Merge tag 'trace-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Add options to the osnoise tracer:
      - 'panic_on_stop' option that panics the kernel if osnoise is
        greater than some user defined threshold.
      - 'preempt' option, to test noise while preemption is disabled
      - 'irq' option, to test noise when interrupts are disabled

 - Add .percent and .graph suffix to histograms to give different
   outputs

 - Add nohitcount to disable showing hitcount in histogram output

 - Add new __cpumask() to trace event fields to annotate that a unsigned
   long array is a cpumask to user space and should be treated as one.

 - Add trace_trigger kernel command line parameter to enable trace event
   triggers at boot up. Useful to trace stack traces, disable tracing
   and take snapshots.

 - Fix x86/kmmio mmio tracer to work with the updates to lockdep

 - Unify the panic and die notifiers

 - Add back ftrace_expect reference that is used to extract more
   information in the ftrace_bug() code.

 - Have trigger filter parsing errors show up in the tracing error log.

 - Updated MAINTAINERS file to add kernel tracing mailing list and
   patchwork info

 - Use IDA to keep track of event type numbers.

 - And minor fixes and clean ups

* tag 'trace-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (44 commits)
  tracing: Fix cpumask() example typo
  tracing: Improve panic/die notifiers
  ftrace: Prevent RCU stall on PREEMPT_VOLUNTARY kernels
  tracing: Do not synchronize freeing of trigger filter on boot up
  tracing: Remove pointer (asterisk) and brackets from cpumask_t field
  tracing: Have trigger filter parsing errors show up in error_log
  x86/mm/kmmio: Remove redundant preempt_disable()
  tracing: Fix infinite loop in tracing_read_pipe on overflowed print_trace_line
  Documentation/osnoise: Add osnoise/options documentation
  tracing/osnoise: Add preempt and/or irq disabled options
  tracing/osnoise: Add PANIC_ON_STOP option
  Documentation/osnoise: Escape underscore of NO_ prefix
  tracing: Fix some checker warnings
  tracing/osnoise: Make osnoise_options static
  tracing: remove unnecessary trace_trigger ifdef
  ring-buffer: Handle resize in early boot up
  tracing/hist: Fix issue of losting command info in error_log
  tracing: Fix issue of missing one synthetic field
  tracing/hist: Fix out-of-bound write on 'action_data.var_ref_idx'
  tracing/hist: Fix wrong return value in parse_action_params()
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -6266,6 +6266,25 @@
 			See also Documentation/trace/ftrace.rst "trace options"
 			section.
 
+	trace_trigger=[trigger-list]
+			[FTRACE] Add a event trigger on specific events.
+			Set a trigger on top of a specific event, with an optional
+			filter.
+
+			The format is is "trace_trigger=<event>.<trigger>[ if <filter>],..."
+			Where more than one trigger may be specified that are comma deliminated.
+
+			For example:
+
+			  trace_trigger="sched_switch.stacktrace if prev_state == 2"
+
+			The above will enable the "stacktrace" trigger on the "sched_switch"
+			event but only trigger it if the "prev_state" of the "sched_switch"
+			event is "2" (TASK_UNINTERUPTIBLE).
+
+			See also "Event triggers" in Documentation/trace/events.rst
+
+
 	traceoff_on_warning
 			[FTRACE] enable this option to disable tracing when a
 			warning is hit. This turns off "tracing_on". Tracing can

Documentation/trace/histogram.rst

@@ -25,7 +25,7 @@ Documentation written by Tom Zanussi
 
         hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
           [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
-          [:clear][:name=histname1][:<handler>.<action>] [if <filter>]
+          [:clear][:name=histname1][:nohitcount][:<handler>.<action>] [if <filter>]
 
   When a matching event is hit, an entry is added to a hash table
   using the key(s) and value(s) named.  Keys and values correspond to
@@ -79,6 +79,8 @@ Documentation written by Tom Zanussi
 	.log2          display log2 value rather than raw number
 	.buckets=size  display grouping of values rather than raw number
 	.usecs         display a common_timestamp in microseconds
+        .percent       display a number of percentage value
+        .graph         display a bar-graph of a value
 	=============  =================================================
 
   Note that in general the semantics of a given field aren't
@@ -137,6 +139,12 @@ Documentation written by Tom Zanussi
   existing trigger, rather than via the '>' operator, which will cause
   the trigger to be removed through truncation.
 
+  The 'nohitcount' (or NOHC) parameter will suppress display of
+  raw hitcount in the histogram. This option requires at least one
+  value field which is not a 'raw hitcount'. For example,
+  'hist:...:vals=hitcount:nohitcount' is rejected, but
+  'hist:...:vals=hitcount.percent:nohitcount' is OK.
+
 - enable_hist/disable_hist
 
   The enable_hist and disable_hist triggers can be used to have one

Documentation/trace/osnoise-tracer.rst

@@ -92,8 +92,8 @@ Note that the example above shows a high number of HW noise samples.
 The reason being is that this sample was taken on a virtual machine,
 and the host interference is detected as a hardware interference.
 
-Tracer options
----------------------
+Tracer Configuration
+--------------------
 
 The tracer has a set of options inside the osnoise directory, they are:
 
@@ -109,6 +109,27 @@ The tracer has a set of options inside the osnoise directory, they are:
  - tracing_threshold: the minimum delta between two time() reads to be
    considered as noise, in us. When set to 0, the default value will
    be used, which is currently 5 us.
+ - osnoise/options: a set of on/off options that can be enabled by
+   writing the option name to the file or disabled by writing the option
+   name preceded with the 'NO\_' prefix. For example, writing
+   NO_OSNOISE_WORKLOAD disables the OSNOISE_WORKLOAD option. The
+   special DEAFAULTS option resets all options to the default value.
+
+Tracer Options
+--------------
+
+The osnoise/options file exposes a set of on/off configuration options for
+the osnoise tracer. These options are:
+
+ - DEFAULTS: reset the options to the default value.
+ - OSNOISE_WORKLOAD: do not dispatch osnoise workload (see dedicated
+   section below).
+ - PANIC_ON_STOP: call panic() if the tracer stops. This option serves to
+   capture a vmcore.
+ - OSNOISE_PREEMPT_DISABLE: disable preemption while running the osnoise
+   workload, allowing only IRQ and hardware-related noise.
+ - OSNOISE_IRQ_DISABLE: disable IRQs while running the osnoise workload,
+   allowing only NMIs and hardware-related noise, like hwlat tracer.
 
 Additional Tracing
 ------------------
@@ -150,3 +171,10 @@ tracepoints is smaller than eight us reported in the sample_threshold.
 The reason roots in the overhead of the entry and exit code that happens
 before and after any interference execution. This justifies the dual
 approach: measuring thread and tracing.
+
+Running osnoise tracer without workload
+---------------------------------------
+
+By enabling the osnoise tracer with the NO_OSNOISE_WORKLOAD option set,
+the osnoise: tracepoints serve to measure the execution time of
+any type of Linux task, free from the interference of other tasks.

MAINTAINERS

@@ -8528,6 +8528,9 @@ FUNCTION HOOKS (FTRACE)
 M:	Steven Rostedt <[email protected]>
 M:	Masami Hiramatsu <[email protected]>
 R:	Mark Rutland <[email protected]>
+L:	[email protected]
+L:	[email protected]
+Q:	https://patchwork.kernel.org/project/linux-trace-kernel/list/
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/ftrace*
@@ -11606,6 +11609,9 @@ M:	Naveen N. Rao <[email protected]>
 M:	Anil S Keshavamurthy <[email protected]>
 M:	"David S. Miller" <[email protected]>
 M:	Masami Hiramatsu <[email protected]>
+L:	[email protected]
+L:	[email protected]
+Q:	https://patchwork.kernel.org/project/linux-trace-kernel/list/
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/kprobes.rst
@@ -21079,6 +21085,9 @@ F:	drivers/hwmon/pmbus/tps546d24.c
 TRACING
 M:	Steven Rostedt <[email protected]>
 M:	Masami Hiramatsu <[email protected]>
+L:	[email protected]
+L:	[email protected]
+Q:	https://patchwork.kernel.org/project/linux-trace-kernel/list/
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/*

arch/x86/kernel/ftrace.c

@@ -221,7 +221,9 @@ void ftrace_replace_code(int enable)
 
 		ret = ftrace_verify_code(rec->ip, old);
 		if (ret) {
+			ftrace_expected = old;
 			ftrace_bug(ret, rec);
+			ftrace_expected = NULL;
 			return;
 		}
 	}

arch/x86/mm/kmmio.c

@@ -62,7 +62,13 @@ struct kmmio_context {
 	int active;
 };
 
-static DEFINE_SPINLOCK(kmmio_lock);
+/*
+ * The kmmio_lock is taken in int3 context, which is treated as NMI context.
+ * This causes lockdep to complain about it bein in both NMI and normal
+ * context. Hide it from lockdep, as it should not have any other locks
+ * taken under it, and this is only enabled for debugging mmio anyway.
+ */
+static arch_spinlock_t kmmio_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 
 /* Protected by kmmio_lock */
 unsigned int kmmio_count;
@@ -240,15 +246,14 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	page_base &= page_level_mask(l);
 
 	/*
-	 * Preemption is now disabled to prevent process switch during
-	 * single stepping. We can only handle one active kmmio trace
+	 * Hold the RCU read lock over single stepping to avoid looking
+	 * up the probe and kmmio_fault_page again. The rcu_read_lock_sched()
+	 * also disables preemption and prevents process switch during
+	 * the single stepping. We can only handle one active kmmio trace
 	 * per cpu, so ensure that we finish it before something else
-	 * gets to run. We also hold the RCU read lock over single
-	 * stepping to avoid looking up the probe and kmmio_fault_page
-	 * again.
+	 * gets to run.
 	 */
-	preempt_disable();
-	rcu_read_lock();
+	rcu_read_lock_sched_notrace();
 
 	faultpage = get_kmmio_fault_page(page_base);
 	if (!faultpage) {
@@ -317,8 +322,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	return 1; /* fault handled */
 
 no_kmmio:
-	rcu_read_unlock();
-	preempt_enable_no_resched();
+	rcu_read_unlock_sched_notrace();
 	return ret;
 }
 
@@ -346,19 +350,18 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 		ctx->probe->post_handler(ctx->probe, condition, regs);
 
 	/* Prevent racing against release_kmmio_fault_page(). */
-	spin_lock(&kmmio_lock);
+	arch_spin_lock(&kmmio_lock);
 	if (ctx->fpage->count)
 		arm_kmmio_fault_page(ctx->fpage);
-	spin_unlock(&kmmio_lock);
+	arch_spin_unlock(&kmmio_lock);
 
 	regs->flags &= ~X86_EFLAGS_TF;
 	regs->flags |= ctx->saved_flags;
 
 	/* These were acquired in kmmio_handler(). */
 	ctx->active--;
 	BUG_ON(ctx->active);
-	rcu_read_unlock();
-	preempt_enable_no_resched();
+	rcu_read_unlock_sched_notrace();
 
 	/*
 	 * if somebody else is singlestepping across a probe point, flags
@@ -440,7 +443,8 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	unsigned int l;
 	pte_t *pte;
 
-	spin_lock_irqsave(&kmmio_lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
 	if (get_kmmio_probe(addr)) {
 		ret = -EEXIST;
 		goto out;
@@ -460,7 +464,9 @@ int register_kmmio_probe(struct kmmio_probe *p)
 		size += page_level_size(l);
 	}
 out:
-	spin_unlock_irqrestore(&kmmio_lock, flags);
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
+
 	/*
 	 * XXX: What should I do here?
 	 * Here was a call to global_flush_tlb(), but it does not exist
@@ -494,7 +500,8 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
 	struct kmmio_fault_page **prevp = &dr->release_list;
 	unsigned long flags;
 
-	spin_lock_irqsave(&kmmio_lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
 	while (f) {
 		if (!f->count) {
 			list_del_rcu(&f->list);
@@ -506,7 +513,8 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
 		}
 		f = *prevp;
 	}
-	spin_unlock_irqrestore(&kmmio_lock, flags);
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
 
 	/* This is the real RCU destroy call. */
 	call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages);
@@ -540,14 +548,16 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 	if (!pte)
 		return;
 
-	spin_lock_irqsave(&kmmio_lock, flags);
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
 	while (size < size_lim) {
 		release_kmmio_fault_page(addr + size, &release_list);
 		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
 	kmmio_count--;
-	spin_unlock_irqrestore(&kmmio_lock, flags);
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
 
 	if (!release_list)
 		return;

include/linux/ring_buffer.h

@@ -113,8 +113,7 @@ void ring_buffer_change_overwrite(struct trace_buffer *buffer, int val);
 
 struct ring_buffer_event *ring_buffer_lock_reserve(struct trace_buffer *buffer,
 						   unsigned long length);
-int ring_buffer_unlock_commit(struct trace_buffer *buffer,
-			      struct ring_buffer_event *event);
+int ring_buffer_unlock_commit(struct trace_buffer *buffer);
 int ring_buffer_write(struct trace_buffer *buffer,
 		      unsigned long length, void *data);
 

include/linux/trace_events.h

@@ -136,7 +136,6 @@ struct trace_event_functions {
 
 struct trace_event {
 	struct hlist_node		node;
-	struct list_head		list;
 	int				type;
 	struct trace_event_functions	*funcs;
 };
@@ -235,7 +234,8 @@ void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
 void tracing_record_cmdline(struct task_struct *task);
 void tracing_record_tgid(struct task_struct *task);
 
-int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...);
+int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
+	 __printf(3, 4);
 
 struct event_filter;
 

include/linux/trace_seq.h

@@ -97,7 +97,8 @@ extern int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str,
 			      const void *buf, size_t len, bool ascii);
 
 #else /* CONFIG_TRACING */
-static inline void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+static inline __printf(2, 3)
+void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
 }
 static inline void

include/trace/bpf_probe.h

@@ -21,6 +21,9 @@
 #undef __get_bitmask
 #define __get_bitmask(field) (char *)__get_dynamic_array(field)
 
+#undef __get_cpumask
+#define __get_cpumask(field) (char *)__get_dynamic_array(field)
+
 #undef __get_sockaddr
 #define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field))
 
@@ -40,6 +43,9 @@
 #undef __get_rel_bitmask
 #define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
 
+#undef __get_rel_cpumask
+#define __get_rel_cpumask(field) (char *)__get_rel_dynamic_array(field)
+
 #undef __get_rel_sockaddr
 #define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field))