perf tool: Fix endianness handling of u32 data in samples

Currently, analyzing PPC data files on x86 the cpu field is always 0 and
the tid and pid are backwards. For example, analyzing a PPC file on PPC
the pid/tid fields show:

        rsyslogd  1210/1212

and analyzing the same PPC file using an x86 perf binary shows:

        rsyslogd  1212/1210

The problem is that the swap_op method for samples is
perf_event__all64_swap which assumes all elements in the sample_data
struct are u64s. cpu, tid and pid are u32s and need to be handled
individually. Given that the swap is done before the sample is parsed,
the simplest solution is to undo the 64-bit swap of those elements when
the sample is parsed and do the proper swap.

The RAW data field is generic and perf cannot have programmatic knowledge
of how to treat that data. Instead a warning is given to the user.

Thanks to Anton Blanchard for providing a data file for a mult-CPU
PPC system so I could verify the fix for the CPU fields.

v3 -> v4:
- fixed use of WARN_ONCE

v2 -> v3:
- used WARN_ONCE for message regarding raw data
- removed struct wrapper around union
- fixed whitespace issues

v1 -> v2:
- added a union for undoing the byte-swap on u64 and redoing swap on
  u32's to address compiler errors (see git commit 65014ab3)

Cc: Anton Blanchard <anton@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-test.c

@@ -561,7 +561,7 @@ static int test__basic_mmap(void)
 		}
 
 		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample);
+					       false, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;

tools/perf/util/event.h

@@ -186,6 +186,6 @@ const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample);
+			     struct perf_sample *sample, bool swapped);
 
 #endif /* __PERF_RECORD_H */

tools/perf/util/evsel.c

@@ -7,6 +7,8 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <byteswap.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -342,10 +344,20 @@ static bool sample_overlap(const union perf_event *event,
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *data)
+			     struct perf_sample *data, bool swapped)
 {
 	const u64 *array;
 
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union {
+		u64 val64;
+		u32 val32[2];
+	} u;
+
+
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 
@@ -366,9 +378,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		data->pid = u.val32[0];
+		data->tid = u.val32[1];
 		array++;
 	}
 
@@ -395,8 +414,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
+
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		data->cpu = u.val32[0];
 		array++;
 	}
 
@@ -423,18 +449,24 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
+		u.val64 = *array;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
 
 		if (sample_overlap(event, array, sizeof(u32)))
 			return -EFAULT;
 
-		data->raw_size = *p;
-		p++;
+		data->raw_size = u.val32[0];
 
-		if (sample_overlap(event, p, data->raw_size))
+		if (sample_overlap(event, &u.val32[1], data->raw_size))
 			return -EFAULT;
 
-		data->raw_data = p;
+		data->raw_data = &u.val32[1];
 	}
 
 	return 0;

tools/perf/util/session.h

@@ -162,7 +162,8 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 {
 	return perf_event__parse_sample(event, session->sample_type,
 					session->sample_size,
-					session->sample_id_all, sample);
+					session->sample_id_all, sample,
+					session->header.needs_swap);
 }
 
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,