[PATCH 03/11 v3] ftrace: Optimize testing what context current is in

From: VMware
Date: Thu Nov 05 2020 - 21:36:30 EST


From: "Steven Rostedt (VMware)" <rostedt@xxxxxxxxxxx>

The preempt_count() is not a simple location in memory, it could be part of
per_cpu code or more. Each access to preempt_count(), or one of its accessor
functions (like in_interrupt()) takes several cycles. By reading
preempt_count() once, and then doing tests to find the context against the
value return is slightly faster than using in_nmi() and in_interrupt().

Link: https://lkml.kernel.org/r/20201028115612.780796355@xxxxxxxxxxx

Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
include/linux/trace_recursion.h | 33 ++++++++++++++++++++-------------
1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index f2a949dbfec7..ac3d73484cb2 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -117,22 +117,29 @@ enum {

#define TRACE_CONTEXT_MASK TRACE_LIST_MAX

+/*
+ * Used for setting context
+ * NMI = 0
+ * IRQ = 1
+ * SOFTIRQ = 2
+ * NORMAL = 3
+ */
+enum {
+ TRACE_CTX_NMI,
+ TRACE_CTX_IRQ,
+ TRACE_CTX_SOFTIRQ,
+ TRACE_CTX_NORMAL,
+};
+
static __always_inline int trace_get_context_bit(void)
{
- int bit;
-
- if (in_interrupt()) {
- if (in_nmi())
- bit = 0;
-
- else if (in_irq())
- bit = 1;
- else
- bit = 2;
- } else
- bit = 3;
+ unsigned long pc = preempt_count();

- return bit;
+ if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+ return TRACE_CTX_NORMAL;
+ else
+ return pc & NMI_MASK ? TRACE_CTX_NMI :
+ pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
}

static __always_inline int trace_test_and_set_recursion(int start, int max)
--
2.28.0