perf intel-pt: Add support for decoding PSB+ only

A single q option decodes ip from only FUP/TIP packets. Make it so that
repeating the q option (i.e. qq) decodes only PSB+, getting ip if there
is a FUP packet within PSB+ (i.e. between PSB and PSBEND).

Example:

 $ perf record -e intel_pt//u grep -rI pudding drivers
 [ perf record: Woken up 52 times to write data ]
 [ perf record: Captured and wrote 57.870 MB perf.data ]
 $ time perf script --itrace=bi | wc -l
 58948289

 real    1m23.863s
 user    1m23.251s
 sys     0m7.452s
 $ time perf script --itrace=biq | wc -l
 3385694

 real    0m4.453s
 user    0m4.455s
 sys     0m0.328s
 $ time perf script --itrace=biqq | wc -l
 1883

 real    0m0.047s
 user    0m0.043s
 sys     0m0.009s

Signed-off-by: Adrian Hunter <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: ahunter6

tools/perf/Documentation/perf-intel-pt.txt

@@ -999,6 +999,21 @@ What *will* be decoded with the (single) q option:
 Note the q option does not specify what events will be synthesized e.g. the p
 option must be used also to show power events.
 
+Repeating the q option (double-q i.e. qq) results in even faster decoding and even
+less detail.  The decoder decodes only extended PSB (PSB+) packets, getting the
+instruction pointer if there is a FUP packet within PSB+ (i.e. between PSB and
+PSBEND).  Note PSB packets occur regularly in the trace based on the psb_period
+config term (refer config terms section).  There will be a FUP packet if the
+PSB+ occurs while control flow is being traced.
+
+What will *not* be decoded with the qq option:
+
+	- everything except instruction pointer associated with PSB packets
+
+What *will* be decoded with the qq option:
+
+	- instruction pointer associated with PSB packets
+
 
 dump option
 ~~~~~~~~~~~

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -113,6 +113,7 @@ struct intel_pt_decoder {
 	bool in_psb;
 	bool hop;
 	bool hop_psb_fup;
+	bool leap;
 	enum intel_pt_param_flags flags;
 	uint64_t pos;
 	uint64_t last_ip;
@@ -240,6 +241,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->return_compression = params->return_compression;
 	decoder->branch_enable      = params->branch_enable;
 	decoder->hop                = params->quick >= 1;
+	decoder->leap               = params->quick >= 2;
 
 	decoder->flags              = params->flags;
 
@@ -1903,9 +1905,18 @@ static int intel_pt_resample(struct intel_pt_decoder *decoder)
 #define HOP_RETURN	2
 #define HOP_AGAIN	3
 
+static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder);
+
 /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */
 static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err)
 {
+	/* Leap from PSB to PSB, getting ip from FUP within PSB+ */
+	if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) {
+		*err = intel_pt_scan_for_psb(decoder);
+		if (*err)
+			return HOP_RETURN;
+	}
+
 	switch (decoder->packet.type) {
 	case INTEL_PT_TNT:
 		return HOP_IGNORE;
@@ -2681,6 +2692,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	decoder->ip = 0;
 	intel_pt_clear_stack(&decoder->stack);
 
+leap:
 	err = intel_pt_scan_for_psb(decoder);
 	if (err)
 		return err;
@@ -2702,6 +2714,12 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 			decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 		else
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+	} else if (decoder->leap) {
+		/*
+		 * In leap mode, only PSB+ is decoded, so keeping leaping to the
+		 * next PSB until there is an ip.
+		 */
+		goto leap;
 	} else {
 		return intel_pt_sync_ip(decoder);
 	}