From: Peter Zijlstra <peterz@infradead.org>
To: linux-kernel@vger.kernel.org, mingo@kernel.org, will@kernel.org
Cc: npiggin@gmail.com, elver@google.com, jgross@suse.com,
paulmck@kernel.org, rostedt@goodmis.org, rjw@rjwysocki.net,
joel@joelfernandes.org, svens@linux.ibm.com, tglx@linutronix.de,
peterz@infradead.org
Subject: [PATCH 1/9] lockdep: Use raw_cpu_*() for per-cpu variables
Date: Thu, 20 Aug 2020 09:30:32 +0200 [thread overview]
Message-ID: <20200820074640.342269393@infradead.org> (raw)
In-Reply-To: 20200820073031.886217423@infradead.org
Sven reported that commit a21ee6055c30 ("lockdep: Change
hardirq{s_enabled,_context} to per-cpu variables") caused trouble on
s390 because their this_cpu_*() primitives disable preemption which
then lands back tracing.
On the one hand, per-cpu ops should use preempt_*able_notrace() and
raw_local_irq_*(), on the other hand, we can trivialy use raw_cpu_*()
ops for this.
Fixes: a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables")
Reported-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
include/linux/irqflags.h | 6 +++---
include/linux/lockdep.h | 18 +++++++++++++-----
kernel/locking/lockdep.c | 4 ++--
3 files changed, 18 insertions(+), 10 deletions(-)
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -53,13 +53,13 @@ DECLARE_PER_CPU(int, hardirq_context);
extern void trace_hardirqs_off_finish(void);
extern void trace_hardirqs_on(void);
extern void trace_hardirqs_off(void);
-# define lockdep_hardirq_context() (this_cpu_read(hardirq_context))
+# define lockdep_hardirq_context() (raw_cpu_read(hardirq_context))
# define lockdep_softirq_context(p) ((p)->softirq_context)
# define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled))
# define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled)
# define lockdep_hardirq_enter() \
do { \
- if (this_cpu_inc_return(hardirq_context) == 1) \
+ if (__this_cpu_inc_return(hardirq_context) == 1)\
current->hardirq_threaded = 0; \
} while (0)
# define lockdep_hardirq_threaded() \
@@ -68,7 +68,7 @@ do { \
} while (0)
# define lockdep_hardirq_exit() \
do { \
- this_cpu_dec(hardirq_context); \
+ __this_cpu_dec(hardirq_context); \
} while (0)
# define lockdep_softirq_enter() \
do { \
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -535,19 +535,27 @@ do { \
DECLARE_PER_CPU(int, hardirqs_enabled);
DECLARE_PER_CPU(int, hardirq_context);
+/*
+ * The below lockdep_assert_*() macros se raw_cpu_read() to access the above
+ * per-cpu variables. This is required because this_cpu_read() will potentially
+ * call into preempt/irq-disable and that obviously isn't right. This is also
+ * correct because when IRQs are enabled, it doesn't matter if we accidentally
+ * read the value from our previous CPU.
+ */
+
#define lockdep_assert_irqs_enabled() \
do { \
- WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled)); \
+ WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled)); \
} while (0)
#define lockdep_assert_irqs_disabled() \
do { \
- WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled)); \
+ WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled)); \
} while (0)
#define lockdep_assert_in_irq() \
do { \
- WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \
+ WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context)); \
} while (0)
#define lockdep_assert_preemption_enabled() \
@@ -555,7 +563,7 @@ do { \
WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \
debug_locks && \
(preempt_count() != 0 || \
- !this_cpu_read(hardirqs_enabled))); \
+ !raw_cpu_read(hardirqs_enabled))); \
} while (0)
#define lockdep_assert_preemption_disabled() \
@@ -563,7 +571,7 @@ do { \
WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \
debug_locks && \
(preempt_count() == 0 && \
- this_cpu_read(hardirqs_enabled))); \
+ raw_cpu_read(hardirqs_enabled))); \
} while (0)
#else
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3756,7 +3756,7 @@ void noinstr lockdep_hardirqs_on(unsigne
skip_checks:
/* we'll do an OFF -> ON transition: */
- this_cpu_write(hardirqs_enabled, 1);
+ __this_cpu_write(hardirqs_enabled, 1);
trace->hardirq_enable_ip = ip;
trace->hardirq_enable_event = ++trace->irq_events;
debug_atomic_inc(hardirqs_on_events);
@@ -3795,7 +3795,7 @@ void noinstr lockdep_hardirqs_off(unsign
/*
* We have done an ON -> OFF transition:
*/
- this_cpu_write(hardirqs_enabled, 0);
+ __this_cpu_write(hardirqs_enabled, 0);
trace->hardirq_disable_ip = ip;
trace->hardirq_disable_event = ++trace->irq_events;
debug_atomic_inc(hardirqs_off_events);
next prev parent reply other threads:[~2020-08-20 7:50 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-20 7:30 [PATCH 0/9] TRACE_IRQFLAGS wreckage Peter Zijlstra
2020-08-20 7:30 ` Peter Zijlstra [this message]
2020-08-20 13:54 ` [PATCH 1/9] lockdep: Use raw_cpu_*() for per-cpu variables Steven Rostedt
2020-08-20 7:30 ` [PATCH 2/9] sched,idle,rcu: Push rcu_idle deeper into the idle path Peter Zijlstra
2020-08-20 13:58 ` Steven Rostedt
2020-08-20 7:30 ` [PATCH 3/9] cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic Peter Zijlstra
2020-08-20 7:30 ` [PATCH 4/9] cpuidle: Move trace_cpu_idle() into generic code Peter Zijlstra
2020-08-20 7:30 ` [PATCH 5/9] x86/entry: Remove unused THUNKs Peter Zijlstra
2020-08-20 7:30 ` [PATCH 6/9] locking/lockdep: Cleanup Peter Zijlstra
2020-08-20 7:30 ` [PATCH 7/9] nds32: Implement arch_irqs_disabled() Peter Zijlstra
2020-08-20 7:30 ` [PATCH 8/9] lockdep: Only trace IRQ edges Peter Zijlstra
2020-08-20 7:30 ` [PATCH 9/9] lockdep,trace: Expose tracepoints Peter Zijlstra
2020-08-20 14:36 ` [PATCH 0/9] TRACE_IRQFLAGS wreckage Steven Rostedt
2020-08-20 14:39 ` Steven Rostedt
2020-08-20 14:49 ` Marco Elver
2020-08-20 14:58 ` peterz
2020-08-20 16:53 ` Steven Rostedt
2020-08-20 17:20 ` Marco Elver
2020-08-20 19:59 ` Steven Rostedt
2020-08-21 6:37 ` Marco Elver
2020-08-21 6:54 ` peterz
2020-08-21 7:05 ` Marco Elver
2020-08-27 7:54 ` [tip: sched/urgent] sched: Use __always_inline on is_idle_task() tip-bot2 for Marco Elver
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=20200820074640.342269393@infradead.org \
--to=peterz@infradead.org \
--cc=elver@google.com \
--cc=jgross@suse.com \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=npiggin@gmail.com \
--cc=paulmck@kernel.org \
--cc=rjw@rjwysocki.net \
--cc=rostedt@goodmis.org \
--cc=svens@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
/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