From f08046cb3082b313e7b08dc35838cf8bd902c36b Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 9 Jan 2019 11:18:33 +0200 Subject: perf thread-stack: Represent jmps to the start of a different symbol The compiler might optimize a call/ret combination by making it a jmp. However the thread-stack does not presently cater for that, so that such control flow is not visible in the call graph. Make it visible by recording on the stack a branch to the start of a different symbol. Note, that means when a ret pops the stack, all jmps must be popped off first. Example: $ cat jmp-to-fn.c __attribute__((noinline)) int bar(void) { return -1; } __attribute__((noinline)) int foo(void) { return bar() + 1; } int main() { return foo(); } $ gcc -ggdb3 -Wall -Wextra -O2 -o jmp-to-fn jmp-to-fn.c $ objdump -d jmp-to-fn 0000000000001040
: 1040: 31 c0 xor %eax,%eax 1042: e9 09 01 00 00 jmpq 1150 0000000000001140 : 1140: b8 ff ff ff ff mov $0xffffffff,%eax 1145: c3 retq 0000000000001150 : 1150: 31 c0 xor %eax,%eax 1152: e8 e9 ff ff ff callq 1140 1157: 83 c0 01 add $0x1,%eax 115a: c3 retq $ perf record -o jmp-to-fn.perf.data -e intel_pt/cyc/u ./jmp-to-fn [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0,017 MB jmp-to-fn.perf.data ] $ perf script -i jmp-to-fn.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py jmp-to-fn.db branches calls 2019-01-08 13:24:58.783069 Creating database... 2019-01-08 13:24:58.794650 Writing records... 2019-01-08 13:24:59.008050 Adding indexes 2019-01-08 13:24:59.015802 Done $ ~/libexec/perf-core/scripts/python/exported-sql-viewer.py jmp-to-fn.db Before: main -> bar After: main -> foo -> bar Committer testing: Install the python2-pyside package, then select these menu options on the GUI: "Reports" "Context sensitive callgraphs" Then go on expanding the symbols, to get, full picture when doing this on a fedora:29 with gcc version 8.2.1 20181215 (Red Hat 8.2.1-6) (GCC): jmp-to-fn PID:TID _start (ld-2.28.so) __libc_start_main main foo bar To verify that indeed, this fixes the problem. Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190109091835.5570-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/export-to-sqlite.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/scripts/python/export-to-sqlite.py') diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index 245caf2643ed..ed237f2ed03f 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -320,7 +320,7 @@ if perf_db_export_calls: 'branch_count,' 'call_id,' 'return_id,' - 'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,' + 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' 'parent_call_path_id' ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') -- cgit From 8ce9a7251d110c7bbb43e30dd42f81d8e6286516 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 28 Feb 2019 15:00:25 +0200 Subject: perf scripts python: export-to-sqlite.py: Export calls parent_id Export to the 'calls' table the newly created 'parent_id'. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: https://lkml.kernel.org/n/tip-b09oukl48rsl9azkp2wmh0bl@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/export-to-sqlite.py | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'tools/perf/scripts/python/export-to-sqlite.py') diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index ed237f2ed03f..eb63e6c7107f 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -222,7 +222,8 @@ if perf_db_export_calls: 'call_id bigint,' 'return_id bigint,' 'parent_call_path_id bigint,' - 'flags integer)') + 'flags integer,' + 'parent_id bigint)') # printf was added to sqlite in version 3.8.3 sqlite_has_printf = False @@ -321,7 +322,8 @@ if perf_db_export_calls: 'call_id,' 'return_id,' 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' - 'parent_call_path_id' + 'parent_call_path_id,' + 'parent_id' ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') do_query(query, 'CREATE VIEW samples_view AS ' @@ -373,7 +375,7 @@ if perf_db_export_calls or perf_db_export_callchains: call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)") if perf_db_export_calls: call_query = QSqlQuery(db) - call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") + call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): print datetime.datetime.today(), "Writing records..." @@ -388,6 +390,7 @@ def trace_begin(): sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) if perf_db_export_calls or perf_db_export_callchains: call_path_table(0, 0, 0, 0) + call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) unhandled_count = 0 @@ -397,6 +400,7 @@ def trace_end(): print datetime.datetime.today(), "Adding indexes" if perf_db_export_calls: do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') + do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" @@ -452,4 +456,4 @@ def call_path_table(*x): bind_exec(call_path_query, 4, x) def call_return_table(*x): - bind_exec(call_query, 11, x) + bind_exec(call_query, 12, x) -- cgit