alloc_percpu: make the per cpu reserve configurable and larger.

This is based on Christoph Lameter's "cpualloc: make the per cpu
reserve configurable" patch, and his "Increase default reserve percpu
area" patch.

Christoph did the hard work of figuring out what the number should be
(based on converting the slub allocator).  allyesconfig on x86-32 uses
7k before mounting root, so 10k seems reasonable.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
---
 Documentation/kernel-parameters.txt |    8 ++++++++
 include/linux/percpu.h              |   10 ++--------
 init/main.c                         |    2 ++
 mm/allocpercpu.c                    |    5 +++++
 4 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1752,6 +1752,14 @@ and is between 256 and 4096 characters. 
 			Format: { 0 | 1 }
 			See arch/parisc/kernel/pdc_chassis.c
 
+	percpu=		[SMP] Configure the number of percpu bytes that can be
+			dynamically allocated. This is used for per cpu
+			variables of modules and other dynamic per cpu data
+			structures. Creation of per cpu structures after boot
+			may fail if this is set too low.
+			Default is 10k/20k for 32 or 64-bit systems.
+			(Note: this option does nothing on IA64).
+
 	pf.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -41,16 +41,10 @@
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
 
-/* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
 #ifndef PERCPU_ENOUGH_ROOM
-#ifdef CONFIG_MODULES
-#define PERCPU_MODULE_RESERVE	8192
-#else
-#define PERCPU_MODULE_RESERVE	0
-#endif
+extern unsigned int percpu_reserve;
 
-#define PERCPU_ENOUGH_ROOM						\
-	(__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE)
+#define PERCPU_ENOUGH_ROOM (__per_cpu_end - __per_cpu_start + percpu_reserve)
 #endif	/* PERCPU_ENOUGH_ROOM */
 
 /*
diff --git a/init/main.c b/init/main.c
--- a/init/main.c
+++ b/init/main.c
@@ -397,6 +397,8 @@ static void __init setup_per_cpu_areas(v
 	/* Copy section for each CPU (we discard the original) */
 	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
+	printk(KERN_INFO "percpu area: %d bytes total, %d available.\n",
+		size, size - (__per_cpu_end - __per_cpu_start));
 
 	for_each_possible_cpu(i) {
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -142,6 +142,11 @@ void percpu_free(void *__pdata)
 }
 EXPORT_SYMBOL_GPL(percpu_free);
 
+/* A heuristic based on observation.  May need to increase. */
+unsigned int percpu_reserve = (sizeof(unsigned long) * 2500);
+
+core_param(percpu, percpu_reserve, uint, 0444);
+
 void *big_alloc_percpu(unsigned long size)
 {
 	unsigned int cpu;