[tip: core/rcu] sched,rcu,tracing: Avoid tracing before in_nmi() is correct

From: tip-bot2 for Peter Zijlstra
Date: Tue May 19 2020 - 15:53:00 EST


The following commit has been merged into the core/rcu branch of tip:

Commit-ID: f93524eb9c54f49be150167918f6546b0a2e09b1
Gitweb: https://git.kernel.org/tip/f93524eb9c54f49be150167918f6546b0a2e09b1
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Wed, 12 Feb 2020 21:01:16 +01:00
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitterDate: Tue, 19 May 2020 15:51:18 +02:00

sched,rcu,tracing: Avoid tracing before in_nmi() is correct

If a tracer is invoked before in_nmi() becomes true, the tracer can no
longer detect it is called from NMI context and behave correctly.

Therefore change nmi_{enter,exit}() to use __preempt_count_{add,sub}()
as the normal preempt_count_{add,sub}() have a (desired) function
trace entry.

This fixes a potential issue with the current code; when the function-tracer
has stack-tracing enabled __trace_stack() will malfunction when it hits the
preempt_count_add() function entry from NMI context.

Suggested-by: Steven Rostedt (VMware) <rosted@xxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Reviewed-by: Alexandre Chartre <alexandre.chartre@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200505134101.434193525@xxxxxxxxxxxxx


---
include/linux/hardirq.h | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index a043ad8..621556e 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -66,6 +66,15 @@ extern void irq_exit(void);
#endif

/*
+ * NMI vs Tracing
+ * --------------
+ *
+ * We must not land in a tracer until (or after) we've changed preempt_count
+ * such that in_nmi() becomes true. To that effect all NMI C entry points must
+ * be marked 'notrace' and call nmi_enter() as soon as possible.
+ */
+
+/*
* nmi_enter() can nest up to 15 times; see NMI_BITS.
*/
#define nmi_enter() \
@@ -75,7 +84,7 @@ extern void irq_exit(void);
lockdep_off(); \
ftrace_nmi_enter(); \
BUG_ON(in_nmi() == NMI_MASK); \
- preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \
+ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \
rcu_nmi_enter(); \
lockdep_hardirq_enter(); \
} while (0)
@@ -85,7 +94,7 @@ extern void irq_exit(void);
lockdep_hardirq_exit(); \
rcu_nmi_exit(); \
BUG_ON(!in_nmi()); \
- preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
+ __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
ftrace_nmi_exit(); \
lockdep_on(); \
printk_nmi_exit(); \