Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux

Pull ACPI & Power Management changes from Len Brown:
 - ACPI 5.0 after-ripples, ACPICA/Linux divergence cleanup
 - cpuidle evolving, more ARM use
 - thermal sub-system evolving, ditto
 - assorted other PM bits

Fix up conflicts in various cpuidle implementations due to ARM cpuidle
cleanups (ARM at91 self-refresh and cpu idle code rewritten into
"standby" in asm conflicting with the consolidation of cpuidle time
keeping), trivial SH include file context conflict and RCU tracing fixes
in generic code.

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux: (77 commits)
  ACPI throttling: fix endian bug in acpi_read_throttling_status()
  Disable MCP limit exceeded messages from Intel IPS driver
  ACPI video: Don't start video device until its associated input device has been allocated
  ACPI video: Harden video bus adding.
  ACPI: Add support for exposing BGRT data
  ACPI: export acpi_kobj
  ACPI: Fix logic for removing mappings in 'acpi_unmap'
  CPER failed to handle generic error records with multiple sections
  ACPI: Clean redundant codes in scan.c
  ACPI: Fix unprotected smp_processor_id() in acpi_processor_cst_has_changed()
  ACPI: consistently use should_use_kmap()
  PNPACPI: Fix device ref leaking in acpi_pnp_match
  ACPI: Fix use-after-free in acpi_map_lsapic
  ACPI: processor_driver: add missing kfree
  ACPI, APEI: Fix incorrect APEI register bit width check and usage
  Update documentation for parameter *notrigger* in einj.txt
  ACPI, APEI, EINJ, new parameter to control trigger action
  ACPI, APEI, EINJ, limit the range of einj_param
  ACPI, APEI, Fix ERST header length check
  cpuidle: power_usage should be declared signed integer
  ...

2 files changed, 224 insertions, 120 deletions

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 555c69a5592..adf175f6149 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -4,11 +4,13 @@ turbostat \- Report processor frequency and idle statistics
 .SH SYNOPSIS
 .ft B
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB command
 .br
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB [ "\-i interval_sec" ]
@@ -25,6 +27,8 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
 on processors that additionally support C-state residency counters.
 
 .SS Options
+The \fB-s\fP option prints only a 1-line summary for each sample interval.
+.PP
 The \fB-v\fP option increases verbosity.
 .PP
 The \fB-M MSR#\fP option dumps the specified MSR,
@@ -39,13 +43,14 @@ displays the statistics gathered since it was forked.
 .SH FIELD DESCRIPTIONS
 .nf
 \fBpk\fP processor package number.
-\fBcr\fP processor core number.
+\fBcor\fP processor core number.
 \fBCPU\fP Linux CPU (logical processor) number.
+Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
 \fB%c0\fP percent of the interval that the CPU retired instructions.
 \fBGHz\fP average clock rate while the CPU was in c0 state.
 \fBTSC\fP average GHz that the TSC ran during the entire interval.
-\fB%c1, %c3, %c6\fP show the percentage residency in hardware core idle states.
-\fB%pc3, %pc6\fP percentage residency in hardware package idle states.
+\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
+\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
 .fi
 .PP
 .SH EXAMPLE
@@ -53,25 +58,37 @@ Without any parameters, turbostat prints out counters ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
 
-The first row of statistics reflect the average for the entire system.
+The first row of statistics is a summary for the entire system.
+Note that the summary is a weighted average.
 Subsequent rows show per-CPU statistics.
 
 .nf
 [root@x980]# ./turbostat
-cr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-          0.04 1.62 3.38   0.11   0.00  99.85   0.00  95.07
-  0   0   0.04 1.62 3.38   0.06   0.00  99.90   0.00  95.07
-  0   6   0.02 1.62 3.38   0.08   0.00  99.90   0.00  95.07
-  1   2   0.10 1.62 3.38   0.29   0.00  99.61   0.00  95.07
-  1   8   0.11 1.62 3.38   0.28   0.00  99.61   0.00  95.07
-  2   4   0.01 1.62 3.38   0.01   0.00  99.98   0.00  95.07
-  2  10   0.01 1.61 3.38   0.02   0.00  99.98   0.00  95.07
-  8   1   0.07 1.62 3.38   0.15   0.00  99.78   0.00  95.07
-  8   7   0.03 1.62 3.38   0.19   0.00  99.78   0.00  95.07
-  9   3   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
-  9   9   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
- 10   5   0.01 1.62 3.38   0.13   0.00  99.86   0.00  95.07
- 10  11   0.08 1.62 3.38   0.05   0.00  99.86   0.00  95.07
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          0.60 1.63 3.38   2.91   0.00  96.49   0.00  76.64
+  0   0   0.59 1.62 3.38   4.51   0.00  94.90   0.00  76.64
+  0   6   1.13 1.64 3.38   3.97   0.00  94.90   0.00  76.64
+  1   2   0.08 1.62 3.38   0.07   0.00  99.85   0.00  76.64
+  1   8   0.03 1.62 3.38   0.12   0.00  99.85   0.00  76.64
+  2   4   0.01 1.62 3.38   0.06   0.00  99.93   0.00  76.64
+  2  10   0.04 1.62 3.38   0.02   0.00  99.93   0.00  76.64
+  8   1   2.85 1.62 3.38  11.71   0.00  85.44   0.00  76.64
+  8   7   1.98 1.62 3.38  12.58   0.00  85.44   0.00  76.64
+  9   3   0.36 1.62 3.38   0.71   0.00  98.93   0.00  76.64
+  9   9   0.09 1.62 3.38   0.98   0.00  98.93   0.00  76.64
+ 10   5   0.03 1.62 3.38   0.09   0.00  99.87   0.00  76.64
+ 10  11   0.07 1.62 3.38   0.06   0.00  99.87   0.00  76.64
+.fi
+.SH SUMMARY EXAMPLE
+The "-s" option prints the column headers just once,
+and then the one line system summary for each sample interval.
+
+.nf
+[root@x980]# ./turbostat -s
+   %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+  0.61 1.89 3.38   5.95   0.00  93.44   0.00  66.33
+  0.52 1.62 3.38   6.83   0.00  92.65   0.00  61.11
+  0.62 1.92 3.38   5.47   0.00  93.91   0.00  67.31
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -101,33 +118,33 @@ until ^C while the other CPUs are mostly idle:
 
 .nf
 [root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
-
-^Ccr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-           8.49 3.63 3.38  16.23   0.66  74.63   0.00   0.00
-   0   0   1.22 3.62 3.38  32.18   0.00  66.60   0.00   0.00
-   0   6   0.40 3.61 3.38  33.00   0.00  66.60   0.00   0.00
-   1   2   0.11 3.14 3.38   0.19   3.95  95.75   0.00   0.00
-   1   8   0.05 2.88 3.38   0.25   3.95  95.75   0.00   0.00
-   2   4   0.00 3.13 3.38   0.02   0.00  99.98   0.00   0.00
-   2  10   0.00 3.09 3.38   0.02   0.00  99.98   0.00   0.00
-   8   1   0.04 3.50 3.38  14.43   0.00  85.54   0.00   0.00
-   8   7   0.03 2.98 3.38  14.43   0.00  85.54   0.00   0.00
-   9   3   0.00 3.16 3.38 100.00   0.00   0.00   0.00   0.00
-   9   9  99.93 3.63 3.38   0.06   0.00   0.00   0.00   0.00
-  10   5   0.01 2.82 3.38   0.08   0.00  99.91   0.00   0.00
-  10  11   0.02 3.36 3.38   0.06   0.00  99.91   0.00   0.00
-6.950866 sec
+^C
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          8.63 3.64 3.38  14.46   0.49  76.42   0.00   0.00
+  0   0   0.34 3.36 3.38  99.66   0.00   0.00   0.00   0.00
+  0   6  99.96 3.64 3.38   0.04   0.00   0.00   0.00   0.00
+  1   2   0.14 3.50 3.38   1.75   2.04  96.07   0.00   0.00
+  1   8   0.38 3.57 3.38   1.51   2.04  96.07   0.00   0.00
+  2   4   0.01 2.65 3.38   0.06   0.00  99.93   0.00   0.00
+  2  10   0.03 2.12 3.38   0.04   0.00  99.93   0.00   0.00
+  8   1   0.91 3.59 3.38  35.27   0.92  62.90   0.00   0.00
+  8   7   1.61 3.63 3.38  34.57   0.92  62.90   0.00   0.00
+  9   3   0.04 3.38 3.38   0.20   0.00  99.76   0.00   0.00
+  9   9   0.04 3.29 3.38   0.20   0.00  99.76   0.00   0.00
+ 10   5   0.03 3.08 3.38   0.12   0.00  99.85   0.00   0.00
+ 10  11   0.05 3.07 3.38   0.10   0.00  99.85   0.00   0.00
+4.907015 sec
 
 .fi
-Above the cycle soaker drives cpu9 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu3 is an HT sibling sharing core9
-with cpu9, and thus it is unable to get to an idle state
-deeper than c1 while cpu9 is busy.
+Note that cpu0 is an HT sibling sharing core0
+with cpu6, and thus it is unable to get to an idle state
+deeper than c1 while cpu6 is busy.
 
-Note that turbostat reports average GHz of 3.61, while
-the arithmetic average of the GHz column above is 3.24.
+Note that turbostat reports average GHz of 3.64, while
+the arithmetic average of the GHz column above is lower.
 This is a weighted average, where the weight is %c0.  ie. it is the total number of
 un-halted cycles elapsed per time divided by the number of CPUs.
 .SH NOTES
@@ -167,6 +184,6 @@ http://www.intel.com/products/processor/manuals/
 .SH "SEE ALSO"
 msr(4), vmstat(8)
 .PP
-.SH AUTHORS
+.SH AUTHOR
 .nf
 Written by Len Brown <len.brown@intel.com>
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 310d3dd5e54..ab2f682fd44 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2,7 +2,7 @@
  * turbostat -- show CPU frequency and C-state residency
  * on modern Intel turbo-capable processors.
  *
- * Copyright (c) 2010, Intel Corporation.
+ * Copyright (c) 2012 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -19,6 +19,7 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#define _GNU_SOURCE
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -32,6 +33,7 @@
 #include <dirent.h>
 #include <string.h>
 #include <ctype.h>
+#include <sched.h>
 
 #define MSR_TSC	0x10
 #define MSR_NEHALEM_PLATFORM_INFO	0xCE
@@ -49,6 +51,7 @@
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
 unsigned int verbose;		/* set with -v */
+unsigned int summary_only;	/* set with -s */
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
@@ -68,9 +71,10 @@ unsigned int show_cpu;
 int aperf_mperf_unstable;
 int backwards_count;
 char *progname;
-int need_reinitialize;
 
 int num_cpus;
+cpu_set_t *cpu_mask;
+size_t cpu_mask_size;
 
 struct counters {
 	unsigned long long tsc;		/* per thread */
@@ -99,44 +103,76 @@ struct timeval tv_even;
 struct timeval tv_odd;
 struct timeval tv_delta;
 
-unsigned long long get_msr(int cpu, off_t offset)
+/*
+ * cpu_mask_init(ncpus)
+ *
+ * allocate and clear cpu_mask
+ * set cpu_mask_size
+ */
+void cpu_mask_init(int ncpus)
+{
+	cpu_mask = CPU_ALLOC(ncpus);
+	if (cpu_mask == NULL) {
+		perror("CPU_ALLOC");
+		exit(3);
+	}
+	cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+}
+
+void cpu_mask_uninit()
+{
+	CPU_FREE(cpu_mask);
+	cpu_mask = NULL;
+	cpu_mask_size = 0;
+}
+
+int cpu_migrate(int cpu)
+{
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+	CPU_SET_S(cpu, cpu_mask_size, cpu_mask);
+	if (sched_setaffinity(0, cpu_mask_size, cpu_mask) == -1)
+		return -1;
+	else
+		return 0;
+}
+
+int get_msr(int cpu, off_t offset, unsigned long long *msr)
 {
 	ssize_t retval;
-	unsigned long long msr;
 	char pathname[32];
 	int fd;
 
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
-	if (fd < 0) {
-		perror(pathname);
-		need_reinitialize = 1;
-		return 0;
-	}
-
-	retval = pread(fd, &msr, sizeof msr, offset);
-	if (retval != sizeof msr) {
-		fprintf(stderr, "cpu%d pread(..., 0x%zx) = %jd\n",
-			cpu, offset, retval);
-		exit(-2);
-	}
+	if (fd < 0)
+		return -1;
 
+	retval = pread(fd, msr, sizeof *msr, offset);
 	close(fd);
-	return msr;
+
+	if (retval != sizeof *msr)
+		return -1;
+
+	return 0;
 }
 
 void print_header(void)
 {
 	if (show_pkg)
 		fprintf(stderr, "pk");
+	if (show_pkg)
+		fprintf(stderr, " ");
 	if (show_core)
-		fprintf(stderr, " cr");
+		fprintf(stderr, "cor");
 	if (show_cpu)
 		fprintf(stderr, " CPU");
+	if (show_pkg || show_core || show_cpu)
+		fprintf(stderr, " ");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c0 ");
+		fprintf(stderr, "   %%c0");
 	if (has_aperf)
-		fprintf(stderr, " GHz");
+		fprintf(stderr, "  GHz");
 	fprintf(stderr, "  TSC");
 	if (do_nhm_cstates)
 		fprintf(stderr, "    %%c1");
@@ -147,13 +183,13 @@ void print_header(void)
 	if (do_snb_cstates)
 		fprintf(stderr, "    %%c7");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc2");
+		fprintf(stderr, "   %%pc2");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc3");
+		fprintf(stderr, "   %%pc3");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc6");
+		fprintf(stderr, "   %%pc6");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc7");
+		fprintf(stderr, "   %%pc7");
 	if (extra_msr_offset)
 		fprintf(stderr, "        MSR 0x%x ", extra_msr_offset);
 
@@ -187,6 +223,15 @@ void dump_list(struct counters *cnt)
 		dump_cnt(cnt);
 }
 
+/*
+ * column formatting convention & formats
+ * package: "pk" 2 columns %2d
+ * core: "cor" 3 columns %3d
+ * CPU: "CPU" 3 columns %3d
+ * GHz: "GHz" 3 columns %3.2
+ * TSC: "TSC" 3 columns %3.2
+ * percentage " %pc3" %6.2
+ */
 void print_cnt(struct counters *p)
 {
 	double interval_float;
@@ -196,39 +241,45 @@ void print_cnt(struct counters *p)
 	/* topology columns, print blanks on 1st (average) line */
 	if (p == cnt_average) {
 		if (show_pkg)
+			fprintf(stderr, "  ");
+		if (show_pkg && show_core)
 			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "    ");
+			fprintf(stderr, "   ");
 		if (show_cpu)
-			fprintf(stderr, "    ");
+			fprintf(stderr, " " "   ");
 	} else {
 		if (show_pkg)
-			fprintf(stderr, "%d", p->pkg);
+			fprintf(stderr, "%2d", p->pkg);
+		if (show_pkg && show_core)
+			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "%4d", p->core);
+			fprintf(stderr, "%3d", p->core);
 		if (show_cpu)
-			fprintf(stderr, "%4d", p->cpu);
+			fprintf(stderr, " %3d", p->cpu);
 	}
 
 	/* %c0 */
 	if (do_nhm_cstates) {
+		if (show_pkg || show_core || show_cpu)
+			fprintf(stderr, " ");
 		if (!skip_c0)
-			fprintf(stderr, "%7.2f", 100.0 * p->mperf/p->tsc);
+			fprintf(stderr, "%6.2f", 100.0 * p->mperf/p->tsc);
 		else
-			fprintf(stderr, "   ****");
+			fprintf(stderr, "  ****");
 	}
 
 	/* GHz */
 	if (has_aperf) {
 		if (!aperf_mperf_unstable) {
-			fprintf(stderr, "%5.2f",
+			fprintf(stderr, " %3.2f",
 				1.0 * p->tsc / units * p->aperf /
 				p->mperf / interval_float);
 		} else {
 			if (p->aperf > p->tsc || p->mperf > p->tsc) {
-				fprintf(stderr, " ****");
+				fprintf(stderr, " ***");
 			} else {
-				fprintf(stderr, "%4.1f*",
+				fprintf(stderr, "%3.1f*",
 					1.0 * p->tsc /
 					units * p->aperf /
 					p->mperf / interval_float);
@@ -241,7 +292,7 @@ void print_cnt(struct counters *p)
 
 	if (do_nhm_cstates) {
 		if (!skip_c1)
-			fprintf(stderr, "%7.2f", 100.0 * p->c1/p->tsc);
+			fprintf(stderr, " %6.2f", 100.0 * p->c1/p->tsc);
 		else
 			fprintf(stderr, "  ****");
 	}
@@ -252,13 +303,13 @@ void print_cnt(struct counters *p)
 	if (do_snb_cstates)
 		fprintf(stderr, " %6.2f", 100.0 * p->c7/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc2/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc2/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc3/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc3/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc6/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc6/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc7/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc7/p->tsc);
 	if (extra_msr_offset)
 		fprintf(stderr, "  0x%016llx", p->extra_msr);
 	putc('\n', stderr);
@@ -267,12 +318,20 @@ void print_cnt(struct counters *p)
 void print_counters(struct counters *counters)
 {
 	struct counters *cnt;
+	static int printed;
+
 
-	print_header();
+	if (!printed || !summary_only)
+		print_header();
 
 	if (num_cpus > 1)
 		print_cnt(cnt_average);
 
+	printed = 1;
+
+	if (summary_only)
+		return;
+
 	for (cnt = counters; cnt != NULL; cnt = cnt->next)
 		print_cnt(cnt);
 
@@ -440,31 +499,51 @@ void compute_average(struct counters *delta, struct counters *avg)
 	free(sum);
 }
 
-void get_counters(struct counters *cnt)
+int get_counters(struct counters *cnt)
 {
 	for ( ; cnt; cnt = cnt->next) {
-		cnt->tsc = get_msr(cnt->cpu, MSR_TSC);
-		if (do_nhm_cstates)
-			cnt->c3 = get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->c6 = get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY);
-		if (do_snb_cstates)
-			cnt->c7 = get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY);
-		if (has_aperf)
-			cnt->aperf = get_msr(cnt->cpu, MSR_APERF);
-		if (has_aperf)
-			cnt->mperf = get_msr(cnt->cpu, MSR_MPERF);
-		if (do_snb_cstates)
-			cnt->pc2 = get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc3 = get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc6 = get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY);
+
+		if (cpu_migrate(cnt->cpu))
+			return -1;
+
+		if (get_msr(cnt->cpu, MSR_TSC, &cnt->tsc))
+			return -1;
+
+		if (has_aperf) {
+			if (get_msr(cnt->cpu, MSR_APERF, &cnt->aperf))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_MPERF, &cnt->mperf))
+				return -1;
+		}
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY, &cnt->c3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY, &cnt->c6))
+				return -1;
+		}
+
 		if (do_snb_cstates)
-			cnt->pc7 = get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY);
+			if (get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY, &cnt->c7))
+				return -1;
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY, &cnt->pc3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY, &cnt->pc6))
+				return -1;
+		}
+		if (do_snb_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY, &cnt->pc2))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY, &cnt->pc7))
+				return -1;
+		}
 		if (extra_msr_offset)
-			cnt->extra_msr = get_msr(cnt->cpu, extra_msr_offset);
+			if (get_msr(cnt->cpu, extra_msr_offset, &cnt->extra_msr))
+				return -1;
 	}
+	return 0;
 }
 
 void print_nehalem_info(void)
@@ -475,7 +554,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_platform_info)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_PLATFORM_INFO);
+	get_msr(0, MSR_NEHALEM_PLATFORM_INFO, &msr);
 
 	ratio = (msr >> 40) & 0xFF;
 	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
@@ -491,7 +570,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_turbo_ratio_limit)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT);
+	get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT, &msr);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
@@ -557,7 +636,8 @@ void insert_counters(struct counters **list,
 		return;
 	}
 
-	show_cpu = 1;	/* there is more than one CPU */
+	if (!summary_only)
+		show_cpu = 1;	/* there is more than one CPU */
 
 	/*
 	 * insert on front of list.
@@ -575,13 +655,15 @@ void insert_counters(struct counters **list,
 
 	while (prev->next && (prev->next->pkg < new->pkg)) {
 		prev = prev->next;
-		show_pkg = 1;	/* there is more than 1 package */
+		if (!summary_only)
+			show_pkg = 1;	/* there is more than 1 package */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
 		&& (prev->next->core < new->core)) {
 		prev = prev->next;
-		show_core = 1;	/* there is more than 1 core */
+		if (!summary_only)
+			show_core = 1;	/* there is more than 1 core */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
@@ -681,7 +763,7 @@ int get_core_id(int cpu)
 }
 
 /*
- * run func(index, cpu) on every cpu in /proc/stat
+ * run func(pkg, core, cpu) on every cpu in /proc/stat
  */
 
 int for_all_cpus(void (func)(int, int, int))
@@ -717,18 +799,18 @@ int for_all_cpus(void (func)(int, int, int))
 
 void re_initialize(void)
 {
-	printf("turbostat: topology changed, re-initializing.\n");
 	free_all_counters();
 	num_cpus = for_all_cpus(alloc_new_counters);
-	need_reinitialize = 0;
-	printf("num_cpus is now %d\n", num_cpus);
+	cpu_mask_uninit();
+	cpu_mask_init(num_cpus);
+	printf("turbostat: re-initialized with num_cpus %d\n", num_cpus);
 }
 
 void dummy(int pkg, int core, int cpu) { return; }
 /*
  * check to see if a cpu came on-line
  */
-void verify_num_cpus(void)
+int verify_num_cpus(void)
 {
 	int new_num_cpus;
 
@@ -738,8 +820,9 @@ void verify_num_cpus(void)
 		if (verbose)
 			printf("num_cpus was %d, is now  %d\n",
 				num_cpus, new_num_cpus);
-		need_reinitialize = 1;
+		return -1;
 	}
+	return 0;
 }
 
 void turbostat_loop()
@@ -749,25 +832,25 @@ restart:
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	while (1) {
-		verify_num_cpus();
-		if (need_reinitialize) {
+		if (verify_num_cpus()) {
 			re_initialize();
 			goto restart;
 		}
 		sleep(interval_sec);
-		get_counters(cnt_odd);
+		if (get_counters(cnt_odd)) {
+			re_initialize();
+			goto restart;
+		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
-
 		compute_delta(cnt_odd, cnt_even, cnt_delta);
 		timersub(&tv_odd, &tv_even, &tv_delta);
 		compute_average(cnt_delta, cnt_average);
 		print_counters(cnt_delta);
-		if (need_reinitialize) {
+		sleep(interval_sec);
+		if (get_counters(cnt_even)) {
 			re_initialize();
 			goto restart;
 		}
-		sleep(interval_sec);
-		get_counters(cnt_even);
 		gettimeofday(&tv_even, (struct timezone *)NULL);
 		compute_delta(cnt_even, cnt_odd, cnt_delta);
 		timersub(&tv_even, &tv_odd, &tv_delta);
@@ -953,6 +1036,7 @@ void turbostat_init()
 	check_super_user();
 
 	num_cpus = for_all_cpus(alloc_new_counters);
+	cpu_mask_init(num_cpus);
 
 	if (verbose)
 		print_nehalem_info();
@@ -1005,8 +1089,11 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+vi:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "+svi:M:")) != -1) {
 		switch (opt) {
+		case 's':
+			summary_only++;
+			break;
 		case 'v':
 			verbose++;
 			break;