[PATCH v3] perf record: collect user registers set jointly with dwarf stacks

[Alexey Budankov]

When dwarf stacks are collected jointly with user specified register
set using --user-regs option like below the full register context is
still captured on a sample:

  $ perf record -g --call-graph dwarf,1024 --user-regs=IP,SP,BP -- matrix.gcc.g.O3

  188143843893585 0x6b48 [0x4f8]: PERF_RECORD_SAMPLE(IP, 0x4002): 23828/23828: 0x401236 period: 1363819 addr: 0x7ffedbdd51ac
  ... FP chain: nr:0
  ... user regs: mask 0xff0fff ABI 64-bit
  .... AX    0x53b
  .... BX    0x7ffedbdd3cc0
  .... CX    0xffffffff
  .... DX    0x33d3a
  .... SI    0x7f09b74c38d0
  .... DI    0x0
  .... BP    0x401260
  .... SP    0x7ffedbdd3cc0
  .... IP    0x401236
  .... FLAGS 0x20a
  .... CS    0x33
  .... SS    0x2b
  .... R8    0x7f09b74c3800
  .... R9    0x7f09b74c2da0
  .... R10   0xfffffffffffff3ce
  .... R11   0x246
  .... R12   0x401070
  .... R13   0x7ffedbdd5db0
  .... R14   0x0
  .... R15   0x0
  ... ustack: size 1024, offset 0xe0
   . data_src: 0x5080021
   ... thread: stack_test2.g.O:23828
   ...... dso: /root/abudanko/stacks/stack_test2.g.O3

After applying the change suggested in the patch the sample data contain
only user specified register values:

  $ perf record -g --call-graph dwarf,1024 --user-regs=BP -- matrix.gcc.g.03

  188368474305373 0x5e40 [0x470]: PERF_RECORD_SAMPLE(IP, 0x4002): 23839/23839: 0x401236 period: 1260507 addr: 0x7ffd3d85e96c
  ... FP chain: nr:0
  ... user regs: mask 0x1c0 ABI 64-bit
  .... BP    0x401260
  .... SP    0x7ffd3d85cc20
  .... IP    0x401236
  ... ustack: size 1024, offset 0x58
   . data_src: 0x5080021
   ... thread: stack_test2.g.O:23839
   ...... dso: /root/abudanko/stacks/stack_test2.g.O3

IP and SP registers (dwarf_regs) are collected anayways regardless of
the --user-regs option value provided from the command line:

  -g call-graph dwarf,K                         full_regs
  -g call-graph dwarf,K --user-regs=user_regs	user_regs | dwarf_regs
  --user-regs=user_regs                         user_regs

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
Changes in v3:
- avoid changes in platform specific header files

Changes in v2:
- implemented dwarf register set to avoid corrupted trace 
  when --user-regs option value omits IP,SP

---
 tools/perf/util/evsel.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 84cfb9fe2fc6..e5e61ee3c6e7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -669,6 +669,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 	return ret;
 }
 
+#define DWARF_REGS_MASK ((1ULL << PERF_REG_IP) | \
+			 (1ULL << PERF_REG_SP))
+
 static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
 					   struct record_opts *opts,
 					   struct callchain_param *param)
@@ -702,7 +705,10 @@ static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user |= PERF_REGS_MASK;
+			if (opts->sample_user_regs)
+				attr->sample_regs_user |= DWARF_REGS_MASK;
+			else
+				attr->sample_regs_user |= PERF_REGS_MASK;
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {
-- 
2.20.1