linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: kbuild test robot <lkp@intel.com>
To: Mark Rutland <mark.rutland@arm.com>
Cc: kbuild-all@01.org, linux-kernel@vger.kernel.org,
	Mark Rutland <mark.rutland@arm.com>,
	Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Will Deacon <will.deacon@arm.com>
Subject: Re: [PATCH] perf/ring_buffer: ensure atomicity and order of updates
Date: Fri, 11 May 2018 09:19:44 +0800	[thread overview]
Message-ID: <201805110700.0mgGxEvX%fengguang.wu@intel.com> (raw)
In-Reply-To: <20180510130632.34497-1-mark.rutland@arm.com>

[-- Attachment #1: Type: text/plain, Size: 10800 bytes --]

Hi Mark,

I love your patch! Perhaps something to improve:

[auto build test WARNING on tip/perf/core]
[also build test WARNING on v4.17-rc4 next-20180510]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Mark-Rutland/perf-ring_buffer-ensure-atomicity-and-order-of-updates/20180511-070205
config: i386-randconfig-s1-201818 (attached as .config)
compiler: gcc-6 (Debian 6.4.0-9) 6.4.0 20171026
reproduce:
        # save the attached .config to linux build tree
        make ARCH=i386 

All warnings (new ones prefixed by >>):

   In file included from include/uapi/linux/swab.h:6:0,
                    from include/linux/swab.h:5,
                    from include/uapi/linux/byteorder/little_endian.h:13,
                    from include/linux/byteorder/little_endian.h:5,
                    from arch/x86/include/uapi/asm/byteorder.h:5,
                    from include/uapi/linux/perf_event.h:20,
                    from include/linux/perf_event.h:17,
                    from kernel//events/ring_buffer.c:12:
   kernel//events/ring_buffer.c: In function 'perf_output_put_handle':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_86' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>> kernel//events/ring_buffer.c:86:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->data_head, head); /* B, matches C */
     ^~~~~~~~~~~~~~~~~
   kernel//events/ring_buffer.c: In function 'perf_aux_output_skip':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_498' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   kernel//events/ring_buffer.c:498:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->aux_head, rb->aux_head);
     ^~~~~~~~~~~~~~~~~
   kernel//events/ring_buffer.c: In function 'perf_aux_output_end':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_466' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   kernel//events/ring_buffer.c:466:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->aux_head, rb->aux_head);
     ^~~~~~~~~~~~~~~~~
--
   In file included from include/uapi/linux/swab.h:6:0,
                    from include/linux/swab.h:5,
                    from include/uapi/linux/byteorder/little_endian.h:13,
                    from include/linux/byteorder/little_endian.h:5,
                    from arch/x86/include/uapi/asm/byteorder.h:5,
                    from include/uapi/linux/perf_event.h:20,
                    from include/linux/perf_event.h:17,
                    from kernel/events/ring_buffer.c:12:
   kernel/events/ring_buffer.c: In function 'perf_output_put_handle':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_86' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   kernel/events/ring_buffer.c:86:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->data_head, head); /* B, matches C */
     ^~~~~~~~~~~~~~~~~
   kernel/events/ring_buffer.c: In function 'perf_aux_output_skip':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_498' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   kernel/events/ring_buffer.c:498:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->aux_head, rb->aux_head);
     ^~~~~~~~~~~~~~~~~
   kernel/events/ring_buffer.c: In function 'perf_aux_output_end':
   include/linux/compiler.h:339:38: error: call to '__compiletime_assert_466' declared with attribute error: Need native word sized stores/loads for atomicity.
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
                                         ^
   include/linux/compiler.h:319:4: note: in definition of macro '__compiletime_assert'
       prefix ## suffix();    \
       ^~~~~~
   include/linux/compiler.h:339:2: note: in expansion of macro '_compiletime_assert'
     _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
     ^~~~~~~~~~~~~~~~~~~
>> include/linux/compiler.h:342:2: note: in expansion of macro 'compiletime_assert'
     compiletime_assert(__native_word(t),    \
     ^~~~~~~~~~~~~~~~~~
>> include/asm-generic/barrier.h:181:2: note: in expansion of macro 'compiletime_assert_atomic_type'
     compiletime_assert_atomic_type(*p);    \
     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   kernel/events/ring_buffer.c:466:2: note: in expansion of macro 'smp_store_release'
     smp_store_release(&rb->user_page->aux_head, rb->aux_head);
     ^~~~~~~~~~~~~~~~~

vim +/smp_store_release +86 kernel//events/ring_buffer.c

    44	
    45	static void perf_output_put_handle(struct perf_output_handle *handle)
    46	{
    47		struct ring_buffer *rb = handle->rb;
    48		unsigned long head;
    49	
    50	again:
    51		head = local_read(&rb->head);
    52	
    53		/*
    54		 * IRQ/NMI can happen here, which means we can miss a head update.
    55		 */
    56	
    57		if (!local_dec_and_test(&rb->nest))
    58			goto out;
    59	
    60		/*
    61		 * Since the mmap() consumer (userspace) can run on a different CPU:
    62		 *
    63		 *   kernel				user
    64		 *
    65		 *   if (LOAD ->data_tail) {		LOAD ->data_head
    66		 *				(A) 	smp_rmb()	(C)
    67		 *	STORE $data			LOAD $data
    68		 *					smp_mb()	(D)
    69		 *	RELEASE ->data_head	(B)	STORE ->data_tail
    70		 *   }
    71		 *
    72		 * Where A pairs with D, and B pairs with C.
    73		 *
    74		 * In our case (A) is a control dependency that separates the load of
    75		 * the ->data_tail and the stores of $data. In case ->data_tail
    76		 * indicates there is no room in the buffer to store $data we do not.
    77		 *
    78		 * D needs to be a full barrier since it separates the data READ
    79		 * from the tail WRITE.
    80		 *
    81		 * For B a WMB is sufficient since it separates two WRITEs, and for C
    82		 * an RMB is sufficient since it separates two READs.
    83		 *
    84		 * See perf_output_begin().
    85		 */
  > 86		smp_store_release(&rb->user_page->data_head, head); /* B, matches C */
    87	
    88		/*
    89		 * Now check if we missed an update -- rely on previous implied
    90		 * compiler barriers to force a re-read.
    91		 */
    92		if (unlikely(head != local_read(&rb->head))) {
    93			local_inc(&rb->nest);
    94			goto again;
    95		}
    96	
    97		if (handle->wakeup != local_read(&rb->wakeup))
    98			perf_output_wakeup(handle);
    99	
   100	out:
   101		preempt_enable();
   102	}
   103	

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 30272 bytes --]

  reply	other threads:[~2018-05-11  1:20 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-10 13:06 [PATCH] perf/ring_buffer: ensure atomicity and order of updates Mark Rutland
2018-05-11  1:19 ` kbuild test robot [this message]
2018-05-11  1:19 ` kbuild test robot
2018-05-11 10:59 ` Mark Rutland
2018-05-11 16:22   ` Peter Zijlstra
2018-05-14 11:05     ` Mark Rutland
2018-05-14 11:28       ` Peter Zijlstra
2018-05-14 15:02         ` Peter Zijlstra
2018-05-14 15:20           ` Mark Rutland
2018-05-14 15:24             ` Peter Zijlstra
2018-05-23 16:42 ` Will Deacon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=201805110700.0mgGxEvX%fengguang.wu@intel.com \
    --to=lkp@intel.com \
    --cc=kbuild-all@01.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).