[PATCH v4] tools/perf: Fix the mask in regs_dump__printf and print_sample_iregs

[Madhavan Srinivasan]

When decoding the perf_regs mask in regs_dump__printf(),
we loop through the mask using find_first_bit and find_next_bit functions.
"mask" is of type "u64", but sent as a "unsigned long *" to
lib functions along with sizeof().

While the exisitng code works fine in most of the case,
the logic is broken when using a 32bit perf on a 64bit kernel (Big Endian).
When reading u64 using (u32 *)(&val)[0], perf (lib/find_*_bit()) assumes it gets
lower 32bits of u64 which is wrong. Proposed fix is to swap the words
of the u64 to handle this case. This is _not_ endianess swap.

Suggested-by: Yury Norov <ynorov at caviumnetworks.com>
Cc: Yury Norov <ynorov at caviumnetworks.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: Arnaldo Carvalho de Melo <acme at kernel.org>
Cc: Alexander Shishkin <alexander.shishkin at linux.intel.com>
Cc: Jiri Olsa <jolsa at kernel.org>
Cc: Adrian Hunter <adrian.hunter at intel.com>
Cc: Kan Liang <kan.liang at intel.com>
Cc: Wang Nan <wangnan0 at huawei.com>
Cc: Michael Ellerman <mpe at ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <maddy at linux.vnet.ibm.com>
---
Changelog v3:
1)Moved the swap function to lib/bitmap.c
2)Added a macro for declaration
3)Added the comments

Changelog v2:
1)Moved the swap code to a common function
2)Added more comments in the code

Changelog v1:
1)updated commit message and patch subject
2)Add the fix to print_sample_iregs() in builtin-script.c

 tools/include/linux/bitmap.h |  5 +++++
 tools/lib/bitmap.c           | 18 ++++++++++++++++++
 tools/perf/builtin-script.c  |  4 +++-
 tools/perf/util/session.c    |  4 +++-
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 28f5493da491..6be9a7ddcb03 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -2,14 +2,19 @@
 #define _PERF_BITOPS_H
 
 #include <string.h>
+#include <limits.h>
 #include <linux/bitops.h>
 
 #define DECLARE_BITMAP(name,bits) \
 	unsigned long name[BITS_TO_LONGS(bits)]
 
+#define DECLARE_U64_BITMAP(__name) \
+	unsigned long __name[sizeof(u64)/sizeof(unsigned long)]
+
 int __bitmap_weight(const unsigned long *bitmap, int bits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
+void bitmap_from_u64(unsigned long *dst, u64 mask);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 0a1adc1111fd..464a0cc63e6a 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -29,3 +29,21 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 	for (k = 0; k < nr; k++)
 		dst[k] = bitmap1[k] | bitmap2[k];
 }
+
+/*
+ * bitmap_from_u64 - Check and swap words within u64.
+ *  @mask: source bitmap
+ *  @dst:  destination bitmap
+ *
+ * In 32 bit big endian userspace on a 64bit kernel, 'unsigned long' is 32 bits.
+ * When reading u64 using (u32 *)(&val)[0] and (u32 *)(&val)[1],
+ * we will get wrong value for the mask. That is "(u32 *)(&val)[0]"
+ * gets upper 32 bits of u64, but perf may expect lower 32bits of u64.
+ */
+void bitmap_from_u64(unsigned long *dst, u64 mask)
+{
+	dst[0] = mask & ULONG_MAX;
+
+	if (sizeof(mask) > sizeof(unsigned long))
+		dst[1] = mask >> 32;
+}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e3ce2f34d3ad..1120ca117071 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -412,11 +412,13 @@ static void print_sample_iregs(struct perf_sample *sample,
 	struct regs_dump *regs = &sample->intr_regs;
 	uint64_t mask = attr->sample_regs_intr;
 	unsigned i = 0, r;
+	DECLARE_U64_BITMAP(_mask);
 
 	if (!regs)
 		return;
 
-	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+	bitmap_from_u64(_mask, mask);
+	for_each_set_bit(r, _mask, sizeof(mask) * 8) {
 		u64 val = regs->regs[i++];
 		printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5214974e841a..fab1f9c1e0f5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -940,8 +940,10 @@ static void branch_stack__printf(struct perf_sample *sample)
 static void regs_dump__printf(u64 mask, u64 *regs)
 {
 	unsigned rid, i = 0;
+	DECLARE_U64_BITMAP(_mask);
 
-	for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+	bitmap_from_u64(_mask, mask);
+	for_each_set_bit(rid, _mask, sizeof(mask) * 8) {
 		u64 val = regs[i++];
 
 		printf(".... %-5s 0x%" PRIx64 "\n",
-- 
1.9.1