All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tom Zanussi <tom.zanussi@linux.intel.com>
To: rostedt@goodmis.org
Cc: tglx@linutronix.de, mhiramat@kernel.org, namhyung@kernel.org,
	vedang.patel@intel.com, bigeasy@linutronix.de,
	joel.opensrc@gmail.com, joelaf@google.com,
	mathieu.desnoyers@efficios.com, baohong.liu@intel.com,
	rajvi.jingar@intel.com, julia@ni.com, fengguang.wu@intel.com,
	linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org,
	Tom Zanussi <tom.zanussi@linux.intel.com>
Subject: [PATCH v6 03/37] tracing: Add support to detect and avoid duplicates
Date: Fri, 17 Nov 2017 14:32:42 -0600	[thread overview]
Message-ID: <824898537fb3c1be3fbee67e5e7a2fce5b42c625.1510948725.git.tom.zanussi@linux.intel.com> (raw)
In-Reply-To: <cover.1510948725.git.tom.zanussi@linux.intel.com>
In-Reply-To: <cover.1510948725.git.tom.zanussi@linux.intel.com>

From: Vedang Patel <vedang.patel@intel.com>

A duplicate in the tracing_map hash table is when 2 different entries
have the same key and, as a result, the key_hash. This is possible due
to a race condition in the algorithm. This race condition is inherent to
the algorithm and not a bug. This was fine because, until now, we were
only interested in the sum of all the values related to a particular
key (the duplicates are dealt with in tracing_map_sort_entries()). But,
with the inclusion of variables[1], we are interested in individual
values. So, it will not be clear what value to choose when
there are duplicates. So, the duplicates need to be removed.

The duplicates can occur in the code in the following scenarios:

- A thread is in the process of adding a new element. It has
successfully executed cmpxchg() and inserted the key. But, it is still
not done acquiring the trace_map_elt struct, populating it and storing
the pointer to the struct in the value field of tracing_map hash table.
If another thread comes in at this time and wants to add an element with
the same key, it will not see the current element and add a new one.

- There are multiple threads trying to execute cmpxchg at the same time,
one of the threads will succeed and the others will fail. The ones which
fail will go ahead increment 'idx' and add a new element there creating
a duplicate.

This patch detects and avoids the first condition by asking the thread
which detects the duplicate to loop one more time. There is also a
possibility of infinite loop if the thread which is trying to insert
goes to sleep indefinitely and the one which is trying to insert a new
element detects a duplicate. Which is why, the thread loops for
map_size iterations before returning NULL.

The second scenario is avoided by preventing the threads which failed
cmpxchg() from incrementing idx. This way, they will loop
around and check if the thread which succeeded in executing cmpxchg()
had the same key.

[1] http://lkml.kernel.org/r/cover.1498510759.git.tom.zanussi@linux.intel.com

Signed-off-by: Vedang Patel <vedang.patel@intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
---
 kernel/trace/tracing_map.c | 41 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 07e7534..b30f343 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -414,7 +414,9 @@ static inline bool keys_match(void *key, void *test_key, unsigned key_size)
 __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 {
 	u32 idx, key_hash, test_key;
+	int dup_try = 0;
 	struct tracing_map_entry *entry;
+	struct tracing_map_elt *val;
 
 	key_hash = jhash(key, map->key_size, 0);
 	if (key_hash == 0)
@@ -426,11 +428,33 @@ static inline bool keys_match(void *key, void *test_key, unsigned key_size)
 		entry = TRACING_MAP_ENTRY(map->map, idx);
 		test_key = entry->key;
 
-		if (test_key && test_key == key_hash && entry->val &&
-		    keys_match(key, entry->val->key, map->key_size)) {
-			if (!lookup_only)
-				atomic64_inc(&map->hits);
-			return entry->val;
+		if (test_key && test_key == key_hash) {
+			val = READ_ONCE(entry->val);
+			if (val &&
+			    keys_match(key, val->key, map->key_size)) {
+				if (!lookup_only)
+					atomic64_inc(&map->hits);
+				return val;
+			} else if (unlikely(!val)) {
+				/*
+				 * The key is present. But, val (pointer to elt
+				 * struct) is still NULL. which means some other
+				 * thread is in the process of inserting an
+				 * element.
+				 *
+				 * On top of that, it's key_hash is same as the
+				 * one being inserted right now. So, it's
+				 * possible that the element has the same
+				 * key as well.
+				 */
+
+				dup_try++;
+				if (dup_try > map->map_size) {
+					atomic64_inc(&map->drops);
+					break;
+				}
+				continue;
+			}
 		}
 
 		if (!test_key) {
@@ -452,6 +476,13 @@ static inline bool keys_match(void *key, void *test_key, unsigned key_size)
 				atomic64_inc(&map->hits);
 
 				return entry->val;
+			} else {
+				/*
+				 * cmpxchg() failed. Loop around once
+				 * more to check what key was inserted.
+				 */
+				dup_try++;
+				continue;
 			}
 		}
 
-- 
1.9.3

  parent reply	other threads:[~2017-11-17 20:35 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-17 20:32 [PATCH v6 00/37] tracing: Inter-event (e.g. latency) support Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 01/37] tracing: Move hist trigger Documentation to histogram.txt Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 02/37] tracing: Add Documentation for log2 modifier Tom Zanussi
2017-11-17 20:32 ` Tom Zanussi [this message]
2017-11-17 20:32 ` [PATCH v6 04/37] tracing: Remove code which merges duplicates Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 05/37] ring-buffer: Add interface for setting absolute time stamps Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 06/37] ring-buffer: Redefine the unimplemented RINGBUF_TYPE_TIME_STAMP Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 07/37] tracing: Add timestamp_mode trace file Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 08/37] tracing: Give event triggers access to ring_buffer_event Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 09/37] tracing: Add ring buffer event param to hist field functions Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 10/37] tracing: Break out hist trigger assignment parsing Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 11/37] tracing: Add hist trigger timestamp support Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 12/37] tracing: Add per-element variable support to tracing_map Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 13/37] tracing: Add hist_data member to hist_field Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 14/37] tracing: Add usecs modifier for hist trigger timestamps Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 15/37] tracing: Add variable support to hist triggers Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 16/37] tracing: Account for variables in named trigger compatibility Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 17/37] tracing: Move get_hist_field_flags() Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 18/37] tracing: Add simple expression support to hist triggers Tom Zanussi
2017-11-20  6:05   ` Namhyung Kim
2017-11-17 20:32 ` [PATCH v6 19/37] tracing: Generalize per-element hist trigger data Tom Zanussi
2017-11-17 20:32 ` [PATCH v6 20/37] tracing: Pass tracing_map_elt to hist_field accessor functions Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 21/37] tracing: Add hist_field 'type' field Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 22/37] tracing: Add variable reference handling to hist triggers Tom Zanussi
2017-11-21 10:53   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 23/37] tracing: Add hist trigger action hook Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 24/37] tracing: Add support for 'synthetic' events Tom Zanussi
2017-11-21 11:32   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 25/37] tracing: Add support for 'field variables' Tom Zanussi
2017-11-21 12:08   ` Namhyung Kim
2017-11-22  6:05   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 26/37] tracing: Add 'onmatch' hist trigger action support Tom Zanussi
2017-11-22  9:49   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 27/37] tracing: Add 'onmax' " Tom Zanussi
2017-11-23  5:09   ` Namhyung Kim
2017-11-29 20:53     ` Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 28/37] tracing: Allow whitespace to surround hist trigger filter Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 29/37] tracing: Add cpu field for hist triggers Tom Zanussi
2017-11-23  5:25   ` Namhyung Kim
2017-11-29 21:02     ` Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 30/37] tracing: Add hist trigger support for variable reference aliases Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 31/37] tracing: Add 'last error' error facility for hist triggers Tom Zanussi
2017-11-23  6:22   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 32/37] tracing: Add inter-event hist trigger Documentation Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 33/37] tracing: Make tracing_set_clock() non-static Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 34/37] tracing: Add a clock attribute for hist triggers Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 35/37] tracing: Increase trace_recursive_lock() limit for synthetic events Tom Zanussi
2017-11-17 20:33 ` [PATCH v6 36/37] tracing: Add inter-event blurb to HIST_TRIGGERS config option Tom Zanussi
2017-11-23  6:57   ` Namhyung Kim
2017-11-17 20:33 ` [PATCH v6 37/37] selftests: ftrace: Add inter-event hist triggers testcases Tom Zanussi

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=824898537fb3c1be3fbee67e5e7a2fce5b42c625.1510948725.git.tom.zanussi@linux.intel.com \
    --to=tom.zanussi@linux.intel.com \
    --cc=baohong.liu@intel.com \
    --cc=bigeasy@linutronix.de \
    --cc=fengguang.wu@intel.com \
    --cc=joel.opensrc@gmail.com \
    --cc=joelaf@google.com \
    --cc=julia@ni.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=rajvi.jingar@intel.com \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=vedang.patel@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.