From b47e330231acbf4506b049643145cc64268a1940 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 16 Mar 2021 12:41:03 -0400
Subject: tracing: Pass buffer of event to trigger operations

The ring_buffer_event_time_stamp() is going to be updated to extract the
time stamp for the event without needing it to be set to have absolute
values for all events. But to do so, it needs the buffer that the event is
on as the buffer saves information for the event before it is committed to
the buffer.

If the trace buffer is disabled, a temporary buffer is used, and there's
no access to this buffer from the current histogram triggers, even though
it is passed to the trace event code.

Pass the buffer that the event is on all the way down to the histogram
triggers.

Link: https://lkml.kernel.org/r/20210316164113.542448131@goodmis.org

Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eccb4e1187cc..f979220238a5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6763,7 +6763,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) {
 		/* do not add \n before testing triggers, but add \0 */
 		entry->buf[cnt] = '\0';
-		tt = event_triggers_call(tr->trace_marker_file, entry, event);
+		tt = event_triggers_call(tr->trace_marker_file, buffer, entry, event);
 	}
 
 	if (entry->buf[cnt - 1] != '\n') {
-- 
cgit v1.2.3


From b94bc80df64823e676b506f8de7dcf6a688d681e Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 16 Mar 2021 12:41:05 -0400
Subject: tracing: Use a no_filter_buffering_ref to stop using the filter
 buffer

Currently, the trace histograms relies on it using absolute time stamps to
trigger the tracing to not use the temp buffer if filters are set. That's
because the histograms need the full timestamp that is saved in the ring
buffer. That is no longer the case, as the ring_buffer_event_time_stamp()
can now return the time stamp for all events without all triggering a full
absolute time stamp.

Now that the absolute time stamp is an unrelated dependency to not using
the filters. There's nothing about having absolute timestamps to keep from
using the filter buffer. Instead, change the interface to explicitly state
to disable filter buffering that the histogram logic can use.

Link: https://lkml.kernel.org/r/20210316164113.847886563@goodmis.org

Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c             | 28 ++++++++++++----------------
 kernel/trace/trace.h             |  4 ++--
 kernel/trace/trace_events_hist.c |  6 +++---
 3 files changed, 17 insertions(+), 21 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f979220238a5..b15436ff85e8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2737,12 +2737,13 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 			  unsigned int trace_ctx)
 {
 	struct ring_buffer_event *entry;
+	struct trace_array *tr = trace_file->tr;
 	int val;
 
-	*current_rb = trace_file->tr->array_buffer.buffer;
+	*current_rb = tr->array_buffer.buffer;
 
-	if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags &
-	     (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
+	if (!tr->no_filter_buffering_ref &&
+	    (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
 	    (entry = this_cpu_read(trace_buffered_event))) {
 		/* Try to use the per cpu buffer first */
 		val = this_cpu_inc_return(trace_buffered_event_cnt);
@@ -6971,31 +6972,26 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs)
+/*
+ * Set or disable using the per CPU trace_buffer_event when possible.
+ */
+int tracing_set_filter_buffering(struct trace_array *tr, bool set)
 {
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
 
-	if (abs && tr->time_stamp_abs_ref++)
+	if (set && tr->no_filter_buffering_ref++)
 		goto out;
 
-	if (!abs) {
-		if (WARN_ON_ONCE(!tr->time_stamp_abs_ref)) {
+	if (!set) {
+		if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) {
 			ret = -EINVAL;
 			goto out;
 		}
 
-		if (--tr->time_stamp_abs_ref)
-			goto out;
+		--tr->no_filter_buffering_ref;
 	}
-
-	ring_buffer_set_time_stamp_abs(tr->array_buffer.buffer, abs);
-
-#ifdef CONFIG_TRACER_MAX_TRACE
-	if (tr->max_buffer.buffer)
-		ring_buffer_set_time_stamp_abs(tr->max_buffer.buffer, abs);
-#endif
  out:
 	mutex_unlock(&trace_types_lock);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 798773178d7e..f2a7a72825c7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -352,7 +352,7 @@ struct trace_array {
 	/* function tracing enabled */
 	int			function_enabled;
 #endif
-	int			time_stamp_abs_ref;
+	int			no_filter_buffering_ref;
 	struct list_head	hist_vars;
 #ifdef CONFIG_TRACER_SNAPSHOT
 	struct cond_snapshot	*cond_snapshot;
@@ -372,7 +372,7 @@ extern int tracing_check_open_get_tr(struct trace_array *tr);
 extern struct trace_array *trace_array_find(const char *instance);
 extern struct trace_array *trace_array_find_get(const char *instance);
 
-extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
+extern int tracing_set_filter_buffering(struct trace_array *tr, bool set);
 extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
 
 extern bool trace_clock_in_ns(struct trace_array *tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 45986cb4637e..c1abd63f1d6c 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5484,7 +5484,7 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
 			goto out;
 		}
 
-		tracing_set_time_stamp_abs(file->tr, true);
+		tracing_set_filter_buffering(file->tr, true);
 	}
 
 	if (named_data)
@@ -5592,7 +5592,7 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
 
 	if (hist_data->enable_timestamps) {
 		if (!hist_data->remove || unregistered)
-			tracing_set_time_stamp_abs(file->tr, false);
+			tracing_set_filter_buffering(file->tr, false);
 	}
 }
 
@@ -5639,7 +5639,7 @@ static void hist_unreg_all(struct trace_event_file *file)
 
 			update_cond_flag(file);
 			if (hist_data->enable_timestamps)
-				tracing_set_time_stamp_abs(file->tr, false);
+				tracing_set_filter_buffering(file->tr, false);
 			if (test->ops->free)
 				test->ops->free(test->ops, test);
 		}
-- 
cgit v1.2.3


From d8279bfc5e9598682f657606d3830ab65932cfe4 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 16 Mar 2021 12:41:07 -0400
Subject: tracing: Add tracing_event_time_stamp() API

Add a tracing_event_time_stamp() API that checks if the event passed in is
not on the ring buffer but a pointer to the per CPU trace_buffered_event
which does not have its time stamp set yet.

If it is a pointer to the trace_buffered_event, then just return the
current time stamp that the ring buffer would produce.

Otherwise, return the time stamp from the event.

Link: https://lkml.kernel.org/r/20210316164114.131996180@goodmis.org

Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 8 ++++++++
 kernel/trace/trace.h | 1 +
 2 files changed, 9 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b15436ff85e8..90ae3140756e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6972,6 +6972,14 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe)
+{
+	if (rbe == this_cpu_read(trace_buffered_event))
+		return ring_buffer_time_stamp(buffer, smp_processor_id());
+
+	return ring_buffer_event_time_stamp(buffer, rbe);
+}
+
 /*
  * Set or disable using the per CPU trace_buffer_event when possible.
  */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f2a7a72825c7..0d8f54f49a3a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -372,6 +372,7 @@ extern int tracing_check_open_get_tr(struct trace_array *tr);
 extern struct trace_array *trace_array_find(const char *instance);
 extern struct trace_array *trace_array_find_get(const char *instance);
 
+extern u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe);
 extern int tracing_set_filter_buffering(struct trace_array *tr, bool set);
 extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
 
-- 
cgit v1.2.3


From 9a6944fee68e25084130386c608c5ac8db487581 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 25 Feb 2021 22:00:57 -0500
Subject: tracing: Add a verifier to check string pointers for trace events

It is a common mistake for someone writing a trace event to save a pointer
to a string in the TP_fast_assign() and then display that string pointer
in the TP_printk() with %s. The problem is that those two events may happen
a long time apart, where the source of the string may no longer exist.

The proper way to handle displaying any string that is not guaranteed to be
in the kernel core rodata section, is to copy it into the ring buffer via
the __string(), __assign_str() and __get_str() helper macros.

Add a check at run time while displaying the TP_printk() of events to make
sure that every %s referenced is safe to dereference, and if it is not,
trigger a warning and only show the address of the pointer, and the
dereferenced string if it can be safely retrieved with a
strncpy_from_kernel_nofault() call.

In order to not have to copy the parsing of vsnprintf() formats, or even
exporting its code, the verifier relies on vsnprintf() being able to
modify the va_list that is passed to it, and it remains modified after it
is called. This is the case for some architectures like x86_64, but other
architectures like x86_32 pass the va_list to vsnprintf() as a value not a
reference, and the verifier can not use it to parse the non string
arguments. Thus, at boot up, it is checked if vsnprintf() modifies the
passed in va_list or not, and a static branch will disable the verifier if
it's not compatible.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c        | 200 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace.h        |   3 +
 kernel/trace/trace_output.c |   2 +-
 kernel/trace/trace_printk.c |  11 +++
 4 files changed, 215 insertions(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 90ae3140756e..e32f5a49f1cf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3558,6 +3558,204 @@ static char *trace_iter_expand_format(struct trace_iterator *iter)
 	return tmp;
 }
 
+/* Returns true if the string is safe to dereference from an event */
+static bool trace_safe_str(struct trace_iterator *iter, const char *str)
+{
+	unsigned long addr = (unsigned long)str;
+	struct trace_event *trace_event;
+	struct trace_event_call *event;
+
+	/* OK if part of the event data */
+	if ((addr >= (unsigned long)iter->ent) &&
+	    (addr < (unsigned long)iter->ent + iter->ent_size))
+		return true;
+
+	/* OK if part of the temp seq buffer */
+	if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
+	    (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
+		return true;
+
+	/* Core rodata can not be freed */
+	if (is_kernel_rodata(addr))
+		return true;
+
+	if (trace_is_tracepoint_string(str))
+		return true;
+
+	/*
+	 * Now this could be a module event, referencing core module
+	 * data, which is OK.
+	 */
+	if (!iter->ent)
+		return false;
+
+	trace_event = ftrace_find_event(iter->ent->type);
+	if (!trace_event)
+		return false;
+
+	event = container_of(trace_event, struct trace_event_call, event);
+	if (!event->mod)
+		return false;
+
+	/* Would rather have rodata, but this will suffice */
+	if (within_module_core(addr, event->mod))
+		return true;
+
+	return false;
+}
+
+static const char *show_buffer(struct trace_seq *s)
+{
+	struct seq_buf *seq = &s->seq;
+
+	seq_buf_terminate(seq);
+
+	return seq->buffer;
+}
+
+static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
+
+static int test_can_verify_check(const char *fmt, ...)
+{
+	char buf[16];
+	va_list ap;
+	int ret;
+
+	/*
+	 * The verifier is dependent on vsnprintf() modifies the va_list
+	 * passed to it, where it is sent as a reference. Some architectures
+	 * (like x86_32) passes it by value, which means that vsnprintf()
+	 * does not modify the va_list passed to it, and the verifier
+	 * would then need to be able to understand all the values that
+	 * vsnprintf can use. If it is passed by value, then the verifier
+	 * is disabled.
+	 */
+	va_start(ap, fmt);
+	vsnprintf(buf, 16, "%d", ap);
+	ret = va_arg(ap, int);
+	va_end(ap);
+
+	return ret;
+}
+
+static void test_can_verify(void)
+{
+	if (!test_can_verify_check("%d %d", 0, 1)) {
+		pr_info("trace event string verifier disabled\n");
+		static_branch_inc(&trace_no_verify);
+	}
+}
+
+/**
+ * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
+ * @iter: The iterator that holds the seq buffer and the event being printed
+ * @fmt: The format used to print the event
+ * @ap: The va_list holding the data to print from @fmt.
+ *
+ * This writes the data into the @iter->seq buffer using the data from
+ * @fmt and @ap. If the format has a %s, then the source of the string
+ * is examined to make sure it is safe to print, otherwise it will
+ * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
+ * pointer.
+ */
+void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
+			 va_list ap)
+{
+	const char *p = fmt;
+	const char *str;
+	int i, j;
+
+	if (WARN_ON_ONCE(!fmt))
+		return;
+
+	if (static_branch_unlikely(&trace_no_verify))
+		goto print;
+
+	/* Don't bother checking when doing a ftrace_dump() */
+	if (iter->fmt == static_fmt_buf)
+		goto print;
+
+	while (*p) {
+		j = 0;
+
+		/* We only care about %s and variants */
+		for (i = 0; p[i]; i++) {
+			if (i + 1 >= iter->fmt_size) {
+				/*
+				 * If we can't expand the copy buffer,
+				 * just print it.
+				 */
+				if (!trace_iter_expand_format(iter))
+					goto print;
+			}
+
+			if (p[i] == '\\' && p[i+1]) {
+				i++;
+				continue;
+			}
+			if (p[i] == '%') {
+				/* Need to test cases like %08.*s */
+				for (j = 1; p[i+j]; j++) {
+					if (isdigit(p[i+j]) ||
+					    p[i+j] == '*' ||
+					    p[i+j] == '.')
+						continue;
+					break;
+				}
+				if (p[i+j] == 's')
+					break;
+			}
+			j = 0;
+		}
+		/* If no %s found then just print normally */
+		if (!p[i])
+			break;
+
+		/* Copy up to the %s, and print that */
+		strncpy(iter->fmt, p, i);
+		iter->fmt[i] = '\0';
+		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+
+		/* The ap now points to the string data of the %s */
+		str = va_arg(ap, const char *);
+
+		/*
+		 * If you hit this warning, it is likely that the
+		 * trace event in question used %s on a string that
+		 * was saved at the time of the event, but may not be
+		 * around when the trace is read. Use __string(),
+		 * __assign_str() and __get_str() helpers in the TRACE_EVENT()
+		 * instead. See samples/trace_events/trace-events-sample.h
+		 * for reference.
+		 */
+		if (WARN_ONCE(!trace_safe_str(iter, str),
+			      "fmt: '%s' current_buffer: '%s'",
+			      fmt, show_buffer(&iter->seq))) {
+			int ret;
+
+			/* Try to safely read the string */
+			ret = strncpy_from_kernel_nofault(iter->fmt, str,
+							  iter->fmt_size);
+			if (ret < 0)
+				trace_seq_printf(&iter->seq, "(0x%px)", str);
+			else
+				trace_seq_printf(&iter->seq, "(0x%px:%s)",
+						 str, iter->fmt);
+			str = "[UNSAFE-MEMORY]";
+			strcpy(iter->fmt, "%s");
+		} else {
+			strncpy(iter->fmt, p + i, j + 1);
+			iter->fmt[j+1] = '\0';
+		}
+		trace_seq_printf(&iter->seq, iter->fmt, str);
+
+		p += i + j + 1;
+	}
+ print:
+	if (*p)
+		trace_seq_vprintf(&iter->seq, p, ap);
+}
+
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
 {
 	const char *p, *new_fmt;
@@ -9675,6 +9873,8 @@ __init static int tracer_alloc_buffers(void)
 
 	register_snapshot_cmd();
 
+	test_can_verify();
+
 	return 0;
 
 out_free_savedcmd:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0d8f54f49a3a..2952bd92bc62 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -582,7 +582,10 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 					struct ring_buffer_event *event);
 
+bool trace_is_tracepoint_string(const char *str);
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
+void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
+			 va_list ap);
 
 int trace_empty(struct trace_iterator *iter);
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 61255bad7e01..a0146e1fffdf 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -317,7 +317,7 @@ void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...)
 	va_list ap;
 
 	va_start(ap, fmt);
-	trace_seq_vprintf(&iter->seq, trace_event_format(iter, fmt), ap);
+	trace_check_vprintf(iter, trace_event_format(iter, fmt), ap);
 	va_end(ap);
 }
 EXPORT_SYMBOL(trace_event_printf);
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index ff32476df072..4b320fe7df70 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -251,6 +251,17 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 }
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
+bool trace_is_tracepoint_string(const char *str)
+{
+	const char **ptr = __start___tracepoint_str;
+
+	for (ptr = __start___tracepoint_str; ptr < __stop___tracepoint_str; ptr++) {
+		if (str == *ptr)
+			return true;
+	}
+	return false;
+}
+
 static const char **find_next(void *v, loff_t *pos)
 {
 	const char **fmt = v;
-- 
cgit v1.2.3


From f2cc020d7876de7583feb52ec939a32419cf9468 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Tue, 23 Mar 2021 18:49:35 +0100
Subject: tracing: Fix various typos in comments

Fix ~59 single-word typos in the tracing code comments, and fix
the grammar in a handful of places.

Link: https://lore.kernel.org/r/20210322224546.GA1981273@gmail.com
Link: https://lkml.kernel.org/r/20210323174935.GA4176821@gmail.com

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/microblaze/include/asm/ftrace.h |  2 +-
 arch/nds32/kernel/ftrace.c           |  2 +-
 arch/powerpc/include/asm/ftrace.h    |  4 ++--
 arch/sh/kernel/ftrace.c              |  2 +-
 arch/sparc/include/asm/ftrace.h      |  2 +-
 fs/tracefs/inode.c                   |  2 +-
 include/linux/ftrace.h               |  4 ++--
 include/linux/trace_events.h         |  2 +-
 include/linux/tracepoint.h           |  2 +-
 include/trace/events/io_uring.h      |  2 +-
 include/trace/events/rcu.h           |  2 +-
 include/trace/events/sched.h         |  2 +-
 include/trace/events/timer.h         |  2 +-
 kernel/trace/bpf_trace.c             |  5 +++--
 kernel/trace/fgraph.c                |  4 ++--
 kernel/trace/ftrace.c                |  8 ++++----
 kernel/trace/ring_buffer.c           |  2 +-
 kernel/trace/synth_event_gen_test.c  |  2 +-
 kernel/trace/trace.c                 | 18 +++++++++---------
 kernel/trace/trace.h                 |  4 ++--
 kernel/trace/trace_event_perf.c      |  2 +-
 kernel/trace/trace_events.c          |  4 ++--
 kernel/trace/trace_events_filter.c   |  4 ++--
 kernel/trace/trace_events_synth.c    |  2 +-
 kernel/trace/trace_functions_graph.c |  2 +-
 kernel/trace/trace_hwlat.c           |  4 ++--
 kernel/trace/trace_kprobe.c          |  2 +-
 kernel/trace/trace_probe.c           |  6 +++---
 kernel/trace/trace_probe.h           |  2 +-
 kernel/trace/trace_probe_tmpl.h      |  2 +-
 kernel/trace/trace_selftest.c        |  4 ++--
 kernel/trace/trace_seq.c             | 12 ++++++------
 32 files changed, 60 insertions(+), 59 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/arch/microblaze/include/asm/ftrace.h b/arch/microblaze/include/asm/ftrace.h
index 5db7f4489f05..6a92bed37794 100644
--- a/arch/microblaze/include/asm/ftrace.h
+++ b/arch/microblaze/include/asm/ftrace.h
@@ -13,7 +13,7 @@ extern void ftrace_call_graph(void);
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-/* reloction of mcount call site is the same as the address */
+/* relocation of mcount call site is the same as the address */
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 414f8a780cc3..0e23e3a8df6b 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -236,7 +236,7 @@ void __naked return_to_handler(void)
 		"bal ftrace_return_to_handler\n\t"
 		"move $lp, $r0               \n\t"
 
-		/* restore state nedded by the ABI  */
+		/* restore state needed by the ABI  */
 		"lmw.bim $r0,[$sp],$r1,#0x0  \n\t");
 }
 
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index bc76970b6ee5..debe8c4f7062 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -12,7 +12,7 @@
 
 #ifdef __ASSEMBLY__
 
-/* Based off of objdump optput from glibc */
+/* Based off of objdump output from glibc */
 
 #define MCOUNT_SAVE_FRAME			\
 	stwu	r1,-48(r1);			\
@@ -52,7 +52,7 @@ extern void _mcount(void);
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
-       /* reloction of mcount call site is the same as the address */
+       /* relocation of mcount call site is the same as the address */
        return addr;
 }
 
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 0646c5961846..295c43315bbe 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -67,7 +67,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  * Modifying code must take extra care. On an SMP machine, if
  * the code being modified is also being executed on another CPU
  * that CPU will have undefined results and possibly take a GPF.
- * We use kstop_machine to stop other CPUS from exectuing code.
+ * We use kstop_machine to stop other CPUS from executing code.
  * But this does not stop NMIs from happening. We still need
  * to protect against that. We separate out the modification of
  * the code to take care of this.
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index d3aa1a524431..e284394cb3aa 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -17,7 +17,7 @@ void _mcount(void);
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-/* reloction of mcount call site is the same as the address */
+/* relocation of mcount call site is the same as the address */
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 4b83cbded559..1261e8b41edb 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -477,7 +477,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
  *
  * The instances directory is special as it allows for mkdir and rmdir to
  * to be done by userspace. When a mkdir or rmdir is performed, the inode
- * locks are released and the methhods passed in (@mkdir and @rmdir) are
+ * locks are released and the methods passed in (@mkdir and @rmdir) are
  * called without locks and with the name of the directory being created
  * within the instances directory.
  *
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 86e5028bfa20..a69f363b61bf 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -33,7 +33,7 @@
 /*
  * If the arch's mcount caller does not support all of ftrace's
  * features, then it must call an indirect function that
- * does. Or at least does enough to prevent any unwelcomed side effects.
+ * does. Or at least does enough to prevent any unwelcome side effects.
  */
 #if !ARCH_SUPPORTS_FTRACE_OPS
 # define FTRACE_FORCE_LIST_FUNC 1
@@ -389,7 +389,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer);
  */
 static inline void stack_tracer_disable(void)
 {
-	/* Preemption or interupts must be disabled */
+	/* Preemption or interrupts must be disabled */
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT))
 		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
 	this_cpu_inc(disable_stack_tracer);
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8cba64ce23a4..36e27c1f42e0 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -206,7 +206,7 @@ static inline unsigned int tracing_gen_ctx_dec(void)
 
 	trace_ctx = tracing_gen_ctx();
 	/*
-	 * Subtract one from the preeption counter if preemption is enabled,
+	 * Subtract one from the preemption counter if preemption is enabled,
 	 * see trace_event_buffer_reserve()for details.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPTION))
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 9cfb099da58f..13f65420f188 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -465,7 +465,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  *	*
  *	* The declared 'local variable' is called '__entry'
  *	*
- *	* __field(pid_t, prev_prid) is equivalent to a standard declariton:
+ *	* __field(pid_t, prev_prid) is equivalent to a standard declaration:
  *	*
  *	*	pid_t	prev_pid;
  *	*
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 9f0d3b7d56b0..ba78a5602cd1 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -49,7 +49,7 @@ TRACE_EVENT(io_uring_create,
 );
 
 /**
- * io_uring_register - called after a buffer/file/eventfd was succesfully
+ * io_uring_register - called after a buffer/file/eventfd was successfully
  * 					   registered for a ring
  *
  * @ctx:			pointer to a ring context structure
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5fc29400e1a2..97177c10bf64 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -48,7 +48,7 @@ TRACE_EVENT(rcu_utilization,
  * RCU flavor, the grace-period number, and a string identifying the
  * grace-period-related event as follows:
  *
- *	"AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL.
+ *	"AccReadyCB": CPU accelerates new callbacks to RCU_NEXT_READY_TAIL.
  *	"AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL.
  *	"newreq": Request a new grace period.
  *	"start": Start a grace period.
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index cbe3e152d24c..1eca2305ca42 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -174,7 +174,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_waking,
 	     TP_ARGS(p));
 
 /*
- * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING.
  * It is not always called from the waking context.
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 19abb6c3eb73..6ad031c71be7 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -119,7 +119,7 @@ TRACE_EVENT(timer_expire_entry,
  * When used in combination with the timer_expire_entry tracepoint we can
  * determine the runtime of the timer callback function.
  *
- * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might
+ * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might
  * be invalid. We solely track the pointer.
  */
 DEFINE_EVENT(timer_class, timer_expire_exit,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b0c45d923f0f..49f7ddb36149 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -658,7 +658,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
 		i++;
 
-		/* skip optional "[0 +-][num]" width formating field */
+		/* skip optional "[0 +-][num]" width formatting field */
 		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
 		       fmt[i] == ' ')
 			i++;
@@ -748,7 +748,8 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 		fmt_cnt++;
 	}
 
-	/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
+	/*
+	 * The maximum we can have is MAX_SEQ_PRINTF_VARARGS parameters, so just give
 	 * all of them to seq_printf().
 	 */
 	seq_printf(m, fmt, params[0], params[1], params[2], params[3],
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 29a6ebeebc9e..b8a0d1d564fb 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -42,7 +42,7 @@ bool ftrace_graph_is_dead(void)
 }
 
 /**
- * ftrace_graph_stop - set to permanently disable function graph tracincg
+ * ftrace_graph_stop - set to permanently disable function graph tracing
  *
  * In case of an error int function graph tracing, this is called
  * to try to keep function graph tracing from causing any more harm.
@@ -117,7 +117,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 
 	/*
 	 * Skip graph tracing if the return location is served by direct trampoline,
-	 * since call sequence and return addresses is unpredicatable anymore.
+	 * since call sequence and return addresses are unpredictable anyway.
 	 * Ex: BPF trampoline may call original function and may skip frame
 	 * depending on type of BPF programs attached.
 	 */
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4d8e35575549..eb7d677cb466 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1045,7 +1045,7 @@ struct ftrace_ops global_ops = {
 };
 
 /*
- * Used by the stack undwinder to know about dynamic ftrace trampolines.
+ * Used by the stack unwinder to know about dynamic ftrace trampolines.
  */
 struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
 {
@@ -3000,7 +3000,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * When the kernel is preemptive, tasks can be preempted
 		 * while on a ftrace trampoline. Just scheduling a task on
 		 * a CPU is not good enough to flush them. Calling
-		 * synchornize_rcu_tasks() will wait for those tasks to
+		 * synchronize_rcu_tasks() will wait for those tasks to
 		 * execute and either schedule voluntarily or enter user space.
 		 */
 		if (IS_ENABLED(CONFIG_PREEMPTION))
@@ -5373,7 +5373,7 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct);
  * @reset - non zero to reset all filters before applying this filter.
  *
  * Filters denote which functions should be enabled when tracing is enabled
- * If @ip is NULL, it failes to update filter.
+ * If @ip is NULL, it fails to update filter.
  */
 int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
 			 int remove, int reset)
@@ -6325,7 +6325,7 @@ clear_mod_from_hash(struct ftrace_page *pg, struct ftrace_hash *hash)
 	}
 }
 
-/* Clear any records from hashs */
+/* Clear any records from hashes */
 static void clear_mod_from_hashes(struct ftrace_page *pg)
 {
 	struct trace_array *tr;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1c61a8cd7b99..f4216df58e31 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3154,7 +3154,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * is called before preempt_count() is updated, since the check will
  * be on the NORMAL bit, the TRANSITION bit will then be set. If an
  * NMI then comes in, it will set the NMI bit, but when the NMI code
- * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * does the trace_recursive_unlock() it will clear the TRANSITION bit
  * and leave the NMI bit set. But this is fine, because the interrupt
  * code that set the TRANSITION bit will then clear the NMI bit when it
  * calls trace_recursive_unlock(). If another NMI comes in, it will
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index a4b4bbf8c3bf..0b15e975d2c2 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Test module for in-kernel sythetic event creation and generation.
+ * Test module for in-kernel synthetic event creation and generation.
  *
  * Copyright (C) 2019 Tom Zanussi <zanussi@kernel.org>
  */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e32f5a49f1cf..c8e54b674d3e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -514,7 +514,7 @@ void trace_free_pid_list(struct trace_pid_list *pid_list)
  * @filtered_pids: The list of pids to check
  * @search_pid: The PID to find in @filtered_pids
  *
- * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis.
+ * Returns true if @search_pid is found in @filtered_pids, and false otherwise.
  */
 bool
 trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
@@ -545,7 +545,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids,
 		       struct task_struct *task)
 {
 	/*
-	 * If filterd_no_pids is not empty, and the task's pid is listed
+	 * If filtered_no_pids is not empty, and the task's pid is listed
 	 * in filtered_no_pids, then return true.
 	 * Otherwise, if filtered_pids is empty, that means we can
 	 * trace all tasks. If it has content, then only trace pids
@@ -612,7 +612,7 @@ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
 
 	(*pos)++;
 
-	/* pid already is +1 of the actual prevous bit */
+	/* pid already is +1 of the actual previous bit */
 	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
 
 	/* Return pid + 1 to allow zero to be represented */
@@ -834,7 +834,7 @@ DEFINE_MUTEX(trace_types_lock);
  * The content of events may become garbage if we allow other process consumes
  * these events concurrently:
  *   A) the page of the consumed events may become a normal page
- *      (not reader page) in ring buffer, and this page will be rewrited
+ *      (not reader page) in ring buffer, and this page will be rewritten
  *      by events producer.
  *   B) The page of the consumed events may become a page for splice_read,
  *      and this page will be returned to system.
@@ -1520,7 +1520,7 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 #undef C
 #define C(a, b) b
 
-/* These must match the bit postions in trace_iterator_flags */
+/* These must match the bit positions in trace_iterator_flags */
 static const char *trace_options[] = {
 	TRACE_FLAGS
 	NULL
@@ -3368,7 +3368,7 @@ int trace_array_vprintk(struct trace_array *tr,
  * buffer (use trace_printk() for that), as writing into the top level
  * buffer should only have events that can be individually disabled.
  * trace_printk() is only used for debugging a kernel, and should not
- * be ever encorporated in normal use.
+ * be ever incorporated in normal use.
  *
  * trace_array_printk() can be used, as it will not add noise to the
  * top level tracing buffer.
@@ -7533,11 +7533,11 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
  * @cmd: The tracing command that caused the error
  * @str: The string to position the caret at within @cmd
  *
- * Finds the position of the first occurence of @str within @cmd.  The
+ * Finds the position of the first occurrence of @str within @cmd.  The
  * return value can be passed to tracing_log_err() for caret placement
  * within @cmd.
  *
- * Returns the index within @cmd of the first occurence of @str or 0
+ * Returns the index within @cmd of the first occurrence of @str or 0
  * if @str was not found.
  */
 unsigned int err_pos(char *cmd, const char *str)
@@ -9320,7 +9320,7 @@ int tracing_init_dentry(void)
 	 * As there may still be users that expect the tracing
 	 * files to exist in debugfs/tracing, we must automount
 	 * the tracefs file system there, so older tools still
-	 * work with the newer kerenl.
+	 * work with the newer kernel.
 	 */
 	tr->dir = debugfs_create_automount("tracing", NULL,
 					   trace_automount, NULL);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2952bd92bc62..5506424eae2a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1347,7 +1347,7 @@ __event_trigger_test_discard(struct trace_event_file *file,
 
 /**
  * event_trigger_unlock_commit - handle triggers and finish event commit
- * @file: The file pointer assoctiated to the event
+ * @file: The file pointer associated with the event
  * @buffer: The ring buffer that the event is being written to
  * @event: The event meta data in the ring buffer
  * @entry: The event itself
@@ -1374,7 +1374,7 @@ event_trigger_unlock_commit(struct trace_event_file *file,
 
 /**
  * event_trigger_unlock_commit_regs - handle triggers and finish event commit
- * @file: The file pointer assoctiated to the event
+ * @file: The file pointer associated with the event
  * @buffer: The ring buffer that the event is being written to
  * @event: The event meta data in the ring buffer
  * @entry: The event itself
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 288ad2c274fb..03be4435d103 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -16,7 +16,7 @@ static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
- * suprises
+ * surprises
  */
 typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 	perf_trace_t;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f58106eaf8cb..80e96989770e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2646,7 +2646,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 		}
 
 		/*
-		 * Since calls are grouped by systems, the likelyhood that the
+		 * Since calls are grouped by systems, the likelihood that the
 		 * next call in the iteration belongs to the same system as the
 		 * previous call is high. As an optimization, we skip searching
 		 * for a map[] that matches the call's system if the last call
@@ -2706,7 +2706,7 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 }
 
 /*
- * Just create a decriptor for early init. A descriptor is required
+ * Just create a descriptor for early init. A descriptor is required
  * for enabling events at boot. We want to enable events before
  * the filesystem is initialized.
  */
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e91259f6a722..9730acf3c03e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -296,7 +296,7 @@ enum {
  * and "FALSE" the program entry after that, we are now done with the first
  * pass.
  *
- * Making the above "a || b && c" have a progam of:
+ * Making the above "a || b && c" have a program of:
  *  prog[0] = { "a", 1, 2 }
  *  prog[1] = { "b", 0, 2 }
  *  prog[2] = { "c", 0, 3 }
@@ -390,7 +390,7 @@ enum {
  * F: return FALSE
  *
  * As "r = a; if (!r) goto n5;" is obviously the same as
- * "if (!a) goto n5;" without doing anything we can interperate the
+ * "if (!a) goto n5;" without doing anything we can interpret the
  * program as:
  * n1: if (!a) goto n5;
  * n2: if (!b) goto n5;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 8d71e6c83f10..2ac75eb6aa86 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1385,7 +1385,7 @@ static int destroy_synth_event(struct synth_event *se)
 
 /**
  * synth_event_delete - Delete a synthetic event
- * @event_name: The name of the new sythetic event
+ * @event_name: The name of the new synthetic event
  *
  * Delete a synthetic event that was created with synth_event_create().
  *
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0aa6e6faa943..0de6837722da 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -764,7 +764,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
  *  - we are inside irq code
  *  - we just entered irq code
  *
- * retunns 0 if
+ * returns 0 if
  *  - funcgraph-interrupts option is set
  *  - we are not inside irq code
  */
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 34dc1a712dcb..632ef88131a9 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -83,7 +83,7 @@ struct hwlat_sample {
 	u64			nmi_total_ts;	/* Total time spent in NMIs */
 	struct timespec64	timestamp;	/* wall time */
 	int			nmi_count;	/* # NMIs during this sample */
-	int			count;		/* # of iteratons over threash */
+	int			count;		/* # of iterations over thresh */
 };
 
 /* keep the global state somewhere. */
@@ -389,7 +389,7 @@ static int start_kthread(struct trace_array *tr)
 }
 
 /**
- * stop_kthread - Inform the hardware latency samping/detector kthread to stop
+ * stop_kthread - Inform the hardware latency sampling/detector kthread to stop
  *
  * This kicks the running hardware latency sampling/detector kernel thread and
  * tells it to stop sampling now. Use this on unload and at system shutdown.
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6fe770d86dc3..ea6178cb5e33 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1748,7 +1748,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
 		kretprobe_perf_func(tk, ri, regs);
 #endif
-	return 0;	/* We don't tweek kernel, so just return 0 */
+	return 0;	/* We don't tweak kernel, so just return 0 */
 }
 NOKPROBE_SYMBOL(kretprobe_dispatcher);
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index ec589a4612df..15413ad7cef2 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -168,7 +168,7 @@ void __trace_probe_log_err(int offset, int err_type)
 	if (!trace_probe_log.argv)
 		return;
 
-	/* Recalcurate the length and allocate buffer */
+	/* Recalculate the length and allocate buffer */
 	for (i = 0; i < trace_probe_log.argc; i++) {
 		if (i == trace_probe_log.index)
 			pos = len;
@@ -182,7 +182,7 @@ void __trace_probe_log_err(int offset, int err_type)
 		/**
 		 * Set the error position is next to the last arg + space.
 		 * Note that len includes the terminal null and the cursor
-		 * appaers at pos + 1.
+		 * appears at pos + 1.
 		 */
 		pos = len;
 		offset = 0;
@@ -592,7 +592,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	}
 
 	/*
-	 * Since $comm and immediate string can not be dereferred,
+	 * Since $comm and immediate string can not be dereferenced,
 	 * we can find those by strcmp.
 	 */
 	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 7ce4027089ee..227d518e5ba5 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -134,7 +134,7 @@ struct fetch_type {
 	size_t			size;		/* Byte size of type */
 	int			is_signed;	/* Signed flag */
 	print_type_func_t	print;		/* Print functions */
-	const char		*fmt;		/* Fromat string */
+	const char		*fmt;		/* Format string */
 	const char		*fmttype;	/* Name in format file */
 };
 
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index e5282828f4a6..f003c5d02a3a 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -167,7 +167,7 @@ array:
 	return code->op == FETCH_OP_END ? ret : -EILSEQ;
 }
 
-/* Sum up total data length for dynamic arraies (strings) */
+/* Sum up total data length for dynamic arrays (strings) */
 static nokprobe_inline int
 __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
 {
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 73ef12092250..adf7ef194005 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -878,7 +878,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/*
-	 * Now that the big kernel lock is no longer preemptable,
+	 * Now that the big kernel lock is no longer preemptible,
 	 * and this is called with the BKL held, it will always
 	 * fail. If preemption is already disabled, simply
 	 * pass the test. When the BKL is removed, or becomes
@@ -940,7 +940,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	int ret;
 
 	/*
-	 * Now that the big kernel lock is no longer preemptable,
+	 * Now that the big kernel lock is no longer preemptible,
 	 * and this is called with the BKL held, it will always
 	 * fail. If preemption is already disabled, simply
 	 * pass the test. When the BKL is removed, or becomes
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 1d84fcc78e3e..9c90b3a7dce2 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -16,7 +16,7 @@
  * The buffer size is currently PAGE_SIZE, although it may become dynamic
  * in the future.
  *
- * A write to the buffer will either succed or fail. That is, unlike
+ * A write to the buffer will either succeed or fail. That is, unlike
  * sprintf() there will not be a partial write (well it may write into
  * the buffer but it wont update the pointers). This allows users to
  * try to write something into the trace_seq buffer and if it fails
@@ -73,7 +73,7 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s)
  * @fmt: printf format string
  *
  * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
+ * copy to user routines. To simplify formatting of a trace
  * trace_seq_printf() is used to store strings into a special
  * buffer (@s). Then the output may be either used by
  * the sequencer or pulled into another buffer.
@@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
  * @fmt: printf format string
  *
  * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
+ * copy to user routines. To simplify formatting of a trace
  * trace_seq_printf is used to store strings into a special
  * buffer (@s). Then the output may be either used by
  * the sequencer or pulled into another buffer.
@@ -226,7 +226,7 @@ EXPORT_SYMBOL_GPL(trace_seq_puts);
  * @c: simple character to record
  *
  * The tracer may use either the sequence operations or its own
- * copy to user routines. This function records a simple charater
+ * copy to user routines. This function records a simple character
  * into a special buffer (@s) for later retrieval by a sequencer
  * or other mechanism.
  */
@@ -348,7 +348,7 @@ int trace_seq_path(struct trace_seq *s, const struct path *path)
 EXPORT_SYMBOL_GPL(trace_seq_path);
 
 /**
- * trace_seq_to_user - copy the squence buffer to user space
+ * trace_seq_to_user - copy the sequence buffer to user space
  * @s: trace sequence descriptor
  * @ubuf: The userspace memory location to copy to
  * @cnt: The amount to copy
@@ -363,7 +363,7 @@ EXPORT_SYMBOL_GPL(trace_seq_path);
  *
  * On failure it returns -EBUSY if all of the content in the
  * sequence has been already read, which includes nothing in the
- * sequenc (@s->len == @s->readpos).
+ * sequence (@s->len == @s->readpos).
  *
  * Returns -EFAULT if the copy to userspace fails.
  */
-- 
cgit v1.2.3


From f3ef7202ef7c705d640d1aeec3b286a641ac9186 Mon Sep 17 00:00:00 2001
From: "Yordan Karadzhov (VMware)" <y.karadz@gmail.com>
Date: Mon, 29 Mar 2021 16:03:31 +0300
Subject: tracing: Remove unused argument from "ring_buffer_time_stamp()

The "cpu" parameter is not being used by the function.

Link: https://lkml.kernel.org/r/20210329130331.199402-1-y.karadz@gmail.com

Signed-off-by: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h | 2 +-
 kernel/trace/ring_buffer.c  | 2 +-
 kernel/trace/trace.c        | 8 ++++----
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 057b7ed4fe24..dac53fd3afea 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -181,7 +181,7 @@ unsigned long ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cp
 unsigned long ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu);
 unsigned long ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu);
 
-u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu);
+u64 ring_buffer_time_stamp(struct trace_buffer *buffer);
 void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer,
 				      int cpu, u64 *ts);
 void ring_buffer_set_clock(struct trace_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f4216df58e31..2c0ee6484990 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1080,7 +1080,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer)
 	return ts << DEBUG_SHIFT;
 }
 
-u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu)
+u64 ring_buffer_time_stamp(struct trace_buffer *buffer)
 {
 	u64 time;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3834de91fb97..507a30bf26e4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -771,7 +771,7 @@ static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu)
 	if (!buf->buffer)
 		return trace_clock_local();
 
-	ts = ring_buffer_time_stamp(buf->buffer, cpu);
+	ts = ring_buffer_time_stamp(buf->buffer);
 	ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts);
 
 	return ts;
@@ -7174,7 +7174,7 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
 u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe)
 {
 	if (rbe == this_cpu_read(trace_buffered_event))
-		return ring_buffer_time_stamp(buffer, smp_processor_id());
+		return ring_buffer_time_stamp(buffer);
 
 	return ring_buffer_event_time_stamp(buffer, rbe);
 }
@@ -8088,7 +8088,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 		trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n",
 								t, usec_rem);
 
-		t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu));
+		t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer));
 		usec_rem = do_div(t, USEC_PER_SEC);
 		trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
 	} else {
@@ -8097,7 +8097,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 				ring_buffer_oldest_event_ts(trace_buf->buffer, cpu));
 
 		trace_seq_printf(s, "now ts: %llu\n",
-				ring_buffer_time_stamp(trace_buf->buffer, cpu));
+				ring_buffer_time_stamp(trace_buf->buffer));
 	}
 
 	cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu);
-- 
cgit v1.2.3


From 20344c54d1c7ab7428e312bbe9b0097750875002 Mon Sep 17 00:00:00 2001
From: "Yordan Karadzhov (VMware)" <y.karadz@gmail.com>
Date: Thu, 15 Apr 2021 21:18:51 +0300
Subject: tracing: Add "last_func_repeats" to struct trace_array

The field is used to keep track of the consecutive (on the same CPU) calls
of a single function. This information is needed in order to consolidate
the function tracing record in the cases when a single function is called
number of times.

Link: https://lkml.kernel.org/r/20210415181854.147448-4-y.karadz@gmail.com

Signed-off-by: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c |  1 +
 kernel/trace/trace.h | 12 ++++++++++++
 2 files changed, 13 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 507a30bf26e4..82833be07c1e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9104,6 +9104,7 @@ static int __remove_instance(struct trace_array *tr)
 	ftrace_clear_pids(tr);
 	ftrace_destroy_function_files(tr);
 	tracefs_remove(tr->dir);
+	free_percpu(tr->last_func_repeats);
 	free_trace_buffers(tr);
 
 	for (i = 0; i < tr->nr_topts; i++) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6a5b4c2a0fa7..a4f1b66049fd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -262,6 +262,17 @@ struct cond_snapshot {
 	cond_update_fn_t		update;
 };
 
+/*
+ * struct trace_func_repeats - used to keep track of the consecutive
+ * (on the same CPU) calls of a single function.
+ */
+struct trace_func_repeats {
+	unsigned long	ip;
+	unsigned long	parent_ip;
+	unsigned long	count;
+	u64		ts_last_call;
+};
+
 /*
  * The trace array - an array of per-CPU trace arrays. This is the
  * highest level data structure that individual tracers deal with.
@@ -358,6 +369,7 @@ struct trace_array {
 #ifdef CONFIG_TRACER_SNAPSHOT
 	struct cond_snapshot	*cond_snapshot;
 #endif
+	struct trace_func_repeats	__percpu *last_func_repeats;
 };
 
 enum {
-- 
cgit v1.2.3


From c658797f1a70561205a224be0c8be64977ed64e8 Mon Sep 17 00:00:00 2001
From: "Yordan Karadzhov (VMware)" <y.karadz@gmail.com>
Date: Thu, 15 Apr 2021 21:18:52 +0300
Subject: tracing: Add method for recording "func_repeats" events

This patch only provides the implementation of the method.
Later we will used it in a combination with a new option for
function tracing.

Link: https://lkml.kernel.org/r/20210415181854.147448-5-y.karadz@gmail.com

Signed-off-by: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 34 ++++++++++++++++++++++++++++++++++
 kernel/trace/trace.h |  4 ++++
 2 files changed, 38 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82833be07c1e..66a4ad93b5e9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3117,6 +3117,40 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 
 #endif /* CONFIG_STACKTRACE */
 
+static inline void
+func_repeats_set_delta_ts(struct func_repeats_entry *entry,
+			  unsigned long long delta)
+{
+	entry->bottom_delta_ts = delta & U32_MAX;
+	entry->top_delta_ts = (delta >> 32);
+}
+
+void trace_last_func_repeats(struct trace_array *tr,
+			     struct trace_func_repeats *last_info,
+			     unsigned int trace_ctx)
+{
+	struct trace_buffer *buffer = tr->array_buffer.buffer;
+	struct func_repeats_entry *entry;
+	struct ring_buffer_event *event;
+	u64 delta;
+
+	event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS,
+					    sizeof(*entry), trace_ctx);
+	if (!event)
+		return;
+
+	delta = ring_buffer_event_time_stamp(buffer, event) -
+		last_info->ts_last_call;
+
+	entry = ring_buffer_event_data(event);
+	entry->ip = last_info->ip;
+	entry->parent_ip = last_info->parent_ip;
+	entry->count = last_info->count;
+	func_repeats_set_delta_ts(entry, delta);
+
+	__buffer_unlock_commit(buffer, event);
+}
+
 /* created for use with alloc_percpu */
 struct trace_buffer_struct {
 	int nesting;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index a4f1b66049fd..cd80d046c7a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -695,6 +695,10 @@ static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 }
 #endif /* CONFIG_STACKTRACE */
 
+void trace_last_func_repeats(struct trace_array *tr,
+			     struct trace_func_repeats *last_info,
+			     unsigned int trace_ctx);
+
 extern u64 ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
-- 
cgit v1.2.3


From 785e3c0a3a870e72dc530856136ab4c8dd207128 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 27 Apr 2021 11:32:07 -0400
Subject: tracing: Map all PIDs to command lines

The default max PID is set by PID_MAX_DEFAULT, and the tracing
infrastructure uses this number to map PIDs to the comm names of the
tasks, such output of the trace can show names from the recorded PIDs in
the ring buffer. This mapping is also exported to user space via the
"saved_cmdlines" file in the tracefs directory.

But currently the mapping expects the PIDs to be less than
PID_MAX_DEFAULT, which is the default maximum and not the real maximum.
Recently, systemd will increases the maximum value of a PID on the system,
and when tasks are traced that have a PID higher than PID_MAX_DEFAULT, its
comm is not recorded. This leads to the entire trace to have "<...>" as
the comm name, which is pretty useless.

Instead, keep the array mapping the size of PID_MAX_DEFAULT, but instead
of just mapping the index to the comm, map a mask of the PID
(PID_MAX_DEFAULT - 1) to the comm, and find the full PID from the
map_cmdline_to_pid array (that already exists).

This bug goes back to the beginning of ftrace, but hasn't been an issue
until user space started increasing the maximum value of PIDs.

Link: https://lkml.kernel.org/r/20210427113207.3c601884@gandalf.local.home

Cc: stable@vger.kernel.org
Fixes: bc0c38d139ec7 ("ftrace: latency tracer infrastructure")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 41 +++++++++++++++--------------------------
 1 file changed, 15 insertions(+), 26 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 66a4ad93b5e9..e28d08905124 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2390,14 +2390,13 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 static int trace_save_cmdline(struct task_struct *tsk)
 {
-	unsigned pid, idx;
+	unsigned tpid, idx;
 
 	/* treat recording of idle task as a success */
 	if (!tsk->pid)
 		return 1;
 
-	if (unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return 0;
+	tpid = tsk->pid & (PID_MAX_DEFAULT - 1);
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -2408,26 +2407,15 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	if (!arch_spin_trylock(&trace_cmdline_lock))
 		return 0;
 
-	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tpid];
 	if (idx == NO_CMDLINE_MAP) {
 		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
-		/*
-		 * Check whether the cmdline buffer at idx has a pid
-		 * mapped. We are going to overwrite that entry so we
-		 * need to clear the map_pid_to_cmdline. Otherwise we
-		 * would read the new comm for the old pid.
-		 */
-		pid = savedcmd->map_cmdline_to_pid[idx];
-		if (pid != NO_CMDLINE_MAP)
-			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
-
-		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
-		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
-
+		savedcmd->map_pid_to_cmdline[tpid] = idx;
 		savedcmd->cmdline_idx = idx;
 	}
 
+	savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
 	set_cmdline(idx, tsk->comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
@@ -2438,6 +2426,7 @@ static int trace_save_cmdline(struct task_struct *tsk)
 static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
+	int tpid;
 
 	if (!pid) {
 		strcpy(comm, "<idle>");
@@ -2449,16 +2438,16 @@ static void __trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	if (pid > PID_MAX_DEFAULT) {
-		strcpy(comm, "<...>");
-		return;
+	tpid = pid & (PID_MAX_DEFAULT - 1);
+	map = savedcmd->map_pid_to_cmdline[tpid];
+	if (map != NO_CMDLINE_MAP) {
+		tpid = savedcmd->map_cmdline_to_pid[map];
+		if (tpid == pid) {
+			strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
+			return;
+		}
 	}
-
-	map = savedcmd->map_pid_to_cmdline[pid];
-	if (map != NO_CMDLINE_MAP)
-		strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
-	else
-		strcpy(comm, "<...>");
+	strcpy(comm, "<...>");
 }
 
 void trace_find_cmdline(int pid, char comm[])
-- 
cgit v1.2.3