Similar to the IRQ tracepoint, the preempt tracepoints are typically disabled in production systems due to the significant overhead they introduce even when not in use.
The overhead primarily comes from two sources: First, when tracepoints are compiled into the kernel, preempt_count_add() and preempt_count_sub() become external function calls rather than inlined operations. Second, these functions perform unnecessary preempt_count() checks even when the tracepoint itself is disabled. This optimization introduces an early check of the tracepoint static key, which allows us to skip both the function call overhead and the redundant preempt_count() checks when tracing is disabled. The change maintains all existing functionality when tracing is active while significantly reducing overhead for the common case where tracing is inactive. Signed-off-by: Wander Lairson Costa <[email protected]> Suggested-by: Steven Rostedt <[email protected]> Cc: Arnaldo Carvalho de Melo <[email protected]> Cc: Clark Williams <[email protected]> Cc: Gabriele Monaco <[email protected]> Cc: Juri Lelli <[email protected]> --- include/linux/preempt.h | 35 ++++++++++++++++++++++++++++++--- kernel/sched/core.c | 12 +---------- kernel/trace/trace_preemptirq.c | 19 ++++++++++++++++++ 3 files changed, 52 insertions(+), 14 deletions(-) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index b0af8d4ef6e6..d13c755cd934 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -10,6 +10,7 @@ #include <linux/linkage.h> #include <linux/cleanup.h> #include <linux/types.h> +#include <linux/tracepoint-defs.h> /* * We put the hardirq and softirq counter into the preemption @@ -191,17 +192,45 @@ static __always_inline unsigned char interrupt_context_level(void) */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) -#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) +#if defined(CONFIG_DEBUG_PREEMPT) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); -#define preempt_count_dec_and_test() \ - ({ preempt_count_sub(1); should_resched(0); }) +#elif defined(CONFIG_TRACE_PREEMPT_TOGGLE) +extern void __trace_preempt_on(void); +extern void __trace_preempt_off(void); + +DECLARE_TRACEPOINT(preempt_enable); +DECLARE_TRACEPOINT(preempt_disable); + +#define __preempt_trace_enabled(type) \ + (tracepoint_enabled(preempt_##type) && preempt_count() == val) + +static inline void preempt_count_add(int val) +{ + __preempt_count_add(val); + + if (__preempt_trace_enabled(disable)) + __trace_preempt_off(); +} + +static inline void preempt_count_sub(int val) +{ + if (__preempt_trace_enabled(enable)) + __trace_preempt_on(); + + __preempt_count_sub(val); +} #else #define preempt_count_add(val) __preempt_count_add(val) #define preempt_count_sub(val) __preempt_count_sub(val) #define preempt_count_dec_and_test() __preempt_count_dec_and_test() #endif +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) +#define preempt_count_dec_and_test() \ + ({ preempt_count_sub(1); should_resched(0); }) +#endif + #define __preempt_count_inc() __preempt_count_add(1) #define __preempt_count_dec() __preempt_count_sub(1) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8988d38d46a3..4feba4738d79 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5840,8 +5840,7 @@ static inline void sched_tick_start(int cpu) { } static inline void sched_tick_stop(int cpu) { } #endif -#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_TRACE_PREEMPT_TOGGLE)) +#if defined(CONFIG_PREEMPTION) && defined(CONFIG_DEBUG_PREEMPT) /* * If the value passed in is equal to the current preempt count * then we just disabled preemption. Start timing the latency. @@ -5850,30 +5849,24 @@ static inline void preempt_latency_start(int val) { if (preempt_count() == val) { unsigned long ip = get_lock_parent_ip(); -#ifdef CONFIG_DEBUG_PREEMPT current->preempt_disable_ip = ip; -#endif trace_preempt_off(CALLER_ADDR0, ip); } } void preempt_count_add(int val) { -#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) return; -#endif __preempt_count_add(val); -#ifdef CONFIG_DEBUG_PREEMPT /* * Spinlock count overflowing soon? */ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); -#endif preempt_latency_start(val); } EXPORT_SYMBOL(preempt_count_add); @@ -5891,7 +5884,6 @@ static inline void preempt_latency_stop(int val) void preempt_count_sub(int val) { -#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ @@ -5903,14 +5895,12 @@ void preempt_count_sub(int val) if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK))) return; -#endif preempt_latency_stop(val); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); NOKPROBE_SYMBOL(preempt_count_sub); - #else static inline void preempt_latency_start(int val) { } static inline void preempt_latency_stop(int val) { } diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 90ee65db4516..deb2428b34a2 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -118,6 +118,25 @@ EXPORT_TRACEPOINT_SYMBOL(irq_enable); #ifdef CONFIG_TRACE_PREEMPT_TOGGLE +#if !defined(CONFIG_DEBUG_PREEMPT) +EXPORT_SYMBOL(__tracepoint_preempt_disable); +EXPORT_SYMBOL(__tracepoint_preempt_enable); + +void __trace_preempt_on(void) +{ + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); +} +EXPORT_SYMBOL(__trace_preempt_on); +NOKPROBE_SYMBOL(__trace_preempt_on); + +void __trace_preempt_off(void) +{ + trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); +} +EXPORT_SYMBOL(__trace_preempt_off); +NOKPROBE_SYMBOL(__trace_preempt_off); +#endif /* !CONFIG_DEBUG_PREEMPT */ + void trace_preempt_on(unsigned long a0, unsigned long a1) { trace(preempt_enable, TP_ARGS(a0, a1)); -- 2.50.0
