milos-linux/kernel/trace
Zheng Yejian 6455b6163d ring-buffer: Fix race while reader and writer are on the same page
When user reads file 'trace_pipe', kernel keeps printing following logs
that warn at "cpu_buffer->reader_page->read > rb_page_size(reader)" in
rb_get_reader_page(). It just looks like there's an infinite loop in
tracing_read_pipe(). This problem occurs several times on arm64 platform
when testing v5.10 and below.

  Call trace:
   rb_get_reader_page+0x248/0x1300
   rb_buffer_peek+0x34/0x160
   ring_buffer_peek+0xbc/0x224
   peek_next_entry+0x98/0xbc
   __find_next_entry+0xc4/0x1c0
   trace_find_next_entry_inc+0x30/0x94
   tracing_read_pipe+0x198/0x304
   vfs_read+0xb4/0x1e0
   ksys_read+0x74/0x100
   __arm64_sys_read+0x24/0x30
   el0_svc_common.constprop.0+0x7c/0x1bc
   do_el0_svc+0x2c/0x94
   el0_svc+0x20/0x30
   el0_sync_handler+0xb0/0xb4
   el0_sync+0x160/0x180

Then I dump the vmcore and look into the problematic per_cpu ring_buffer,
I found that tail_page/commit_page/reader_page are on the same page while
reader_page->read is obviously abnormal:
  tail_page == commit_page == reader_page == {
    .write = 0x100d20,
    .read = 0x8f9f4805,  // Far greater than 0xd20, obviously abnormal!!!
    .entries = 0x10004c,
    .real_end = 0x0,
    .page = {
      .time_stamp = 0x857257416af0,
      .commit = 0xd20,  // This page hasn't been full filled.
      // .data[0...0xd20] seems normal.
    }
 }

The root cause is most likely the race that reader and writer are on the
same page while reader saw an event that not fully committed by writer.

To fix this, add memory barriers to make sure the reader can see the
content of what is committed. Since commit a0fcaaed0c ("ring-buffer: Fix
race between reset page and reading page") has added the read barrier in
rb_get_reader_page(), here we just need to add the write barrier.

Link: https://lore.kernel.org/linux-trace-kernel/20230325021247.2923907-1-zhengyejian1@huawei.com

Cc: stable@vger.kernel.org
Fixes: 77ae365eca ("ring-buffer: make lockless")
Suggested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Zheng Yejian <zhengyejian1@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-04-03 11:51:38 -04:00
..
rv rv: remove redundant initialization of pointer ptr 2023-01-25 10:31:02 -05:00
blktrace.c block: remove more NULL checks after bdev_get_queue() 2023-02-21 09:23:22 -07:00
bpf_trace.c Networking changes for 6.3. 2023-02-21 18:24:12 -08:00
bpf_trace.h
error_report-traces.c
fgraph.c
fprobe.c tracing/fprobe: Fix to check whether fprobe is registered correctly 2022-11-04 08:50:07 +09:00
ftrace.c Tracing fixes for 6.3: 2023-03-19 10:46:02 -07:00
ftrace_internal.h
Kconfig tracing updates for 6.3: 2023-02-23 10:20:49 -08:00
kprobe_event_gen_test.c tracing: Fix wrong return in kprobe_event_gen_test.c 2023-03-19 12:20:48 -04:00
Makefile
pid_list.c
pid_list.h
power-traces.c
preemptirq_delay_test.c
rethook.c rethook: fix a potential memleak in rethook_alloc() 2022-11-18 10:15:34 +09:00
ring_buffer.c ring-buffer: Fix race while reader and writer are on the same page 2023-04-03 11:51:38 -04:00
ring_buffer_benchmark.c ring_buffer: Remove unused "event" parameter 2022-11-23 19:08:30 -05:00
rpm-traces.c
synth_event_gen_test.c tracing: Always use canonical ftrace path 2023-02-18 14:34:09 -05:00
trace.c Tracing fixes for 6.3: 2023-03-19 10:46:02 -07:00
trace.h Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mattst88/alpha 2023-02-25 12:49:29 -08:00
trace_benchmark.c
trace_benchmark.h
trace_boot.c
trace_branch.c
trace_clock.c
trace_dynevent.c tracing: Free buffers when a used dynamic event is removed 2022-11-23 19:07:12 -05:00
trace_dynevent.h
trace_entries.h
trace_eprobe.c kernel/trace: extract common part in process_fetch_insn 2023-02-24 10:04:13 +09:00
trace_event_perf.c tracing/perf: Use strndup_user instead of kzalloc/strncpy_from_user 2022-11-23 19:08:31 -05:00
trace_events.c tracing updates for 6.3: 2023-02-23 10:20:49 -08:00
trace_events_filter.c tracing: Add a way to filter function addresses to function names 2023-01-25 10:31:11 -05:00
trace_events_filter_test.h
trace_events_hist.c tracing: Check field value in hist_field_name() 2023-03-09 22:17:06 -05:00
trace_events_inject.c
trace_events_synth.c tracing/synthetic: Fix races on freeing last_cmd 2023-04-03 11:51:12 -04:00
trace_events_trigger.c tracing: Do not synchronize freeing of trigger filter on boot up 2022-12-14 08:50:56 -05:00
trace_events_user.c Tracing updates for 6.2: 2022-12-15 18:01:16 -08:00
trace_export.c tracing: Fix TASK_COMM_LEN in trace event format file 2023-02-12 10:23:39 -05:00
trace_functions.c
trace_functions_graph.c
trace_hwlat.c tracing/hwlat: Replace sched_setaffinity with set_cpus_allowed_ptr 2023-03-19 13:23:22 -04:00
trace_irqsoff.c
trace_kdb.c
trace_kprobe.c kernel/trace: extract common part in process_fetch_insn 2023-02-24 10:04:13 +09:00
trace_kprobe_selftest.c
trace_kprobe_selftest.h
trace_mmiotrace.c
trace_nop.c
trace_osnoise.c tracing/osnoise: set several trace_osnoise.c variables storage-class-specifier to static 2023-03-19 12:20:48 -04:00
trace_output.c tracing: Make sure trace_printk() can output as soon as it can be used 2023-01-24 11:27:29 -05:00
trace_output.h
trace_preemptirq.c cpuidle: tracing, preempt: Squash _rcuidle tracing 2023-01-31 15:01:46 +01:00
trace_printk.c
trace_probe.c kernel/trace: Introduce trace_probe_print_args and use it in *probes 2023-02-24 09:44:15 +09:00
trace_probe.h kernel/trace: Introduce trace_probe_print_args and use it in *probes 2023-02-24 09:44:15 +09:00
trace_probe_kernel.h kernel/trace: Provide default impelentations defined in trace_probe_tmpl.h 2023-02-24 09:44:27 +09:00
trace_probe_tmpl.h kernel/trace: extract common part in process_fetch_insn 2023-02-24 10:04:13 +09:00
trace_recursion_record.c
trace_sched_switch.c
trace_sched_wakeup.c
trace_selftest.c
trace_selftest_dynamic.c
trace_seq.c tracing: Acquire buffer from temparary trace sequence 2023-02-07 12:42:54 -05:00
trace_stack.c
trace_stat.c
trace_stat.h
trace_synth.h tracing: Allow synthetic events to pass around stacktraces 2023-01-25 10:31:24 -05:00
trace_syscalls.c tracing: Remove unused __bad_type_size() method 2022-11-17 20:21:06 -05:00
trace_uprobe.c kernel/trace: extract common part in process_fetch_insn 2023-02-24 10:04:13 +09:00
tracing_map.c
tracing_map.h