| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20180507204143.13061-5-joelaf@google.com>
Date: Mon, 7 May 2018 13:41:42 -0700
From: Joel Fernandes <joelaf@...gle.com>
To: linux-kernel@...r.kernel.org
Cc: "Joel Fernandes (Google)" <joel@...lfernandes.org>,
Steven Rostedt <rostedt@...dmis.org>,
Peter Zilstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Tom Zanussi <tom.zanussi@...ux.intel.com>,
Namhyung Kim <namhyung@...nel.org>,
Thomas Glexiner <tglx@...utronix.de>,
Boqun Feng <boqun.feng@...il.com>,
Paul McKenney <paulmck@...ux.vnet.ibm.com>,
Frederic Weisbecker <fweisbec@...il.com>,
Randy Dunlap <rdunlap@...radead.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Fenguang Wu <fengguang.wu@...el.com>,
Baohong Liu <baohong.liu@...el.com>,
Vedang Patel <vedang.patel@...el.com>, kernel-team@...roid.com
Subject: [PATCH RFC v6 4/5] tracepoint: Make rcuidle tracepoint callers use SRCU
From: "Joel Fernandes (Google)" <joel@...lfernandes.org>
In recent tests with IRQ on/off tracepoints, a large performance
overhead ~10% is noticed when running hackbench. This is root caused to
calls to rcu_irq_enter_irqson and rcu_irq_exit_irqson from the
tracepoint code. Following a long discussion on the list [1] about this,
we concluded that srcu is a better alternative for use during rcu idle.
Although it does involve extra barriers, its lighter than the sched-rcu
version which has to do additional RCU calls to notify RCU idle about
entry into RCU sections.
In this patch, we change the underlying implementation of the
trace_*_rcuidle API to use SRCU. This has shown to improve performance
alot for the high frequency irq enable/disable tracepoints.
Test: Tested idle and preempt/irq tracepoints.
Here are some performance numbers:
With a run of the following 30 times on a single core x86 Qemu instance
with 1GB memory:
hackbench -g 4 -f 2 -l 3000
Completion times in seconds. CONFIG_PROVE_LOCKING=y.
No patches (without this series)
Mean: 3.048
Median: 3.025
Std Dev: 0.064
With Lockdep using irq tracepoints with RCU implementation:
Mean: 3.451 (-11.66 %)
Median: 3.447 (-12.22%)
Std Dev: 0.049
With Lockdep using irq tracepoints with SRCU implementation (this series):
Mean: 3.020 (I would consider the improvement against the "without
this series" case as just noise).
Median: 3.013
Std Dev: 0.033
[1] https://patchwork.kernel.org/patch/10344297/
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Peter Zilstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc: Tom Zanussi <tom.zanussi@...ux.intel.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Thomas Glexiner <tglx@...utronix.de>
Cc: Boqun Feng <boqun.feng@...il.com>
Cc: Paul McKenney <paulmck@...ux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: Randy Dunlap <rdunlap@...radead.org>
Cc: Masami Hiramatsu <mhiramat@...nel.org>
Cc: Fenguang Wu <fengguang.wu@...el.com>
Cc: Baohong Liu <baohong.liu@...el.com>
Cc: Vedang Patel <vedang.patel@...el.com>
Cc: kernel-team@...roid.com
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
---
include/linux/tracepoint.h | 46 +++++++++++++++++++++++++++++++-------
kernel/tracepoint.c | 15 ++++++++++++-
2 files changed, 52 insertions(+), 9 deletions(-)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index c94f466d57ef..f56f290cf8eb 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -15,6 +15,7 @@
*/
#include <linux/smp.h>
+#include <linux/srcu.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/cpumask.h>
@@ -33,6 +34,8 @@ struct trace_eval_map {
#define TRACEPOINT_DEFAULT_PRIO 10
+extern struct srcu_struct tracepoint_srcu;
+
extern int
tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data);
extern int
@@ -77,6 +80,9 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb)
*/
static inline void tracepoint_synchronize_unregister(void)
{
+#ifdef CONFIG_TRACEPOINTS
+ synchronize_srcu(&tracepoint_srcu);
+#endif
synchronize_sched();
}
@@ -129,18 +135,38 @@ extern void syscall_unregfunc(void);
* as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
* "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
*/
-#define __DO_TRACE(tp, proto, args, cond, rcucheck) \
+#define __DO_TRACE(tp, proto, args, cond, rcuidle) \
do { \
struct tracepoint_func *it_func_ptr; \
void *it_func; \
void *__data; \
+ int __maybe_unused idx = 0; \
\
if (!(cond)) \
return; \
- if (rcucheck) \
- rcu_irq_enter_irqson(); \
- rcu_read_lock_sched_notrace(); \
- it_func_ptr = rcu_dereference_sched((tp)->funcs); \
+ \
+ /* \
+ * For rcuidle callers, use srcu since sched-rcu \
+ * doesn't work from the idle path. \
+ */ \
+ if (rcuidle) { \
+ if (in_nmi()) { \
+ WARN_ON_ONCE(1); \
+ return; /* no srcu from nmi */ \
+ } \
+ \
+ idx = srcu_read_lock_notrace(&tracepoint_srcu); \
+ it_func_ptr = \
+ srcu_dereference_notrace((tp)->funcs, \
+ &tracepoint_srcu); \
+ /* To keep it consistent with !rcuidle path */ \
+ preempt_disable_notrace(); \
+ } else { \
+ rcu_read_lock_sched_notrace(); \
+ it_func_ptr = \
+ rcu_dereference_sched((tp)->funcs); \
+ } \
+ \
if (it_func_ptr) { \
do { \
it_func = (it_func_ptr)->func; \
@@ -148,9 +174,13 @@ extern void syscall_unregfunc(void);
((void(*)(proto))(it_func))(args); \
} while ((++it_func_ptr)->func); \
} \
- rcu_read_unlock_sched_notrace(); \
- if (rcucheck) \
- rcu_irq_exit_irqson(); \
+ \
+ if (rcuidle) { \
+ preempt_enable_notrace(); \
+ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\
+ } else { \
+ rcu_read_unlock_sched_notrace(); \
+ } \
} while (0)
#ifndef MODULE
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 671b13457387..2089f579f790 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -31,6 +31,9 @@
extern struct tracepoint * const __start___tracepoints_ptrs[];
extern struct tracepoint * const __stop___tracepoints_ptrs[];
+DEFINE_SRCU(tracepoint_srcu);
+EXPORT_SYMBOL_GPL(tracepoint_srcu);
+
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
@@ -67,16 +70,26 @@ static inline void *allocate_probes(int count)
return p == NULL ? NULL : p->probes;
}
-static void rcu_free_old_probes(struct rcu_head *head)
+static void srcu_free_old_probes(struct rcu_head *head)
{
kfree(container_of(head, struct tp_probes, rcu));
}
+static void rcu_free_old_probes(struct rcu_head *head)
+{
+ call_srcu(&tracepoint_srcu, head, srcu_free_old_probes);
+}
+
static inline void release_probes(struct tracepoint_func *old)
{
if (old) {
struct tp_probes *tp_probes = container_of(old,
struct tp_probes, probes[0]);
+ /*
+ * Tracepoint probes are protected by both sched RCU and SRCU,
+ * by calling the SRCU callback in the sched RCU callback we
+ * cover both cases. So lets chain the SRCU and RCU callbacks.
+ */
call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
}
}
--
2.17.0.441.gb46fe60e1d-goog
Powered by blists - more mailing lists