[PATCH 2/5] x86/mbm: Intel Memory B/W Monitoring enumeration and init

[Vikas Shivappa]

The MBM init patch enumerates the Intel (Memory b/w monitoring)MBM and
initializes the perf events and datastructures for monitoring the memory
b/w. Its based on original patch series by Kanaka Juvva.

Memory bandwidth monitoring(MBM) provides OS/VMM a way to monitor
bandwidth from one level of cache to another. The current patches
support L3 external bandwidth monitoring. It supports both 'local
bandwidth' and 'total bandwidth' monitoring for the socket. Local
bandwidth measures the amount of data sent through the memory controller
on the socket and total b/w measures the total system bandwidth.

Extending the cache quality of service monitoring(CQM) we add four more
events to the perf infrastructure:
intel_cqm_llc/local_bytes - bytes sent through local socket memory
controller
intel_cqm_llc/total_bytes - total L3 external bytes sent
intel_cqm_llc/local_bw - Current local b/w
intel_cqm_llc/total_bw - current total b/w

The tasks are associated with a Resouce Monitoring ID(RMID) just like in
cqm and OS uses a MSR write to indicate the RMID of the task during
scheduling.

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/cpufeature.h          |   2 +
 arch/x86/kernel/cpu/common.c               |   4 +-
 arch/x86/kernel/cpu/perf_event_intel_cqm.c | 172 +++++++++++++++++++++++++++--
 3 files changed, 169 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 7ad8c94..fd80ef6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -241,6 +241,8 @@
 
 /* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
 #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring  */
+#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring  */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 37830de..f770221 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -635,7 +635,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
 			c->x86_capability[CPUID_F_1_EDX] = edx;
 
-			if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) {
+			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
+			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
+			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
 				c->x86_cache_max_rmid = ecx;
 				c->x86_cache_occ_scale = ebx;
 			}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e6be335..e45f5aa 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -15,6 +15,8 @@
 
 static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
+static bool cqm_enabled, mbm_enabled;
+static u16  mbm_socket_max;
 
 /**
  * struct intel_pqr_state - State cache for the PQR MSR
@@ -42,6 +44,30 @@ struct intel_pqr_state {
  * interrupts disabled, which is sufficient for the protection.
  */
 static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+/**
+ * struct sample - mbm event's (local or total) data
+ * @interval_start Time this interval began
+ * @interval_bytes #bytes in this interval
+ * @total_bytes    #bytes since we began monitoring
+ * @prev_msr       previous value of MSR
+ * @bandwidth      bytes/sec in previous completed interval
+ */
+struct sample {
+	ktime_t interval_start;
+	u64	interval_bytes;
+	u64	total_bytes;
+	u64	prev_msr;
+	u64	bandwidth;
+};
+
+/*
+ * samples profiled for total memory bandwidth type events
+ */
+static struct sample *mbm_total;
+/*
+ * samples profiled for local memory bandwidth type events
+ */
+static struct sample *mbm_local;
 
 /*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -1152,6 +1178,28 @@ EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes");
 EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL);
 EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1");
 
+EVENT_ATTR_STR(total_bytes, intel_cqm_total_bytes, "event=0x02");
+EVENT_ATTR_STR(total_bytes.per-pkg, intel_cqm_total_bytes_pkg, "1");
+EVENT_ATTR_STR(total_bytes.unit, intel_cqm_total_bytes_unit, "MB");
+EVENT_ATTR_STR(total_bytes.scale, intel_cqm_total_bytes_scale, "1e-6");
+
+EVENT_ATTR_STR(local_bytes, intel_cqm_local_bytes, "event=0x03");
+EVENT_ATTR_STR(local_bytes.per-pkg, intel_cqm_local_bytes_pkg, "1");
+EVENT_ATTR_STR(local_bytes.unit, intel_cqm_local_bytes_unit, "MB");
+EVENT_ATTR_STR(local_bytes.scale, intel_cqm_local_bytes_scale, "1e-6");
+
+EVENT_ATTR_STR(total_bw, intel_cqm_total_bw, "event=0x04");
+EVENT_ATTR_STR(total_bw.per-pkg, intel_cqm_total_bw_pkg, "1");
+EVENT_ATTR_STR(total_bw.unit, intel_cqm_total_bw_unit, "MB/sec");
+EVENT_ATTR_STR(total_bw.scale, intel_cqm_total_bw_scale, "1e-6");
+EVENT_ATTR_STR(total_bw.snapshot, intel_cqm_total_bw_snapshot, "1");
+
+EVENT_ATTR_STR(local_bw, intel_cqm_local_bw, "event=0x05");
+EVENT_ATTR_STR(local_bw.per-pkg, intel_cqm_local_bw_pkg, "1");
+EVENT_ATTR_STR(local_bw.unit, intel_cqm_local_bw_unit, "MB/sec");
+EVENT_ATTR_STR(local_bw.scale, intel_cqm_local_bw_scale, "1e-6");
+EVENT_ATTR_STR(local_bw.snapshot, intel_cqm_local_bw_snapshot, "1");
+
 static struct attribute *intel_cqm_events_attr[] = {
 	EVENT_PTR(intel_cqm_llc),
 	EVENT_PTR(intel_cqm_llc_pkg),
@@ -1161,9 +1209,58 @@ static struct attribute *intel_cqm_events_attr[] = {
 	NULL,
 };
 
+static struct attribute *intel_mbm_events_attr[] = {
+	EVENT_PTR(intel_cqm_total_bytes),
+	EVENT_PTR(intel_cqm_local_bytes),
+	EVENT_PTR(intel_cqm_total_bw),
+	EVENT_PTR(intel_cqm_local_bw),
+	EVENT_PTR(intel_cqm_total_bytes_pkg),
+	EVENT_PTR(intel_cqm_local_bytes_pkg),
+	EVENT_PTR(intel_cqm_total_bw_pkg),
+	EVENT_PTR(intel_cqm_local_bw_pkg),
+	EVENT_PTR(intel_cqm_total_bytes_unit),
+	EVENT_PTR(intel_cqm_local_bytes_unit),
+	EVENT_PTR(intel_cqm_total_bw_unit),
+	EVENT_PTR(intel_cqm_local_bw_unit),
+	EVENT_PTR(intel_cqm_total_bytes_scale),
+	EVENT_PTR(intel_cqm_local_bytes_scale),
+	EVENT_PTR(intel_cqm_total_bw_scale),
+	EVENT_PTR(intel_cqm_local_bw_scale),
+	EVENT_PTR(intel_cqm_total_bw_snapshot),
+	EVENT_PTR(intel_cqm_local_bw_snapshot),
+	NULL,
+};
+
+static struct attribute *intel_cmt_mbm_events_attr[] = {
+	EVENT_PTR(intel_cqm_llc),
+	EVENT_PTR(intel_cqm_total_bytes),
+	EVENT_PTR(intel_cqm_local_bytes),
+	EVENT_PTR(intel_cqm_total_bw),
+	EVENT_PTR(intel_cqm_local_bw),
+	EVENT_PTR(intel_cqm_llc_pkg),
+	EVENT_PTR(intel_cqm_total_bytes_pkg),
+	EVENT_PTR(intel_cqm_local_bytes_pkg),
+	EVENT_PTR(intel_cqm_total_bw_pkg),
+	EVENT_PTR(intel_cqm_local_bw_pkg),
+	EVENT_PTR(intel_cqm_llc_unit),
+	EVENT_PTR(intel_cqm_total_bytes_unit),
+	EVENT_PTR(intel_cqm_local_bytes_unit),
+	EVENT_PTR(intel_cqm_total_bw_unit),
+	EVENT_PTR(intel_cqm_local_bw_unit),
+	EVENT_PTR(intel_cqm_llc_scale),
+	EVENT_PTR(intel_cqm_total_bytes_scale),
+	EVENT_PTR(intel_cqm_local_bytes_scale),
+	EVENT_PTR(intel_cqm_total_bw_scale),
+	EVENT_PTR(intel_cqm_local_bw_scale),
+	EVENT_PTR(intel_cqm_llc_snapshot),
+	EVENT_PTR(intel_cqm_total_bw_snapshot),
+	EVENT_PTR(intel_cqm_local_bw_snapshot),
+	NULL,
+};
+
 static struct attribute_group intel_cqm_events_group = {
 	.name = "events",
-	.attrs = intel_cqm_events_attr,
+	.attrs = NULL,
 };
 
 PMU_FORMAT_ATTR(event, "config:0-7");
@@ -1320,12 +1417,51 @@ static const struct x86_cpu_id intel_cqm_match[] = {
 	{}
 };
 
+static const struct x86_cpu_id intel_mbm_local_match[] = {
+	{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_LOCAL },
+	{}
+};
+
+static const struct x86_cpu_id intel_mbm_total_match[] = {
+	{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_TOTAL },
+	{}
+};
+
+static int intel_mbm_init(void)
+{
+	int ret = 0, array_size, maxid = cqm_max_rmid + 1;
+
+	mbm_socket_max = cpumask_weight(&cqm_cpumask);
+	array_size = sizeof(struct sample) * maxid * mbm_socket_max;
+	mbm_local = kmalloc(array_size, GFP_KERNEL);
+	if (!mbm_local) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	mbm_total = kmalloc(array_size, GFP_KERNEL);
+	if (!mbm_total) {
+		kfree(mbm_local);
+		ret = -ENOMEM;
+	}
+out:
+
+	return ret;
+}
+
 static int __init intel_cqm_init(void)
 {
-	char *str, scale[20];
+	char *str = NULL, scale[20];
 	int i, cpu, ret;
 
-	if (!x86_match_cpu(intel_cqm_match))
+	if (x86_match_cpu(intel_cqm_match))
+		cqm_enabled = true;
+
+	if (x86_match_cpu(intel_mbm_local_match) &&
+	     x86_match_cpu(intel_mbm_total_match))
+		mbm_enabled = true;
+
+	if (!cqm_enabled && !mbm_enabled)
 		return -ENODEV;
 
 	cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale;
@@ -1384,14 +1520,34 @@ static int __init intel_cqm_init(void)
 
 	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 
-	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
-	if (ret)
-		pr_err("Intel CQM perf registration failed: %d\n", ret);
-	else
-		pr_info("Intel CQM monitoring enabled\n");
+	if (mbm_enabled)
+		ret = intel_mbm_init();
+	if (ret && !cqm_enabled)
+		goto out;
+
+	if (cqm_enabled && mbm_enabled)
+		intel_cqm_events_group.attrs = intel_cmt_mbm_events_attr;
+	else if (!cqm_enabled && mbm_enabled)
+		intel_cqm_events_group.attrs = intel_mbm_events_attr;
+	else if (cqm_enabled && !mbm_enabled)
+		intel_cqm_events_group.attrs = intel_cqm_events_attr;
 
+	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
+	if (ret) {
+		pr_err("Intel CQM MBM perf registration failed: %d\n", ret);
+	} else {
+		if (cqm_enabled)
+			pr_info("Intel CQM monitoring enabled\n");
+		if (mbm_enabled)
+			pr_info("Intel MBM enabled\n");
+	}
 out:
 	cpu_notifier_register_done();
+	if (ret) {
+		mbm_enabled = false;
+		cqm_enabled = false;
+		kfree(str);
+	}
 
 	return ret;
 }
-- 
1.9.1