Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 21 9月, 2017 1 次提交
    • Y
      bpf: one perf event close won't free bpf program attached by another perf event · ec9dd352
      由 Yonghong Song 提交于 
      This patch fixes a bug exhibited by the following scenario:
  1. fd1 = perf_event_open with attr.config = ID1
  2. attach bpf program prog1 to fd1
  3. fd2 = perf_event_open with attr.config = ID1
     <this will be successful>
  4. user program closes fd2 and prog1 is detached from the tracepoint.
  5. user program with fd1 does not work properly as tracepoint
     no output any more.

The issue happens at step 4. Multiple perf_event_open can be called
successfully, but only one bpf prog pointer in the tp_event. In the
current logic, any fd release for the same tp_event will free
the tp_event->prog.

The fix is to free tp_event->prog only when the closing fd
corresponds to the one which registered the program.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ec9dd352
  3. 01 9月, 2017 1 次提交
    • S
      tracing: Only have rmmod clear buffers that its events were active in · 065e63f9
      由 Steven Rostedt (VMware) 提交于 
      Currently, when a module event is enabled, when that module is removed, it
clears all ring buffers. This is to prevent another module from being loaded
and having one of its trace event IDs from reusing a trace event ID of the
removed module. This could cause undesirable effects as the trace event of
the new module would be using its own processing algorithms to process raw
data of another event. To prevent this, when a module is loaded, if any of
its events have been used (signified by the WAS_ENABLED event call flag,
which is never cleared), all ring buffers are cleared, just in case any one
of them contains event data of the removed event.

The problem is, there's no reason to clear all ring buffers if only one (or
less than all of them) uses one of the events. Instead, only clear the ring
buffers that recorded the events of a module that is being removed.

To do this, instead of keeping the WAS_ENABLED flag with the trace event
call, move it to the per instance (per ring buffer) event file descriptor.
The event file descriptor maps each event to a separate ring buffer
instance. Then when the module is removed, only the ring buffers that
activated one of the module's events get cleared. The rest are not touched.
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      065e63f9
  5. 29 8月, 2017 1 次提交
    • Z
      perf/ftrace: Fix double traces of perf on ftrace:function · 75e83876
      由 Zhou Chengming 提交于 
      When running perf on the ftrace:function tracepoint, there is a bug
which can be reproduced by:

  perf record -e ftrace:function -a sleep 20 &
  perf record -e ftrace:function ls
  perf script

              ls 10304 [005]   171.853235: ftrace:function:
  perf_output_begin
              ls 10304 [005]   171.853237: ftrace:function:
  perf_output_begin
              ls 10304 [005]   171.853239: ftrace:function:
  task_tgid_nr_ns
              ls 10304 [005]   171.853240: ftrace:function:
  task_tgid_nr_ns
              ls 10304 [005]   171.853242: ftrace:function:
  __task_pid_nr_ns
              ls 10304 [005]   171.853244: ftrace:function:
  __task_pid_nr_ns

We can see that all the function traces are doubled.

The problem is caused by the inconsistency of the register
function perf_ftrace_event_register() with the probe function
perf_ftrace_function_call(). The former registers one probe
for every perf_event. And the latter handles all perf_events
on the current cpu. So when two perf_events on the current cpu,
the traces of them will be doubled.

So this patch adds an extra parameter "event" for perf_tp_event,
only send sample data to this event when it's not NULL.
Signed-off-by: NZhou Chengming <zhouchengming1@huawei.com>
Reviewed-by: NJiri Olsa <jolsa@kernel.org>
Acked-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: alexander.shishkin@linux.intel.com
Cc: huawei.libin@huawei.com
Link: http://lkml.kernel.org/r/1503668977-12526-1-git-send-email-zhouchengming1@huawei.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      75e83876
  7. 20 7月, 2017 1 次提交
  9. 28 6月, 2017 1 次提交
    • J
      tracing: Add support for recording tgid of tasks · d914ba37
      由 Joel Fernandes 提交于 
      Inorder to support recording of tgid, the following changes are made:

* Introduce a new API (tracing_record_taskinfo) to additionally record the tgid
  along with the task's comm at the same time. This has has the benefit of not
  setting trace_cmdline_save before all the information for a task is saved.
* Add a new API tracing_record_taskinfo_sched_switch to record task information
  for 2 tasks at a time (previous and next) and use it from sched_switch probe.
* Preserve the old API (tracing_record_cmdline) and create it as a wrapper
  around the new one so that existing callers aren't affected.
* Reuse the existing sched_switch and sched_wakeup probes to record tgid
  information and add a new option 'record-tgid' to enable recording of tgid

When record-tgid option isn't enabled to being with, we take care to make sure
that there's isn't memory or runtime overhead.

Link: http://lkml.kernel.org/r/20170627020155.5139-1-joelaf@google.com

Cc: kernel-team@android.com
Cc: Ingo Molnar <mingo@redhat.com>
Tested-by: NMichael Sartain <mikesart@gmail.com>
Signed-off-by: NJoel Fernandes <joelaf@google.com>
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      d914ba37
  11. 25 3月, 2017 1 次提交
    • S
      tracing: Move trace_handle_return() out of line · af0009fc
      由 Steven Rostedt (VMware) 提交于 
      Currently trace_handle_return() looks like this:

 static inline enum print_line_t trace_handle_return(struct trace_seq *s)
 {
        return trace_seq_has_overflowed(s) ?
                TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
 }

Where trace_seq_overflowed(s) is:

 static inline bool trace_seq_has_overflowed(struct trace_seq *s)
 {
	return s->full || seq_buf_has_overflowed(&s->seq);
 }

And seq_buf_has_overflowed(&s->seq) is:

 static inline bool
 seq_buf_has_overflowed(struct seq_buf *s)
 {
	return s->len > s->size;
 }

Making trace_handle_return() into:

 return (s->full || (s->seq->len > s->seq->size)) ?
           TRACE_TYPE_PARTIAL_LINE :
           TRACE_TYPE_HANDLED;

One would think this is not an issue to keep as an inline. But because this
is used in the TRACE_EVENT() macro, it is extended for every tracepoint in
the system. Taking a look at a single tracepoint x86_irq_vector (was the
first one I randomly chosen). As trace_handle_return is used in the
TRACE_EVENT() macro of trace_raw_output_##call() we disassemble
trace_raw_output_x86_irq_vector and do a diff:

- is the original
+ is the out-of-line code

I removed identical lines that were different just due to different
addresses.

--- /tmp/irq-vec-orig	2017-03-16 09:12:48.569384851 -0400
+++ /tmp/irq-vec-ool	2017-03-16 09:13:39.378153385 -0400
@@ -6,27 +6,23 @@
        53                      push   %rbx
        48 89 fb                mov    %rdi,%rbx
        4c 8b a7 c0 20 00 00    mov    0x20c0(%rdi),%r12
        e8 f7 72 13 00          callq  ffffffff81155c80 <trace_raw_output_prep>
        83 f8 01                cmp    $0x1,%eax
        74 05                   je     ffffffff8101e993 <trace_raw_output_x86_irq_vector+0x23>
        5b                      pop    %rbx
        41 5c                   pop    %r12
        5d                      pop    %rbp
        c3                      retq
        41 8b 54 24 08          mov    0x8(%r12),%edx
-       48 8d bb 98 10 00 00    lea    0x1098(%rbx),%rdi
+       48 81 c3 98 10 00 00    add    $0x1098,%rbx
-       48 c7 c6 7b 8a a0 81    mov    $0xffffffff81a08a7b,%rsi
+       48 c7 c6 ab 8a a0 81    mov    $0xffffffff81a08aab,%rsi
-       e8 c5 85 13 00          callq  ffffffff81156f70 <trace_seq_printf>

 === here's the start of the main difference ===

+       48 89 df                mov    %rbx,%rdi
+       e8 62 7e 13 00          callq  ffffffff81156810 <trace_seq_printf>
-       8b 93 b8 20 00 00       mov    0x20b8(%rbx),%edx
-       31 c0                   xor    %eax,%eax
-       85 d2                   test   %edx,%edx
-       75 11                   jne    ffffffff8101e9c8 <trace_raw_output_x86_irq_vector+0x58>
-       48 8b 83 a8 20 00 00    mov    0x20a8(%rbx),%rax
-       48 39 83 a0 20 00 00    cmp    %rax,0x20a0(%rbx)
-       0f 93 c0                setae  %al
+       48 89 df                mov    %rbx,%rdi
+       e8 4a c5 12 00          callq  ffffffff8114af00 <trace_handle_return>
        5b                      pop    %rbx
-       0f b6 c0                movzbl %al,%eax

 === end ===

        41 5c                   pop    %r12
        5d                      pop    %rbp
        c3                      retq

If you notice, the original has 22 bytes of text more than the out of line
version. As this is for every TRACE_EVENT() defined in the system, this can
become quite large.

   text	   data	    bss	    dec	    hex	filename
8690305	5450490	1298432	15439227	 eb957b	vmlinux-orig
8681725	5450490	1298432	15430647	 eb73f7	vmlinux-handle

This change has a total of 8580 bytes in savings.

 $ objdump -dr /tmp/vmlinux-orig | grep '^[0-9a-f]* <trace_raw_output' | wc -l
324

That's 324 tracepoints. But this does not include modules (which contain
many more tracepoints). For an allyesconfig build:

 $ objdump -dr vmlinux-allyes-orig | grep '^[0-9a-f]* <trace_raw_output' | wc -l
1401

That's 1401 tracepoints giving us:

   text    data     bss     dec     hex filename
137920629       140221067       53264384        331406080       13c0db00 vmlinux-allyes-orig
137827709       140221067       53264384        331313160       13bf7008 vmlinux-allyes-handle

92920 bytes in savings!!!

Link: http://lkml.kernel.org/r/20170315021431.13107-2-andi@firstfloor.orgReported-by: NAndi Kleen <andi@firstfloor.org>
Signed-off-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      af0009fc
  13. 23 2月, 2017 1 次提交
    • R
      tracing: add __print_flags_u64() · d3213e8f
      由 Ross Zwisler 提交于 
      Patch series "DAX tracepoints, mm argument simplification", v4.

This contains both my DAX tracepoint code and Dave Jiang's MM argument
simplifications.  Dave's code was written with my tracepoint code as a
baseline, so it seemed simplest to keep them together in a single series.

This patch (of 7):

Add __print_flags_u64() and the helper trace_print_flags_seq_u64() in the
same spirit as __print_symbolic_u64() and trace_print_symbols_seq_u64().
These functions allow us to print symbols associated with flags that are
64 bits wide even on 32 bit machines.

These will be used by the DAX code so that we can print the flags set in a
pfn_t such as PFN_SG_CHAIN, PFN_SG_LAST, PFN_DEV and PFN_MAP.

Without this new function I was getting errors like the following when
compiling for i386:

  include/linux/pfn_t.h:13:22: warning: large integer implicitly truncated to unsigned type [-Woverflow]
   #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
    ^

Link: http://lkml.kernel.org/r/1484085142-2297-2-git-send-email-ross.zwisler@linux.intel.comSigned-off-by: NRoss Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      d3213e8f
  15. 04 2月, 2017 1 次提交
  17. 26 1月, 2017 1 次提交
  19. 03 5月, 2016 1 次提交
  21. 30 4月, 2016 3 次提交
  23. 27 4月, 2016 2 次提交
  25. 22 4月, 2016 1 次提交
  27. 20 4月, 2016 2 次提交
    • T
      tracing: Add enable_hist/disable_hist triggers · d0bad49b
      由 Tom Zanussi 提交于 
      Similar to enable_event/disable_event triggers, these triggers enable
and disable the aggregation of events into maps rather than enabling
and disabling their writing into the trace buffer.

They can be used to automatically start and stop hist triggers based
on a matching filter condition.

If there's a paused hist trigger on system:event, the following would
start it when the filter condition was hit:

  # echo enable_hist:system:event [ if filter] > event/trigger

And the following would disable a running system:event hist trigger:

  # echo disable_hist:system:event [ if filter] > event/trigger

See Documentation/trace/events.txt for real examples.

Link: http://lkml.kernel.org/r/f812f086e52c8b7c8ad5443487375e03c96a601f.1457029949.git.tom.zanussi@linux.intel.comSigned-off-by: NTom Zanussi <tom.zanussi@linux.intel.com>
Tested-by: NMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      d0bad49b
    • T
      tracing: Add 'hist' event trigger command · 7ef224d1
      由 Tom Zanussi 提交于 
      'hist' triggers allow users to continually aggregate trace events,
which can then be viewed afterwards by simply reading a 'hist' file
containing the aggregation in a human-readable format.

The basic idea is very simple and boils down to a mechanism whereby
trace events, rather than being exhaustively dumped in raw form and
viewed directly, are automatically 'compressed' into meaningful tables
completely defined by the user.

This is done strictly via single-line command-line commands and
without the aid of any kind of programming language or interpreter.

A surprising number of typical use cases can be accomplished by users
via this simple mechanism.  In fact, a large number of the tasks that
users typically do using the more complicated script-based tracing
tools, at least during the initial stages of an investigation, can be
accomplished by simply specifying a set of keys and values to be used
in the creation of a hash table.

The Linux kernel trace event subsystem happens to provide an extensive
list of keys and values ready-made for such a purpose in the form of
the event format files associated with each trace event.  By simply
consulting the format file for field names of interest and by plugging
them into the hist trigger command, users can create an endless number
of useful aggregations to help with investigating various properties
of the system.  See Documentation/trace/events.txt for examples.

hist triggers are implemented on top of the existing event trigger
infrastructure, and as such are consistent with the existing triggers
from a user's perspective as well.

The basic syntax follows the existing trigger syntax.  Users start an
aggregation by writing a 'hist' trigger to the event of interest's
trigger file:

  # echo hist:keys=xxx [ if filter] > event/trigger

Once a hist trigger has been set up, by default it continually
aggregates every matching event into a hash table using the event key
and a value field named 'hitcount'.

To view the aggregation at any point in time, simply read the 'hist'
file in the same directory as the 'trigger' file:

  # cat event/hist

The detailed syntax provides additional options for user control, and
is described exhaustively in Documentation/trace/events.txt and in the
virtual tracing/README file in the tracing subsystem.

Link: http://lkml.kernel.org/r/72d263b5e1853fe9c314953b65833c3aa75479f2.1457029949.git.tom.zanussi@linux.intel.comSigned-off-by: NTom Zanussi <tom.zanussi@linux.intel.com>
Tested-by: NMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Reviewed-by: NNamhyung Kim <namhyung@kernel.org>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      7ef224d1
  29. 08 4月, 2016 2 次提交
  31. 16 3月, 2016 1 次提交
  33. 09 3月, 2016 1 次提交
  35. 04 3月, 2016 1 次提交
    • S
      tracing: Do not have 'comm' filter override event 'comm' field · e57cbaf0
      由 Steven Rostedt (Red Hat) 提交于 
      Commit 9f616680 "tracing: Allow triggers to filter for CPU ids and
process names" added a 'comm' filter that will filter events based on the
current tasks struct 'comm'. But this now hides the ability to filter events
that have a 'comm' field too. For example, sched_migrate_task trace event.
That has a 'comm' field of the task to be migrated.

 echo 'comm == "bash"' > events/sched_migrate_task/filter

will now filter all sched_migrate_task events for tasks named "bash" that
migrates other tasks (in interrupt context), instead of seeing when "bash"
itself gets migrated.

This fix requires a couple of changes.

1) Change the look up order for filter predicates to look at the events
   fields before looking at the generic filters.

2) Instead of basing the filter function off of the "comm" name, have the
   generic "comm" filter have its own filter_type (FILTER_COMM). Test
   against the type instead of the name to assign the filter function.

3) Add a new "COMM" filter that works just like "comm" but will filter based
   on the current task, even if the trace event contains a "comm" field.

Do the same for "cpu" field, adding a FILTER_CPU and a filter "CPU".

Cc: stable@vger.kernel.org # v4.3+
Fixes: 9f616680 "tracing: Allow triggers to filter for CPU ids and process names"
Reported-by: NMatt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      e57cbaf0
  37. 26 10月, 2015 1 次提交
    • S
      tracing: Implement event pid filtering · 3fdaf80f
      由 Steven Rostedt (Red Hat) 提交于 
      Add the necessary hooks to use the pids loaded in set_event_pid to filter
all the events enabled in the tracing instance that match the pids listed.

Two probes are added to both sched_switch and sched_wakeup tracepoints to be
called before other probes are called and after the other probes are called.
The first is used to set the necessary flags to let the probes know to test
if they should be traced or not.

The sched_switch pre probe will set the "ignore_pid" flag if neither the
previous or next task has a matching pid.

The sched_switch probe will set the "ignore_pid" flag if the next task
does not match the matching pid.

The pre probe allows for probes tracing sched_switch to be traced if
necessary.

The sched_wakeup pre probe will set the "ignore_pid" flag if neither the
current task nor the wakee task has a matching pid.

The sched_wakeup post probe will set the "ignore_pid" flag if the current
task does not have a matching pid.

Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      3fdaf80f
  39. 26 9月, 2015 2 次提交
  41. 07 8月, 2015 2 次提交
    • W
      tracing, perf: Implement BPF programs attached to uprobes · 04a22fae
      由 Wang Nan 提交于 
      By copying BPF related operation to uprobe processing path, this patch
allow users attach BPF programs to uprobes like what they are already
doing on kprobes.

After this patch, users are allowed to use PERF_EVENT_IOC_SET_BPF on a
uprobe perf event. Which make it possible to profile user space programs
and kernel events together using BPF.

Because of this patch, CONFIG_BPF_EVENTS should be selected by
CONFIG_UPROBE_EVENT to ensure trace_call_bpf() is compiled even if
KPROBE_EVENT is not set.
Signed-off-by: NWang Nan <wangnan0@huawei.com>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-3-git-send-email-wangnan0@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      04a22fae
    • W
      bpf: Use correct #ifdef controller for trace_call_bpf() · 098d2164
      由 Wang Nan 提交于 
      Commit e1abf2cc ("bpf: Fix the build on
BPF_SYSCALL=y && !CONFIG_TRACING kernels, make it more configurable")
updated the building condition of bpf_trace.o from CONFIG_BPF_SYSCALL
to CONFIG_BPF_EVENTS, but the corresponding #ifdef controller in
trace_events.h for trace_call_bpf() was not changed. Which, in theory,
is incorrect.

With current Kconfigs, we can create a .config with CONFIG_BPF_SYSCALL=y
and CONFIG_BPF_EVENTS=n by unselecting CONFIG_KPROBE_EVENT and
selecting CONFIG_BPF_SYSCALL. With these options, trace_call_bpf() will
be defined as an extern function, but if anyone calls it a symbol missing
error will be triggered since bpf_trace.o was not built.

This patch changes the #ifdef controller for trace_call_bpf() from
CONFIG_BPF_SYSCALL to CONFIG_BPF_EVENTS. I'll show its correctness:

Before this patch:

   BPF_SYSCALL   BPF_EVENTS   trace_call_bpf   bpf_trace.o
   y             y           normal           compiled
   n             n           inline           not compiled
   y             n           normal           not compiled (incorrect)
   n             y          impossible (BPF_EVENTS depends on BPF_SYSCALL)

After this patch:

   BPF_SYSCALL   BPF_EVENTS   trace_call_bpf   bpf_trace.o
   y             y           normal           compiled
   n             n           inline           not compiled
   y             n           inline           not compiled (fixed)
   n             y          impossible (BPF_EVENTS depends on BPF_SYSCALL)

So this patch doesn't break anything. QED.
Signed-off-by: NWang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-2-git-send-email-wangnan0@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      098d2164
  43. 14 5月, 2015 12 次提交