Skip to contentSkip to conversation

numa: in-kernel profiling: use cpu_to_mem() for per cpu allocations

PATCH New [email protected] 1 participant 1 message May 26, 2010 Generic include/asm header files

lore
Share & tools
lore
#0 lore raw

PATCH 202/203 numa: in-kernel profiling: use cpu_to_mem() for per cpu allocations

From: Lee Schermerhorn <[email protected]>

In kernel profiling requires that we be able to allocate "local" memory for each cpu. Use "cpu_to_mem()" instead of "cpu_to_node()" to support memoryless nodes.

Depends on the "numa_mem_id()" patch.

Cc Tejun Heo <[email protected]>
Cc Mel Gorman <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Nick Piggin <[email protected]>
Cc David Rientjes <[email protected]>
Cc Eric Whitney <[email protected]>
Cc KAMEZAWA Hiroyuki <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc "Luck, Tony" <[email protected]>
Cc Pekka Enberg <[email protected]>

---

 kernel/profile.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/profile.c renamed from kernel/profile.c~numa-in-kernel-profiling-use-cpu_to_mem-for-per-cpu-allocations +2 -2
diff -puN kernel/profile.c~numa-in-kernel-profiling-use-cpu_to_mem-for-per-cpu-allocations kernel/profile.c
@@ -365,7 +365,7 @@ static int __cpuinit profile_cpu_callbac
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		node = cpu_to_node(cpu);
+		node = cpu_to_mem(cpu);
 		per_cpu(cpu_profile_flip, cpu) = 0;
 		if (!per_cpu(cpu_profile_hits, cpu)[1]) {
 			page = alloc_pages_exact_node(node,
@@ -567,7 +567,7 @@ static int create_hash_tables(void)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		int node = cpu_to_node(cpu);
+		int node = cpu_to_mem(cpu);
 		struct page *page;
 
 		page = alloc_pages_exact_node(node,

_