Skip to main content

Browse the archive

Revision 511e19b9e2112463c33a744ecb8a798056074408 authored by Namhyung Kim on 19 December 2022, 20:17:30 UTC, committed by Arnaldo Carvalho de Melo on 21 December 2022, 17:52:39 UTC 
perf lock contention: Add -L/--lock-filter option
 
The -L/--lock-filter option is to filter only given locks.  The locks
can be specified by address or name (if exists).

  $ sudo ./perf lock record -a  sleep 1

  $ sudo ./perf lock con -l
   contended  total wait  max wait  avg wait           address  symbol

          57     1.11 ms  42.83 us  19.54 us  ffff9f4140059000
          15   280.88 us  23.51 us  18.73 us  ffffffff9d007a40  jiffies_lock
           1    20.49 us  20.49 us  20.49 us  ffffffff9d0d50c0  rcu_state
           1     9.02 us   9.02 us   9.02 us  ffff9f41759e9ba0

  $ sudo ./perf lock con -L jiffies_lock,rcu_state
   contended  total wait  max wait  avg wait      type  caller

          15   280.88 us  23.51 us  18.73 us  spinlock  tick_sched_do_timer+0x93
           1    20.49 us  20.49 us  20.49 us  spinlock  __softirqentry_text_start+0xeb

  $ sudo ./perf lock con -L ffff9f4140059000
   contended  total wait  max wait  avg wait      type  caller

          38   779.40 us  42.83 us  20.51 us  spinlock  worker_thread+0x50
          11   216.30 us  39.87 us  19.66 us  spinlock  queue_work_on+0x39
           8   118.13 us  20.51 us  14.77 us  spinlock  kthread+0xe5

Committer testing:

  # uname -a
  Linux quaco 6.0.12-200.fc36.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Dec 8 17:15:53 UTC 2022 x86_64 x86_64 x86_64 GNU/Linux
  # perf lock record
  ^C[ perf record: Woken up 1 times to write data ]
  # perf lock con -L jiffies_lock,rcu_state
   contended   total wait     max wait     avg wait         type   caller

  # perf lock con
   contended   total wait     max wait     avg wait         type   caller

           1      9.06 us      9.06 us      9.06 us     spinlock   call_timer_fn+0x24
  # perf lock con -L call
  ignore unknown symbol: call
   contended   total wait     max wait     avg wait         type   caller

           1      9.06 us      9.06 us      9.06 us     spinlock   call_timer_fn+0x24
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20221219201732.460111-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
1 parent 529772c
Raw File
memweight.c 
// SPDX-License-Identifier: GPL-2.0
#include <linux/export.h>
#include <linux/bug.h>
#include <linux/bitmap.h>

/**
 * memweight - count the total number of bits set in memory area
 * @ptr: pointer to the start of the area
 * @bytes: the size of the area
 */
size_t memweight(const void *ptr, size_t bytes)
{
	size_t ret = 0;
	size_t longs;
	const unsigned char *bitmap = ptr;

	for (; bytes > 0 && ((unsigned long)bitmap) % sizeof(long);
			bytes--, bitmap++)
		ret += hweight8(*bitmap);

	longs = bytes / sizeof(long);
	if (longs) {
		BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
		ret += bitmap_weight((unsigned long *)bitmap,
				longs * BITS_PER_LONG);
		bytes -= longs * sizeof(long);
		bitmap += longs * sizeof(long);
	}
	/*
	 * The reason that this last loop is distinct from the preceding
	 * bitmap_weight() call is to compute 1-bits in the last region smaller
	 * than sizeof(long) properly on big-endian systems.
	 */
	for (; bytes > 0; bytes--, bitmap++)
		ret += hweight8(*bitmap);

	return ret;
}
EXPORT_SYMBOL(memweight);
back to top