summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-01-17 00:00:25 -0500
committerDavid S. Miller <davem@davemloft.net>2018-01-17 00:10:42 -0500
commitc02b3741eb99a1ec733e6134c53ba59e43e19e97 (patch)
treeff7dd96c32dec2abe530e7101378443dabcb8962 /kernel/trace
parent7018d1b3f20fb4308ed9bc577160cb8ffb79b62a (diff)
parent8cbab92dff778e516064c13113ca15d4869ec883 (diff)
downloadlinux-c02b3741eb99a1ec733e6134c53ba59e43e19e97.tar.gz
linux-c02b3741eb99a1ec733e6134c53ba59e43e19e97.tar.bz2
linux-c02b3741eb99a1ec733e6134c53ba59e43e19e97.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Overlapping changes all over. The mini-qdisc bits were a little bit tricky, however. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/ring_buffer.c62
2 files changed, 46 insertions, 18 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 7114c885a78a..0b249e2f0c3c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES
on if you need to profile the system's use of these macros.
config PROFILE_ALL_BRANCHES
- bool "Profile all if conditionals"
+ bool "Profile all if conditionals" if !FORTIFY_SOURCE
select TRACE_BRANCH_PROFILING
help
This tracer profiles all branch conditions. Every if ()
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ab18995ff1e..0cddf60186da 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2534,29 +2534,59 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
* The lock and unlock are done within a preempt disable section.
* The current_context per_cpu variable can only be modified
* by the current task between lock and unlock. But it can
- * be modified more than once via an interrupt. There are four
- * different contexts that we need to consider.
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
*
- * Normal context.
- * SoftIRQ context
- * IRQ context
- * NMI context
+ * bit 0 = NMI context
+ * bit 1 = IRQ context
+ * bit 2 = SoftIRQ context
+ * bit 3 = normal context.
*
- * If for some reason the ring buffer starts to recurse, we
- * only allow that to happen at most 4 times (one for each
- * context). If it happens 5 times, then we consider this a
- * recusive loop and do not let it go further.
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ * 101 - 1 = 100
+ * 101 & 100 = 100 (clearing bit zero)
+ *
+ * 1010 - 1 = 1001
+ * 1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
*/
static __always_inline int
trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
{
- if (cpu_buffer->current_context >= 4)
+ unsigned int val = cpu_buffer->current_context;
+ unsigned long pc = preempt_count();
+ int bit;
+
+ if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+ bit = RB_CTX_NORMAL;
+ else
+ bit = pc & NMI_MASK ? RB_CTX_NMI :
+ pc & HARDIRQ_MASK ? RB_CTX_IRQ :
+ pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ;
+
+ if (unlikely(val & (1 << bit)))
return 1;
- cpu_buffer->current_context++;
- /* Interrupts must see this update */
- barrier();
+ val |= (1 << bit);
+ cpu_buffer->current_context = val;
return 0;
}
@@ -2564,9 +2594,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
static __always_inline void
trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
{
- /* Don't let the dec leak out */
- barrier();
- cpu_buffer->current_context--;
+ cpu_buffer->current_context &= cpu_buffer->current_context - 1;
}
/**