Merge tag 'trace-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - Rework of the kprobe/uprobe and synthetic events to consolidate all
   the dynamic event code. This will make changes in the future easier.

 - Partial rewrite of the function graph tracing infrastructure. This
   will allow for multiple users of hooking onto functions to get the
   callback (return) of the function. This is the ground work for having
   kprobes and function graph tracer using one code base.

 - Clean up of the histogram code that will facilitate adding more
   features to the histograms in the future.

 - Addition of str_has_prefix() and a few use cases. There currently is
   a similar function strstart() that is used in a few places, but only
   returns a bool and not a length. These instances will be removed in
   the future to use str_has_prefix() instead.

 - A few other various clean ups as well.

* tag 'trace-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (57 commits)
  tracing: Use the return of str_has_prefix() to remove open coded numbers
  tracing: Have the historgram use the result of str_has_prefix() for len of prefix
  tracing: Use str_has_prefix() instead of using fixed sizes
  tracing: Use str_has_prefix() helper for histogram code
  string.h: Add str_has_prefix() helper function
  tracing: Make function ‘ftrace_exports’ static
  tracing: Simplify printf'ing in seq_print_sym
  tracing: Avoid -Wformat-nonliteral warning
  tracing: Merge seq_print_sym_short() and seq_print_sym_offset()
  tracing: Add hist trigger comments for variable-related fields
  tracing: Remove hist trigger synth_var_refs
  tracing: Use hist trigger's var_ref array to destroy var_refs
  tracing: Remove open-coding of hist trigger var_ref management
  tracing: Use var_refs[] for hist trigger reference checking
  tracing: Change strlen to sizeof for hist trigger static strings
  tracing: Remove unnecessary hist trigger struct field
  tracing: Fix ftrace_graph_get_ret_stack() to use task and not current
  seq_buf: Use size_t for len in seq_buf_puts()
  seq_buf: Make seq_buf_puts() null-terminate the buffer
  arm64: Use ftrace_graph_get_ret_stack() instead of curr_ret_stack
  ...

Documentation/trace/kprobetrace.rst

@@ -20,6 +20,9 @@ current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/kprobe_events, and enable it via
 /sys/kernel/debug/tracing/events/kprobes/<EVENT>/enable.
 
+You can also use /sys/kernel/debug/tracing/dynamic_events instead of
+kprobe_events. That interface will provide unified access to other
+dynamic events too.
 
 Synopsis of kprobe_events
 -------------------------

Documentation/trace/uprobetracer.rst

@@ -18,6 +18,10 @@ current_tracer. Instead of that, add probe points via
 However unlike kprobe-event tracer, the uprobe event interface expects the
 user to calculate the offset of the probepoint in the object.
 
+You can also use /sys/kernel/debug/tracing/dynamic_events instead of
+uprobe_events. That interface will provide unified access to other
+dynamic events too.
+
 Synopsis of uprobe_tracer
 -------------------------
 ::

arch/arm64/kernel/ftrace.c

@@ -193,6 +193,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 
 void arch_ftrace_update_code(int command)
 {
+	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
 }
 

arch/arm64/kernel/perf_callchain.c

@@ -168,7 +168,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 	frame.fp = regs->regs[29];
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
+	frame.graph = 0;
 #endif
 
 	walk_stackframe(current, &frame, callchain_trace, entry);

arch/arm64/kernel/process.c

@@ -461,7 +461,7 @@ unsigned long get_wchan(struct task_struct *p)
 	frame.fp = thread_saved_fp(p);
 	frame.pc = thread_saved_pc(p);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = p->curr_ret_stack;
+	frame.graph = 0;
 #endif
 	do {
 		if (unwind_frame(p, &frame))

arch/arm64/kernel/return_address.c

@@ -44,7 +44,7 @@ void *return_address(unsigned int level)
 	frame.fp = (unsigned long)__builtin_frame_address(0);
 	frame.pc = (unsigned long)return_address; /* dummy */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
+	frame.graph = 0;
 #endif
 
 	walk_stackframe(current, &frame, save_return_addr, &data);

arch/arm64/kernel/stacktrace.c

@@ -59,18 +59,17 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
-		if (WARN_ON_ONCE(frame->graph == -1))
-			return -EINVAL;
-		if (frame->graph < -1)
-			frame->graph += FTRACE_NOTRACE_DEPTH;
-
+		struct ftrace_ret_stack *ret_stack;
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
 		 * to hook a function return.
 		 * So replace it to an original value.
 		 */
-		frame->pc = tsk->ret_stack[frame->graph--].ret;
+		ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++);
+		if (WARN_ON_ONCE(!ret_stack))
+			return -EINVAL;
+		frame->pc = ret_stack->ret;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -137,7 +136,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	frame.fp = regs->regs[29];
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
+	frame.graph = 0;
 #endif
 
 	walk_stackframe(current, &frame, save_trace, &data);
@@ -168,7 +167,7 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 		frame.pc = (unsigned long)__save_stack_trace;
 	}
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = tsk->curr_ret_stack;
+	frame.graph = 0;
 #endif
 
 	walk_stackframe(tsk, &frame, save_trace, &data);

arch/arm64/kernel/time.c

@@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 	frame.fp = regs->regs[29];
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = current->curr_ret_stack;
+	frame.graph = 0;
 #endif
 	do {
 		int ret = unwind_frame(NULL, &frame);

arch/arm64/kernel/traps.c

@@ -123,7 +123,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		frame.pc = thread_saved_pc(tsk);
 	}
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = tsk->curr_ret_stack;
+	frame.graph = 0;
 #endif
 
 	skip = !!regs;

arch/powerpc/kernel/process.c

@@ -2061,9 +2061,10 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 	int count = 0;
 	int firstframe = 1;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	int curr_frame = current->curr_ret_stack;
+	struct ftrace_ret_stack *ret_stack;
 	extern void return_to_handler(void);
 	unsigned long rth = (unsigned long)return_to_handler;
+	int curr_frame = 0;
 #endif
 
 	sp = (unsigned long) stack;
@@ -2089,9 +2090,13 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 			if ((ip == rth) && curr_frame >= 0) {
-				pr_cont(" (%pS)",
-				       (void *)current->ret_stack[curr_frame].ret);
-				curr_frame--;
+				ret_stack = ftrace_graph_get_ret_stack(current,
+								  curr_frame++);
+				if (ret_stack)
+					pr_cont(" (%pS)",
+						(void *)ret_stack->ret);
+				else
+					curr_frame = -1;
 			}
 #endif
 			if (firstframe)

arch/sh/kernel/dumpstack.c

@@ -56,17 +56,20 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
 			struct thread_info *tinfo, int *graph)
 {
 	struct task_struct *task = tinfo->task;
+	struct ftrace_ret_stack *ret_stack;
 	unsigned long ret_addr;
-	int index = task->curr_ret_stack;
 
 	if (addr != (unsigned long)return_to_handler)
 		return;
 
-	if (!task->ret_stack || index < *graph)
+	if (!task->ret_stack)
 		return;
 
-	index -= *graph;
-	ret_addr = task->ret_stack[index].ret;
+	ret_stack = ftrace_graph_get_ret_stack(task, *graph);
+	if (!ret_stack)
+		return;
+
+	ret_addr = ret_stack->ret;
 
 	ops->address(data, ret_addr, 1);
 

arch/sh/kernel/dwarf.c

@@ -605,17 +605,18 @@ struct dwarf_frame *dwarf_unwind_stack(unsigned long pc,
 	 * expected to find the real return address.
 	 */
 	if (pc == (unsigned long)&return_to_handler) {
-		int index = current->curr_ret_stack;
+		struct ftrace_ret_stack *ret_stack;
 
+		ret_stack = ftrace_graph_get_ret_stack(current, 0);
+		if (ret_stack)
+			pc = ret_stack->ret;
 		/*
 		 * We currently have no way of tracking how many
 		 * return_to_handler()'s we've seen. If there is more
 		 * than one patched return address on our stack,
 		 * complain loudly.
 		 */
-		WARN_ON(index > 0);
-
-		pc = current->ret_stack[index].ret;
+		WARN_ON(ftrace_graph_get_ret_stack(current, 1);
 	}
 #endif
 

arch/sparc/kernel/perf_event.c

@@ -1767,9 +1767,11 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 		perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
-			int index = current->curr_ret_stack;
-			if (current->ret_stack && index >= graph) {
-				pc = current->ret_stack[index - graph].ret;
+			struct ftrace_ret_stack *ret_stack;
+			ret_stack = ftrace_graph_get_ret_stack(current,
+							       graph);
+			if (ret_stack) {
+				pc = ret_stack->ret;
 				perf_callchain_store(entry, pc);
 				graph++;
 			}

arch/sparc/kernel/stacktrace.c

@@ -57,9 +57,11 @@ static void __save_stack_trace(struct thread_info *tp,
 			trace->entries[trace->nr_entries++] = pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 			if ((pc + 8UL) == (unsigned long) &return_to_handler) {
-				int index = t->curr_ret_stack;
-				if (t->ret_stack && index >= graph) {
-					pc = t->ret_stack[index - graph].ret;
+				struct ftrace_ret_stack *ret_stack;
+				ret_stack = ftrace_graph_get_ret_stack(t,
+								       graph);
+				if (ret_stack) {
+					pc = ret_stack->ret;
 					if (trace->nr_entries <
 					    trace->max_entries)
 						trace->entries[trace->nr_entries++] = pc;

arch/sparc/kernel/traps_64.c

@@ -2502,9 +2502,10 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp)
 		printk(" [%016lx] %pS\n", pc, (void *) pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
-			int index = tsk->curr_ret_stack;
-			if (tsk->ret_stack && index >= graph) {
-				pc = tsk->ret_stack[index - graph].ret;
+			struct ftrace_ret_stack *ret_stack;
+			ret_stack = ftrace_graph_get_ret_stack(tsk, graph);
+			if (ret_stack) {
+				pc = ret_stack->ret;
 				printk(" [%016lx] %pS\n", pc, (void *) pc);
 				graph++;
 			}

arch/x86/kernel/ftrace.c

@@ -733,18 +733,20 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
+#define RET_SIZE		1
+
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 {
-	unsigned const char *jmp;
 	unsigned long start_offset;
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
 	unsigned long size;
-	unsigned long ip;
+	unsigned long retq;
 	unsigned long *ptr;
 	void *trampoline;
+	void *ip;
 	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	union ftrace_op_code_union op_ptr;
@@ -764,27 +766,27 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/*
 	 * Allocate enough size to store the ftrace_caller code,
-	 * the jmp to ftrace_epilogue, as well as the address of
-	 * the ftrace_ops this trampoline is used for.
+	 * the iret , as well as the address of the ftrace_ops this
+	 * trampoline is used for.
 	 */
-	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
+	trampoline = alloc_tramp(size + RET_SIZE + sizeof(void *));
 	if (!trampoline)
 		return 0;
 
-	*tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *);
+	*tramp_size = size + RET_SIZE + sizeof(void *);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
-	if (WARN_ON(ret < 0)) {
-		tramp_free(trampoline, *tramp_size);
-		return 0;
-	}
+	if (WARN_ON(ret < 0))
+		goto fail;
 
-	ip = (unsigned long)trampoline + size;
+	ip = trampoline + size;
 
-	/* The trampoline ends with a jmp to ftrace_epilogue */
-	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_epilogue);
-	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
+	/* The trampoline ends with ret(q) */
+	retq = (unsigned long)ftrace_stub;
+	ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+	if (WARN_ON(ret < 0))
+		goto fail;
 
 	/*
 	 * The address of the ftrace_ops that is used for this trampoline
@@ -794,17 +796,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the global function_trace_op variable.
 	 */
 
-	ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE);
+	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
 	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
 
 	/* Are we pointing to the reference? */
-	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
-		tramp_free(trampoline, *tramp_size);
-		return 0;
-	}
+	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0))
+		goto fail;
 
 	/* Load the contents of ptr into the callback parameter */
 	offset = (unsigned long)ptr;
@@ -819,6 +819,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
 	return (unsigned long)trampoline;
+fail:
+	tramp_free(trampoline, *tramp_size);
+	return 0;
 }
 
 static unsigned long calc_trampoline_call_offset(bool save_regs)

arch/x86/kernel/ftrace_64.S

@@ -171,9 +171,6 @@ GLOBAL(ftrace_call)
 	restore_mcount_regs
 
 	/*
-	 * The copied trampoline must call ftrace_epilogue as it
-	 * still may need to call the function graph tracer.
-	 *
 	 * The code up to this label is copied into trampolines so
 	 * think twice before adding any new code or changing the
 	 * layout here.
@@ -185,7 +182,10 @@ GLOBAL(ftrace_graph_call)
 	jmp ftrace_stub
 #endif
 
-/* This is weak to keep gas from relaxing the jumps */
+/*
+ * This is weak to keep gas from relaxing the jumps.
+ * It is also used to copy the retq for trampolines.
+ */
 WEAK(ftrace_stub)
 	retq
 ENDPROC(ftrace_caller)

include/linux/ftrace.h

@@ -389,6 +389,7 @@ enum {
 	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
 	FTRACE_START_FUNC_RET		= (1 << 3),
 	FTRACE_STOP_FUNC_RET		= (1 << 4),
+	FTRACE_MAY_SLEEP		= (1 << 5),
 };
 
 /*
@@ -752,6 +753,11 @@ typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
+struct fgraph_ops {
+	trace_func_graph_ent_t		entryfunc;
+	trace_func_graph_ret_t		retfunc;
+};
+
 /*
  * Stack of return addresses for functions
  * of a thread.
@@ -783,6 +789,9 @@ extern int
 function_graph_enter(unsigned long ret, unsigned long func,
 		     unsigned long frame_pointer, unsigned long *retp);
 
+struct ftrace_ret_stack *
+ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
+
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
 
@@ -793,11 +802,11 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
  */
 #define __notrace_funcgraph		notrace
 
-#define FTRACE_NOTRACE_DEPTH 65536
 #define FTRACE_RETFUNC_DEPTH 50
 #define FTRACE_RETSTACK_ALLOC_SIZE 32
-extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
-				trace_func_graph_ent_t entryfunc);
+
+extern int register_ftrace_graph(struct fgraph_ops *ops);
+extern void unregister_ftrace_graph(struct fgraph_ops *ops);
 
 extern bool ftrace_graph_is_dead(void);
 extern void ftrace_graph_stop(void);
@@ -806,17 +815,10 @@ extern void ftrace_graph_stop(void);
 extern trace_func_graph_ret_t ftrace_graph_return;
 extern trace_func_graph_ent_t ftrace_graph_entry;
 
-extern void unregister_ftrace_graph(void);
-
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
 extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
-static inline int task_curr_ret_stack(struct task_struct *t)
-{
-	return t->curr_ret_stack;
-}
-
 static inline void pause_graph_tracing(void)
 {
 	atomic_inc(&current->tracing_graph_pause);
@@ -834,17 +836,9 @@ static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
 static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
 
-static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
-			  trace_func_graph_ent_t entryfunc)
-{
-	return -1;
-}
-static inline void unregister_ftrace_graph(void) { }
-
-static inline int task_curr_ret_stack(struct task_struct *tsk)
-{
-	return -1;
-}
+/* Define as macros as fgraph_ops may not be defined */
+#define register_ftrace_graph(ops) ({ -1; })
+#define unregister_ftrace_graph(ops) do { } while (0)
 
 static inline unsigned long
 ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret,

include/linux/ring_buffer.h

@@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full);
 __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
 
@@ -189,6 +189,8 @@ bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer);
 
 size_t ring_buffer_page_len(void *page);
 
+size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu);
+size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu);
 
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu);
 void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data);

include/linux/string.h

@@ -456,4 +456,24 @@ static inline void memcpy_and_pad(void *dest, size_t dest_len,
 		memcpy(dest, src, dest_len);
 }
 
+/**
+ * str_has_prefix - Test if a string has a given prefix
+ * @str: The string to test
+ * @prefix: The string to see if @str starts with
+ *
+ * A common way to test a prefix of a string is to do:
+ *  strncmp(str, prefix, sizeof(prefix) - 1)
+ *
+ * But this can lead to bugs due to typos, or if prefix is a pointer
+ * and not a constant. Instead use str_has_prefix().
+ *
+ * Returns: 0 if @str does not start with @prefix
+         strlen(@prefix) if @str does start with @prefix
+ */
+static __always_inline size_t str_has_prefix(const char *str, const char *prefix)
+{
+	size_t len = strlen(prefix);
+	return strncmp(str, prefix, len) == 0 ? len : 0;
+}
+
 #endif /* _LINUX_STRING_H_ */

kernel/trace/Kconfig

@@ -461,6 +461,7 @@ config KPROBE_EVENTS
 	bool "Enable kprobes-based dynamic events"
 	select TRACING
 	select PROBE_EVENTS
+	select DYNAMIC_EVENTS
 	default y
 	help
 	  This allows the user to add tracing events (similar to tracepoints)
@@ -500,6 +501,7 @@ config UPROBE_EVENTS
 	depends on PERF_EVENTS
 	select UPROBES
 	select PROBE_EVENTS
+	select DYNAMIC_EVENTS
 	select TRACING
 	default y
 	help
@@ -518,6 +520,9 @@ config BPF_EVENTS
 	help
 	  This allows the user to attach BPF programs to kprobe events.
 
+config DYNAMIC_EVENTS
+	def_bool n
+
 config PROBE_EVENTS
 	def_bool n
 
@@ -630,6 +635,7 @@ config HIST_TRIGGERS
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select TRACING_MAP
 	select TRACING
+	select DYNAMIC_EVENTS
 	default n
 	help
 	  Hist triggers allow one or more arbitrary trace event fields

kernel/trace/Makefile

@@ -57,6 +57,7 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += fgraph.o
 ifeq ($(CONFIG_BLOCK),y)
 obj-$(CONFIG_EVENT_TRACING) += blktrace.o
 endif
@@ -78,6 +79,7 @@ endif
 ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
+obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 

kernel/trace/ftrace_internal.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H
+#define  _LINUX_KERNEL_FTRACE_INTERNAL_H
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+/*
+ * Traverse the ftrace_global_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw_notrace() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism.  The rcu_dereference_raw_notrace() calls are needed to handle
+ * concurrent insertions into the ftrace_global_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
+#define do_for_each_ftrace_op(op, list)			\
+	op = rcu_dereference_raw_notrace(list);			\
+	do
+
+/*
+ * Optimized for just a single item in the list (as that is the normal case).
+ */
+#define while_for_each_ftrace_op(op)				\
+	while (likely(op = rcu_dereference_raw_notrace((op)->next)) &&	\
+	       unlikely((op) != &ftrace_list_end))
+
+extern struct ftrace_ops __rcu *ftrace_ops_list;
+extern struct ftrace_ops ftrace_list_end;
+extern struct mutex ftrace_lock;
+extern struct ftrace_ops global_ops;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+int ftrace_startup(struct ftrace_ops *ops, int command);
+int ftrace_shutdown(struct ftrace_ops *ops, int command);
+int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs);
+
+#else /* !CONFIG_DYNAMIC_FTRACE */
+
+int __register_ftrace_function(struct ftrace_ops *ops);
+int __unregister_ftrace_function(struct ftrace_ops *ops);
+/* Keep as macros so we do not need to define the commands */
+# define ftrace_startup(ops, command)					\
+	({								\
+		int ___ret = __register_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags |= FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
+	})
+# define ftrace_shutdown(ops, command)					\
+	({								\
+		int ___ret = __unregister_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags &= ~FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
+	})
+static inline int
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
+{
+	return 1;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern int ftrace_graph_active;
+void update_function_graph_func(void);
+#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
+# define ftrace_graph_active 0
+static inline void update_function_graph_func(void) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#else /* !CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#endif

kernel/trace/ring_buffer.c

@@ -487,6 +487,10 @@ struct ring_buffer_per_cpu {
 	local_t				dropped_events;
 	local_t				committing;
 	local_t				commits;
+	local_t				pages_touched;
+	local_t				pages_read;
+	long				last_pages_touch;
+	size_t				shortest_full;
 	unsigned long			read;
 	unsigned long			read_bytes;
 	u64				write_stamp;
@@ -529,6 +533,41 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 };
 
+/**
+ * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer
+ * @buffer: The ring_buffer to get the number of pages from
+ * @cpu: The cpu of the ring_buffer to get the number of pages from
+ *
+ * Returns the number of pages used by a per_cpu buffer of the ring buffer.
+ */
+size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu)
+{
+	return buffer->buffers[cpu]->nr_pages;
+}
+
+/**
+ * ring_buffer_nr_pages_dirty - get the number of used pages in the ring buffer
+ * @buffer: The ring_buffer to get the number of pages from
+ * @cpu: The cpu of the ring_buffer to get the number of pages from
+ *
+ * Returns the number of pages that have content in the ring buffer.
+ */
+size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu)
+{
+	size_t read;
+	size_t cnt;
+
+	read = local_read(&buffer->buffers[cpu]->pages_read);
+	cnt = local_read(&buffer->buffers[cpu]->pages_touched);
+	/* The reader can read an empty page, but not more than that */
+	if (cnt < read) {
+		WARN_ON_ONCE(read > cnt + 1);
+		return 0;
+	}
+
+	return cnt - read;
+}
+
 /*
  * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
  *
@@ -556,7 +595,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
 	DEFINE_WAIT(wait);
@@ -571,7 +610,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 	if (cpu == RING_BUFFER_ALL_CPUS) {
 		work = &buffer->irq_work;
 		/* Full only makes sense on per cpu reads */
-		full = false;
+		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -ENODEV;
@@ -623,15 +662,22 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 		    !ring_buffer_empty_cpu(buffer, cpu)) {
 			unsigned long flags;
 			bool pagebusy;
+			size_t nr_pages;
+			size_t dirty;
 
 			if (!full)
 				break;
 
 			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+			nr_pages = cpu_buffer->nr_pages;
+			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+			if (!cpu_buffer->shortest_full ||
+			    cpu_buffer->shortest_full < full)
+				cpu_buffer->shortest_full = full;
 			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
-			if (!pagebusy)
+			if (!pagebusy &&
+			    (!nr_pages || (dirty * 100) > full * nr_pages))
 				break;
 		}
 
@@ -1054,6 +1100,7 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
 	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
 
+	local_inc(&cpu_buffer->pages_touched);
 	/*
 	 * Just make sure we have seen our old_write and synchronize
 	 * with any interrupts that come in.
@@ -2586,7 +2633,9 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static __always_inline void
 rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 {
-	bool pagebusy;
+	size_t nr_pages;
+	size_t dirty;
+	size_t full;
 
 	if (buffer->irq_work.waiters_pending) {
 		buffer->irq_work.waiters_pending = false;
@@ -2600,14 +2649,27 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 		irq_work_queue(&cpu_buffer->irq_work.work);
 	}
 
-	pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+	if (cpu_buffer->last_pages_touch == local_read(&cpu_buffer->pages_touched))
+		return;
 
-	if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) {
-		cpu_buffer->irq_work.wakeup_full = true;
-		cpu_buffer->irq_work.full_waiters_pending = false;
-		/* irq_work_queue() supplies it's own memory barriers */
-		irq_work_queue(&cpu_buffer->irq_work.work);
-	}
+	if (cpu_buffer->reader_page == cpu_buffer->commit_page)
+		return;
+
+	if (!cpu_buffer->irq_work.full_waiters_pending)
+		return;
+
+	cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched);
+
+	full = cpu_buffer->shortest_full;
+	nr_pages = cpu_buffer->nr_pages;
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu);
+	if (full && nr_pages && (dirty * 100) <= full * nr_pages)
+		return;
+
+	cpu_buffer->irq_work.wakeup_full = true;
+	cpu_buffer->irq_work.full_waiters_pending = false;
+	/* irq_work_queue() supplies it's own memory barriers */
+	irq_work_queue(&cpu_buffer->irq_work.work);
 }
 
 /*
@@ -3732,13 +3794,15 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto spin;
 
 	/*
-	 * Yeah! We succeeded in replacing the page.
+	 * Yay! We succeeded in replacing the page.
 	 *
 	 * Now make the new head point back to the reader page.
 	 */
 	rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
 	rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
+	local_inc(&cpu_buffer->pages_read);
+
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
 	cpu_buffer->reader_page->read = 0;
@@ -4334,6 +4398,10 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->entries, 0);
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
+	local_set(&cpu_buffer->pages_touched, 0);
+	local_set(&cpu_buffer->pages_read, 0);
+	cpu_buffer->last_pages_touch = 0;
+	cpu_buffer->shortest_full = 0;
 	cpu_buffer->read = 0;
 	cpu_buffer->read_bytes = 0;
 

kernel/trace/trace.c

@@ -1431,7 +1431,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static int wait_on_pipe(struct trace_iterator *iter, bool full)
+static int wait_on_pipe(struct trace_iterator *iter, int full)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
@@ -2452,7 +2452,7 @@ static inline void ftrace_exports_disable(void)
 	static_branch_disable(&ftrace_exports_enabled);
 }
 
-void ftrace_exports(struct ring_buffer_event *event)
+static void ftrace_exports(struct ring_buffer_event *event)
 {
 	struct trace_export *export;
 
@@ -4408,13 +4408,15 @@ static int trace_set_options(struct trace_array *tr, char *option)
 	int neg = 0;
 	int ret;
 	size_t orig_len = strlen(option);
+	int len;
 
 	cmp = strstrip(option);
 
-	if (strncmp(cmp, "no", 2) == 0) {
+	len = str_has_prefix(cmp, "no");
+	if (len)
 		neg = 1;
-		cmp += 2;
-	}
+
+	cmp += len;
 
 	mutex_lock(&trace_types_lock);
 
@@ -4604,6 +4606,10 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
+#ifdef CONFIG_DYNAMIC_EVENTS
+	"  dynamic_events\t\t- Add/remove/show the generic dynamic events\n"
+	"\t\t\t  Write into this file to define/undefine new trace events.\n"
+#endif
 #ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
@@ -4616,6 +4622,9 @@ static const char readme_msg[] =
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           r[maxactive][:[<group>/]<event>] <place> [<args>]\n"
+#ifdef CONFIG_HIST_TRIGGERS
+	"\t           s:[synthetic/]<event> <field> [<field>]\n"
+#endif
 	"\t           -:[<group>/]<event>\n"
 #ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
@@ -4634,6 +4643,11 @@ static const char readme_msg[] =
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>,\n"
 	"\t           <type>\\[<array-size>\\]\n"
+#ifdef CONFIG_HIST_TRIGGERS
+	"\t    field: <stype> <name>;\n"
+	"\t    stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n"
+	"\t           [unsigned] char/int/long\n"
+#endif
 #endif
 	"  events/\t\t- Directory containing all trace event subsystems:\n"
 	"      enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
@@ -5693,7 +5707,7 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		ret = wait_on_pipe(iter, false);
+		ret = wait_on_pipe(iter, 0);
 
 		mutex_lock(&iter->mutex);
 
@@ -6751,7 +6765,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 			if ((filp->f_flags & O_NONBLOCK))
 				return -EAGAIN;
 
-			ret = wait_on_pipe(iter, false);
+			ret = wait_on_pipe(iter, 0);
 			if (ret)
 				return ret;
 
@@ -6948,7 +6962,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
 			goto out;
 
-		ret = wait_on_pipe(iter, true);
+		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
@@ -7662,6 +7676,53 @@ static const struct file_operations rb_simple_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t
+buffer_percent_read(struct file *filp, char __user *ubuf,
+		    size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = tr->buffer_percent;
+	r = sprintf(buf, "%d\n", r);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_percent_write(struct file *filp, const char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val > 100)
+		return -EINVAL;
+
+	if (!val)
+		val = 1;
+
+	tr->buffer_percent = val;
+
+	(*ppos)++;
+
+	return cnt;
+}
+
+static const struct file_operations buffer_percent_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= buffer_percent_read,
+	.write		= buffer_percent_write,
+	.release	= tracing_release_generic_tr,
+	.llseek		= default_llseek,
+};
+
 struct dentry *trace_instance_dir;
 
 static void
@@ -7970,6 +8031,11 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("timestamp_mode", 0444, d_tracer, tr,
 			  &trace_time_stamp_mode_fops);
 
+	tr->buffer_percent = 50;
+
+	trace_create_file("buffer_percent", 0444, d_tracer,
+			tr, &buffer_percent_fops);
+
 	create_trace_options_dir(tr);
 
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)

kernel/trace/trace.h

@@ -247,6 +247,7 @@ struct trace_array {
 	int			clock_id;
 	int			nr_topts;
 	bool			clear_trace;
+	int			buffer_percent;
 	struct tracer		*current_trace;
 	unsigned int		trace_flags;
 	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
@@ -534,6 +535,13 @@ enum {
 
 	TRACE_GRAPH_DEPTH_START_BIT,
 	TRACE_GRAPH_DEPTH_END_BIT,
+
+	/*
+	 * To implement set_graph_notrace, if this bit is set, we ignore
+	 * function graph tracing of called functions, until the return
+	 * function is called to clear it.
+	 */
+	TRACE_GRAPH_NOTRACE_BIT,
 };
 
 #define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -855,7 +863,12 @@ static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
 #define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
 
 extern void ftrace_graph_sleep_time_control(bool enable);
+
+#ifdef CONFIG_FUNCTION_PROFILER
 extern void ftrace_graph_graph_time_control(bool enable);
+#else
+static inline void ftrace_graph_graph_time_control(bool enable) { }
+#endif
 
 extern enum print_line_t
 print_graph_function_flags(struct trace_iterator *iter, u32 flags);

kernel/trace/trace_dynevent.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generic dynamic event control interface
+ *
+ * Copyright (C) 2018 Masami Hiramatsu <mhiramat@kernel.org>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/tracefs.h>
+
+#include "trace.h"
+#include "trace_dynevent.h"
+
+static DEFINE_MUTEX(dyn_event_ops_mutex);
+static LIST_HEAD(dyn_event_ops_list);
+
+int dyn_event_register(struct dyn_event_operations *ops)
+{
+	if (!ops || !ops->create || !ops->show || !ops->is_busy ||
+	    !ops->free || !ops->match)
+		return -EINVAL;
+
+	INIT_LIST_HEAD(&ops->list);
+	mutex_lock(&dyn_event_ops_mutex);
+	list_add_tail(&ops->list, &dyn_event_ops_list);
+	mutex_unlock(&dyn_event_ops_mutex);
+	return 0;
+}
+
+int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
+{
+	struct dyn_event *pos, *n;
+	char *system = NULL, *event, *p;
+	int ret = -ENOENT;
+
+	if (argv[0][0] == '-') {
+		if (argv[0][1] != ':')
+			return -EINVAL;
+		event = &argv[0][2];
+	} else {
+		event = strchr(argv[0], ':');
+		if (!event)
+			return -EINVAL;
+		event++;
+	}
+
+	p = strchr(event, '/');
+	if (p) {
+		system = event;
+		event = p + 1;
+		*p = '\0';
+	}
+	if (event[0] == '\0')
+		return -EINVAL;
+
+	mutex_lock(&event_mutex);
+	for_each_dyn_event_safe(pos, n) {
+		if (type && type != pos->ops)
+			continue;
+		if (pos->ops->match(system, event, pos)) {
+			ret = pos->ops->free(pos);
+			break;
+		}
+	}
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int create_dyn_event(int argc, char **argv)
+{
+	struct dyn_event_operations *ops;
+	int ret;
+
+	if (argv[0][0] == '-' || argv[0][0] == '!')
+		return dyn_event_release(argc, argv, NULL);
+
+	mutex_lock(&dyn_event_ops_mutex);
+	list_for_each_entry(ops, &dyn_event_ops_list, list) {
+		ret = ops->create(argc, (const char **)argv);
+		if (!ret || ret != -ECANCELED)
+			break;
+	}
+	mutex_unlock(&dyn_event_ops_mutex);
+	if (ret == -ECANCELED)
+		ret = -EINVAL;
+
+	return ret;
+}
+
+/* Protected by event_mutex */
+LIST_HEAD(dyn_event_list);
+
+void *dyn_event_seq_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&event_mutex);
+	return seq_list_start(&dyn_event_list, *pos);
+}
+
+void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &dyn_event_list, pos);
+}
+
+void dyn_event_seq_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&event_mutex);
+}
+
+static int dyn_event_seq_show(struct seq_file *m, void *v)
+{
+	struct dyn_event *ev = v;
+
+	if (ev && ev->ops)
+		return ev->ops->show(m, ev);
+
+	return 0;
+}
+
+static const struct seq_operations dyn_event_seq_op = {
+	.start	= dyn_event_seq_start,
+	.next	= dyn_event_seq_next,
+	.stop	= dyn_event_seq_stop,
+	.show	= dyn_event_seq_show
+};
+
+/*
+ * dyn_events_release_all - Release all specific events
+ * @type:	the dyn_event_operations * which filters releasing events
+ *
+ * This releases all events which ->ops matches @type. If @type is NULL,
+ * all events are released.
+ * Return -EBUSY if any of them are in use, and return other errors when
+ * it failed to free the given event. Except for -EBUSY, event releasing
+ * process will be aborted at that point and there may be some other
+ * releasable events on the list.
+ */
+int dyn_events_release_all(struct dyn_event_operations *type)
+{
+	struct dyn_event *ev, *tmp;
+	int ret = 0;
+
+	mutex_lock(&event_mutex);
+	for_each_dyn_event(ev) {
+		if (type && ev->ops != type)
+			continue;
+		if (ev->ops->is_busy(ev)) {
+			ret = -EBUSY;
+			goto out;
+		}
+	}
+	for_each_dyn_event_safe(ev, tmp) {
+		if (type && ev->ops != type)
+			continue;
+		ret = ev->ops->free(ev);
+		if (ret)
+			break;
+	}
+out:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int dyn_event_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = dyn_events_release_all(NULL);
+		if (ret < 0)
+			return ret;
+	}
+
+	return seq_open(file, &dyn_event_seq_op);
+}
+
+static ssize_t dyn_event_write(struct file *file, const char __user *buffer,
+				size_t count, loff_t *ppos)
+{
+	return trace_parse_run_command(file, buffer, count, ppos,
+				       create_dyn_event);
+}
+
+static const struct file_operations dynamic_events_ops = {
+	.owner          = THIS_MODULE,
+	.open           = dyn_event_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+	.write		= dyn_event_write,
+};
+
+/* Make a tracefs interface for controlling dynamic events */
+static __init int init_dynamic_event(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer))
+		return 0;
+
+	entry = tracefs_create_file("dynamic_events", 0644, d_tracer,
+				    NULL, &dynamic_events_ops);
+
+	/* Event list interface */
+	if (!entry)
+		pr_warn("Could not create tracefs 'dynamic_events' entry\n");
+
+	return 0;
+}
+fs_initcall(init_dynamic_event);

kernel/trace/trace_dynevent.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common header file for generic dynamic events.
+ */
+
+#ifndef _TRACE_DYNEVENT_H
+#define _TRACE_DYNEVENT_H
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+
+#include "trace.h"
+
+struct dyn_event;
+
+/**
+ * struct dyn_event_operations - Methods for each type of dynamic events
+ *
+ * These methods must be set for each type, since there is no default method.
+ * Before using this for dyn_event_init(), it must be registered by
+ * dyn_event_register().
+ *
+ * @create: Parse and create event method. This is invoked when user passes
+ *  a event definition to dynamic_events interface. This must not destruct
+ *  the arguments and return -ECANCELED if given arguments doesn't match its
+ *  command prefix.
+ * @show: Showing method. This is invoked when user reads the event definitions
+ *  via dynamic_events interface.
+ * @is_busy: Check whether given event is busy so that it can not be deleted.
+ *  Return true if it is busy, otherwides false.
+ * @free: Delete the given event. Return 0 if success, otherwides error.
+ * @match: Check whether given event and system name match this event.
+ *  Return true if it matches, otherwides false.
+ *
+ * Except for @create, these methods are called under holding event_mutex.
+ */
+struct dyn_event_operations {
+	struct list_head	list;
+	int (*create)(int argc, const char *argv[]);
+	int (*show)(struct seq_file *m, struct dyn_event *ev);
+	bool (*is_busy)(struct dyn_event *ev);
+	int (*free)(struct dyn_event *ev);
+	bool (*match)(const char *system, const char *event,
+			struct dyn_event *ev);
+};
+
+/* Register new dyn_event type -- must be called at first */
+int dyn_event_register(struct dyn_event_operations *ops);
+
+/**
+ * struct dyn_event - Dynamic event list header
+ *
+ * The dyn_event structure encapsulates a list and a pointer to the operators
+ * for making a global list of dynamic events.
+ * User must includes this in each event structure, so that those events can
+ * be added/removed via dynamic_events interface.
+ */
+struct dyn_event {
+	struct list_head		list;
+	struct dyn_event_operations	*ops;
+};
+
+extern struct list_head dyn_event_list;
+
+static inline
+int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops)
+{
+	if (!ev || !ops)
+		return -EINVAL;
+
+	INIT_LIST_HEAD(&ev->list);
+	ev->ops = ops;
+	return 0;
+}
+
+static inline int dyn_event_add(struct dyn_event *ev)
+{
+	lockdep_assert_held(&event_mutex);
+
+	if (!ev || !ev->ops)
+		return -EINVAL;
+
+	list_add_tail(&ev->list, &dyn_event_list);
+	return 0;
+}
+
+static inline void dyn_event_remove(struct dyn_event *ev)
+{
+	lockdep_assert_held(&event_mutex);
+	list_del_init(&ev->list);
+}
+
+void *dyn_event_seq_start(struct seq_file *m, loff_t *pos);
+void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos);
+void dyn_event_seq_stop(struct seq_file *m, void *v);
+int dyn_events_release_all(struct dyn_event_operations *type);
+int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type);
+
+/*
+ * for_each_dyn_event	-	iterate over the dyn_event list
+ * @pos:	the struct dyn_event * to use as a loop cursor
+ *
+ * This is just a basement of for_each macro. Wrap this for
+ * each actual event structure with ops filtering.
+ */
+#define for_each_dyn_event(pos)	\
+	list_for_each_entry(pos, &dyn_event_list, list)
+
+/*
+ * for_each_dyn_event	-	iterate over the dyn_event list safely
+ * @pos:	the struct dyn_event * to use as a loop cursor
+ * @n:		the struct dyn_event * to use as temporary storage
+ */
+#define for_each_dyn_event_safe(pos, n)	\
+	list_for_each_entry_safe(pos, n, &dyn_event_list, list)
+
+#endif

kernel/trace/trace_events.c

@@ -1251,7 +1251,7 @@ static int f_show(struct seq_file *m, void *v)
 	 */
 	array_descriptor = strchr(field->type, '[');
 
-	if (!strncmp(field->type, "__data_loc", 10))
+	if (str_has_prefix(field->type, "__data_loc"))
 		array_descriptor = NULL;
 
 	if (!array_descriptor)
@@ -2309,7 +2309,8 @@ static void __add_event_to_tracers(struct trace_event_call *call);
 int trace_add_event_call(struct trace_event_call *call)
 {
 	int ret;
-	mutex_lock(&event_mutex);
+	lockdep_assert_held(&event_mutex);
+
 	mutex_lock(&trace_types_lock);
 
 	ret = __register_event(call, NULL);
@@ -2317,7 +2318,6 @@ int trace_add_event_call(struct trace_event_call *call)
 		__add_event_to_tracers(call);
 
 	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
 	return ret;
 }
 
@@ -2371,13 +2371,13 @@ int trace_remove_event_call(struct trace_event_call *call)
 {
 	int ret;
 
-	mutex_lock(&event_mutex);
+	lockdep_assert_held(&event_mutex);
+
 	mutex_lock(&trace_types_lock);
 	down_write(&trace_event_sem);
 	ret = probe_remove_event_call(call);
 	up_write(&trace_event_sem);
 	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
 
 	return ret;
 }

kernel/trace/trace_irqsoff.c

@@ -218,6 +218,11 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
 	atomic_dec(&data->disabled);
 }
 
+static struct fgraph_ops fgraph_ops = {
+	.entryfunc		= &irqsoff_graph_entry,
+	.retfunc		= &irqsoff_graph_return,
+};
+
 static void irqsoff_trace_open(struct trace_iterator *iter)
 {
 	if (is_graph(iter->tr))
@@ -272,13 +277,6 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-#ifdef CONFIG_FUNCTION_TRACER
-static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
-{
-	return -1;
-}
-#endif
-
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
 	return TRACE_TYPE_UNHANDLED;
@@ -288,7 +286,6 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { }
 static void irqsoff_trace_close(struct trace_iterator *iter) { }
 
 #ifdef CONFIG_FUNCTION_TRACER
-static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
 static void irqsoff_print_header(struct seq_file *s)
 {
 	trace_default_header(s);
@@ -468,8 +465,7 @@ static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
 		return 0;
 
 	if (graph)
-		ret = register_ftrace_graph(&irqsoff_graph_return,
-					    &irqsoff_graph_entry);
+		ret = register_ftrace_graph(&fgraph_ops);
 	else
 		ret = register_ftrace_function(tr->ops);
 
@@ -485,7 +481,7 @@ static void unregister_irqsoff_function(struct trace_array *tr, int graph)
 		return;
 
 	if (graph)
-		unregister_ftrace_graph();
+		unregister_ftrace_graph(&fgraph_ops);
 	else
 		unregister_ftrace_function(tr->ops);
 

kernel/trace/trace_output.c

@@ -339,43 +339,24 @@ static inline const char *kretprobed(const char *name)
 #endif /* CONFIG_KRETPROBES */
 
 static void
-seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
+seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
 {
-	char str[KSYM_SYMBOL_LEN];
 #ifdef CONFIG_KALLSYMS
-	const char *name;
-
-	kallsyms_lookup(address, NULL, NULL, NULL, str);
-
-	name = kretprobed(str);
-
-	if (name && strlen(name)) {
-		trace_seq_printf(s, fmt, name);
-		return;
-	}
-#endif
-	snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
-	trace_seq_printf(s, fmt, str);
-}
-
-static void
-seq_print_sym_offset(struct trace_seq *s, const char *fmt,
-		     unsigned long address)
-{
 	char str[KSYM_SYMBOL_LEN];
-#ifdef CONFIG_KALLSYMS
 	const char *name;
 
-	sprint_symbol(str, address);
+	if (offset)
+		sprint_symbol(str, address);
+	else
+		kallsyms_lookup(address, NULL, NULL, NULL, str);
 	name = kretprobed(str);
 
 	if (name && strlen(name)) {
-		trace_seq_printf(s, fmt, name);
+		trace_seq_puts(s, name);
 		return;
 	}
 #endif
-	snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
-	trace_seq_printf(s, fmt, str);
+	trace_seq_printf(s, "0x%08lx", address);
 }
 
 #ifndef CONFIG_64BIT
@@ -424,10 +405,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 		goto out;
 	}
 
-	if (sym_flags & TRACE_ITER_SYM_OFFSET)
-		seq_print_sym_offset(s, "%s", ip);
-	else
-		seq_print_sym_short(s, "%s", ip);
+	seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
 
 	if (sym_flags & TRACE_ITER_SYM_ADDR)
 		trace_seq_printf(s, " <" IP_FMT ">", ip);

kernel/trace/trace_probe.c

@@ -154,24 +154,52 @@ int traceprobe_split_symbol_offset(char *symbol, long *offset)
 	return 0;
 }
 
+/* @buf must has MAX_EVENT_NAME_LEN size */
+int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
+				char *buf)
+{
+	const char *slash, *event = *pevent;
+
+	slash = strchr(event, '/');
+	if (slash) {
+		if (slash == event) {
+			pr_info("Group name is not specified\n");
+			return -EINVAL;
+		}
+		if (slash - event + 1 > MAX_EVENT_NAME_LEN) {
+			pr_info("Group name is too long\n");
+			return -E2BIG;
+		}
+		strlcpy(buf, event, slash - event + 1);
+		*pgroup = buf;
+		*pevent = slash + 1;
+	}
+	if (strlen(event) == 0) {
+		pr_info("Event name is not specified\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
 
 static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			    struct fetch_insn *code, unsigned int flags)
 {
-	int ret = 0;
 	unsigned long param;
+	int ret = 0;
+	int len;
 
 	if (strcmp(arg, "retval") == 0) {
 		if (flags & TPARG_FL_RETURN)
 			code->op = FETCH_OP_RETVAL;
 		else
 			ret = -EINVAL;
-	} else if (strncmp(arg, "stack", 5) == 0) {
-		if (arg[5] == '\0') {
+	} else if ((len = str_has_prefix(arg, "stack"))) {
+		if (arg[len] == '\0') {
 			code->op = FETCH_OP_STACKP;
-		} else if (isdigit(arg[5])) {
-			ret = kstrtoul(arg + 5, 10, &param);
+		} else if (isdigit(arg[len])) {
+			ret = kstrtoul(arg + len, 10, &param);
 			if (ret || ((flags & TPARG_FL_KERNEL) &&
 				    param > PARAM_MAX_STACK))
 				ret = -EINVAL;
@@ -186,10 +214,10 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
 	} else if (((flags & TPARG_FL_MASK) ==
 		    (TPARG_FL_KERNEL | TPARG_FL_FENTRY)) &&
-		   strncmp(arg, "arg", 3) == 0) {
-		if (!isdigit(arg[3]))
+		   (len = str_has_prefix(arg, "arg"))) {
+		if (!isdigit(arg[len]))
 			return -EINVAL;
-		ret = kstrtoul(arg + 3, 10, &param);
+		ret = kstrtoul(arg + len, 10, &param);
 		if (ret || !param || param > PARAM_MAX_STACK)
 			return -EINVAL;
 		code->op = FETCH_OP_ARG;
@@ -348,7 +376,7 @@ static int __parse_bitfield_probe_arg(const char *bf,
 }
 
 /* String length checking wrapper */
-int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
+static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		struct probe_arg *parg, unsigned int flags)
 {
 	struct fetch_insn *code, *scode, *tmp = NULL;
@@ -491,8 +519,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 }
 
 /* Return 1 if name is reserved or already used by another argument */
-int traceprobe_conflict_field_name(const char *name,
-			       struct probe_arg *args, int narg)
+static int traceprobe_conflict_field_name(const char *name,
+					  struct probe_arg *args, int narg)
 {
 	int i;
 
@@ -507,6 +535,47 @@ int traceprobe_conflict_field_name(const char *name,
 	return 0;
 }
 
+int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, char *arg,
+				unsigned int flags)
+{
+	struct probe_arg *parg = &tp->args[i];
+	char *body;
+	int ret;
+
+	/* Increment count for freeing args in error case */
+	tp->nr_args++;
+
+	body = strchr(arg, '=');
+	if (body) {
+		parg->name = kmemdup_nul(arg, body - arg, GFP_KERNEL);
+		body++;
+	} else {
+		/* If argument name is omitted, set "argN" */
+		parg->name = kasprintf(GFP_KERNEL, "arg%d", i + 1);
+		body = arg;
+	}
+	if (!parg->name)
+		return -ENOMEM;
+
+	if (!is_good_name(parg->name)) {
+		pr_info("Invalid argument[%d] name: %s\n",
+			i, parg->name);
+		return -EINVAL;
+	}
+
+	if (traceprobe_conflict_field_name(parg->name, tp->args, i)) {
+		pr_info("Argument[%d]: '%s' conflicts with another field.\n",
+			i, parg->name);
+		return -EINVAL;
+	}
+
+	/* Parse fetch argument */
+	ret = traceprobe_parse_probe_arg_body(body, &tp->size, parg, flags);
+	if (ret)
+		pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
+	return ret;
+}
+
 void traceprobe_free_probe_arg(struct probe_arg *arg)
 {
 	struct fetch_insn *code = arg->code;

kernel/trace/trace_probe.h

@@ -272,16 +272,15 @@ find_event_file_link(struct trace_probe *tp, struct trace_event_file *file)
 #define TPARG_FL_FENTRY BIT(2)
 #define TPARG_FL_MASK	GENMASK(2, 0)
 
-extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
-		   struct probe_arg *parg, unsigned int flags);
-
-extern int traceprobe_conflict_field_name(const char *name,
-			       struct probe_arg *args, int narg);
+extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
+				char *arg, unsigned int flags);
 
 extern int traceprobe_update_arg(struct probe_arg *arg);
 extern void traceprobe_free_probe_arg(struct probe_arg *arg);
 
 extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
+extern int traceprobe_parse_event_name(const char **pevent,
+				       const char **pgroup, char *buf);
 
 extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);
 

kernel/trace/trace_selftest.c

@@ -741,6 +741,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 	return trace_graph_entry(trace);
 }
 
+static struct fgraph_ops fgraph_ops __initdata  = {
+	.entryfunc		= &trace_graph_entry_watchdog,
+	.retfunc		= &trace_graph_return,
+};
+
 /*
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.
@@ -765,8 +770,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 */
 	tracing_reset_online_cpus(&tr->trace_buffer);
 	set_graph_array(tr);
-	ret = register_ftrace_graph(&trace_graph_return,
-				    &trace_graph_entry_watchdog);
+	ret = register_ftrace_graph(&fgraph_ops);
 	if (ret) {
 		warn_failed_init_tracer(trace, ret);
 		goto out;

kernel/trace/trace_stack.c

@@ -286,7 +286,7 @@ __next(struct seq_file *m, loff_t *pos)
 {
 	long n = *pos - 1;
 
-	if (n > stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+	if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
 		return NULL;
 
 	m->private = (void *)n;
@@ -448,8 +448,10 @@ static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata;
 
 static __init int enable_stacktrace(char *str)
 {
-	if (strncmp(str, "_filter=", 8) == 0)
-		strncpy(stack_trace_filter_buf, str+8, COMMAND_LINE_SIZE);
+	int len;
+
+	if ((len = str_has_prefix(str, "_filter=")))
+		strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
 
 	stack_tracer_enabled = 1;
 	last_stack_tracer_enabled = 1;

lib/seq_buf.c

@@ -140,13 +140,17 @@ int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
  */
 int seq_buf_puts(struct seq_buf *s, const char *str)
 {
-	unsigned int len = strlen(str);
+	size_t len = strlen(str);
 
 	WARN_ON(s->size == 0);
 
+	/* Add 1 to len for the trailing null byte which must be there */
+	len += 1;
+
 	if (seq_buf_can_fit(s, len)) {
 		memcpy(s->buffer + s->len, str, len);
-		s->len += len;
+		/* Don't count the trailing null byte against the capacity */
+		s->len += len - 1;
 		return 0;
 	}
 	seq_buf_set_overflow(s);

scripts/recordmcount.c

@@ -397,7 +397,7 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return strcmp(".text",           txtname) == 0 ||
+	return strncmp(".text",          txtname, 5) == 0 ||
 		strcmp(".init.text",     txtname) == 0 ||
 		strcmp(".ref.text",      txtname) == 0 ||
 		strcmp(".sched.text",    txtname) == 0 ||