summaryrefslogtreecommitdiff
path: root/tools/perf/scripts/python/stackcollapse.py
blob: 1697b5e18c9622bdc82f7f9355745febb0a28705 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
# stackcollapse.py - format perf samples with one line per distinct call stack
# SPDX-License-Identifier: GPL-2.0
#
# This script's output has two space-separated fields.  The first is a semicolon
# separated stack including the program name (from the "comm" field) and the
# function names from the call stack.  The second is a count:
#
#  swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2
#
# The file is sorted according to the first field.
#
# Input may be created and processed using:
#
#  perf record -a -g -F 99 sleep 60
#  perf script report stackcollapse > out.stacks-folded
#
# (perf script record stackcollapse works too).
#
# Written by Paolo Bonzini <pbonzini@redhat.com>
# Based on Brendan Gregg's stackcollapse-perf.pl script.

import os
import sys
from collections import defaultdict
from optparse import OptionParser, make_option

sys.path.append(os.environ['PERF_EXEC_PATH'] + \
                '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')

from perf_trace_context import *
from Core import *
from EventClass import *

# command line parsing

option_list = [
    # formatting options for the bottom entry of the stack
    make_option("--include-tid", dest="include_tid",
                 action="store_true", default=False,
                 help="include thread id in stack"),
    make_option("--include-pid", dest="include_pid",
                 action="store_true", default=False,
                 help="include process id in stack"),
    make_option("--no-comm", dest="include_comm",
                 action="store_false", default=True,
                 help="do not separate stacks according to comm"),
    make_option("--tidy-java", dest="tidy_java",
                 action="store_true", default=False,
                 help="beautify Java signatures"),
    make_option("--kernel", dest="annotate_kernel",
                 action="store_true", default=False,
                 help="annotate kernel functions with _[k]")
]

parser = OptionParser(option_list=option_list)
(opts, args) = parser.parse_args()

if len(args) != 0:
    parser.error("unexpected command line argument")
if opts.include_tid and not opts.include_comm:
    parser.error("requesting tid but not comm is invalid")
if opts.include_pid and not opts.include_comm:
    parser.error("requesting pid but not comm is invalid")

# event handlers

lines = defaultdict(lambda: 0)

def process_event(param_dict):
    def tidy_function_name(sym, dso):
        if sym is None:
            sym = '[unknown]'

        sym = sym.replace(';', ':')
        if opts.tidy_java:
            # the original stackcollapse-perf.pl script gives the
            # example of converting this:
            #    Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V
            # to this:
            #    org/mozilla/javascript/MemberBox:.init
            sym = sym.replace('<', '')
            sym = sym.replace('>', '')
            if sym[0] == 'L' and sym.find('/'):
                sym = sym[1:]
            try:
                sym = sym[:sym.index('(')]
            except ValueError:
                pass

        if opts.annotate_kernel and dso == '[kernel.kallsyms]':
            return sym + '_[k]'
        else:
            return sym

    stack = list()
    if 'callchain' in param_dict:
        for entry in param_dict['callchain']:
            entry.setdefault('sym', dict())
            entry['sym'].setdefault('name', None)
            entry.setdefault('dso', None)
            stack.append(tidy_function_name(entry['sym']['name'],
                                            entry['dso']))
    else:
        param_dict.setdefault('symbol', None)
        param_dict.setdefault('dso', None)
        stack.append(tidy_function_name(param_dict['symbol'],
                                        param_dict['dso']))

    if opts.include_comm:
        comm = param_dict["comm"].replace(' ', '_')
        sep = "-"
        if opts.include_pid:
            comm = comm + sep + str(param_dict['sample']['pid'])
            sep = "/"
        if opts.include_tid:
            comm = comm + sep + str(param_dict['sample']['tid'])
        stack.append(comm)

    stack_string = ';'.join(reversed(stack))
    lines[stack_string] = lines[stack_string] + 1

def trace_end():
    list = lines.keys()
    list.sort()
    for stack in list:
        print "%s %d" % (stack, lines[stack])
. While iterating though the possible solutions a few archs kindly acked other variations that still zero initialized the struct. These sites have been modified in previous changes using the pattern acked by the respective arch. So to be reduce the chance of bugs via uninitialized fields, perform a tree wide change using the consensus for the best general way to do this change. Use C99 static initializing to zero the struct and remove and statements that simply set members to zero. Link: https://lkml.kernel.org/r/20240326021656.202649-11-rick.p.edgecombe@intel.com Link: https://lore.kernel.org/lkml/202402280912.33AEE7A9CF@keescook/#t Link: https://lore.kernel.org/lkml/j7bfvig3gew3qruouxrh7z7ehjjafrgkbcmg6tcghhfh3rhmzi@wzlcoecgy5rs/ Link: https://lore.kernel.org/lkml/ec3e377a-c0a0-4dd3-9cb9-96517e54d17e@csgroup.eu/ Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar@kernel.org> Cc: Borislav Petkov (AMD) <bp@alien8.de> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Guo Ren <guoren@kernel.org> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin (Intel) <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Mark Brown <broonie@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> 2024-04-10LoongArch: Make virt_addr_valid()/__virt_addr_valid() work with KFENCEHuacai Chen When enabling both CONFIG_KFENCE and CONFIG_DEBUG_SG, I get the following backtraces when running LongArch kernels. [ 2.496257] kernel BUG at include/linux/scatterlist.h:187! ... [ 2.501925] Call Trace: [ 2.501950] [<9000000004ad59c4>] sg_init_one+0xac/0xc0 [ 2.502204] [<9000000004a438f8>] do_test_kpp+0x278/0x6e4 [ 2.502353] [<9000000004a43dd4>] alg_test_kpp+0x70/0xf4 [ 2.502494] [<9000000004a41b48>] alg_test+0x128/0x690 [ 2.502631] [<9000000004a3d898>] cryptomgr_test+0x20/0x40 [ 2.502775] [<90000000041b4508>] kthread+0x138/0x158 [ 2.502912] [<9000000004161c48>] ret_from_kernel_thread+0xc/0xa4 The backtrace is always similar but not exactly the same. It is always triggered from cryptomgr_test, but not always from the same test. Analysis shows that with CONFIG_KFENCE active, the address returned from kmalloc() and friends is not always below vm_map_base. It is allocated by kfence_alloc() which at least sometimes seems to get its memory from an address space above vm_map_base. This causes __virt_addr_valid() to return false for the affected objects. Let __virt_addr_valid() return 1 for kfence pool addresses, this make virt_addr_valid()/__virt_addr_valid() work with KFENCE. Reported-by: Guenter Roeck <linux@roeck-us.net> Suggested-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> 2023-09-06LoongArch: Remove shm_align_mask and use SHMLBA insteadHuacai Chen Both shm_align_mask and SHMLBA want to avoid cache alias. But they are inconsistent: shm_align_mask is (PAGE_SIZE - 1) while SHMLBA is SZ_64K, but PAGE_SIZE is not always equal to SZ_64K. This may cause problems when shmat() twice. Fix this problem by removing shm_align_mask and using SHMLBA (strictly SHMLBA - 1) instead. Reported-by: Jiantao Shan <shanjiantao@loongson.cn> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>