From 68a3a7feb08f960095072f28ec20f7900793c506 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Fri, 7 Apr 2006 19:49:18 +0200
Subject: [PATCH] x86_64: Reserve SRAT hotadd memory on x86-64

From: Keith Mannthey, Andi Kleen

Implement memory hotadd without sparsemem. The memory in the SRAT
hotadd area is just preserved instead and can be activated later.

There are a few restrictions:
- Only one continuous hotadd area allowed per node

The main problem is dealing with the many buggy SRAT tables
that are out there. The strategy here is to reject anything
suspicious.

Originally from Keith Mannthey, with several hacks and changes by AK
and also contributions from Andrew Morton

[ TBD: Problems pointed out by KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>:

 1) Goto's rebuild_zonelist patch will not work if CONFIG_MEMORY_HOTPLUG=n.

    Rebuilding zonelist is necessary when the system has just memory <
    4G at boot, and hot add memory > 4G.  because x86_64 has DMA32,
    ZONE_NORAML is not included into zonelist at boot time if system
    doesn't have memory >4G at boot.

    [AK: should just force the higher zones at boot time when SRAT tells us]

 2) zone and node's spanned_pages and present_pages are not incremented.
    They should be.

    For example, our server (ia64/Fujitsu PrimeQuest) can equip memory
    from 4G to 1T(maybe 2T in future), and SRAT will *always* say we have
    possible 1T +memory.  (Microsoft requires "write all possible memory
    in SRAT") When we reserve memmap for possible 1T memory, Linux will
    not work well in +minimum 4G configuraion ;)

    [AK: needs limiting to 5-10% of max memory]
 ]

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 arch/x86_64/mm/numa.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'arch/x86_64/mm/numa.c')

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 4be82d6e2b4..779132af29a 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -142,6 +142,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 
 	reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); 
 	reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<<PAGE_SHIFT);
+#ifdef CONFIG_ACPI_NUMA
+	srat_reserve_add_area(nodeid);
+#endif
 	node_set_online(nodeid);
 } 
 
@@ -335,6 +338,8 @@ __init int numa_setup(char *opt)
 #ifdef CONFIG_ACPI_NUMA
  	if (!strncmp(opt,"noacpi",6))
  		acpi_numa = -1;
+	if (!strncmp(opt,"hotadd=", 7))
+		hotadd_percent = simple_strtoul(opt+7, NULL, 10);
 #endif
 	return 1;
 } 
-- 
cgit v1.2.3


From a8062231d80239cf3405982858c02aea21a6066a Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Fri, 7 Apr 2006 19:49:21 +0200
Subject: [PATCH] x86_64: Handle empty PXMs that only contain hotplug memory

The node setup code would try to allocate the node metadata in the node
itself, but that fails if there is no memory in there.

This can happen with memory hotplug when the hotplug area defines an so
far empty node.

Now use bootmem to try to allocate the mem_map in other nodes.

And if it fails don't panic, but just ignore the node.

To make this work I added a new __alloc_bootmem_nopanic function that
does what its name implies.

TBD should try to use nearby nodes here.  Currently we just use any.
It's hard to do it better because bootmem doesn't have proper fallback
lists yet.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
---
 arch/x86_64/mm/numa.c | 41 ++++++++++++++++++++++++++++++++---------
 1 file changed, 32 insertions(+), 9 deletions(-)

(limited to 'arch/x86_64/mm/numa.c')

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 779132af29a..cc02573a327 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -100,11 +100,30 @@ int early_pfn_to_nid(unsigned long pfn)
 }
 #endif
 
+static void * __init
+early_node_mem(int nodeid, unsigned long start, unsigned long end,
+	      unsigned long size)
+{
+	unsigned long mem = find_e820_area(start, end, size);
+	void *ptr;
+	if (mem != -1L)
+		return __va(mem);
+	ptr = __alloc_bootmem_nopanic(size,
+				SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
+	if (ptr == 0) {
+		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+			size, nodeid);
+		return NULL;
+	}
+	return ptr;
+}
+
 /* Initialize bootmem allocator for a node */
 void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 { 
 	unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size, bootmap_start; 
 	unsigned long nodedata_phys;
+	void *bootmap;
 	const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
 
 	start = round_up(start, ZONE_ALIGN); 
@@ -114,13 +133,11 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 	start_pfn = start >> PAGE_SHIFT;
 	end_pfn = end >> PAGE_SHIFT;
 
-	nodedata_phys = find_e820_area(start, end, pgdat_size); 
-	if (nodedata_phys == -1L) 
-		panic("Cannot find memory pgdat in node %d\n", nodeid);
-
-	Dprintk("nodedata_phys %lx\n", nodedata_phys); 
+	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size);
+	if (node_data[nodeid] == NULL)
+		return;
+	nodedata_phys = __pa(node_data[nodeid]);
 
-	node_data[nodeid] = phys_to_virt(nodedata_phys);
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
 	NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
@@ -129,9 +146,15 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 	/* Find a place for the bootmem map */
 	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); 
 	bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
-	bootmap_start = find_e820_area(bootmap_start, end, bootmap_pages<<PAGE_SHIFT);
-	if (bootmap_start == -1L) 
-		panic("Not enough continuous space for bootmap on node %d", nodeid); 
+	bootmap = early_node_mem(nodeid, bootmap_start, end,
+					bootmap_pages<<PAGE_SHIFT);
+	if (bootmap == NULL)  {
+		if (nodedata_phys < start || nodedata_phys >= end)
+			free_bootmem((unsigned long)node_data[nodeid],pgdat_size);
+		node_data[nodeid] = NULL;
+		return;
+	}
+	bootmap_start = __pa(bootmap);
 	Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages); 
 	
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-- 
cgit v1.2.3