Merge tag 'trace-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/g…

…it/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - The biggest news in that the tracing ring buffer can now time events
   that interrupted other ring buffer events.

   Before this change, if an interrupt came in while recording another
   event, and that interrupt also had an event, those events would all
   have the same time stamp as the event it interrupted.

   Now, with the new design, those events will have a unique time stamp
   and rightfully display the time for those events that were recorded
   while interrupting another event.

 - Bootconfig how has an "override" operator that lets the users have a
   default config, but then add options to override the default.

 - A fix was made to properly filter function graph tracing to the
   ftrace PIDs. This came in at the end of the -rc cycle, and needs to
   be backported.

 - Several clean ups, performance updates, and minor fixes as well.

* tag 'trace-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (39 commits)
  tracing: Add trace_array_init_printk() to initialize instance trace_printk() buffers
  kprobes: Fix compiler warning for !CONFIG_KPROBES_ON_FTRACE
  tracing: Use trace_sched_process_free() instead of exit() for pid tracing
  bootconfig: Fix to find the initargs correctly
  Documentation: bootconfig: Add bootconfig override operator
  tools/bootconfig: Add testcases for value override operator
  lib/bootconfig: Add override operator support
  kprobes: Remove show_registers() function prototype
  tracing/uprobe: Remove dead code in trace_uprobe_register()
  kprobes: Fix NULL pointer dereference at kprobe_ftrace_handler
  ftrace: Fix ftrace_trace_task return value
  tracepoint: Use __used attribute definitions from compiler_attributes.h
  tracepoint: Mark __tracepoint_string's __used
  trace : Have tracing buffer info use kvzalloc instead of kzalloc
  tracing: Remove outdated comment in stack handling
  ftrace: Do not let direct or IPMODIFY ftrace_ops be added to module and set trampolines
  ftrace: Setup correct FTRACE_FL_REGS flags for module
  tracing/hwlat: Honor the tracing_cpumask
  tracing/hwlat: Drop the duplicate assignment in start_kthread()
  tracing: Save one trace_event->type by using __TRACE_LAST_TYPE
  ...

Documentation/admin-guide/bootconfig.rst

@@ -71,6 +71,16 @@ For example,::
  foo = bar, baz
  foo = qux  # !ERROR! we can not re-define same key
 
+If you want to update the value, you must use the override operator
+``:=`` explicitly. For example::
+
+ foo = bar, baz
+ foo := qux
+
+then, the ``qux`` is assigned to ``foo`` key. This is useful for
+overriding the default value by adding (partial) custom bootconfigs
+without parsing the default bootconfig.
+
 If you want to append the value to existing key as an array member,
 you can use ``+=`` operator. For example::
 
@@ -84,6 +94,7 @@ For example, following config is NOT allowed.::
 
  foo = value1
  foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist
+ foo.bar := value2 # !ERROR! even with the override operator, this is NOT allowed.
 
 
 Comments

arch/x86/kernel/ftrace.c

@@ -286,6 +286,7 @@ extern void ftrace_regs_caller_ret(void);
 extern void ftrace_caller_end(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);
+extern void ftrace_regs_caller_jmp(void);
 
 /* movq function_trace_op(%rip), %rdx */
 /* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */
@@ -316,6 +317,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long call_offset;
+	unsigned long jmp_offset;
 	unsigned long offset;
 	unsigned long npages;
 	unsigned long size;
@@ -333,11 +335,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		end_offset = (unsigned long)ftrace_regs_caller_end;
 		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
 		call_offset = (unsigned long)ftrace_regs_call;
+		jmp_offset = (unsigned long)ftrace_regs_caller_jmp;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
 		end_offset = (unsigned long)ftrace_caller_end;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
 		call_offset = (unsigned long)ftrace_call;
+		jmp_offset = 0;
 	}
 
 	size = end_offset - start_offset;
@@ -367,10 +371,14 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	if (WARN_ON(ret < 0))
 		goto fail;
 
+	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
-		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
-		ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
-		if (WARN_ON(ret < 0))
+		/* NOP the jnz 1f; but make sure it's a 2 byte jnz */
+		ip = trampoline + (jmp_offset - start_offset);
+		if (WARN_ON(*(char *)ip != 0x75))
+			goto fail;
+		ret = copy_from_kernel_nofault(ip, ideal_nops[2], 2);
+		if (ret < 0)
 			goto fail;
 	}
 

arch/x86/kernel/ftrace_64.S

@@ -241,22 +241,10 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	 */
 	movq ORIG_RAX(%rsp), %rax
 	testq	%rax, %rax
-	jz	1f
+SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
+	jnz	1f
 
-	/* Swap the flags with orig_rax */
-	movq MCOUNT_REG_SIZE(%rsp), %rdi
-	movq %rdi, MCOUNT_REG_SIZE-8(%rsp)
-	movq %rax, MCOUNT_REG_SIZE(%rsp)
-
-	restore_mcount_regs 8
-	/* Restore flags */
-	popfq
-
-SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL);
-	UNWIND_HINT_RET_OFFSET
-	jmp	ftrace_epilogue
-
-1:	restore_mcount_regs
+	restore_mcount_regs
 	/* Restore flags */
 	popfq
 
@@ -269,6 +257,17 @@ SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL);
 SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	jmp ftrace_epilogue
 
+	/* Swap the flags with orig_rax */
+1:	movq MCOUNT_REG_SIZE(%rsp), %rdi
+	movq %rdi, MCOUNT_REG_SIZE-8(%rsp)
+	movq %rax, MCOUNT_REG_SIZE(%rsp)
+
+	restore_mcount_regs 8
+	/* Restore flags */
+	popfq
+	UNWIND_HINT_RET_OFFSET
+	jmp	ftrace_epilogue
+
 SYM_FUNC_END(ftrace_regs_caller)
 
 

include/linux/kprobes.h

@@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
-extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);

include/linux/ring_buffer.h

@@ -143,6 +143,7 @@ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
+void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
 void ring_buffer_reset(struct trace_buffer *buffer);
 
 #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP

include/linux/trace.h

@@ -29,6 +29,7 @@ struct trace_array;
 void trace_printk_init_buffers(void);
 int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		const char *fmt, ...);
+int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
 struct trace_array *trace_array_get_by_name(const char *name);
 int trace_array_destroy(struct trace_array *tr);

include/linux/tracepoint.h

@@ -116,8 +116,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __TRACEPOINT_ENTRY(name)					 \
 	static tracepoint_ptr_t __tracepoint_ptr_##name __used		 \
-	__attribute__((section("__tracepoints_ptrs"))) =		 \
-		&__tracepoint_##name
+	__section(__tracepoints_ptrs) = &__tracepoint_##name
 #endif
 
 #endif /* _LINUX_TRACEPOINT_H */
@@ -280,9 +279,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  */
 #define DEFINE_TRACE_FN(name, reg, unreg)				 \
 	static const char __tpstrtab_##name[]				 \
-	__attribute__((section("__tracepoints_strings"))) = #name;	 \
-	struct tracepoint __tracepoint_##name				 \
-	__attribute__((section("__tracepoints"), used)) =		 \
+	__section(__tracepoints_strings) = #name;			 \
+	struct tracepoint __tracepoint_##name __used			 \
+	__section(__tracepoints) =					 \
 		{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
 	__TRACEPOINT_ENTRY(name);
 
@@ -361,7 +360,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__attribute__((section("__tracepoint_str")))
+#define __tracepoint_string	__used __section(__tracepoint_str)
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace

include/trace/trace_events.h

@@ -210,8 +210,7 @@ TRACE_MAKE_SYSTEM_STR();
 #define DEFINE_EVENT(template, name, proto, args)
 
 #undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
 #undef TRACE_EVENT_FLAGS
 #define TRACE_EVENT_FLAGS(event, flag)
@@ -443,12 +442,8 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 	tstruct								\
 	{} };
 
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)
-
 #undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
@@ -523,13 +518,6 @@ static inline notrace int trace_event_get_offsets_##call(		\
 	return __data_size;						\
 }
 
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
-
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
@@ -721,9 +709,6 @@ static inline void ftrace_test_probe_##call(void)			\
 	check_trace_callback_type_##call(trace_event_raw_event_##template); \
 }
 
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
-
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 #undef __entry

init/main.c

@@ -388,8 +388,6 @@ static int __init bootconfig_params(char *param, char *val,
 {
 	if (strcmp(param, "bootconfig") == 0) {
 		bootconfig_found = true;
-	} else if (strcmp(param, "--") == 0) {
-		initargs_found = true;
 	}
 	return 0;
 }
@@ -400,19 +398,23 @@ static void __init setup_boot_config(const char *cmdline)
 	const char *msg;
 	int pos;
 	u32 size, csum;
-	char *data, *copy;
+	char *data, *copy, *err;
 	int ret;
 
 	/* Cut out the bootconfig data even if we have no bootconfig option */
 	data = get_boot_config_from_initrd(&size, &csum);
 
 	strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
-	parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
-		   bootconfig_params);
+	err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
+			 bootconfig_params);
 
-	if (!bootconfig_found)
+	if (IS_ERR(err) || !bootconfig_found)
 		return;
 
+	/* parse_args() stops at '--' and returns an address */
+	if (err)
+		initargs_found = true;
+
 	if (!data) {
 		pr_err("'bootconfig' found on command line, but no bootconfig found\n");
 		return;

kernel/kprobes.c

@@ -1111,9 +1111,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
-#define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	(-ENODEV)
-#define disarm_kprobe_ftrace(p)	(-ENODEV)
+static inline int prepare_kprobe(struct kprobe *p)
+{
+	return arch_prepare_kprobe(p);
+}
+
+static inline int arm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
+
+static inline int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
 #endif
 
 /* Arm a kprobe with text_mutex */
@@ -2145,6 +2156,13 @@ static void kill_kprobe(struct kprobe *p)
 	 * the original probed function (which will be freed soon) any more.
 	 */
 	arch_remove_kprobe(p);
+
+	/*
+	 * The module is going away. We should disarm the kprobe which
+	 * is using ftrace.
+	 */
+	if (kprobe_ftrace(p))
+		disarm_kprobe_ftrace(p);
 }
 
 /* Disable one kprobe */

kernel/trace/ftrace.c

@@ -139,9 +139,6 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 #endif
 }
 
-#define FTRACE_PID_IGNORE	-1
-#define FTRACE_PID_TRACE	-2
-
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
@@ -2388,6 +2385,14 @@ struct ftrace_ops direct_ops = {
 	.flags		= FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE
 			  | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,
+	/*
+	 * By declaring the main trampoline as this trampoline
+	 * it will never have one allocated for it. Allocated
+	 * trampolines should not call direct functions.
+	 * The direct_ops should only be called by the builtin
+	 * ftrace_regs_caller trampoline.
+	 */
+	.trampoline	= FTRACE_REGS_ADDR,
 };
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
@@ -6255,8 +6260,19 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
+				continue;
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+				continue;
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+			if (cnt == 1 && ops->trampoline)
+				rec->flags |= FTRACE_FL_TRAMP;
+			else
+				rec->flags &= ~FTRACE_FL_TRAMP;
+		}
 	}
 
 	return cnt;
@@ -6435,8 +6451,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -7066,12 +7082,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }