diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a7f7ed0..99bf905 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -136,7 +136,7 @@
 The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
 .SH COLUMN DESCRIPTIONS
 .PP
-\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to collect the counters on all cpus.
+\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to snapshot the procfs/sysfs and collect the counters on all cpus.
 .PP
 \fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected.  This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug".  On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU.
 .PP
@@ -190,7 +190,7 @@
 .PP
 \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
 .PP
-\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default.  Enable with --enable SysWatt.
+\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS).
 .PP
 \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.  Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system.  Note that the meaning of this field is model specific.  For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits.  Comparing PkgWatt and PkgTmp to system limits is necessary.
 .PP
@@ -516,14 +516,40 @@
 Volume 3B: System Programming Guide"
 https://www.intel.com/products/processor/manuals/
 
+.SH RUN THE LATEST VERSION
+If turbostat complains that it doesn't recognize your processor,
+please try the latest version.
+
+The latest version of turbostat does not require the latest version of the Linux kernel.
+However, some features, such as perf(1) counters, do require kernel support.
+
+The latest turbostat release is available in the upstream Linux Kernel source tree.
+eg. "git pull https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git"
+and run make in tools/power/x86/turbostat/.
+
+n.b. "make install" will update your system manually, but a distro update may subsequently downgrade your turbostat to an older version.
+For this reason, manually installing to /usr/local/bin may be what you want.
+
+Note that turbostat/Makefile has a "make snapshot" target, which will create a tar file
+that can build without a local kernel source tree.
+
+If the upstream version isn't new enough, the development tree can be found here:
+"git pull https://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat"
+
+If the development tree doesn't work, please contact the author via chat,
+or via email with the word "turbostat" on the Subject line.
+
 .SH FILES
 .ta
 .nf
+/sys/bus/event_source/devices/
 /dev/cpu/*/msr
+/sys/class/intel_pmt/
+/sys/devices/system/cpu/
 .fi
 
 .SH "SEE ALSO"
-msr(4), vmstat(8)
+perf(1), msr(4), vmstat(8)
 .PP
 .SH AUTHOR
 .nf
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 58a487c..8d5011a 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
  * turbostat -- show CPU frequency and C-state residency
  * on modern Intel and AMD processors.
  *
- * Copyright (c) 2024 Intel Corporation.
+ * Copyright (c) 2025 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  */
 
@@ -95,6 +95,8 @@
 #define INTEL_ECORE_TYPE	0x20
 #define INTEL_PCORE_TYPE	0x40
 
+#define ROUND_UP_TO_PAGE_SIZE(n) (((n) + 0x1000UL-1UL) & ~(0x1000UL-1UL))
+
 enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
 enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M };
 enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE };
@@ -202,6 +204,8 @@ struct msr_counter bic[] = {
 	{ 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 },
+	{ 0x0, "NMI", NULL, 0, 0, 0, NULL, 0 },
+	{ 0x0, "CPU%c1e", NULL, 0, 0, 0, NULL, 0 },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -266,14 +270,16 @@ struct msr_counter bic[] = {
 #define	BIC_Diec6		(1ULL << 58)
 #define	BIC_SysWatt		(1ULL << 59)
 #define	BIC_Sys_J		(1ULL << 60)
+#define	BIC_NMI			(1ULL << 61)
+#define	BIC_CPU_c1e		(1ULL << 62)
 
-#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
-#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
+#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die)
+#define BIC_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt)
 #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6)
-#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
+#define BIC_IDLE (BIC_Busy | BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6)
+#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
 
-#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J)
+#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
 unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
 unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
@@ -326,6 +332,7 @@ unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int list_header_only;
 unsigned int dump_only;
+unsigned int force_load;
 unsigned int has_aperf;
 unsigned int has_aperf_access;
 unsigned int has_epb;
@@ -353,7 +360,7 @@ unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int tj_max;
 unsigned int tj_max_override;
 double rapl_power_units, rapl_time_units;
-double rapl_dram_energy_units, rapl_energy_units;
+double rapl_dram_energy_units, rapl_energy_units, rapl_psys_energy_units;
 double rapl_joule_counter_range;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
@@ -365,6 +372,9 @@ unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;	/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;	/* IA32_HWP_REQUEST_PKG */
 unsigned int first_counter_read = 1;
+
+static struct timeval procsysfs_tv_begin;
+
 int ignore_stdin;
 bool no_msr;
 bool no_perf;
@@ -419,6 +429,7 @@ struct platform_features {
 	bool has_per_core_rapl;	/* Indicates cores energy collection is per-core, not per-package. AMD specific for now */
 	bool has_rapl_divisor;	/* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */
 	bool has_fixed_rapl_unit;	/* Fixed Energy Unit used for DRAM RAPL Domain */
+	bool has_fixed_rapl_psys_unit;	/* Fixed Energy Unit used for PSYS RAPL Domain */
 	int rapl_quirk_tdp;	/* Hardcoded TDP value when cannot be retrieved from hardware */
 	int tcc_offset_bits;	/* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */
 	bool enable_tsc_tweak;	/* Use CPU Base freq instead of TSC freq for aperf/mperf counter */
@@ -819,6 +830,7 @@ static const struct platform_features spr_features = {
 	.has_msr_core_c1_res = 1,
 	.has_irtl_msrs = 1,
 	.has_cst_prewake_bit = 1,
+	.has_fixed_rapl_psys_unit = 1,
 	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
 	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS,
 };
@@ -1024,6 +1036,7 @@ static const struct platform_data turbostat_pdata[] = {
 	{ INTEL_ARROWLAKE_U, &adl_features },
 	{ INTEL_ARROWLAKE, &adl_features },
 	{ INTEL_LUNARLAKE_M, &lnl_features },
+	{ INTEL_PANTHERLAKE_L, &lnl_features },
 	{ INTEL_ATOM_SILVERMONT, &slv_features },
 	{ INTEL_ATOM_SILVERMONT_D, &slvd_features },
 	{ INTEL_ATOM_AIRMONT, &amt_features },
@@ -1036,6 +1049,7 @@ static const struct platform_data turbostat_pdata[] = {
 	{ INTEL_ATOM_GRACEMONT, &adl_features },
 	{ INTEL_ATOM_CRESTMONT_X, &srf_features },
 	{ INTEL_ATOM_CRESTMONT, &grr_features },
+	{ INTEL_ATOM_DARKMONT_X, &srf_features },
 	{ INTEL_XEON_PHI_KNL, &knl_features },
 	{ INTEL_XEON_PHI_KNM, &knl_features },
 	/*
@@ -1054,9 +1068,10 @@ void probe_platform_features(unsigned int family, unsigned int model)
 {
 	int i;
 
-	platform = &default_features;
 
 	if (authentic_amd || hygon_genuine) {
+		/* fallback to default features on unsupported models */
+		force_load++;
 		if (max_extended_level >= 0x80000007) {
 			unsigned int eax, ebx, ecx, edx;
 
@@ -1065,11 +1080,11 @@ void probe_platform_features(unsigned int family, unsigned int model)
 			if ((edx & (1 << 14)) && family >= 0x17)
 				platform = &amd_features_with_rapl;
 		}
-		return;
+		goto end;
 	}
 
 	if (!genuine_intel)
-		return;
+		goto end;
 
 	for (i = 0; turbostat_pdata[i].features; i++) {
 		if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) {
@@ -1077,6 +1092,19 @@ void probe_platform_features(unsigned int family, unsigned int model)
 			return;
 		}
 	}
+
+end:
+	if (force_load && !platform) {
+		fprintf(outf, "Forced to run on unsupported platform!\n");
+		platform = &default_features;
+	}
+
+	if (platform)
+		return;
+
+	fprintf(stderr, "Unsupported platform detected.\n"
+		"\tSee RUN THE LATEST VERSION on turbostat(8)\n");
+	exit(1);
 }
 
 /* Model specific support End */
@@ -1094,8 +1122,8 @@ int backwards_count;
 char *progname;
 
 #define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
-cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
-size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
+cpu_set_t *cpu_present_set, *cpu_possible_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_possible_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
 #define MAX_ADDED_THREAD_COUNTERS 24
 #define MAX_ADDED_CORE_COUNTERS 8
 #define MAX_ADDED_PACKAGE_COUNTERS 16
@@ -1271,7 +1299,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = {
 	 .msr = MSR_PLATFORM_ENERGY_STATUS,
 	 .msr_mask = 0x00000000FFFFFFFF,
 	 .msr_shift = 0,
-	 .platform_rapl_msr_scale = &rapl_energy_units,
+	 .platform_rapl_msr_scale = &rapl_psys_energy_units,
 	 .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM,
 	 .bic = BIC_SysWatt | BIC_Sys_J,
 	 .compat_scale = 1.0,
@@ -1510,6 +1538,17 @@ static struct msr_counter_arch_info msr_counter_arch_infos[] = {
 #define PMT_COUNTER_MTL_DC6_LSB    0
 #define PMT_COUNTER_MTL_DC6_MSB    63
 #define PMT_MTL_DC6_GUID           0x1a067102
+#define PMT_MTL_DC6_SEQ            0
+
+#define PMT_COUNTER_CWF_MC1E_OFFSET_BASE          20936
+#define PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT     24
+#define PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE 12
+#define PMT_COUNTER_CWF_CPUS_PER_MODULE           4
+#define PMT_COUNTER_CWF_MC1E_LSB                  0
+#define PMT_COUNTER_CWF_MC1E_MSB                  63
+#define PMT_CWF_MC1E_GUID                         0x14421519
+
+unsigned long long tcore_clock_freq_hz = 800000000;
 
 #define PMT_COUNTER_NAME_SIZE_BYTES      16
 #define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32
@@ -1533,6 +1572,7 @@ struct pmt_mmio {
 enum pmt_datatype {
 	PMT_TYPE_RAW,
 	PMT_TYPE_XTAL_TIME,
+	PMT_TYPE_TCORE_CLOCK,
 };
 
 struct pmt_domain_info {
@@ -1562,6 +1602,93 @@ struct pmt_counter {
 	struct pmt_domain_info *domains;
 };
 
+/*
+ * PMT telemetry directory iterator.
+ * Used to iterate telemetry files in sysfs in correct order.
+ */
+struct pmt_diriter_t {
+	DIR *dir;
+	struct dirent **namelist;
+	unsigned int num_names;
+	unsigned int current_name_idx;
+};
+
+int pmt_telemdir_filter(const struct dirent *e)
+{
+	unsigned int dummy;
+
+	return sscanf(e->d_name, "telem%u", &dummy);
+}
+
+int pmt_telemdir_sort(const struct dirent **a, const struct dirent **b)
+{
+	unsigned int aidx = 0, bidx = 0;
+
+	sscanf((*a)->d_name, "telem%u", &aidx);
+	sscanf((*b)->d_name, "telem%u", &bidx);
+
+	return aidx >= bidx;
+}
+
+const struct dirent *pmt_diriter_next(struct pmt_diriter_t *iter)
+{
+	const struct dirent *ret = NULL;
+
+	if (!iter->dir)
+		return NULL;
+
+	if (iter->current_name_idx >= iter->num_names)
+		return NULL;
+
+	ret = iter->namelist[iter->current_name_idx];
+	++iter->current_name_idx;
+
+	return ret;
+}
+
+const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *pmt_root_path)
+{
+	int num_names = iter->num_names;
+
+	if (!iter->dir) {
+		iter->dir = opendir(pmt_root_path);
+		if (iter->dir == NULL)
+			return NULL;
+
+		num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort);
+		if (num_names == -1)
+			return NULL;
+	}
+
+	iter->current_name_idx = 0;
+	iter->num_names = num_names;
+
+	return pmt_diriter_next(iter);
+}
+
+void pmt_diriter_init(struct pmt_diriter_t *iter)
+{
+	memset(iter, 0, sizeof(*iter));
+}
+
+void pmt_diriter_remove(struct pmt_diriter_t *iter)
+{
+	if (iter->namelist) {
+		for (unsigned int i = 0; i < iter->num_names; i++) {
+			free(iter->namelist[i]);
+			iter->namelist[i] = NULL;
+		}
+	}
+
+	free(iter->namelist);
+	iter->namelist = NULL;
+	iter->num_names = 0;
+	iter->current_name_idx = 0;
+
+	closedir(iter->dir);
+	iter->dir = NULL;
+}
+
 unsigned int pmt_counter_get_width(const struct pmt_counter *p)
 {
 	return (p->msb - p->lsb) + 1;
@@ -1611,6 +1738,7 @@ struct thread_data {
 	unsigned long long c1;
 	unsigned long long instr_count;
 	unsigned long long irq_count;
+	unsigned long long nmi_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int apic_id;
@@ -1917,6 +2045,7 @@ struct timeval tv_even, tv_odd, tv_delta;
 
 int *irq_column_2_cpu;		/* /proc/interrupts column numbers */
 int *irqs_per_cpu;		/* indexed by cpu_num */
+int *nmi_per_cpu;		/* indexed by cpu_num */
 
 void setup_all_buffers(bool startup);
 
@@ -1944,6 +2073,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 {
 	int retval, pkg_no, core_no, thread_no, node_no;
 
+	retval = 0;
+
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
 		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
 			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
@@ -1959,14 +2090,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 					c = GET_CORE(core_base, core_no, node_no, pkg_no);
 					p = GET_PKG(pkg_base, pkg_no);
 
-					retval = func(t, c, p);
-					if (retval)
-						return retval;
+					retval |= func(t, c, p);
 				}
 			}
 		}
 	}
-	return 0;
+	return retval;
 }
 
 int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -2085,13 +2214,17 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 int probe_msr(int cpu, off_t offset)
 {
 	ssize_t retval;
-	unsigned long long dummy;
+	unsigned long long value;
 
 	assert(!no_msr);
 
-	retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset);
+	retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset);
 
-	if (retval != sizeof(dummy))
+	/*
+	 * 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)
 		return 1;
 
 	return 0;
@@ -2135,41 +2268,54 @@ void help(void)
 		"when COMMAND completes.\n"
 		"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
 		"to print statistics, until interrupted.\n"
-		"  -a, --add	add a counter\n"
+		"  -a, --add counter\n"
+		"		add a counter\n"
 		"		  eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
 		"		  eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n"
 		"		  eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n"
-		"  -c, --cpu	cpu-set	limit output to summary plus cpu-set:\n"
+		"  -c, --cpu cpu-set\n"
+		"		limit output to summary plus cpu-set:\n"
 		"		  {core | package | j,k,l..m,n-p }\n"
-		"  -d, --debug	displays usec, Time_Of_Day_Seconds and more debugging\n"
+		"  -d, --debug\n"
+		"		displays usec, Time_Of_Day_Seconds and more debugging\n"
 		"		debug messages are printed to stderr\n"
-		"  -D, --Dump	displays the raw counter values\n"
-		"  -e, --enable	[all | column]\n"
+		"  -D, --Dump\n"
+		"		displays the raw counter values\n"
+		"  -e, --enable [all | column]\n"
 		"		shows all or the specified disabled column\n"
-		"  -H, --hide [column|column,column,...]\n"
+		"  -f, --force\n"
+		"		force load turbostat with minimum default features on unsupported platforms.\n"
+		"  -H, --hide [column | column,column,...]\n"
 		"		hide the specified column(s)\n"
 		"  -i, --interval sec.subsec\n"
-		"		Override default 5-second measurement interval\n"
-		"  -J, --Joules	displays energy in Joules instead of Watts\n"
-		"  -l, --list	list column headers only\n"
-		"  -M, --no-msr Disable all uses of the MSR driver\n"
-		"  -P, --no-perf Disable all uses of the perf API\n"
+		"		override default 5-second measurement interval\n"
+		"  -J, --Joules\n"
+		"		displays energy in Joules instead of Watts\n"
+		"  -l, --list\n"
+		"		list column headers only\n"
+		"  -M, --no-msr\n"
+		"		disable all uses of the MSR driver\n"
+		"  -P, --no-perf\n"
+		"		disable all uses of the perf API\n"
 		"  -n, --num_iterations num\n"
 		"		number of the measurement iterations\n"
 		"  -N, --header_iterations num\n"
 		"		print header every num iterations\n"
 		"  -o, --out file\n"
 		"		create or truncate \"file\" for all output\n"
-		"  -q, --quiet	skip decoding system configuration header\n"
-		"  -s, --show [column|column,column,...]\n"
+		"  -q, --quiet\n"
+		"		skip decoding system configuration header\n"
+		"  -s, --show [column | column,column,...]\n"
 		"		show only the specified column(s)\n"
 		"  -S, --Summary\n"
 		"		limits output to 1-line system summary per interval\n"
 		"  -T, --TCC temperature\n"
 		"		sets the Thermal Control Circuit temperature in\n"
 		"		  degrees Celsius\n"
-		"  -h, --help	print this help message\n"
-		"  -v, --version	print version information\n" "\n" "For more help, run \"man turbostat\"\n");
+		"  -h, --help\n"
+		"		print this help message\n"
+		"  -v, --version\n"
+		"		print version information\n\nFor more help, run \"man turbostat\"\n");
 }
 
 /*
@@ -2289,6 +2435,12 @@ void print_header(char *delim)
 		else
 			outp += sprintf(outp, "%sIRQ", (printed++ ? delim : ""));
 	}
+	if (DO_BIC(BIC_NMI)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "%s     NMI", (printed++ ? delim : ""));
+		else
+			outp += sprintf(outp, "%sNMI", (printed++ ? delim : ""));
+	}
 
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "%sSMI", (printed++ ? delim : ""));
@@ -2335,6 +2487,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2409,6 +2562,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2540,6 +2694,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2575,6 +2730,8 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		if (DO_BIC(BIC_IRQ))
 			outp += sprintf(outp, "IRQ: %lld\n", t->irq_count);
+		if (DO_BIC(BIC_NMI))
+			outp += sprintf(outp, "IRQ: %lld\n", t->nmi_count);
 		if (DO_BIC(BIC_SMI))
 			outp += sprintf(outp, "SMI: %d\n", t->smi_count);
 
@@ -2794,6 +2951,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count);
 	}
 
+	/* NMI */
+	if (DO_BIC(BIC_NMI)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->nmi_count);
+		else
+			outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->nmi_count);
+	}
+
 	/* SMI */
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count);
@@ -2848,7 +3013,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = t->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -2860,8 +3025,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -2928,7 +3098,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = c->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -2940,8 +3110,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -3126,7 +3301,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = p->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -3138,8 +3313,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -3409,6 +3589,9 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 	if (DO_BIC(BIC_IRQ))
 		old->irq_count = new->irq_count - old->irq_count;
 
+	if (DO_BIC(BIC_NMI))
+		old->nmi_count = new->nmi_count - old->nmi_count;
+
 	if (DO_BIC(BIC_SMI))
 		old->smi_count = new->smi_count - old->smi_count;
 
@@ -3447,12 +3630,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 
 	/* always calculate thread delta */
 	retval = delta_thread(t, t2, c2);	/* c2 is core delta */
-	if (retval)
-		return retval;
 
 	/* calculate package delta only for 1st core in package */
 	if (is_cpu_first_core_in_package(t, c, p))
-		retval = delta_package(p, p2);
+		retval |= delta_package(p, p2);
 
 	return retval;
 }
@@ -3489,6 +3670,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->instr_count = 0;
 
 	t->irq_count = 0;
+	t->nmi_count = 0;
 	t->smi_count = 0;
 
 	c->c3 = 0;
@@ -3580,7 +3762,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	/* remember first tv_begin */
 	if (average.threads.tv_begin.tv_sec == 0)
-		average.threads.tv_begin = t->tv_begin;
+		average.threads.tv_begin = procsysfs_tv_begin;
 
 	/* remember last tv_end */
 	average.threads.tv_end = t->tv_end;
@@ -3593,6 +3775,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	average.threads.instr_count += t->instr_count;
 
 	average.threads.irq_count += t->irq_count;
+	average.threads.nmi_count += t->nmi_count;
 	average.threads.smi_count += t->smi_count;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -3734,6 +3917,9 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	if (average.threads.irq_count > 9999999)
 		sums_need_wide_columns = 1;
+	if (average.threads.nmi_count > 9999999)
+		sums_need_wide_columns = 1;
+
 
 	average.cores.c3 /= topo.allowed_cores;
 	average.cores.c6 /= topo.allowed_cores;
@@ -4546,7 +4732,8 @@ unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb)
 
 unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id)
 {
-	assert(domain_id < ppmt->num_domains);
+	if (domain_id >= ppmt->num_domains)
+		return 0;
 
 	const unsigned long *pmmio = ppmt->domains[domain_id].pcounter;
 	const unsigned long value = pmmio ? *pmmio : 0;
@@ -4590,6 +4777,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	if (DO_BIC(BIC_IRQ))
 		t->irq_count = irqs_per_cpu[cpu];
+	if (DO_BIC(BIC_NMI))
+		t->nmi_count = nmi_per_cpu[cpu];
 
 	get_cstate_counters(cpu, t, c, p);
 
@@ -5335,6 +5524,7 @@ void free_all_buffers(void)
 
 	free(irq_column_2_cpu);
 	free(irqs_per_cpu);
+	free(nmi_per_cpu);
 
 	for (i = 0; i <= topo.max_cpu_num; ++i) {
 		if (cpus[i].put_ids)
@@ -5566,6 +5756,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 {
 	int retval, pkg_no, node_no, core_no, thread_no;
 
+	retval = 0;
+
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
 		for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) {
 			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
@@ -5587,14 +5779,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 					p = GET_PKG(pkg_base, pkg_no);
 					p2 = GET_PKG(pkg_base2, pkg_no);
 
-					retval = func(t, c, p, t2, c2, p2);
-					if (retval)
-						return retval;
+					retval |= func(t, c, p, t2, c2, p2);
 				}
 			}
 		}
 	}
-	return 0;
+	return retval;
 }
 
 /*
@@ -5791,31 +5981,37 @@ int snapshot_proc_interrupts(void)
 
 		irq_column_2_cpu[column] = cpu_number;
 		irqs_per_cpu[cpu_number] = 0;
+		nmi_per_cpu[cpu_number] = 0;
 	}
 
 	/* read /proc/interrupt count lines and sum up irqs per cpu */
 	while (1) {
 		int column;
 		char buf[64];
+		int this_row_is_nmi = 0;
 
-		retval = fscanf(fp, " %s:", buf);	/* flush irq# "N:" */
+		retval = fscanf(fp, " %s:", buf);	/* irq# "N:" */
 		if (retval != 1)
 			break;
 
+		if (strncmp(buf, "NMI", strlen("NMI")) == 0)
+			this_row_is_nmi = 1;
+
 		/* read the count per cpu */
 		for (column = 0; column < topo.num_cpus; ++column) {
 
 			int cpu_number, irq_count;
 
 			retval = fscanf(fp, " %d", &irq_count);
+
 			if (retval != 1)
 				break;
 
 			cpu_number = irq_column_2_cpu[column];
 			irqs_per_cpu[cpu_number] += irq_count;
-
+			if (this_row_is_nmi)
+				nmi_per_cpu[cpu_number] += irq_count;
 		}
-
 		while (getc(fp) != '\n') ;	/* flush interrupt description */
 
 	}
@@ -5912,7 +6108,9 @@ int snapshot_sys_lpi_us(void)
  */
 int snapshot_proc_sysfs_files(void)
 {
-	if (DO_BIC(BIC_IRQ))
+	gettimeofday(&procsysfs_tv_begin, (struct timezone *)NULL);
+
+	if (DO_BIC(BIC_IRQ) || DO_BIC(BIC_NMI))
 		if (snapshot_proc_interrupts())
 			return 1;
 
@@ -7043,6 +7241,11 @@ void rapl_probe_intel(void)
 	else
 		rapl_dram_energy_units = rapl_energy_units;
 
+	if (platform->has_fixed_rapl_psys_unit)
+		rapl_psys_energy_units = 1.0;
+	else
+		rapl_psys_energy_units = rapl_energy_units;
+
 	time_unit = msr >> 16 & 0xF;
 	if (time_unit == 0)
 		time_unit = 0xA;
@@ -8233,6 +8436,7 @@ void process_cpuid()
 		aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1;
 
 	BIC_PRESENT(BIC_IRQ);
+	BIC_PRESENT(BIC_NMI);
 	BIC_PRESENT(BIC_TSC_MHz);
 }
 
@@ -8292,6 +8496,33 @@ int dir_filter(const struct dirent *dirp)
 		return 0;
 }
 
+char *possible_file = "/sys/devices/system/cpu/possible";
+char possible_buf[1024];
+
+int initialize_cpu_possible_set(void)
+{
+	FILE *fp;
+
+	fp = fopen(possible_file, "r");
+	if (!fp) {
+		warn("open %s", possible_file);
+		return -1;
+	}
+	if (fread(possible_buf, sizeof(char), 1024, fp) == 0) {
+		warn("read %s", possible_file);
+		goto err;
+	}
+	if (parse_cpu_str(possible_buf, cpu_possible_set, cpu_possible_setsize)) {
+		warnx("%s: cpu str malformat %s\n", possible_file, cpu_effective_str);
+		goto err;
+	}
+	return 0;
+
+err:
+	fclose(fp);
+	return -1;
+}
+
 void topology_probe(bool startup)
 {
 	int i;
@@ -8324,6 +8555,16 @@ void topology_probe(bool startup)
 	for_all_proc_cpus(mark_cpu_present);
 
 	/*
+	 * Allocate and initialize cpu_possible_set
+	 */
+	cpu_possible_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_possible_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_possible_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_possible_setsize, cpu_possible_set);
+	initialize_cpu_possible_set();
+
+	/*
 	 * Allocate and initialize cpu_effective_set
 	 */
 	cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1));
@@ -8583,7 +8824,11 @@ void allocate_irq_buffers(void)
 
 	irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (irqs_per_cpu == NULL)
-		err(-1, "calloc %d", topo.max_cpu_num + 1);
+		err(-1, "calloc %d IRQ", topo.max_cpu_num + 1);
+
+	nmi_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
+	if (nmi_per_cpu == NULL)
+		err(-1, "calloc %d NMI", topo.max_cpu_num + 1);
 }
 
 int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -8854,49 +9099,36 @@ int parse_telem_info_file(int fd_dir, const char *info_filename, const char *for
 
 struct pmt_mmio *pmt_mmio_open(unsigned int target_guid)
 {
-	DIR *dirp;
-	struct dirent *entry;
+	struct pmt_diriter_t pmt_iter;
+	const struct dirent *entry;
 	struct stat st;
-	unsigned int telem_idx;
 	int fd_telem_dir, fd_pmt;
 	unsigned long guid, size, offset;
 	size_t mmap_size;
 	void *mmio;
-	struct pmt_mmio *ret = NULL;
+	struct pmt_mmio *head = NULL, *last = NULL;
+	struct pmt_mmio *new_pmt = NULL;
 
 	if (stat(SYSFS_TELEM_PATH, &st) == -1)
 		return NULL;
 
-	dirp = opendir(SYSFS_TELEM_PATH);
-	if (dirp == NULL)
+	pmt_diriter_init(&pmt_iter);
+	entry = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH);
+	if (!entry) {
+		pmt_diriter_remove(&pmt_iter);
 		return NULL;
+	}
 
-	for (;;) {
-		entry = readdir(dirp);
-
-		if (entry == NULL)
+	for ( ; entry != NULL; entry = pmt_diriter_next(&pmt_iter)) {
+		if (fstatat(dirfd(pmt_iter.dir), entry->d_name, &st, 0) == -1)
 			break;
 
-		if (strcmp(entry->d_name, ".") == 0)
-			continue;
-
-		if (strcmp(entry->d_name, "..") == 0)
-			continue;
-
-		if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1)
-			continue;
-
-		if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) {
-			break;
-		}
-
 		if (!S_ISDIR(st.st_mode))
 			continue;
 
-		fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY);
-		if (fd_telem_dir == -1) {
+		fd_telem_dir = openat(dirfd(pmt_iter.dir), entry->d_name, O_RDONLY);
+		if (fd_telem_dir == -1)
 			break;
-		}
 
 		if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) {
 			close(fd_telem_dir);
@@ -8924,38 +9156,54 @@ struct pmt_mmio *pmt_mmio_open(unsigned int target_guid)
 		if (fd_pmt == -1)
 			goto loop_cleanup_and_break;
 
-		mmap_size = (size + 0x1000UL) & (~0x1000UL);
+		mmap_size = ROUND_UP_TO_PAGE_SIZE(size);
 		mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0);
 		if (mmio != MAP_FAILED) {
-
 			if (debug)
 				fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio);
 
-			ret = calloc(1, sizeof(*ret));
+			new_pmt = calloc(1, sizeof(*new_pmt));
 
-			if (!ret) {
+			if (!new_pmt) {
 				fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__);
 				exit(1);
 			}
 
-			ret->guid = guid;
-			ret->mmio_base = mmio;
-			ret->pmt_offset = offset;
-			ret->size = size;
+			/*
+			 * Create linked list of mmaped regions,
+			 * but preserve the ordering from sysfs.
+			 * Ordering is important for the user to
+			 * use the seq=%u parameter when adding a counter.
+			 */
+			new_pmt->guid = guid;
+			new_pmt->mmio_base = mmio;
+			new_pmt->pmt_offset = offset;
+			new_pmt->size = size;
+			new_pmt->next = pmt_mmios;
 
-			ret->next = pmt_mmios;
-			pmt_mmios = ret;
+			if (last)
+				last->next = new_pmt;
+			else
+				head = new_pmt;
+
+			last = new_pmt;
 		}
 
 loop_cleanup_and_break:
 		close(fd_pmt);
 		close(fd_telem_dir);
-		break;
 	}
 
-	closedir(dirp);
+	pmt_diriter_remove(&pmt_iter);
 
-	return ret;
+	/*
+	 * If we found something, stick just
+	 * created linked list to the front.
+	 */
+	if (head)
+		pmt_mmios = head;
+
+	return head;
 }
 
 struct pmt_mmio *pmt_mmio_find(unsigned int guid)
@@ -8992,7 +9240,7 @@ void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offs
 	return ret;
 }
 
-struct pmt_mmio *pmt_add_guid(unsigned int guid)
+struct pmt_mmio *pmt_add_guid(unsigned int guid, unsigned int seq)
 {
 	struct pmt_mmio *ret;
 
@@ -9000,6 +9248,11 @@ struct pmt_mmio *pmt_add_guid(unsigned int guid)
 	if (!ret)
 		ret = pmt_mmio_open(guid);
 
+	while (ret && seq) {
+		ret = ret->next;
+		--seq;
+	}
+
 	return ret;
 }
 
@@ -9046,7 +9299,7 @@ void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio,
 	pcounter->domains[domain_id].pcounter = pmmio;
 }
 
-int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
+int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum pmt_datatype type,
 		    unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope,
 		    enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode)
 {
@@ -9066,10 +9319,10 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
 		exit(1);
 	}
 
-	mmio = pmt_add_guid(guid);
+	mmio = pmt_add_guid(guid, seq);
 	if (!mmio) {
 		if (mode != PMT_OPEN_TRY) {
-			fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid);
+			fprintf(stderr, "%s: failed to map PMT MMIO for guid %x, seq %u\n", __func__, guid, seq);
 			exit(1);
 		}
 
@@ -9124,10 +9377,68 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
 
 void pmt_init(void)
 {
+	int cpu_num;
+	unsigned long seq, offset, mod_num;
+
 	if (BIC_IS_ENABLED(BIC_Diec6)) {
-		pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB,
-				PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA,
-				0, PMT_OPEN_TRY);
+		pmt_add_counter(PMT_MTL_DC6_GUID, PMT_MTL_DC6_SEQ, "Die%c6", PMT_TYPE_XTAL_TIME,
+				PMT_COUNTER_MTL_DC6_LSB, PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET,
+				SCOPE_PACKAGE, FORMAT_DELTA, 0, PMT_OPEN_TRY);
+	}
+
+	if (BIC_IS_ENABLED(BIC_CPU_c1e)) {
+		seq = 0;
+		offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE;
+		mod_num = 0;	/* Relative module number for current PMT file. */
+
+		/* Open the counter for each CPU. */
+		for (cpu_num = 0; cpu_num < topo.max_cpu_num;) {
+
+			if (cpu_is_not_allowed(cpu_num))
+				goto next_loop_iter;
+
+			/*
+			 * Set the scope to CPU, even though CWF report the counter per module.
+			 * CPUs inside the same module will read from the same location, instead of reporting zeros.
+			 *
+			 * CWF with newer firmware might require a PMT_TYPE_XTAL_TIME intead of PMT_TYPE_TCORE_CLOCK.
+			 */
+			pmt_add_counter(PMT_CWF_MC1E_GUID, seq, "CPU%c1e", PMT_TYPE_TCORE_CLOCK,
+					PMT_COUNTER_CWF_MC1E_LSB, PMT_COUNTER_CWF_MC1E_MSB, offset, SCOPE_CPU,
+					FORMAT_DELTA, cpu_num, PMT_OPEN_TRY);
+
+			/*
+			 * Rather complex logic for each time we go to the next loop iteration,
+			 * so keep it as a label.
+			 */
+next_loop_iter:
+			/*
+			 * Advance the cpu number and check if we should also advance offset to
+			 * the next counter inside the PMT file.
+			 *
+			 * On Clearwater Forest platform, the counter is reported per module,
+			 * so open the same counter for all of the CPUs inside the module.
+			 * That way, reported table show the correct value for all of the CPUs inside the module,
+			 * instead of zeros.
+			 */
+			++cpu_num;
+			if (cpu_num % PMT_COUNTER_CWF_CPUS_PER_MODULE == 0) {
+				offset += PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT;
+				++mod_num;
+			}
+
+			/*
+			 * There are PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE in each PMT file.
+			 *
+			 * If that number is reached, seq must be incremented to advance to the next file in a sequence.
+			 * Offset inside that file and a module counter has to be reset.
+			 */
+			if (mod_num == PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE) {
+				++seq;
+				offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE;
+				mod_num = 0;
+			}
+		}
 	}
 }
 
@@ -9163,6 +9474,18 @@ void turbostat_init()
 	}
 }
 
+void affinitize_child(void)
+{
+	/* Prefer cpu_possible_set, if available */
+	if (sched_setaffinity(0, cpu_possible_setsize, cpu_possible_set)) {
+		warn("sched_setaffinity cpu_possible_set");
+
+		/* Otherwise, allow child to run on same cpu set as turbostat */
+		if (sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set))
+			warn("sched_setaffinity cpu_allowed_set");
+	}
+}
+
 int fork_it(char **argv)
 {
 	pid_t child_pid;
@@ -9178,6 +9501,7 @@ int fork_it(char **argv)
 	child_pid = fork();
 	if (!child_pid) {
 		/* child */
+		affinitize_child();
 		execvp(argv[0], argv);
 		err(errno, "exec %s", argv[0]);
 	} else {
@@ -9204,10 +9528,9 @@ int fork_it(char **argv)
 	timersub(&tv_odd, &tv_even, &tv_delta);
 	if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS))
 		fprintf(outf, "%s: Counter reset detected\n", progname);
-	else {
-		compute_average(EVEN_COUNTERS);
-		format_all_counters(EVEN_COUNTERS);
-	}
+
+	compute_average(EVEN_COUNTERS);
+	format_all_counters(EVEN_COUNTERS);
 
 	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0);
 
@@ -9236,7 +9559,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2025.02.02 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -9561,7 +9884,7 @@ void parse_add_command_msr(char *add_command)
 
 	}
 	if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) {
-		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n");
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event) required\n");
 		fail++;
 	}
 
@@ -9599,15 +9922,100 @@ bool starts_with(const char *str, const char *prefix)
 	return strncmp(prefix, str, strlen(prefix)) == 0;
 }
 
+int pmt_parse_from_path(const char *target_path, unsigned int *out_guid, unsigned int *out_seq)
+{
+	struct pmt_diriter_t pmt_iter;
+	const struct dirent *dirname;
+	struct stat stat, target_stat;
+	int fd_telem_dir = -1;
+	int fd_target_dir;
+	unsigned int seq = 0;
+	unsigned long guid, target_guid;
+	int ret = -1;
+
+	fd_target_dir = open(target_path, O_RDONLY | O_DIRECTORY);
+	if (fd_target_dir == -1) {
+		return -1;
+	}
+
+	if (fstat(fd_target_dir, &target_stat) == -1) {
+		fprintf(stderr, "%s: Failed to stat the target: %s", __func__, strerror(errno));
+		exit(1);
+	}
+
+	if (parse_telem_info_file(fd_target_dir, "guid", "%lx", &target_guid)) {
+		fprintf(stderr, "%s: Failed to parse the target guid file: %s", __func__, strerror(errno));
+		exit(1);
+	}
+
+	close(fd_target_dir);
+
+	pmt_diriter_init(&pmt_iter);
+
+	for (dirname = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); dirname != NULL;
+	     dirname = pmt_diriter_next(&pmt_iter)) {
+
+		fd_telem_dir = openat(dirfd(pmt_iter.dir), dirname->d_name, O_RDONLY | O_DIRECTORY);
+		if (fd_telem_dir == -1)
+			continue;
+
+		if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) {
+			fprintf(stderr, "%s: Failed to parse the guid file: %s", __func__, strerror(errno));
+			continue;
+		}
+
+		if (fstat(fd_telem_dir, &stat) == -1) {
+			fprintf(stderr, "%s: Failed to stat %s directory: %s", __func__,
+				dirname->d_name, strerror(errno));
+			continue;
+		}
+
+		/*
+		 * If reached the same directory as target, exit the loop.
+		 * Seq has the correct value now.
+		 */
+		if (stat.st_dev == target_stat.st_dev && stat.st_ino == target_stat.st_ino) {
+			ret = 0;
+			break;
+		}
+
+		/*
+		 * If reached directory with the same guid,
+		 * but it's not the target directory yet,
+		 * increment seq and continue the search.
+		 */
+		if (guid == target_guid)
+			++seq;
+
+		close(fd_telem_dir);
+		fd_telem_dir = -1;
+	}
+
+	pmt_diriter_remove(&pmt_iter);
+
+	if (fd_telem_dir != -1)
+		close(fd_telem_dir);
+
+	if (!ret) {
+		*out_guid = target_guid;
+		*out_seq = seq;
+	}
+
+	return ret;
+}
+
 void parse_add_command_pmt(char *add_command)
 {
 	char *name = NULL;
 	char *type_name = NULL;
 	char *format_name = NULL;
+	char *direct_path = NULL;
+	static const char direct_path_prefix[] = "path=";
 	unsigned int offset;
 	unsigned int lsb;
 	unsigned int msb;
 	unsigned int guid;
+	unsigned int seq = 0; /* By default, pick first file in a sequence with a given GUID. */
 	unsigned int domain_id;
 	enum counter_scope scope = 0;
 	enum pmt_datatype type = PMT_TYPE_RAW;
@@ -9687,6 +10095,13 @@ void parse_add_command_pmt(char *add_command)
 			goto next;
 		}
 
+		if (sscanf(add_command, "seq=%x", &seq) == 1)
+			goto next;
+
+		if (strncmp(add_command, direct_path_prefix, strlen(direct_path_prefix)) == 0) {
+			direct_path = add_command + strlen(direct_path_prefix);
+			goto next;
+		}
 next:
 		add_command = strchr(add_command, ',');
 		if (add_command) {
@@ -9737,6 +10152,11 @@ void parse_add_command_pmt(char *add_command)
 			has_type = true;
 		}
 
+		if (strcmp("tcore_clock", type_name) == 0) {
+			type = PMT_TYPE_TCORE_CLOCK;
+			has_type = true;
+		}
+
 		if (!has_type) {
 			printf("%s: invalid %s: %s\n", __func__, "type", type_name);
 			exit(1);
@@ -9758,8 +10178,24 @@ void parse_add_command_pmt(char *add_command)
 		exit(1);
 	}
 
+	if (direct_path && has_guid) {
+		printf("%s: path and guid+seq parameters are mutually exclusive\n"
+		       "notice: passed guid=0x%x and path=%s\n", __func__, guid, direct_path);
+		exit(1);
+	}
+
+	if (direct_path) {
+		if (pmt_parse_from_path(direct_path, &guid, &seq)) {
+			printf("%s: failed to parse PMT file from %s\n", __func__, direct_path);
+			exit(1);
+		}
+
+		/* GUID was just infered from the direct path. */
+		has_guid = true;
+	}
+
 	if (!has_guid) {
-		printf("%s: missing %s\n", __func__, "guid");
+		printf("%s: missing %s\n", __func__, "guid or path");
 		exit(1);
 	}
 
@@ -9773,7 +10209,7 @@ void parse_add_command_pmt(char *add_command)
 		exit(1);
 	}
 
-	pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED);
+	pmt_add_counter(guid, seq, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED);
 }
 
 void parse_add_command(char *add_command)
@@ -9921,6 +10357,7 @@ void cmdline(int argc, char **argv)
 		{ "Dump", no_argument, 0, 'D' },
 		{ "debug", no_argument, 0, 'd' },	/* internal, not documented */
 		{ "enable", required_argument, 0, 'e' },
+		{ "force", no_argument, 0, 'f' },
 		{ "interval", required_argument, 0, 'i' },
 		{ "IPC", no_argument, 0, 'I' },
 		{ "num_iterations", required_argument, 0, 'n' },
@@ -9981,6 +10418,9 @@ void cmdline(int argc, char **argv)
 			/* --enable specified counter */
 			bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST);
 			break;
+		case 'f':
+			force_load++;
+			break;
 		case 'd':
 			debug++;
 			ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);