_of_ram(void)
 }
 
 /* 
+ * Compute how much memory is missing in a range.
+ * Unlike the other functions in this file the arguments are in page numbers.
+ */
+unsigned long __init
+e820_hole_size(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long ram = 0;
+	unsigned long start = start_pfn << PAGE_SHIFT;
+	unsigned long end = end_pfn << PAGE_SHIFT;
+	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) >> PAGE_SHIFT;
+}
+
+/*
  * Mark e820 reserved areas as busy for the resource manager.
  */
 void __init e820_reserve_resources(void)