Merge tag 'trace-v4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from

 - allow module init functions to be traced

 - clean up some unused or not used by config events (saves space)

 - clean up of trace histogram code

 - add support for preempt and interrupt enabled/disable events

 - other various clean ups

* tag 'trace-v4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (30 commits)
  tracing, thermal: Hide cpu cooling trace events when not in use
  tracing, thermal: Hide devfreq trace events when not in use
  ftrace: Kill FTRACE_OPS_FL_PER_CPU
  perf/ftrace: Small cleanup
  perf/ftrace: Fix function trace events
  perf/ftrace: Revert ("perf/ftrace: Fix double traces of perf on ftrace:function")
  tracing, dma-buf: Remove unused trace event dma_fence_annotate_wait_on
  tracing, memcg, vmscan: Hide trace events when not in use
  tracing/xen: Hide events that are not used when X86_PAE is not defined
  tracing: mark trace_test_buffer as __maybe_unused
  printk: Remove superfluous memory barriers from printk_safe
  ftrace: Clear hashes of stale ips of init memory
  tracing: Add support for preempt and irq enable/disable events
  tracing: Prepare to add preempt and irq trace events
  ftrace/kallsyms: Have /proc/kallsyms show saved mod init functions
  ftrace: Add freeing algorithm to free ftrace_mod_maps
  ftrace: Save module init functions kallsyms symbols for tracing
  ftrace: Allow module init functions to be traced
  ftrace: Add a ftrace_free_mem() function for modules to use
  tracing: Reimplement log2
  ...

9 files changed, 149 insertions, 132 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e54d257..2bab819 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -52,6 +52,30 @@ static inline void early_trace_init(void) { }
 struct module;
 struct ftrace_hash;
 
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \
+	defined(CONFIG_DYNAMIC_FTRACE)
+const char *
+ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
+		   unsigned long *off, char **modname, char *sym);
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
+static inline const char *
+ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
+		   unsigned long *off, char **modname, char *sym)
+{
+	return NULL;
+}
+static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+					 char *type, char *name,
+					 char *module_name, int *exported)
+{
+	return -1;
+}
+#endif
+
+
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -79,10 +103,6 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  * ENABLED - set/unset when ftrace_ops is registered/unregistered
  * DYNAMIC - set when ftrace_ops is registered to denote dynamically
  *           allocated ftrace_ops which need special care
- * PER_CPU - set manualy by ftrace_ops user to denote the ftrace_ops
- *           could be controlled by following calls:
- *             ftrace_function_local_enable
- *             ftrace_function_local_disable
  * SAVE_REGS - The ftrace_ops wants regs saved at each function called
  *            and passed to the callback. If this flag is set, but the
  *            architecture does not support passing regs
@@ -126,21 +146,20 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
 	FTRACE_OPS_FL_DYNAMIC			= 1 << 1,
-	FTRACE_OPS_FL_PER_CPU			= 1 << 2,
-	FTRACE_OPS_FL_SAVE_REGS			= 1 << 3,
-	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 4,
-	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 5,
-	FTRACE_OPS_FL_STUB			= 1 << 6,
-	FTRACE_OPS_FL_INITIALIZED		= 1 << 7,
-	FTRACE_OPS_FL_DELETED			= 1 << 8,
-	FTRACE_OPS_FL_ADDING			= 1 << 9,
-	FTRACE_OPS_FL_REMOVING			= 1 << 10,
-	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
-	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 12,
-	FTRACE_OPS_FL_IPMODIFY			= 1 << 13,
-	FTRACE_OPS_FL_PID			= 1 << 14,
-	FTRACE_OPS_FL_RCU			= 1 << 15,
-	FTRACE_OPS_FL_TRACE_ARRAY		= 1 << 16,
+	FTRACE_OPS_FL_SAVE_REGS			= 1 << 2,
+	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 3,
+	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 4,
+	FTRACE_OPS_FL_STUB			= 1 << 5,
+	FTRACE_OPS_FL_INITIALIZED		= 1 << 6,
+	FTRACE_OPS_FL_DELETED			= 1 << 7,
+	FTRACE_OPS_FL_ADDING			= 1 << 8,
+	FTRACE_OPS_FL_REMOVING			= 1 << 9,
+	FTRACE_OPS_FL_MODIFYING			= 1 << 10,
+	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 11,
+	FTRACE_OPS_FL_IPMODIFY			= 1 << 12,
+	FTRACE_OPS_FL_PID			= 1 << 13,
+	FTRACE_OPS_FL_RCU			= 1 << 14,
+	FTRACE_OPS_FL_TRACE_ARRAY		= 1 << 15,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -152,8 +171,10 @@ struct ftrace_ops_hash {
 };
 
 void ftrace_free_init_mem(void);
+void ftrace_free_mem(struct module *mod, void *start, void *end);
 #else
 static inline void ftrace_free_init_mem(void) { }
+static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
 #endif
 
 /*
@@ -173,7 +194,6 @@ struct ftrace_ops {
 	unsigned long			flags;
 	void				*private;
 	ftrace_func_t			saved_func;
-	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	struct ftrace_ops_hash		local_hash;
 	struct ftrace_ops_hash		*func_hash;
@@ -205,55 +225,6 @@ int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
 void clear_ftrace_function(void);
 
-/**
- * ftrace_function_local_enable - enable ftrace_ops on current cpu
- *
- * This function enables tracing on current cpu by decreasing
- * the per cpu control variable.
- * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
- * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
- */
-static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
-{
-	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
-		return;
-
-	(*this_cpu_ptr(ops->disabled))--;
-}
-
-/**
- * ftrace_function_local_disable - disable ftrace_ops on current cpu
- *
- * This function disables tracing on current cpu by increasing
- * the per cpu control variable.
- * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
- * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
- */
-static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
-{
-	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
-		return;
-
-	(*this_cpu_ptr(ops->disabled))++;
-}
-
-/**
- * ftrace_function_local_disabled - returns ftrace_ops disabled value
- *                                  on current cpu
- *
- * This function returns value of ftrace_ops::disabled on current cpu.
- * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
- * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
- */
-static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
-{
-	WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU));
-	return *this_cpu_ptr(ops->disabled);
-}
-
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
 			struct ftrace_ops *op, struct pt_regs *regs);
 
@@ -271,6 +242,7 @@ static inline int ftrace_nr_registered_ops(void)
 static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_free_init_mem(void) { }
+static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_STACK_TRACER
@@ -743,7 +715,8 @@ static inline unsigned long get_lock_parent_ip(void)
   static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
 #endif
 
-#ifdef CONFIG_PREEMPT_TRACER
+#if defined(CONFIG_PREEMPT_TRACER) || \
+	(defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
   extern void trace_preempt_on(unsigned long a0, unsigned long a1);
   extern void trace_preempt_off(unsigned long a0, unsigned long a1);
 #else
diff --git a/include/linux/init.h b/include/linux/init.h
index f38b993..ea1b311 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -40,7 +40,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold __inittrace __latent_entropy
+#define __init		__section(.init.text) __cold  __latent_entropy
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
@@ -69,10 +69,8 @@
 
 #ifdef MODULE
 #define __exitused
-#define __inittrace notrace
 #else
 #define __exitused  __used
-#define __inittrace
 #endif
 
 #define __exit          __section(.exit.text) __exitused __cold notrace
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 874b71a..2c9c87d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1169,7 +1169,7 @@ extern void perf_event_init(void);
 extern void perf_tp_event(u16 event_type, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
 			  struct hlist_head *head, int rctx,
-			  struct task_struct *task, struct perf_event *event);
+			  struct task_struct *task);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 84014ec..af44e7c 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -174,6 +174,11 @@ enum trace_reg {
 	TRACE_REG_PERF_UNREGISTER,
 	TRACE_REG_PERF_OPEN,
 	TRACE_REG_PERF_CLOSE,
+	/*
+	 * These (ADD/DEL) use a 'boolean' return value, where 1 (true) means a
+	 * custom action was taken and the default action is not to be
+	 * performed.
+	 */
 	TRACE_REG_PERF_ADD,
 	TRACE_REG_PERF_DEL,
 #endif
@@ -542,9 +547,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
 		       u64 count, struct pt_regs *regs, void *head,
-		       struct task_struct *task, struct perf_event *event)
+		       struct task_struct *task)
 {
-	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event);
+	perf_tp_event(type, count, raw_data, size, regs, head, rctx, task);
 }
 
 #endif
diff --git a/include/trace/events/dma_fence.h b/include/trace/events/dma_fence.h
index d61bfdd..2212add 100644
--- a/include/trace/events/dma_fence.h
+++ b/include/trace/events/dma_fence.h
@@ -9,46 +9,6 @@
 
 struct dma_fence;
 
-TRACE_EVENT(dma_fence_annotate_wait_on,
-
-	/* fence: the fence waiting on f1, f1: the fence to be waited on. */
-	TP_PROTO(struct dma_fence *fence, struct dma_fence *f1),
-
-	TP_ARGS(fence, f1),
-
-	TP_STRUCT__entry(
-		__string(driver, fence->ops->get_driver_name(fence))
-		__string(timeline, fence->ops->get_timeline_name(fence))
-		__field(unsigned int, context)
-		__field(unsigned int, seqno)
-
-		__string(waiting_driver, f1->ops->get_driver_name(f1))
-		__string(waiting_timeline, f1->ops->get_timeline_name(f1))
-		__field(unsigned int, waiting_context)
-		__field(unsigned int, waiting_seqno)
-	),
-
-	TP_fast_assign(
-		__assign_str(driver, fence->ops->get_driver_name(fence))
-		__assign_str(timeline, fence->ops->get_timeline_name(fence))
-		__entry->context = fence->context;
-		__entry->seqno = fence->seqno;
-
-		__assign_str(waiting_driver, f1->ops->get_driver_name(f1))
-		__assign_str(waiting_timeline, f1->ops->get_timeline_name(f1))
-		__entry->waiting_context = f1->context;
-		__entry->waiting_seqno = f1->seqno;
-
-	),
-
-	TP_printk("driver=%s timeline=%s context=%u seqno=%u "	\
-		  "waits on driver=%s timeline=%s context=%u seqno=%u",
-		  __get_str(driver), __get_str(timeline), __entry->context,
-		  __entry->seqno,
-		  __get_str(waiting_driver), __get_str(waiting_timeline),
-		  __entry->waiting_context, __entry->waiting_seqno)
-);
-
 DECLARE_EVENT_CLASS(dma_fence,
 
 	TP_PROTO(struct dma_fence *fence),
diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h
new file mode 100644
index 0000000..f5024c5
--- /dev/null
+++ b/include/trace/events/preemptirq.h
@@ -0,0 +1,70 @@
+#ifdef CONFIG_PREEMPTIRQ_EVENTS
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM preemptirq
+
+#if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PREEMPTIRQ_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+#include <linux/string.h>
+#include <asm/sections.h>
+
+DECLARE_EVENT_CLASS(preemptirq_template,
+
+	TP_PROTO(unsigned long ip, unsigned long parent_ip),
+
+	TP_ARGS(ip, parent_ip),
+
+	TP_STRUCT__entry(
+		__field(u32, caller_offs)
+		__field(u32, parent_offs)
+	),
+
+	TP_fast_assign(
+		__entry->caller_offs = (u32)(ip - (unsigned long)_stext);
+		__entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext);
+	),
+
+	TP_printk("caller=%pF parent=%pF",
+		  (void *)((unsigned long)(_stext) + __entry->caller_offs),
+		  (void *)((unsigned long)(_stext) + __entry->parent_offs))
+);
+
+#ifndef CONFIG_PROVE_LOCKING
+DEFINE_EVENT(preemptirq_template, irq_disable,
+	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
+	     TP_ARGS(ip, parent_ip));
+
+DEFINE_EVENT(preemptirq_template, irq_enable,
+	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
+	     TP_ARGS(ip, parent_ip));
+#endif
+
+#ifdef CONFIG_DEBUG_PREEMPT
+DEFINE_EVENT(preemptirq_template, preempt_disable,
+	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
+	     TP_ARGS(ip, parent_ip));
+
+DEFINE_EVENT(preemptirq_template, preempt_enable,
+	     TP_PROTO(unsigned long ip, unsigned long parent_ip),
+	     TP_ARGS(ip, parent_ip));
+#endif
+
+#endif /* _TRACE_PREEMPTIRQ_H */
+
+#include <trace/define_trace.h>
+
+#else /* !CONFIG_PREEMPTIRQ_EVENTS */
+
+#define trace_irq_enable(...)
+#define trace_irq_disable(...)
+#define trace_preempt_enable(...)
+#define trace_preempt_disable(...)
+#define trace_irq_enable_rcuidle(...)
+#define trace_irq_disable_rcuidle(...)
+#define trace_preempt_enable_rcuidle(...)
+#define trace_preempt_disable_rcuidle(...)
+
+#endif
diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h
index 466c09d..7894664 100644
--- a/include/trace/events/thermal.h
+++ b/include/trace/events/thermal.h
@@ -91,6 +91,7 @@ TRACE_EVENT(thermal_zone_trip,
 		show_tzt_type(__entry->trip_type))
 );
 
+#ifdef CONFIG_CPU_THERMAL
 TRACE_EVENT(thermal_power_cpu_get_power,
 	TP_PROTO(const struct cpumask *cpus, unsigned long freq, u32 *load,
 		size_t load_len, u32 dynamic_power, u32 static_power),
@@ -148,7 +149,9 @@ TRACE_EVENT(thermal_power_cpu_limit,
 		__get_bitmask(cpumask), __entry->freq, __entry->cdev_state,
 		__entry->power)
 );
+#endif /* CONFIG_CPU_THERMAL */
 
+#ifdef CONFIG_DEVFREQ_THERMAL
 TRACE_EVENT(thermal_power_devfreq_get_power,
 	TP_PROTO(struct thermal_cooling_device *cdev,
 		 struct devfreq_dev_status *status, unsigned long freq,
@@ -204,6 +207,7 @@ TRACE_EVENT(thermal_power_devfreq_limit,
 		__get_str(type), __entry->freq, __entry->cdev_state,
 		__entry->power)
 );
+#endif /* CONFIG_DEVFREQ_THERMAL */
 #endif /* _TRACE_THERMAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index dc23cf0..d70b53e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -134,6 +134,7 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_b
 	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
+#ifdef CONFIG_MEMCG
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
 
 	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
@@ -147,6 +148,7 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_
 
 	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
+#endif /* CONFIG_MEMCG */
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
 
@@ -172,6 +174,7 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end
 	TP_ARGS(nr_reclaimed)
 );
 
+#ifdef CONFIG_MEMCG
 DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
 
 	TP_PROTO(unsigned long nr_reclaimed),
@@ -185,6 +188,7 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re
 
 	TP_ARGS(nr_reclaimed)
 );
+#endif /* CONFIG_MEMCG */
 
 TRACE_EVENT(mm_shrink_slab_start,
 	TP_PROTO(struct shrinker *shr, struct shrink_control *sc,
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index a7c8b45..b8adf05 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -148,7 +148,6 @@ DECLARE_EVENT_CLASS(xen_mmu__set_pte,
 		     TP_ARGS(ptep, pteval))
 
 DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte);
-DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte_atomic);
 
 TRACE_EVENT(xen_mmu_set_pte_at,
 	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
@@ -170,21 +169,6 @@ TRACE_EVENT(xen_mmu_set_pte_at,
 		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
 	);
 
-TRACE_EVENT(xen_mmu_pte_clear,
-	    TP_PROTO(struct mm_struct *mm, unsigned long addr, pte_t *ptep),
-	    TP_ARGS(mm, addr, ptep),
-	    TP_STRUCT__entry(
-		    __field(struct mm_struct *, mm)
-		    __field(unsigned long, addr)
-		    __field(pte_t *, ptep)
-		    ),
-	    TP_fast_assign(__entry->mm = mm;
-			   __entry->addr = addr;
-			   __entry->ptep = ptep),
-	    TP_printk("mm %p addr %lx ptep %p",
-		      __entry->mm, __entry->addr, __entry->ptep)
-	);
-
 TRACE_DEFINE_SIZEOF(pmdval_t);
 
 TRACE_EVENT(xen_mmu_set_pmd,
@@ -202,6 +186,24 @@ TRACE_EVENT(xen_mmu_set_pmd,
 		      (int)sizeof(pmdval_t) * 2, (unsigned long long)__entry->pmdval)
 	);
 
+#ifdef CONFIG_X86_PAE
+DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte_atomic);
+
+TRACE_EVENT(xen_mmu_pte_clear,
+	    TP_PROTO(struct mm_struct *mm, unsigned long addr, pte_t *ptep),
+	    TP_ARGS(mm, addr, ptep),
+	    TP_STRUCT__entry(
+		    __field(struct mm_struct *, mm)
+		    __field(unsigned long, addr)
+		    __field(pte_t *, ptep)
+		    ),
+	    TP_fast_assign(__entry->mm = mm;
+			   __entry->addr = addr;
+			   __entry->ptep = ptep),
+	    TP_printk("mm %p addr %lx ptep %p",
+		      __entry->mm, __entry->addr, __entry->ptep)
+	);
+
 TRACE_EVENT(xen_mmu_pmd_clear,
 	    TP_PROTO(pmd_t *pmdp),
 	    TP_ARGS(pmdp),
@@ -211,6 +213,7 @@ TRACE_EVENT(xen_mmu_pmd_clear,
 	    TP_fast_assign(__entry->pmdp = pmdp),
 	    TP_printk("pmdp %p", __entry->pmdp)
 	);
+#endif
 
 #if CONFIG_PGTABLE_LEVELS >= 4