Merge 17c66e9e49a181498ae3c75809c98fdbe630de28 on remote branch

Change-Id: I49238aefe09bba152a8000c046959157c328f183

6 files changed, 57 insertions, 13 deletions

diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 5ad9ee1dd7f6..57187d6790c1 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -3,17 +3,14 @@
 
 #include <asm/types.h>
 #include <linux/kernel.h>
-#include <linux/compiler.h>
-
 #ifndef __WORDSIZE
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
 #endif
 
 #define BITS_PER_LONG __WORDSIZE
+#include <linux/bits.h>
+#include <linux/compiler.h>
 
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/tools/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 73d192f57dc3..df41deed0320 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -32,6 +32,10 @@
 #include <numa.h>
 #include <numaif.h>
 
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
 /*
  * Regular printout to the terminal, supressed if -q is specified:
  */
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 62b38f2ff60d..c1944765533c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -58,6 +58,7 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_NO_IP,
 	INTEL_PT_STATE_ERR_RESYNC,
 	INTEL_PT_STATE_IN_SYNC,
+	INTEL_PT_STATE_TNT_CONT,
 	INTEL_PT_STATE_TNT,
 	INTEL_PT_STATE_TIP,
 	INTEL_PT_STATE_TIP_PGD,
@@ -72,8 +73,9 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
 	case INTEL_PT_STATE_NO_IP:
 	case INTEL_PT_STATE_ERR_RESYNC:
 	case INTEL_PT_STATE_IN_SYNC:
-	case INTEL_PT_STATE_TNT:
+	case INTEL_PT_STATE_TNT_CONT:
 		return true;
+	case INTEL_PT_STATE_TNT:
 	case INTEL_PT_STATE_TIP:
 	case INTEL_PT_STATE_TIP_PGD:
 	case INTEL_PT_STATE_FUP:
@@ -854,16 +856,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder)
 	timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
 	masked_timestamp = timestamp & decoder->period_mask;
 	if (decoder->continuous_period) {
-		if (masked_timestamp != decoder->last_masked_timestamp)
+		if (masked_timestamp > decoder->last_masked_timestamp)
 			return 1;
 	} else {
 		timestamp += 1;
 		masked_timestamp = timestamp & decoder->period_mask;
-		if (masked_timestamp != decoder->last_masked_timestamp) {
+		if (masked_timestamp > decoder->last_masked_timestamp) {
 			decoder->last_masked_timestamp = masked_timestamp;
 			decoder->continuous_period = true;
 		}
 	}
+
+	if (masked_timestamp < decoder->last_masked_timestamp)
+		return decoder->period_ticks;
+
 	return decoder->period_ticks - (timestamp - masked_timestamp);
 }
 
@@ -892,7 +898,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder)
 	case INTEL_PT_PERIOD_TICKS:
 		timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
 		masked_timestamp = timestamp & decoder->period_mask;
-		decoder->last_masked_timestamp = masked_timestamp;
+		if (masked_timestamp > decoder->last_masked_timestamp)
+			decoder->last_masked_timestamp = masked_timestamp;
+		else
+			decoder->last_masked_timestamp += decoder->period_ticks;
 		break;
 	case INTEL_PT_PERIOD_NONE:
 	case INTEL_PT_PERIOD_MTC:
@@ -1141,7 +1150,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
 				return -ENOENT;
 			}
 			decoder->tnt.count -= 1;
-			if (!decoder->tnt.count)
+			if (decoder->tnt.count)
+				decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+			else
 				decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->tnt.payload <<= 1;
 			decoder->state.from_ip = decoder->ip;
@@ -1172,7 +1183,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
 
 		if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
 			decoder->tnt.count -= 1;
-			if (!decoder->tnt.count)
+			if (decoder->tnt.count)
+				decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+			else
 				decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			if (decoder->tnt.payload & BIT63) {
 				decoder->tnt.payload <<= 1;
@@ -1192,8 +1205,11 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
 				return 0;
 			}
 			decoder->ip += intel_pt_insn.length;
-			if (!decoder->tnt.count)
+			if (!decoder->tnt.count) {
+				decoder->sample_timestamp = decoder->timestamp;
+				decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
 				return -EAGAIN;
+			}
 			decoder->tnt.payload <<= 1;
 			continue;
 		}
@@ -2116,6 +2132,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_walk_trace(decoder);
 			break;
 		case INTEL_PT_STATE_TNT:
+		case INTEL_PT_STATE_TNT_CONT:
 			err = intel_pt_walk_tnt(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_trace(decoder);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index accb7ece1d3c..3d7af024c73f 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,4 +1,5 @@
 #include "util.h"
+#include <linux/compiler.h>
 #include "linux/string.h"
 
 #define K 1024LL
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dcc659017976..ee5d1dfe13da 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -76,7 +76,6 @@
 #include <sys/ttydefaults.h>
 #include <api/fs/tracing_path.h>
 #include <termios.h>
-#include <linux/bitops.h>
 #include <termios.h>
 
 extern const char *graph_line;