Date:   Sat, 22 Oct 2016 06:19:57 -0700
From:   "Fenghua Yu" <fenghua.yu@...el.com>
To:     "Thomas Gleixner" <tglx@...utronix.de>
Cc:     "H. Peter Anvin" <h.peter.anvin@...el.com>,
        "Ingo Molnar" <mingo@...e.hu>, "Tony Luck" <tony.luck@...el.com>,
        "Peter Zijlstra" <peterz@...radead.org>,
        "Stephane Eranian" <eranian@...gle.com>,
        "Borislav Petkov" <bp@...e.de>,
        "Dave Hansen" <dave.hansen@...el.com>,
        "Nilay Vaish" <nilayvaish@...il.com>, "Shaohua Li" <shli@...com>,
        "David Carrillo-Cisneros" <davidcc@...gle.com>,
        "Ravi V Shankar" <ravi.v.shankar@...el.com>,
        "Sai Prakhya" <sai.praneeth.prakhya@...el.com>,
        "Vikas Shivappa" <vikas.shivappa@...ux.intel.com>,
        "linux-kernel" <linux-kernel@...r.kernel.org>,
        "x86" <x86@...nel.org>, "Fenghua Yu" <fenghua.yu@...el.com>
Subject: [PATCH v5 10/18] x86/intel_rdt: Build structures for each resource based on cache topology

From: Tony Luck <tony.luck@...el.com>

We use the cpu hotplug notifier to catch each cpu in turn and look at
its cache topology w.r.t each of the resource groups. As we discover
new resources, we initialize the bitmask array for each to the default
(full access) value.

Signed-off-by: Tony Luck <tony.luck@...el.com>
Signed-off-by: Fenghua Yu <fenghua.yu@...el.com>
---
 arch/x86/include/asm/intel_rdt.h |  35 ++++++++
 arch/x86/kernel/cpu/intel_rdt.c  | 175 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 210 insertions(+)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 9780409..c0d0a6e 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -39,6 +39,34 @@ struct rdt_resource {
 	int			cbm_idx_offset;
 };
 
+/**
+ * struct rdt_domain - group of cpus sharing an RDT resource
+ * @list:	all instances of this resource
+ * @id:		unique id for this instance
+ * @cpu_mask:	which cpus share this resource
+ * @cbm:	array of cache bit masks (indexed by CLOSID)
+ */
+struct rdt_domain {
+	struct list_head	list;
+	int			id;
+	struct cpumask		cpu_mask;
+	u32			*cbm;
+};
+
+/**
+ * struct msr_param - set a range of MSRs from a domain
+ * @res:       The resource to use
+ * @low:       Beginning index from base MSR
+ * @high:      End index
+ */
+struct msr_param {
+	struct rdt_resource	*res;
+	int			low;
+	int			high;
+};
+
+extern struct mutex rdtgroup_mutex;
+
 extern struct rdt_resource rdt_resources_all[];
 
 enum {
@@ -56,6 +84,11 @@ enum {
 	     r++) 							      \
 		if (r->capable)
 
+#define for_each_enabled_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->enabled)
+
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
 	struct {
@@ -71,4 +104,6 @@ union cpuid_0x10_1_edx {
 	} split;
 	unsigned int full;
 };
+
+void rdt_cbm_update(void *arg);
 #endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 157dc8d0..4ca9718 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -26,11 +26,16 @@
 
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/intel_rdt_common.h>
 #include <asm/intel-family.h>
 #include <asm/intel_rdt.h>
 
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
 struct rdt_resource rdt_resources_all[] = {
@@ -72,6 +77,11 @@ struct rdt_resource rdt_resources_all[] = {
 	},
 };
 
+static int cbm_idx(struct rdt_resource *r, int closid)
+{
+	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+}
+
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
  * as they do not have CPUID enumeration support for Cache allocation.
@@ -176,13 +186,178 @@ static inline bool get_rdt_resources(void)
 	return ret;
 }
 
+static int get_cache_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level)
+			return ci->info_list[i].id;
+	}
+
+	return -1;
+}
+
+void rdt_cbm_update(void *arg)
+{
+	struct msr_param *m = (struct msr_param *)arg;
+	struct rdt_resource *r = m->res;
+	int i, cpu = smp_processor_id();
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+			goto found;
+	}
+	pr_info_once("cpu %d not found in any domain for resource %s\n",
+		     cpu, r->name);
+
+	return;
+
+found:
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+}
+
+static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+					  struct list_head **pos)
+{
+	struct rdt_domain *d;
+	struct list_head *l;
+
+	if (id < 0)
+		return ERR_PTR(id);
+
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+	/*
+	 * No id is found in resource domains. Record the position
+	 * that the new domain will be added. The posistion is not used
+	 * when removing a domain.
+	 */
+	*pos = l;
+
+	return NULL;
+}
+
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
+{
+	int i, id = get_cache_id(cpu, r->cache_level);
+	struct list_head *add_pos = NULL;
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, &add_pos);
+	if (IS_ERR(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	if (d) {
+		cpumask_set_cpu(cpu, &d->cpu_mask);
+		return;
+	}
+
+	if (!add_pos) {
+		pr_warn("Couldn't add cpu %d in %s domain\n", cpu, r->name);
+		return;
+	}
+
+	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
+	if (!d)
+		return;
+
+	d->id = id;
+	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
+	if (!d->cbm) {
+		pr_warn("Failed to alloc CBM array for cpu %d\n", cpu);
+		kfree(d);
+		return;
+	}
+	for (i = 0; i < r->num_closid; i++) {
+		int idx = cbm_idx(r, i);
+
+		d->cbm[i] = r->max_cbm;
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+	cpumask_set_cpu(cpu, &d->cpu_mask);
+	list_add_tail(&d->list, add_pos);
+	r->num_domains++;
+}
+
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+	int id = get_cache_id(cpu, r->cache_level);
+	struct list_head *pos;
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, &pos);
+	if (IS_ERR_OR_NULL(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	cpumask_clear_cpu(cpu, &d->cpu_mask);
+	if (cpumask_empty(&d->cpu_mask)) {
+		r->num_domains--;
+		kfree(d->cbm);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+static int intel_rdt_online_cpu(unsigned int cpu)
+{
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_add_cpu(cpu, r);
+	state->closid = 0;
+	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int intel_rdt_offline_cpu(unsigned int cpu)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_remove_cpu(cpu, r);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
+	int state;
 
 	if (!get_rdt_resources())
 		return -ENODEV;
 
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				  "x86/rdt/cat:online:",
+				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+	if (state < 0)
+		return state;
+
 	for_each_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
 
-- 
2.5.0

Powered by blists - more mailing lists