Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/…

…lenb/linux.git

tools/power/x86/turbostat/turbostat.8

@@ -160,6 +160,10 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 .PP
 \fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval.  The system summary line shows the sum for all CPUs.  These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name.  While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system.
 .PP
+\fBC1+, C2+, C3+...\fP The idle governor idle state misprediction statistics. Inidcates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a deeper idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/below file.
+.PP
+\fBC1-, C2-, C3-...\fP The idle governor idle state misprediction statistics. Inidcates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a shallower idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/above file.
+.PP
 \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3....  The system summary is the average of all CPUs in the system.  Note that these are software, reflecting what was requested.  The hardware counters reflect what was actually achieved.
 .PP
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
@@ -199,6 +203,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 \fBUncMHz\fP per-package uncore MHz, instantaneous sample.
 .PP
 \fBUMHz1.0\fP per-package uncore MHz for domain=1 and fabric_cluster=0, instantaneous sample.  System summary is the average of all packages.
+For the "--show" and "--hide" options, use "UncMHz" to operate on all UMHz*.* as a group.
 .SH TOO MUCH INFORMATION EXAMPLE
 By default, turbostat dumps all possible information -- a system configuration header, followed by columns for all counters.
 This is ideal for remote debugging, use the "--out" option to save everything to a text file, and get that file to the expert helping you debug.

tools/power/x86/turbostat/turbostat.c

@@ -2211,7 +2211,7 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	return 0;
 }
 
-int probe_msr(int cpu, off_t offset)
+int probe_rapl_msr(int cpu, off_t offset, int index)
 {
 	ssize_t retval;
 	unsigned long long value;
@@ -2220,13 +2220,22 @@ int probe_msr(int cpu, off_t offset)
 
 	retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset);
 
-	/*
-	 * Expect MSRs to accumulate some non-zero value since the system was powered on.
-	 * Treat zero as a read failure.
-	 */
-	if (retval != sizeof(value) || value == 0)
+	/* if the read failed, the probe fails */
+	if (retval != sizeof(value))
 		return 1;
 
+	/* If an Energy Status Counter MSR returns 0, the probe fails */
+	switch (index) {
+	case RAPL_RCI_INDEX_ENERGY_PKG:
+	case RAPL_RCI_INDEX_ENERGY_CORES:
+	case RAPL_RCI_INDEX_DRAM:
+	case RAPL_RCI_INDEX_GFX:
+	case RAPL_RCI_INDEX_ENERGY_PLATFORM:
+		if (value == 0)
+			return 1;
+	}
+
+	/* PKG,DRAM_PERF_STATUS MSRs, can return any value */
 	return 0;
 }
 
@@ -6703,7 +6712,18 @@ static void probe_intel_uncore_frequency_cluster(void)
 		sprintf(path, "%s/current_freq_khz", path_base);
 		sprintf(name_buf, "UMHz%d.%d", domain_id, cluster_id);
 
-		add_counter(0, path, name_buf, 0, SCOPE_PACKAGE, COUNTER_K2M, FORMAT_AVERAGE, 0, package_id);
+		/*
+		 * Once add_couter() is called, that counter is always read
+		 * and reported -- So it is effectively (enabled & present).
+		 * Only call add_counter() here if legacy BIC_UNCORE_MHZ (UncMHz)
+		 * is (enabled).  Since we are in this routine, we
+		 * know we will not probe and set (present) the legacy counter.
+		 *
+		 * This allows "--show/--hide UncMHz" to be effective for
+		 * the clustered MHz counters, as a group.
+		 */
+		if BIC_IS_ENABLED(BIC_UNCORE_MHZ)
+			add_counter(0, path, name_buf, 0, SCOPE_PACKAGE, COUNTER_K2M, FORMAT_AVERAGE, 0, package_id);
 
 		if (quiet)
 			continue;
@@ -7896,7 +7916,7 @@ void rapl_perf_init(void)
 					rci->flags[cai->rci_index] = cai->flags;
 
 					/* Use MSR for this counter */
-				} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+				} else if (!no_msr && cai->msr && probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
 					rci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
 					rci->msr[cai->rci_index] = cai->msr;
 					rci->msr_mask[cai->rci_index] = cai->msr_mask;
@@ -8034,7 +8054,7 @@ void msr_perf_init_(void)
 					cai->present = true;
 
 					/* User MSR for this counter */
-				} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+				} else if (!no_msr && cai->msr && probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
 					cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
 					cci->msr[cai->rci_index] = cai->msr;
 					cci->msr_mask[cai->rci_index] = cai->msr_mask;
@@ -8148,7 +8168,7 @@ void cstate_perf_init_(bool soft_c1)
 
 					/* User MSR for this counter */
 				} else if (!no_msr && cai->msr && pkg_cstate_limit >= cai->pkg_cstate_limit
-					   && probe_msr(cpu, cai->msr) == 0) {
+					   && probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
 					cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
 					cci->msr[cai->rci_index] = cai->msr;
 				}
@@ -9592,7 +9612,7 @@ struct msr_counter *find_msrp_by_name(struct msr_counter *head, char *name)
 	for (mp = head; mp; mp = mp->next) {
 		if (debug)
 			fprintf(stderr, "%s: %s %s\n", __func__, name, mp->name);
-		if (!strncmp(name, mp->name, strlen(mp->name)))
+		if (!strcmp(name, mp->name))
 			return mp;
 	}
 	return NULL;
@@ -10245,6 +10265,7 @@ void probe_sysfs(void)
 	char name_buf[16];
 	FILE *input;
 	int state;
+	int min_state = 1024, max_state = 0;
 	char *sp;
 
 	for (state = 10; state >= 0; --state) {
@@ -10276,6 +10297,11 @@ void probe_sysfs(void)
 			continue;
 
 		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC, FORMAT_PERCENT, SYSFS_PERCPU, 0);
+
+		if (state > max_state)
+			max_state = state;
+		if (state < min_state)
+			min_state = state;
 	}
 
 	for (state = 10; state >= 0; --state) {
@@ -10286,26 +10312,52 @@ void probe_sysfs(void)
 			continue;
 		if (!fgets(name_buf, sizeof(name_buf), input))
 			err(1, "%s: failed to read file", path);
-		/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
-		sp = strchr(name_buf, '-');
-		if (!sp)
-			sp = strchrnul(name_buf, '\n');
-		*sp = '\0';
 		fclose(input);
 
 		remove_underbar(name_buf);
 
-		sprintf(path, "cpuidle/state%d/usage", state);
-
 		if (!DO_BIC(BIC_sysfs) && !is_deferred_add(name_buf))
 			continue;
 
 		if (is_deferred_skip(name_buf))
 			continue;
 
+		/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+		sp = strchr(name_buf, '-');
+		if (!sp)
+			sp = strchrnul(name_buf, '\n');
+
+		/*
+		 * The 'below' sysfs file always contains 0 for the deepest state (largest index),
+		 * do not add it.
+		 */
+		if (state != max_state) {
+			/*
+			 * Add 'C1+' for C1, and so on. The 'below' sysfs file always contains 0 for
+			 * the last state, so do not add it.
+			 */
+
+			*sp = '+';
+			*(sp + 1) = '\0';
+			sprintf(path, "cpuidle/state%d/below", state);
+			add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+		}
+
+		*sp = '\0';
+		sprintf(path, "cpuidle/state%d/usage", state);
 		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
-	}
 
+		/*
+		 * The 'above' sysfs file always contains 0 for the shallowest state (smallest
+		 * index), do not add it.
+		 */
+		if (state != min_state) {
+			*sp = '-';
+			*(sp + 1) = '\0';
+			sprintf(path, "cpuidle/state%d/above", state);
+			add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+		}
+	}
 }
 
 /*