[PATCH v3 6/6] pseries/sysfs: Minimise IPI noise while reading [idle_][s]purr

[Gautham R. Shenoy]

From: "Gautham R. Shenoy" <ego@xxxxxxxxxxxxxxxxxx>

Currently purr, spurr, idle_purr, idle_spurr are exposed for every CPU
via the sysfs interface
/sys/devices/system/cpu/cpuX/[idle_][s]purr. Each sysfs read currently
generates an IPI to obtain the desired value from the target CPU X.
Since these aforementioned sysfs files are typically read one after
another, we end up generating 4 IPIs per CPU in a short duration.

In order to minimize the IPI noise, this patch caches the values of
all the four entities whenever one of them is read. If subsequently
any of these are read within the next 10ms, the cached value is
returned. With this, we will generate at most one IPI every 10ms for
every CPU.

Test-results: While reading the four sysfs files back-to-back for a
given CPU every second for 100 seconds.

Without the patch:
		 16 [XICS 2 Edge IPI] = 422 times
		 DBL [Doorbell interrupts] = 13 times
		 Total : 435 IPIs.

With the patch:
		  16 [XICS 2 Edge IPI] = 111 times
		  DBL [Doorbell interrupts] = 17 times
		  Total : 128 IPIs.

Signed-off-by: Gautham R. Shenoy <ego@xxxxxxxxxxxxxxxxxx>
---
 arch/powerpc/kernel/sysfs.c | 109 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 90 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index c9ddb83..db8fc90 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -586,8 +586,6 @@ void ppc_enable_pmcs(void)
  * SPRs which are not related to PMU.
  */
 #ifdef CONFIG_PPC64
-SYSFS_SPRSETUP(purr, SPRN_PURR);
-SYSFS_SPRSETUP(spurr, SPRN_SPURR);
 SYSFS_SPRSETUP(pir, SPRN_PIR);
 SYSFS_SPRSETUP(tscr, SPRN_TSCR);
 
@@ -596,8 +594,6 @@ void ppc_enable_pmcs(void)
   enable write when needed with a separate function.
   Lets be conservative and default to pseries.
 */
-static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
-static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
 #endif /* CONFIG_PPC64 */
@@ -761,39 +757,114 @@ static void create_svm_file(void)
 }
 #endif /* CONFIG_PPC_SVM */
 
-static void read_idle_purr(void *val)
+/*
+ * The duration (in ms) from the last IPI to the target CPU until
+ * which a cached value of purr, spurr, idle_purr, idle_spurr can be
+ * reported to the user on a corresponding sysfs file read. Beyond
+ * this duration, fresh values need to be obtained by sending IPIs to
+ * the target CPU when the sysfs files are read.
+ */
+static unsigned long util_stats_staleness_tolerance_ms = 10;
+struct util_acct_stats {
+	u64 latest_purr;
+	u64 latest_spurr;
+	u64 latest_idle_purr;
+	u64 latest_idle_spurr;
+	unsigned long last_update_jiffies;
+};
+
+DEFINE_PER_CPU(struct util_acct_stats, util_acct_stats);
+
+static void update_util_acct_stats(void *ptr)
 {
-	u64 *ret = val;
+	struct util_acct_stats *stats = ptr;
 
-	*ret = read_this_idle_purr();
+	stats->latest_purr = mfspr(SPRN_PURR);
+	stats->latest_spurr = mfspr(SPRN_SPURR);
+	stats->latest_idle_purr = read_this_idle_purr();
+	stats->latest_idle_spurr = read_this_idle_spurr();
+	stats->last_update_jiffies = jiffies;
 }
 
-static ssize_t idle_purr_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
+struct util_acct_stats *get_util_stats_ptr(int cpu)
+{
+	struct util_acct_stats *stats = per_cpu_ptr(&util_acct_stats, cpu);
+	unsigned long delta_jiffies;
+
+	delta_jiffies = jiffies - stats->last_update_jiffies;
+
+	/*
+	 * If we have a recent enough data, reuse that instead of
+	 * sending an IPI.
+	 */
+	if (jiffies_to_msecs(delta_jiffies) < util_stats_staleness_tolerance_ms)
+		return stats;
+
+	smp_call_function_single(cpu, update_util_acct_stats, stats, 1);
+	return stats;
+}
+
+static ssize_t show_purr(struct device *dev,
+			 struct device_attribute *attr, char *buf)
 {
 	struct cpu *cpu = container_of(dev, struct cpu, dev);
-	u64 val;
+	struct util_acct_stats *stats;
 
-	smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
-	return sprintf(buf, "%llx\n", val);
+	stats = get_util_stats_ptr(cpu->dev.id);
+	return sprintf(buf, "%llx\n", stats->latest_purr);
 }
-static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
 
-static void read_idle_spurr(void *val)
+static void write_purr(void *val)
 {
-	u64 *ret = val;
+	mtspr(SPRN_PURR, *(unsigned long *)val);
+}
 
-	*ret = read_this_idle_spurr();
+static ssize_t __used store_purr(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	unsigned long val;
+	int ret = kstrtoul(buf, 16, &val);
+
+	if (ret != 0)
+		return -EINVAL;
+
+	smp_call_function_single(cpu->dev.id, write_purr, &val, 1);
+	return count;
+}
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
+
+static ssize_t show_spurr(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	struct util_acct_stats *stats;
+
+	stats = get_util_stats_ptr(cpu->dev.id);
+	return sprintf(buf, "%llx\n", stats->latest_spurr);
 }
+static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
+
+static ssize_t idle_purr_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	struct util_acct_stats *stats;
+
+	stats = get_util_stats_ptr(cpu->dev.id);
+	return sprintf(buf, "%llx\n", stats->latest_idle_purr);
+}
+static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
 
 static ssize_t idle_spurr_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct cpu *cpu = container_of(dev, struct cpu, dev);
-	u64 val;
+	struct util_acct_stats *stats;
 
-	smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
-	return sprintf(buf, "%llx\n", val);
+	stats =  get_util_stats_ptr(cpu->dev.id);
+	return sprintf(buf, "%llx\n", stats->latest_idle_spurr);
 }
 static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
 
-- 
1.9.4