[RESENT PATCH v5 1/2] tools/perf: Fix the mask...

[RESENT PATCH v5 1/2] tools/perf: Fix the mask in regs_dump__printf and print_sample_iregs

From: Madhavan Srinivasan <hidden>
Date: 2016-08-03 08:29:45

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 <redacted>
Reviewed-by: Yury Norov <redacted>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Yury Norov <redacted>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Kan Liang <redacted>
Cc: Wang Nan <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <redacted>
---
 tools/include/linux/bitmap.h |  2 ++
 tools/lib/bitmap.c           | 18 ++++++++++++++++++
 tools/perf/builtin-script.c  |  4 +++-
 tools/perf/util/session.c    |  4 +++-
 4 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 28f5493da491..5e98525387dc 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h

@@ -2,6 +2,7 @@
 #define _PERF_BITOPS_H
 
 #include <string.h>
+#include <limits.h>
 #include <linux/bitops.h>
 
 #define DECLARE_BITMAP(name,bits) \

@@ -10,6 +11,7 @@
 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 971ff91b16cb..20d7988a1636 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c

@@ -418,11 +418,13 @@ 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_BITMAP(_mask, 64);
 
 	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 5d61242a6e64..440a9fb2a6fb 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c

@@ -944,8 +944,10 @@ static void branch_stack__printf(struct perf_sample *sample)
 static void regs_dump__printf(u64 mask, u64 *regs)
 {
 	unsigned rid, i = 0;
+	DECLARE_BITMAP(_mask, 64);
 
-	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",

-- 
2.7.4

[RESEND PATCH 2/2] perf/core: Fix the mask in perf_output_sample_regs

From: Madhavan Srinivasan <hidden>
Date: 2016-08-03 08:29:57

When decoding the perf_regs mask in perf_output_sample_regs(),
we loop through the mask using find_first_bit and find_next_bit functions.
While the exisitng code works fine in most of the case,
the logic is broken for 32bit kernel (Big Endian).
When reading u64 mask using (u32 *)(&val)[0], find_*_bit() assumes it gets
lower 32bits of u64 but instead gets upper 32bits which is wrong.
Proposed fix is to swap the words of the u64 to handle this case.
This is _not_ endianness swap.

Suggested-by: Yury Norov <redacted>
Reviewed-by: Yury Norov <redacted>
Cc: Yury Norov <redacted>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <redacted>
---
 include/linux/bitmap.h |  2 ++
 kernel/events/core.c   |  4 +++-
 lib/bitmap.c           | 19 +++++++++++++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 27bfc0b631a9..6f2cc9eb12d9 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h

@@ -188,6 +188,8 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf,
 #define small_const_nbits(nbits) \
 	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
 
+extern void bitmap_from_u64(unsigned long *dst, u64 mask);
+
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 356a6c7cb52a..f5ed20a63a5e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c

@@ -5269,8 +5269,10 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 			struct pt_regs *regs, u64 mask)
 {
 	int bit;
+	DECLARE_BITMAP(_mask, 64);
 
-	for_each_set_bit(bit, (const unsigned long *) &mask,
+	bitmap_from_u64(_mask, mask);
+	for_each_set_bit(bit, _mask,
 			 sizeof(mask) * BITS_PER_BYTE) {
 		u64 val;

diff --git a/lib/bitmap.c b/lib/bitmap.c
index eca88087fa8a..2b9bda507645 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c

@@ -1170,3 +1170,22 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n
 }
 EXPORT_SYMBOL(bitmap_copy_le);
 #endif
+
+/*
+ * bitmap_from_u64 - Check and swap words within u64.
+ *  @mask: source bitmap
+ *  @dst:  destination bitmap
+ *
+ * In 32bit Big Endian kernel, when using (u32 *)(&val)[*]
+ * to read u64 mask, we will get wrong word.
+ * That is "(u32 *)(&val)[0]" gets upper 32 bits,
+ * but expected could be 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;
+}
+EXPORT_SYMBOL(bitmap_from_u64);

-- 
2.7.4

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help