From: Borislav Petkov <borislav.petkov@amd.com>
Currently, we're allocating L3 cache info and calculating indices for
each online cpu which is clearly superfluous. Instead, we need to do
this per-node as is each L3 cache.
No functional change, only per-cpu memory savings.
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
---
arch/x86/kernel/cpu/intel_cacheinfo.c | 49 +++++++++++++++++++++++---------
1 files changed, 35 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index ff663ca..c42b5c5 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -307,19 +307,20 @@ struct _cache_attr {
};
#ifdef CONFIG_CPU_SUP_AMD
+
+/* max 8 nodes on a system */
+static struct amd_l3_cache * __cpuinitdata l3_caches[8];
+
+/*
+ * We're called over smp_call_function_single() and
+ * therefore are on the correct cpu.
+ */
static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
{
- /*
- * We're called over smp_call_function_single() and therefore
- * are on the correct cpu.
- */
- int cpu = smp_processor_id();
- int node = cpu_to_node(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
unsigned int sc0, sc1, sc2, sc3;
u32 val = 0;
- pci_read_config_dword(dev, 0x1C4, &val);
+ pci_read_config_dword(l3->dev, 0x1C4, &val);
/* calculate subcache sizes */
l3->subcaches[0] = sc0 = !(val & BIT(0));
@@ -328,13 +329,31 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
+static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
+{
+ struct amd_l3_cache *l3;
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+
+ l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
+ if (!l3) {
+ printk(KERN_WARNING "Error allocating L3 struct\n");
+ return NULL;
+ }
...
