From: George Beshers <gbeshers@redhat.com>
Date: Thu, 31 Jul 2008 15:34:10 -0400
Subject: [IA64] Fix large MCA bootmem allocation
Message-id: 20080731192815.4411.29311.sendpatchset@dhcp-100-2-194.bos.redhat.com
O-Subject: [RHEL5.3 PATCH 18/19] [IA64] Fix large MCA bootmem allocation
Bugzilla: 455308
RH-Acked-by: Prarit Bhargava <prarit@redhat.com>

[patch] Fix large MCA bootmem allocation

BZ#455308

Upstream: http://git.kernel.org/?p=linux/kernel/git/aegl/linux-2.6.git;a=commitdiff;h=785285fc8bc7f846ab68a063a8bf5a009d67725d

The MCA code allocates bootmem memory for NR_CPUS, regardless
of how many cpus the system actually has.  This change allocates
memory only for cpus that actually exist.

On my test system with NR_CPUS = 1024, reserved memory was reduced by 130944k.

Before: Memory: 27886976k/28111168k available (8282k code, 242304k reserved, 5928k data, 1792k init)
After:  Memory: 28017920k/28111168k available (8282k code, 111360k reserved, 5928k data, 1792k init)

Signed-off-by: Russ Anderson <rja@sgi.com>

Note: Patch cleaned up slightly because Prarit rejected another patch,
    the results is close to what is upstream.

diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index c666582..39ed501 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -18,7 +18,7 @@
  * Copyright (C) 2000 Intel
  * Copyright (C) Chuck Fleckenstein (cfleck@co.intel.com)
  *
- * Copyright (C) 1999, 2004 Silicon Graphics, Inc.
+ * Copyright (C) 1999, 2004-2008 Silicon Graphics, Inc.
  * Copyright (C) Vijay Chander(vijay@engr.sgi.com)
  *
  * 03/04/15 D. Mosberger Added INIT backtrace support.
@@ -1757,43 +1757,46 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
 	strncpy(p->comm, type, sizeof(p->comm)-1);
 }
 
+/* Caller prevents this from being called after init */
+static void * __cpuinit mca_bootmem(void)
+{
+	return __alloc_bootmem(sizeof(struct ia64_mca_cpu),
+	                    KERNEL_STACK_SIZE, 0);
+}
+
 /* Do per-CPU MCA-related initialization.  */
 
 void __cpuinit
 ia64_mca_cpu_init(void *cpu_data)
 {
 	void *pal_vaddr;
+	void *data;
+	long sz = sizeof(struct ia64_mca_cpu);
+	int cpu = smp_processor_id();
 	static int first_time = 1;
 
-	if (first_time) {
-		void *mca_data;
-		int cpu;
-
-		first_time = 0;
-		mca_data = alloc_bootmem(sizeof(struct ia64_mca_cpu)
-					 * NR_CPUS + KERNEL_STACK_SIZE);
-		mca_data = (void *)(((unsigned long)mca_data +
-					KERNEL_STACK_SIZE - 1) &
-				(-KERNEL_STACK_SIZE));
-		for (cpu = 0; cpu < NR_CPUS; cpu++) {
-			format_mca_init_stack(mca_data,
-					offsetof(struct ia64_mca_cpu, mca_stack),
-					"MCA", cpu);
-			format_mca_init_stack(mca_data,
-					offsetof(struct ia64_mca_cpu, init_stack),
-					"INIT", cpu);
-			__per_cpu_mca[cpu] = __pa(mca_data);
-			mca_data += sizeof(struct ia64_mca_cpu);
-		}
-	}
-
 	/*
-	 * The MCA info structure was allocated earlier and its
-	 * physical address saved in __per_cpu_mca[cpu].  Copy that
-	 * address * to ia64_mca_data so we can access it as a per-CPU
-	 * variable.
+	 * Structure will already be allocated if cpu has been online,
+	 * then offlined.
 	 */
-	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[smp_processor_id()];
+	if (__per_cpu_mca[cpu]) {
+		data = __va(__per_cpu_mca[cpu]);
+	} else {
+		if (first_time) {
+			data = mca_bootmem();
+			first_time = 0;
+		} else
+			data = page_address(alloc_pages_node(numa_node_id(),
+					GFP_KERNEL, get_order(sz)));
+		if (!data)
+			panic("Could not allocate MCA memory for cpu %d\n",
+					cpu);
+	}
+	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, mca_stack),
+		"MCA", cpu);
+	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, init_stack),
+		"INIT", cpu);
+	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[cpu] = __pa(data);
 
 	/*
 	 * Stash away a copy of the PTE needed to map the per-CPU page.