[PATCH 8/9] x86/intel_rdt: Hot cpu support for Cache Allocation

[Vikas Shivappa <vikas.shivappa@linux.intel.com>]

This patch adds hot cpu support for Intel Cache allocation. Support
includes updating the cache bitmask MSRs IA32_L3_QOS_n when a new CPU
package comes online. The IA32_L3_QOS_n MSRs are one per Class of
service on each CPU package. The new package's MSRs are synchronized
with the values of existing MSRs. Also the software cache for
IA32_PQR_ASSOC MSRs are reset during hot cpu notifications.

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
---
 arch/x86/kernel/cpu/intel_rdt.c | 95 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 90 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 06cba8da..f151200 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/spinlock.h>
+#include <linux/cpu.h>
 #include <asm/intel_rdt.h>
 
 /*
@@ -40,6 +41,11 @@ struct static_key __read_mostly rdt_enable_key = STATIC_KEY_INIT_FALSE;
  * Mask of CPUs for writing CBM values. We only need one CPU per-socket.
  */
 static cpumask_t rdt_cpumask;
+/*
+ * Temporary cpumask used during hot cpu notificaiton handling. The usage
+ * is serialized by hot cpu locks.
+ */
+static cpumask_t tmp_cpumask;
 
 #define rdt_for_each_child(pos_css, parent_ir)		\
 	css_for_each_child((pos_css), &(parent_ir)->css)
@@ -311,13 +317,86 @@ out:
 	return err;
 }
 
-static inline void rdt_cpumask_update(int cpu)
+static inline bool rdt_cpumask_update(int cpu)
 {
-	static cpumask_t tmp;
-
-	cpumask_and(&tmp, &rdt_cpumask, topology_core_cpumask(cpu));
-	if (cpumask_empty(&tmp))
+	cpumask_and(&tmp_cpumask, &rdt_cpumask, topology_core_cpumask(cpu));
+	if (cpumask_empty(&tmp_cpumask)) {
 		cpumask_set_cpu(cpu, &rdt_cpumask);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * cbm_update_msrs() - Updates all the existing IA32_L3_MASK_n MSRs
+ * which are one per CLOSid except IA32_L3_MASK_0 on the current package.
+ */
+static void cbm_update_msrs(void *info)
+{
+	int maxid = boot_cpu_data.x86_cache_max_closid;
+	unsigned int i;
+
+	/*
+	 * At cpureset, all bits of IA32_L3_MASK_n are set.
+	 * The index starts from one as there is no need
+	 * to update IA32_L3_MASK_0 as it belongs to root cgroup
+	 * whose cache mask is all 1s always.
+	 */
+	for (i = 1; i < maxid; i++) {
+		if (cctable[i].clos_refcnt)
+			cbm_cpu_update((void *)i);
+	}
+}
+
+static inline void intel_rdt_cpu_start(int cpu)
+{
+	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
+
+	state->closid = 0;
+	mutex_lock(&rdt_group_mutex);
+	if (rdt_cpumask_update(cpu))
+		smp_call_function_single(cpu, cbm_update_msrs, NULL, 1);
+	mutex_unlock(&rdt_group_mutex);
+}
+
+static void intel_rdt_cpu_exit(unsigned int cpu)
+{
+	int i;
+
+	mutex_lock(&rdt_group_mutex);
+	if (!cpumask_test_and_clear_cpu(cpu, &rdt_cpumask)) {
+		mutex_unlock(&rdt_group_mutex);
+		return;
+	}
+
+	cpumask_and(&tmp_cpumask, topology_core_cpumask(cpu), cpu_online_mask);
+	cpumask_clear_cpu(cpu, &tmp_cpumask);
+	i = cpumask_any(&tmp_cpumask);
+
+	if (i < nr_cpu_ids)
+		cpumask_set_cpu(i, &rdt_cpumask);
+	mutex_unlock(&rdt_group_mutex);
+}
+
+static int intel_rdt_cpu_notifier(struct notifier_block *nb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned int cpu  = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+		intel_rdt_cpu_start(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		intel_rdt_cpu_exit(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
 }
 
 static int __init intel_rdt_late_init(void)
@@ -355,9 +434,15 @@ static int __init intel_rdt_late_init(void)
 	cct->l3_cbm = (1ULL << max_cbm_len) - 1;
 	cct->clos_refcnt = 1;
 
+	cpu_notifier_register_begin();
+
 	for_each_online_cpu(i)
 		rdt_cpumask_update(i);
 
+	__hotcpu_notifier(intel_rdt_cpu_notifier, 0);
+
+	cpu_notifier_register_done();
+
 	static_key_slow_inc(&rdt_enable_key);
 	pr_info("Intel cache allocation enabled\n");
 out_err:
-- 
1.9.1