Merge branch 'master' into next

Merge master back into next, this allows us to resolve some conflicts in
arch/powerpc/Kconfig, and also re-sort the symbols under config PPC so
that they are in alphabetical order again.

26 files changed, 2085 insertions, 921 deletions

diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c
index 1639b4d832cd..4096bcd511d1 100644
--- a/tools/gpio/gpio-utils.c
+++ b/tools/gpio/gpio-utils.c
@@ -20,7 +20,7 @@
 #define CONSUMER "gpio-utils"
 
 /**
- * doc: Operation of gpio
+ * DOC: Operation of gpio
  *
  * Provide the api of gpiochip for chardev interface. There are two
  * types of api.  The first one provide as same function as each
@@ -100,7 +100,7 @@ exit_free_name:
 }
 
 /**
- * gpiotools_set_values(): Set the value of gpio(s)
+ * gpiotools_set_values() - Set the value of gpio(s)
  * @fd:			The fd returned by
  *			gpiotools_request_line().
  * @values:		The array of values want to set.
@@ -124,7 +124,7 @@ int gpiotools_set_values(const int fd, struct gpio_v2_line_values *values)
 }
 
 /**
- * gpiotools_get_values(): Get the value of gpio(s)
+ * gpiotools_get_values() - Get the value of gpio(s)
  * @fd:			The fd returned by
  *			gpiotools_request_line().
  * @values:		The array of values get from hardware.
@@ -148,7 +148,7 @@ int gpiotools_get_values(const int fd, struct gpio_v2_line_values *values)
 }
 
 /**
- * gpiotools_release_line(): Release the line(s) of gpiochip
+ * gpiotools_release_line() - Release the line(s) of gpiochip
  * @fd:			The fd returned by
  *			gpiotools_request_line().
  *
@@ -169,7 +169,7 @@ int gpiotools_release_line(const int fd)
 }
 
 /**
- * gpiotools_get(): Get value from specific line
+ * gpiotools_get() - Get value from specific line
  * @device_name:	The name of gpiochip without prefix "/dev/",
  *			such as "gpiochip0"
  * @line:		number of line, such as 2.
@@ -191,7 +191,7 @@ int gpiotools_get(const char *device_name, unsigned int line)
 
 
 /**
- * gpiotools_gets(): Get values from specific lines.
+ * gpiotools_gets() - Get values from specific lines.
  * @device_name:	The name of gpiochip without prefix "/dev/",
  *			such as "gpiochip0".
  * @lines:		An array desired lines, specified by offset
@@ -230,7 +230,7 @@ int gpiotools_gets(const char *device_name, unsigned int *lines,
 }
 
 /**
- * gpiotools_set(): Set value to specific line
+ * gpiotools_set() - Set value to specific line
  * @device_name:	The name of gpiochip without prefix "/dev/",
  *			such as "gpiochip0"
  * @line:		number of line, such as 2.
@@ -248,13 +248,13 @@ int gpiotools_set(const char *device_name, unsigned int line,
 }
 
 /**
- * gpiotools_sets(): Set values to specific lines.
+ * gpiotools_sets() - Set values to specific lines.
  * @device_name:	The name of gpiochip without prefix "/dev/",
  *			such as "gpiochip0".
  * @lines:		An array desired lines, specified by offset
  *			index for the associated GPIO device.
  * @num_lines:		The number of lines to request.
- * @value:		The array of values set to gpiochip, must be
+ * @values:		The array of values set to gpiochip, must be
  *			0(low) or 1(high).
  *
  * Return:		On success return 0;
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
index 16ed1982cb34..6481fd11012a 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/asm-generic/bitops/find.h
@@ -2,6 +2,13 @@
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
 
+extern unsigned long _find_next_bit(const unsigned long *addr1,
+		const unsigned long *addr2, unsigned long nbits,
+		unsigned long start, unsigned long invert, unsigned long le);
+extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -12,8 +19,22 @@
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
-		size, unsigned long offset);
+static inline
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_and_bit
@@ -27,13 +48,26 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_and_bit(const unsigned long *addr1,
+static inline
+unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
-		unsigned long offset);
+		unsigned long offset)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr1 & *addr2 & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_zero_bit
-
 /**
  * find_next_zero_bit - find the next cleared bit in a memory region
  * @addr: The address to base the search on
@@ -43,8 +77,22 @@ extern unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
+static inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset);
+				 unsigned long offset)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr | ~GENMASK(size - 1, offset);
+		return val == ~0UL ? size : ffz(val);
+	}
+
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
+}
 #endif
 
 #ifndef find_first_bit
@@ -57,8 +105,17 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number of the first set bit.
  * If no bits are set, returns @size.
  */
-extern unsigned long find_first_bit(const unsigned long *addr,
-				    unsigned long size);
+static inline
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_bit(addr, size);
+}
 
 #endif /* find_first_bit */
 
@@ -72,7 +129,17 @@ extern unsigned long find_first_bit(const unsigned long *addr,
  * Returns the bit number of the first cleared bit.
  * If no bits are zero, returns @size.
  */
-unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size);
+static inline
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr | ~GENMASK(size - 1, 0);
+
+		return val == ~0UL ? size : ffz(val);
+	}
+
+	return _find_first_zero_bit(addr, size);
+}
 #endif
 
 #endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
index 8f2283052333..2093d56ddd11 100644
--- a/tools/include/asm-generic/bitsperlong.h
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -18,4 +18,7 @@
 #define BITS_PER_LONG_LONG 64
 #endif
 
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0)
+
 #endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 477a1cae513f..330dbf7509cc 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -20,17 +20,9 @@ int __bitmap_equal(const unsigned long *bitmap1,
 void bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
+#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
-#define BITMAP_LAST_WORD_MASK(nbits)					\
-(									\
-	((nbits) % BITS_PER_LONG) ?					\
-		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
-)
-
-#define small_const_nbits(nbits) \
-	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
-
-static inline void bitmap_zero(unsigned long *dst, int nbits)
+static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = 0UL;
@@ -66,7 +58,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
 	return find_first_zero_bit(src, nbits) == nbits;
 }
 
-static inline int bitmap_weight(const unsigned long *src, int nbits)
+static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -74,7 +66,7 @@ static inline int bitmap_weight(const unsigned long *src, int nbits)
 }
 
 static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			     const unsigned long *src2, int nbits)
+			     const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 | *src2;
@@ -141,7 +133,7 @@ static inline void bitmap_free(unsigned long *bitmap)
  * @buf: buffer to store output
  * @size: size of @buf
  */
-size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
+size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
 			char *buf, size_t size);
 
 /**
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 5043747ef6c5..f4e914712b6f 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -28,11 +28,11 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		dst[k] = bitmap1[k] | bitmap2[k];
 }
 
-size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
+size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
 			char *buf, size_t size)
 {
 	/* current bit is 'cur', most recently seen range is [rbot, rtop] */
-	int cur, rbot, rtop;
+	unsigned int cur, rbot, rtop;
 	bool first = true;
 	size_t ret = 0;
 
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index ac37022e9486..109aa7ffcf97 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -28,11 +28,12 @@
  *    searching it for one bits.
  *  - The optional "addr2", which is anded with "addr1" if present.
  */
-static inline unsigned long _find_next_bit(const unsigned long *addr1,
+unsigned long _find_next_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert)
+		unsigned long start, unsigned long invert, unsigned long le)
 {
-	unsigned long tmp;
+	unsigned long tmp, mask;
+	(void) le;
 
 	if (unlikely(start >= nbits))
 		return nbits;
@@ -43,7 +44,19 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
 	tmp ^= invert;
 
 	/* Handle 1st word. */
-	tmp &= BITMAP_FIRST_WORD_MASK(start);
+	mask = BITMAP_FIRST_WORD_MASK(start);
+
+	/*
+	 * Due to the lack of swab() in tools, and the fact that it doesn't
+	 * need little-endian support, just comment it out
+	 */
+#if (0)
+	if (le)
+		mask = swab(mask);
+#endif
+
+	tmp &= mask;
+
 	start = round_down(start, BITS_PER_LONG);
 
 	while (!tmp) {
@@ -57,18 +70,12 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
 		tmp ^= invert;
 	}
 
-	return min(start + __ffs(tmp), nbits);
-}
+#if (0)
+	if (le)
+		tmp = swab(tmp);
 #endif
 
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL);
+	return min(start + __ffs(tmp), nbits);
 }
 #endif
 
@@ -76,7 +83,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 /*
  * Find the first set bit in a memory region.
  */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
@@ -93,7 +100,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 /*
  * Find the first cleared bit in a memory region.
  */
-unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
@@ -105,20 +112,3 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 	return size;
 }
 #endif
-
-#ifndef find_next_zero_bit
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL);
-}
-#endif
-
-#ifndef find_next_and_bit
-unsigned long find_next_and_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long size,
-		unsigned long offset)
-{
-	return _find_next_bit(addr1, addr2, size, offset, 0UL);
-}
-#endif
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index f6b7e85b121c..9b17097bc3d7 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -54,12 +54,14 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
 .PP
-\fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
+\fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.
 .PP
 \fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec", "Time_Of_Day_Seconds", "APIC" and "X2APIC".
 The column name "all" can be used to enable all disabled-by-default built-in counters.
 .PP
-\fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
+\fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.
+.PP
+\fB--show CATEGORY --hide CATEGORY\fP  Show and hide also accept a single CATEGORY of columns: "all", "topology", "idle", "frequency", "power", "sysfs", "other".
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 5939615265f1..47d3ba895d6d 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) 2013 Intel Corporation.
+ * Copyright (c) 2021 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  */
 
@@ -33,12 +33,20 @@
 #include <sys/capability.h>
 #include <errno.h>
 #include <math.h>
+#include <linux/perf_event.h>
+#include <asm/unistd.h>
+#include <stdbool.h>
 
 char *proc_stat = "/proc/stat";
 FILE *outf;
 int *fd_percpu;
-struct timeval interval_tv = {5, 0};
-struct timespec interval_ts = {5, 0};
+int *fd_instr_count_percpu;
+struct timeval interval_tv = { 5, 0 };
+struct timespec interval_ts = { 5, 0 };
+
+/* Save original CPU model */
+unsigned int model_orig;
+
 unsigned int num_iterations;
 unsigned int debug;
 unsigned int quiet;
@@ -75,30 +83,33 @@ char *output_buffer, *outp;
 unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
-unsigned long long  gfx_cur_rc6_ms;
+unsigned int do_ipc;
+unsigned long long gfx_cur_rc6_ms;
 unsigned long long cpuidle_cur_cpu_lpi_us;
 unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int gfx_cur_mhz;
 unsigned int gfx_act_mhz;
-unsigned int tcc_activation_temp;
-unsigned int tcc_activation_temp_override;
+unsigned int tj_max;
+unsigned int tj_max_override;
+int tcc_offset_bits;
 double rapl_power_units, rapl_time_units;
 double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
 unsigned int do_core_perf_limit_reasons;
 unsigned int has_automatic_cstate_conversion;
+unsigned int dis_cstate_prewake;
 unsigned int do_gfx_perf_limit_reasons;
 unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
 double discover_bclk(unsigned int family, unsigned int model);
-unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
+unsigned int has_hwp;		/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
-unsigned int has_hwp_notify;		/* IA32_HWP_INTERRUPT */
+unsigned int has_hwp_notify;	/* IA32_HWP_INTERRUPT */
 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 has_hwp_epp;	/* IA32_HWP_REQUEST[bits 31:24] */
+unsigned int has_hwp_pkg;	/* IA32_HWP_REQUEST_PKG */
 unsigned int has_misc_feature_control;
 unsigned int first_counter_read = 1;
 int ignore_stdin;
@@ -173,12 +184,14 @@ struct thread_data {
 	unsigned long long aperf;
 	unsigned long long mperf;
 	unsigned long long c1;
-	unsigned long long  irq_count;
+	unsigned long long instr_count;
+	unsigned long long irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int apic_id;
 	unsigned int x2apic_id;
 	unsigned int flags;
+	bool is_atom;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
 	unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
@@ -240,12 +253,11 @@ struct pkg_data {
 	 ((node_no) * topo.cores_per_node) +				\
 	 (core_no))
 
-
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
-enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
-enum counter_type {COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC};
-enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
+enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
+enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
+enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
 
 struct msr_counter {
 	unsigned int msr_num;
@@ -281,9 +293,9 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr);
 struct msr_sum_array {
 	/* get_msr_sum() = sum + (get_msr() - last) */
 	struct {
-		/*The accumulated MSR value is updated by the timer*/
+		/*The accumulated MSR value is updated by the timer */
 		unsigned long long sum;
-		/*The MSR footprint recorded in last timer*/
+		/*The MSR footprint recorded in last timer */
 		unsigned long long last;
 	} entries[IDX_COUNT];
 };
@@ -291,13 +303,16 @@ struct msr_sum_array {
 /* The percpu MSR sum array.*/
 struct msr_sum_array *per_cpu_msr_sum;
 
-int idx_to_offset(int idx)
+off_t idx_to_offset(int idx)
 {
-	int offset;
+	off_t offset;
 
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		offset = MSR_PKG_ENERGY_STATUS;
+		if (do_rapl & RAPL_AMD_F17H)
+			offset = MSR_PKG_ENERGY_STAT;
+		else
+			offset = MSR_PKG_ENERGY_STATUS;
 		break;
 	case IDX_DRAM_ENERGY:
 		offset = MSR_DRAM_ENERGY_STATUS;
@@ -320,12 +335,13 @@ int idx_to_offset(int idx)
 	return offset;
 }
 
-int offset_to_idx(int offset)
+int offset_to_idx(off_t offset)
 {
 	int idx;
 
 	switch (offset) {
 	case MSR_PKG_ENERGY_STATUS:
+	case MSR_PKG_ENERGY_STAT:
 		idx = IDX_PKG_ENERGY;
 		break;
 	case MSR_DRAM_ENERGY_STATUS:
@@ -353,7 +369,7 @@ int idx_valid(int idx)
 {
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		return do_rapl & RAPL_PKG;
+		return do_rapl & (RAPL_PKG | RAPL_AMD_F17H);
 	case IDX_DRAM_ENERGY:
 		return do_rapl & RAPL_DRAM;
 	case IDX_PP0_ENERGY:
@@ -368,6 +384,7 @@ int idx_valid(int idx)
 		return 0;
 	}
 }
+
 struct sys_counters {
 	unsigned int added_thread_counters;
 	unsigned int added_core_counters;
@@ -391,7 +408,7 @@ struct cpu_topology {
 	int logical_node_id;	/* 0-based count within the package */
 	int physical_core_id;
 	int thread_id;
-	cpu_set_t *put_ids; /* Processing Unit/Thread IDs */
+	cpu_set_t *put_ids;	/* Processing Unit/Thread IDs */
 } *cpus;
 
 struct topo_params {
@@ -408,7 +425,7 @@ struct topo_params {
 
 struct timeval tv_even, tv_odd, tv_delta;
 
-int *irq_column_2_cpu;	/* /proc/interrupts column numbers */
+int *irq_column_2_cpu;		/* /proc/interrupts column numbers */
 int *irqs_per_cpu;		/* indexed by cpu_num */
 
 void setup_all_buffers(void);
@@ -421,34 +438,31 @@ int cpu_is_not_present(int cpu)
 {
 	return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
 }
+
 /*
  * run func(thread, core, package) in topology order
  * skip non-present cpus
  */
 
-int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
-	struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
+int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pkg_data *),
+		 struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
 {
 	int retval, pkg_no, core_no, thread_no, node_no;
 
 	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) {
-				for (thread_no = 0; thread_no <
-					topo.threads_per_core; ++thread_no) {
+				for (thread_no = 0; thread_no < topo.threads_per_core; ++thread_no) {
 					struct thread_data *t;
 					struct core_data *c;
 					struct pkg_data *p;
 
-					t = GET_THREAD(thread_base, thread_no,
-						       core_no, node_no,
-						       pkg_no);
+					t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no);
 
 					if (cpu_is_not_present(t->cpu_id))
 						continue;
 
-					c = GET_CORE(core_base, core_no,
-						     node_no, pkg_no);
+					c = GET_CORE(core_base, core_no, node_no, pkg_no);
 					p = GET_PKG(pkg_base, pkg_no);
 
 					retval = func(t, c, p);
@@ -470,6 +484,7 @@ int cpu_migrate(int cpu)
 	else
 		return 0;
 }
+
 int get_msr_fd(int cpu)
 {
 	char pathname[32];
@@ -490,6 +505,39 @@ int get_msr_fd(int cpu)
 	return fd;
 }
 
+static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags);
+}
+
+static int perf_instr_count_open(int cpu_num)
+{
+	struct perf_event_attr pea;
+	int fd;
+
+	memset(&pea, 0, sizeof(struct perf_event_attr));
+	pea.type = PERF_TYPE_HARDWARE;
+	pea.size = sizeof(struct perf_event_attr);
+	pea.config = PERF_COUNT_HW_INSTRUCTIONS;
+
+	/* counter for cpu_num, including user + kernel and all processes */
+	fd = perf_event_open(&pea, -1, cpu_num, -1, 0);
+	if (fd == -1)
+		err(-1, "cpu%d: perf instruction counter\n", cpu_num);
+
+	return fd;
+}
+
+int get_instr_count_fd(int cpu)
+{
+	if (fd_instr_count_percpu[cpu])
+		return fd_instr_count_percpu[cpu];
+
+	fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu);
+
+	return fd_instr_count_percpu[cpu];
+}
+
 int get_msr(int cpu, off_t offset, unsigned long long *msr)
 {
 	ssize_t retval;
@@ -518,7 +566,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "Bzy_MHz" },
 	{ 0x0, "TSC_MHz" },
 	{ 0x0, "IRQ" },
-	{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
+	{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL },
 	{ 0x0, "sysfs" },
 	{ 0x0, "CPU%c1" },
 	{ 0x0, "CPU%c3" },
@@ -561,6 +609,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "X2APIC" },
 	{ 0x0, "Die" },
 	{ 0x0, "GFXAMHz" },
+	{ 0x0, "IPC" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -616,6 +665,13 @@ struct msr_counter bic[] = {
 #define	BIC_X2APIC	(1ULL << 49)
 #define	BIC_Die		(1ULL << 50)
 #define	BIC_GFXACTMHz	(1ULL << 51)
+#define	BIC_IPC		(1ULL << 52)
+
+#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_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz )
+#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)
+#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -627,7 +683,7 @@ unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC
 #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
 #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
-
+#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
 
 #define MAX_DEFERRED 16
 char *deferred_skip_names[MAX_DEFERRED];
@@ -642,42 +698,40 @@ enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST;
 void help(void)
 {
 	fprintf(outf,
-	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
-	"\n"
-	"Turbostat forks the specified COMMAND and prints statistics\n"
-	"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"
-	"		  eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-	"  -c, --cpu	cpu-set	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, --Dump	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"
-	"		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"
-	"  -n, --num_iterations num\n"
-	"		number of the measurement 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"
-	"		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