Skip to content

tracing/timerlat: Move hrtimer_init to timerlat_fd open()

John Kacur requested to merge jkacur/centos-stream-9:RHEL-26665 into main

commit b467624b (HEAD -> RHEL-26665, jkacur/RHEL-26665) Author: John Kacur jkacur@redhat.com Date: Wed Feb 28 13:58:46 2024 -0500

tracing/timerlat: Move hrtimer_init to timerlat_fd open()

JIRA: https://issues.redhat.com/browse/RHEL-26665

commit 1389358bb008e7625942846e9f03554319b7fecc Author: Daniel Bristot de Oliveira bristot@kernel.org Date: Thu Feb 1 16:13:39 2024 +0100

        tracing/timerlat: Move hrtimer_init to timerlat_fd open()

        Currently, the timerlat's hrtimer is initialized at the first read of
        timerlat_fd, and destroyed at close(). It works, but it causes an error
        if the user program open() and close() the file without reading.

        Here's an example:

         # echo NO_OSNOISE_WORKLOAD > /sys/kernel/debug/tracing/osnoise/options
         # echo timerlat > /sys/kernel/debug/tracing/current_tracer

         # cat <<EOF > ./timerlat_load.py
         # !/usr/bin/env python3

         timerlat_fd = open("/sys/kernel/tracing/osnoise/per_cpu/cpu0/timerlat_fd", 'r')
         timerlat_fd.close();
         EOF

         # ./taskset -c 0 ./timerlat_load.py
        <BOOM>

         BUG: kernel NULL pointer dereference, address: 0000000000000010
         #PF: supervisor read access in kernel mode
         #PF: error_code(0x0000) - not-present page
         PGD 0 P4D 0
         Oops: 0000 [#1] PREEMPT SMP NOPTI
         CPU: 1 PID: 2673 Comm: python3 Not tainted 6.6.13-200.fc39.x86_64 #1
         Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39 04/01/2014
         RIP: 0010:hrtimer_active+0xd/0x50
         Code: 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 48 8b 57 30 <8b> 42 10 a8 01 74 09 f3 90 8b 42 10 a8 01 75 f7 80 7f 38 00 75 1d
         RSP: 0018:ffffb031009b7e10 EFLAGS: 00010286
         RAX: 000000000002db00 RBX: ffff9118f786db08 RCX: 0000000000000000
         RDX: 0000000000000000 RSI: ffff9117a0e64400 RDI: ffff9118f786db08
         RBP: ffff9118f786db80 R08: ffff9117a0ddd420 R09: ffff9117804d4f70
         R10: 0000000000000000 R11: 0000000000000000 R12: ffff9118f786db08
         R13: ffff91178fdd5e20 R14: ffff9117840978c0 R15: 0000000000000000
         FS:  00007f2ffbab1740(0000) GS:ffff9118f7840000(0000) knlGS:0000000000000000
         CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
         CR2: 0000000000000010 CR3: 00000001b402e000 CR4: 0000000000750ee0
         PKRU: 55555554
         Call Trace:
          <TASK>
          ? __die+0x23/0x70
          ? page_fault_oops+0x171/0x4e0
          ? srso_alias_return_thunk+0x5/0x7f
          ? avc_has_extended_perms+0x237/0x520
          ? exc_page_fault+0x7f/0x180
          ? asm_exc_page_fault+0x26/0x30
          ? hrtimer_active+0xd/0x50
          hrtimer_cancel+0x15/0x40
          timerlat_fd_release+0x48/0xe0
          __fput+0xf5/0x290
          __x64_sys_close+0x3d/0x80
          do_syscall_64+0x60/0x90
          ? srso_alias_return_thunk+0x5/0x7f
          ? __x64_sys_ioctl+0x72/0xd0
          ? srso_alias_return_thunk+0x5/0x7f
          ? syscall_exit_to_user_mode+0x2b/0x40
          ? srso_alias_return_thunk+0x5/0x7f
          ? do_syscall_64+0x6c/0x90
          ? srso_alias_return_thunk+0x5/0x7f
          ? exit_to_user_mode_prepare+0x142/0x1f0
          ? srso_alias_return_thunk+0x5/0x7f
          ? syscall_exit_to_user_mode+0x2b/0x40
          ? srso_alias_return_thunk+0x5/0x7f
          ? do_syscall_64+0x6c/0x90
          entry_SYSCALL_64_after_hwframe+0x6e/0xd8
         RIP: 0033:0x7f2ffb321594
         Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 80 3d d5 cd 0d 00 00 74 13 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3c c3 0f 1f 00 55 48 89 e5 48 83 ec 10 89 7d
         RSP: 002b:00007ffe8d8eef18 EFLAGS: 00000202 ORIG_RAX: 0000000000000003
         RAX: ffffffffffffffda RBX: 00007f2ffba4e668 RCX: 00007f2ffb321594
         RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
         RBP: 00007ffe8d8eef40 R08: 0000000000000000 R09: 0000000000000000
         R10: 55c926e3167eae79 R11: 0000000000000202 R12: 0000000000000003
         R13: 00007ffe8d8ef030 R14: 0000000000000000 R15: 00007f2ffba4e668
          </TASK>
         CR2: 0000000000000010
         ---[ end trace 0000000000000000 ]---

        Move hrtimer_init to timerlat_fd open() to avoid this problem.

        Link: https://lore.kernel.org/linux-trace-kernel/7324dd3fc0035658c99b825204a66049389c56e3.1706798888.git.bristot@kernel.org

        Cc: Masami Hiramatsu <mhiramat@kernel.org>
        Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
        Cc: stable@vger.kernel.org
        Fixes: e88ed227f639 ("tracing/timerlat: Add user-space interface")
        Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
        Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

Signed-off-by: John Kacur <jkacur@redhat.com>
Edited by John Kacur

Merge request reports