[for-next][PATCH 00/16] tracing: Updates for 5.18

[for-next][PATCH 00/16] tracing: Updates for 5.18

[Steven Rostedt]

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
for-next

Head SHA1: 864ea0e10cc90416a01b46f0d47a6f26dc020820


Beau Belgrave (12):
      user_events: Add minimal support for trace_event into ftrace
      user_events: Add print_fmt generation support for basic types
      user_events: Handle matching arguments from dyn_events
      user_events: Add basic perf and eBPF support
      user_events: Optimize writing events by only copying data once
      user_events: Validate user payloads for size and null termination
      user_events: Add self-test for ftrace integration
      user_events: Add self-test for dynamic_events integration
      user_events: Add self-test for perf_event integration
      user_events: Add self-test for validator boundaries
      user_events: Add sample code for typical usage
      user_events: Add documentation file

Steven Rostedt (Google) (1):
      tracing: Save both wakee and current on wakeup events

Tom Zanussi (3):
      tracing: Remove size restriction on tracing_log_err cmd strings
      tracing: Remove size restriction on hist trigger cmd error logging
      tracing: Remove size restriction on synthetic event cmd error logging

----
 Documentation/trace/index.rst                     |    1 +
 Documentation/trace/user_events.rst               |  216 +++
 include/uapi/linux/user_events.h                  |  116 ++
 kernel/trace/Kconfig                              |   14 +
 kernel/trace/Makefile                             |    1 +
 kernel/trace/trace.c                              |   55 +-
 kernel/trace/trace.h                              |    2 +-
 kernel/trace/trace_events_hist.c                  |   30 +-
 kernel/trace/trace_events_synth.c                 |   17 +-
 kernel/trace/trace_events_user.c                  | 1617 +++++++++++++++++++++
 kernel/trace/trace_sched_switch.c                 |    2 +-
 samples/user_events/Makefile                      |    5 +
 samples/user_events/example.c                     |   91 ++
 tools/testing/selftests/user_events/Makefile      |    9 +
 tools/testing/selftests/user_events/dyn_test.c    |  130 ++
 tools/testing/selftests/user_events/ftrace_test.c |  452 ++++++
 tools/testing/selftests/user_events/perf_test.c   |  168 +++
 tools/testing/selftests/user_events/settings      |    1 +
 18 files changed, 2902 insertions(+), 25 deletions(-)
 create mode 100644 Documentation/trace/user_events.rst
 create mode 100644 include/uapi/linux/user_events.h
 create mode 100644 kernel/trace/trace_events_user.c
 create mode 100644 samples/user_events/Makefile
 create mode 100644 samples/user_events/example.c
 create mode 100644 tools/testing/selftests/user_events/Makefile
 create mode 100644 tools/testing/selftests/user_events/dyn_test.c
 create mode 100644 tools/testing/selftests/user_events/ftrace_test.c
 create mode 100644 tools/testing/selftests/user_events/perf_test.c
 create mode 100644 tools/testing/selftests/user_events/settings

[for-next][PATCH 01/16] tracing: Remove size restriction on tracing_log_err cmd strings

[Steven Rostedt]

From: Tom Zanussi <zanussi@kernel.org>

Currently, tracing_log_err.cmd strings are restricted to a length of
MAX_FILTER_STR_VAL (256), which is too short for some commands already
seen in the wild (with cmd strings longer than that showing up
truncated).

Remove the restriction so that no command string is ever truncated.

Link: https://lkml.kernel.org/r/ca965f23256b350ebd94b3dc1a319f28e8267f5f.1643319703.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 55 +++++++++++++++++++++++++++++++++-----------
 kernel/trace/trace.h |  2 +-
 2 files changed, 43 insertions(+), 14 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7c2578efde26..7c85ce9ffdc3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7723,7 +7723,7 @@ const struct file_operations trace_min_max_fops = {
 struct err_info {
 	const char	**errs;	/* ptr to loc-specific array of err strings */
 	u8		type;	/* index into errs -> specific err string */
-	u8		pos;	/* MAX_FILTER_STR_VAL = 256 */
+	u16		pos;	/* caret position */
 	u64		ts;
 };
 
@@ -7731,26 +7731,52 @@ struct tracing_log_err {
 	struct list_head	list;
 	struct err_info		info;
 	char			loc[TRACING_LOG_LOC_MAX]; /* err location */
-	char			cmd[MAX_FILTER_STR_VAL]; /* what caused err */
+	char			*cmd;                     /* what caused err */
 };
 
 static DEFINE_MUTEX(tracing_err_log_lock);
 
-static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+static struct tracing_log_err *alloc_tracing_log_err(int len)
+{
+	struct tracing_log_err *err;
+
+	err = kzalloc(sizeof(*err), GFP_KERNEL);
+	if (!err)
+		return ERR_PTR(-ENOMEM);
+
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd) {
+		kfree(err);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return err;
+}
+
+static void free_tracing_log_err(struct tracing_log_err *err)
+{
+	kfree(err->cmd);
+	kfree(err);
+}
+
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr,
+						   int len)
 {
 	struct tracing_log_err *err;
 
 	if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) {
-		err = kzalloc(sizeof(*err), GFP_KERNEL);
-		if (!err)
-			err = ERR_PTR(-ENOMEM);
-		else
+		err = alloc_tracing_log_err(len);
+		if (PTR_ERR(err) != -ENOMEM)
 			tr->n_err_log_entries++;
 
 		return err;
 	}
 
 	err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
+	kfree(err->cmd);
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd)
+		return ERR_PTR(-ENOMEM);
 	list_del(&err->list);
 
 	return err;
@@ -7811,22 +7837,25 @@ unsigned int err_pos(char *cmd, const char *str)
  */
 void tracing_log_err(struct trace_array *tr,
 		     const char *loc, const char *cmd,
-		     const char **errs, u8 type, u8 pos)
+		     const char **errs, u8 type, u16 pos)
 {
 	struct tracing_log_err *err;
+	int len = 0;
 
 	if (!tr)
 		tr = &global_trace;
 
+	len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1;
+
 	mutex_lock(&tracing_err_log_lock);
-	err = get_tracing_log_err(tr);
+	err = get_tracing_log_err(tr, len);
 	if (PTR_ERR(err) == -ENOMEM) {
 		mutex_unlock(&tracing_err_log_lock);
 		return;
 	}
 
 	snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc);
-	snprintf(err->cmd, MAX_FILTER_STR_VAL,"\n" CMD_PREFIX "%s\n", cmd);
+	snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd);
 
 	err->info.errs = errs;
 	err->info.type = type;
@@ -7844,7 +7873,7 @@ static void clear_tracing_err_log(struct trace_array *tr)
 	mutex_lock(&tracing_err_log_lock);
 	list_for_each_entry_safe(err, next, &tr->err_log, list) {
 		list_del(&err->list);
-		kfree(err);
+		free_tracing_log_err(err);
 	}
 
 	tr->n_err_log_entries = 0;
@@ -7872,9 +7901,9 @@ static void tracing_err_log_seq_stop(struct seq_file *m, void *v)
 	mutex_unlock(&tracing_err_log_lock);
 }
 
-static void tracing_err_log_show_pos(struct seq_file *m, u8 pos)
+static void tracing_err_log_show_pos(struct seq_file *m, u16 pos)
 {
-	u8 i;
+	u16 i;
 
 	for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++)
 		seq_putc(m, ' ');
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d038ddbf1bea..0f5e22238cd2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1878,7 +1878,7 @@ extern ssize_t trace_parse_run_command(struct file *file,
 extern unsigned int err_pos(char *cmd, const char *str);
 extern void tracing_log_err(struct trace_array *tr,
 			    const char *loc, const char *cmd,
-			    const char **errs, u8 type, u8 pos);
+			    const char **errs, u8 type, u16 pos);
 
 /*
  * Normal trace_printk() and friends allocates special buffers
-- 
2.34.1

[for-next][PATCH 02/16] tracing: Remove size restriction on hist trigger cmd error logging

[Steven Rostedt]

From: Tom Zanussi <zanussi@kernel.org>

Currently, hist trigger command error strings are restricted to a
length of MAX_FILTER_STR_VAL (256), which is too short for some
commands already seen in the wild (with cmd strings longer than that
showing up truncated in err_log).

Remove the restriction so that no hist trigger command error string is
ever truncated.

Link: https://lkml.kernel.org/r/0f9d46407222eaf6632cd3b417bc50a11f401b71.1643399022.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ada87bfb5bb8..5e8970624bce 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -727,11 +727,16 @@ static struct track_data *track_data_alloc(unsigned int key_len,
 	return data;
 }
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+#define HIST_PREFIX "hist:"
+
+static char *last_cmd;
 static char last_cmd_loc[MAX_FILTER_STR_VAL];
 
 static int errpos(char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -739,12 +744,19 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 {
 	const char *system = NULL, *name = NULL;
 	struct trace_event_call *call;
+	int len = 0;
 
 	if (!str)
 		return;
 
-	strcpy(last_cmd, "hist:");
-	strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:"));
+	len += sizeof(HIST_PREFIX) + strlen(str) + 1;
+	kfree(last_cmd);
+	last_cmd = kzalloc(len, GFP_KERNEL);
+	if (!last_cmd)
+		return;
+
+	strcpy(last_cmd, HIST_PREFIX);
+	strncat(last_cmd, str, len - sizeof(HIST_PREFIX));
 
 	if (file) {
 		call = file->event_call;
@@ -757,18 +769,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 	}
 
 	if (system)
-		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name);
+		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, HIST_PREFIX "%s:%s", system, name);
 }
 
-static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos)
+static void hist_err(struct trace_array *tr, u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(tr, last_cmd_loc, last_cmd, err_text,
 			err_type, err_pos);
 }
 
 static void hist_err_clear(void)
 {
-	last_cmd[0] = '\0';
+	if (last_cmd)
+		last_cmd[0] = '\0';
 	last_cmd_loc[0] = '\0';
 }
 
@@ -5610,7 +5626,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 	bool have_var = false;
 	unsigned int i;
 
-	seq_puts(m, "hist:");
+	seq_puts(m, HIST_PREFIX);
 
 	if (data->name)
 		seq_printf(m, "%s:", data->name);
-- 
2.34.1

[for-next][PATCH 03/16] tracing: Remove size restriction on synthetic event cmd error logging

[Steven Rostedt]

From: Tom Zanussi <zanussi@kernel.org>

Currently, synthetic event command error strings are restricted to a
length of MAX_FILTER_STR_VAL (256), which is too short for some
commands already seen in the wild (with cmd strings longer than that
showing up truncated in err_log).

Remove the restriction so that no synthetic event command error string
is ever truncated.

Link: https://lkml.kernel.org/r/0376692396a81d0b795127c66ea92ca5bf60f481.1643399022.git.zanussi@kernel.org

Signed-off-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_synth.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 154db74dadbc..fdd79e07e2fc 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -42,10 +42,13 @@ enum { ERRORS };
 
 static const char *err_text[] = { ERRORS };
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+static char *last_cmd;
 
 static int errpos(const char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -54,11 +57,19 @@ static void last_cmd_set(const char *str)
 	if (!str)
 		return;
 
-	strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1);
+	kfree(last_cmd);
+	last_cmd = kzalloc(strlen(str) + 1, GFP_KERNEL);
+	if (!last_cmd)
+		return;
+
+	strncpy(last_cmd, str, strlen(str) + 1);
 }
 
-static void synth_err(u8 err_type, u8 err_pos)
+static void synth_err(u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(NULL, "synthetic_events", last_cmd, err_text,
 			err_type, err_pos);
 }
-- 
2.34.1

[for-next][PATCH 04/16] tracing: Save both wakee and current on wakeup events

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

Use the sched_switch function to save both the wakee and the waker comms
in the saved cmdlines list when sched_wakeup is done.

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

diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e304196d7c28..5cd33be2031b 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -44,7 +44,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 
 	if (!flags)
 		return;
-	tracing_record_taskinfo(current, flags);
+	tracing_record_taskinfo_sched_switch(current, wakee, flags);
 }
 
 static int tracing_sched_register(void)
-- 
2.34.1

[for-next][PATCH 05/16] user_events: Add minimal support for trace_event into ftrace

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Minimal support for interacting with dynamic events, trace_event and
ftrace. Core outline of flow between user process, ioctl and trace_event
APIs.

User mode processes that wish to use trace events to get data into
ftrace, perf, eBPF, etc are limited to uprobes today. The user events
features enables an ABI for user mode processes to create and write to
trace events that are isolated from kernel level trace events. This
enables a faster path for tracing from user mode data as well as opens
managed code to participate in trace events, where stub locations are
dynamic.

User processes often want to trace only when it's useful. To enable this
a set of pages are mapped into the user process space that indicate the
current state of the user events that have been registered. User
processes can check if their event is hooked to a trace/probe, and if it
is, emit the event data out via the write() syscall.

Two new files are introduced into tracefs to accomplish this:
user_events_status - This file is mmap'd into participating user mode
processes to indicate event status.

user_events_data - This file is opened and register/delete ioctl's are
issued to create/open/delete trace events that can be used for tracing.

The typical scenario is on process start to mmap user_events_status. Processes
then register the events they plan to use via the REG ioctl. The ioctl reads
and updates the passed in user_reg struct. The status_index of the struct is
used to know the byte in the status page to check for that event. The
write_index of the struct is used to describe that event when writing out to
the fd that was used for the ioctl call. The data must always include this
index first when writing out data for an event. Data can be written either by
write() or by writev().

For example, in memory:
int index;
char data[];

Psuedo code example of typical usage:
struct user_reg reg;

int page_fd = open("user_events_status", O_RDWR);
char *page_data = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, page_fd, 0);
close(page_fd);

int data_fd = open("user_events_data", O_RDWR);

reg.size = sizeof(reg);
reg.name_args = (__u64)"test";

ioctl(data_fd, DIAG_IOCSREG, &reg);
int status_id = reg.status_index;
int write_id = reg.write_index;

struct iovec io[2];
io[0].iov_base = &write_id;
io[0].iov_len = sizeof(write_id);
io[1].iov_base = payload;
io[1].iov_len = sizeof(payload);

if (page_data[status_id])
	writev(data_fd, io, 2);

User events are also exposed via the dynamic_events tracefs file for
both create and delete. Current status is exposed via the user_events_status
tracefs file.

Simple example to register a user event via dynamic_events:
	echo u:test >> dynamic_events
	cat dynamic_events
	u:test

If an event is hooked to a probe, the probe hooked shows up:
	echo 1 > events/user_events/test/enable
	cat user_events_status
	1:test # Used by ftrace

	Active: 1
	Busy: 1
	Max: 4096

If an event is not hooked to a probe, no probe status shows up:
	echo 0 > events/user_events/test/enable
	cat user_events_status
	1:test

	Active: 1
	Busy: 0
	Max: 4096

Users can describe the trace event format via the following format:
	name[:FLAG1[,FLAG2...] [field1[;field2...]]

Each field has the following format:
	type name

Example for char array with a size of 20 named msg:
	echo 'u:detailed char[20] msg' >> dynamic_events
	cat dynamic_events
	u:detailed char[20] msg

Data offsets are based on the data written out via write() and will be
updated to reflect the correct offset in the trace_event fields. For dynamic
data it is recommended to use the new __rel_loc data type. This type will be
the same as __data_loc, but the offset is relative to this entry. This allows
user_events to not worry about what common fields are being inserted before
the data.

The above format is valid for both the ioctl and the dynamic_events file.

Link: https://lkml.kernel.org/r/20220118204326.2169-2-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/uapi/linux/user_events.h |  116 +++
 kernel/trace/Kconfig             |   14 +
 kernel/trace/Makefile            |    1 +
 kernel/trace/trace_events_user.c | 1187 ++++++++++++++++++++++++++++++
 4 files changed, 1318 insertions(+)
 create mode 100644 include/uapi/linux/user_events.h
 create mode 100644 kernel/trace/trace_events_user.c

diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h
new file mode 100644
index 000000000000..e570840571e1
--- /dev/null
+++ b/include/uapi/linux/user_events.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Beau Belgrave <beaub@linux.microsoft.com>
+ */
+#ifndef _UAPI_LINUX_USER_EVENTS_H
+#define _UAPI_LINUX_USER_EVENTS_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#ifdef __KERNEL__
+#include <linux/uio.h>
+#else
+#include <sys/uio.h>
+#endif
+
+#define USER_EVENTS_SYSTEM "user_events"
+#define USER_EVENTS_PREFIX "u:"
+
+/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */
+#define EVENT_BIT_FTRACE 0
+#define EVENT_BIT_PERF 1
+#define EVENT_BIT_OTHER 7
+
+#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE)
+#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF)
+#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER)
+
+/* Create dynamic location entry within a 32-bit value */
+#define DYN_LOC(offset, size) ((size) << 16 | (offset))
+
+/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */
+#define FLAG_BPF_ITER (1 << 0)
+
+/*
+ * Describes an event registration and stores the results of the registration.
+ * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum
+ * must set the size and name_args before invocation.
+ */
+struct user_reg {
+
+	/* Input: Size of the user_reg structure being used */
+	__u32 size;
+
+	/* Input: Pointer to string with event name, description and flags */
+	__u64 name_args;
+
+	/* Output: Byte index of the event within the status page */
+	__u32 status_index;
+
+	/* Output: Index of the event to use when writing data */
+	__u32 write_index;
+};
+
+#define DIAG_IOC_MAGIC '*'
+
+/* Requests to register a user_event */
+#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*)
+
+/* Requests to delete a user_event */
+#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*)
+
+/* Data type that was passed to the BPF program */
+enum {
+	/* Data resides in kernel space */
+	USER_BPF_DATA_KERNEL,
+
+	/* Data resides in user space */
+	USER_BPF_DATA_USER,
+
+	/* Data is a pointer to a user_bpf_iter structure */
+	USER_BPF_DATA_ITER,
+};
+
+/*
+ * Describes an iovec iterator that BPF programs can use to access data for
+ * a given user_event write() / writev() call.
+ */
+struct user_bpf_iter {
+
+	/* Offset of the data within the first iovec */
+	__u32 iov_offset;
+
+	/* Number of iovec structures */
+	__u32 nr_segs;
+
+	/* Pointer to iovec structures */
+	const struct iovec *iov;
+};
+
+/* Context that BPF programs receive when attached to a user_event */
+struct user_bpf_context {
+
+	/* Data type being passed (see union below) */
+	__u32 data_type;
+
+	/* Length of the data */
+	__u32 data_len;
+
+	/* Pointer to data, varies by data type */
+	union {
+		/* Kernel data (data_type == USER_BPF_DATA_KERNEL) */
+		void *kdata;
+
+		/* User data (data_type == USER_BPF_DATA_USER) */
+		void *udata;
+
+		/* Direct iovec (data_type == USER_BPF_DATA_ITER) */
+		struct user_bpf_iter *iter;
+	};
+};
+
+#endif /* _UAPI_LINUX_USER_EVENTS_H */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5eb5e7fd624..16a52a71732d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -737,6 +737,20 @@ config SYNTH_EVENTS
 
 	  If in doubt, say N.
 
+config USER_EVENTS
+	bool "User trace events"
+	select TRACING
+	select DYNAMIC_EVENTS
+	help
+	  User trace events are user-defined trace events that
+	  can be used like an existing kernel trace event.  User trace
+	  events are generated by writing to a tracefs file.  User
+	  processes can determine if their tracing events should be
+	  generated by memory mapping a tracefs file and checking for
+	  an associated byte being non-zero.
+
+	  If in doubt, say N.
+
 config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index bedc5caceec7..19ef3758da95 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o
 obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
 obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
+obj-$(CONFIG_USER_EVENTS) += trace_events_user.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
new file mode 100644
index 000000000000..77105233115e
--- /dev/null
+++ b/kernel/trace/trace_events_user.c
@@ -0,0 +1,1187 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <linux/bitmap.h>
+#include <linux/cdev.h>
+#include <linux/hashtable.h>
+#include <linux/list.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+#include <linux/ioctl.h>
+#include <linux/jhash.h>
+#include <linux/trace_events.h>
+#include <linux/tracefs.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/user_events.h>
+#include "trace.h"
+#include "trace_dynevent.h"
+
+#define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1)
+
+#define FIELD_DEPTH_TYPE 0
+#define FIELD_DEPTH_NAME 1
+#define FIELD_DEPTH_SIZE 2
+
+/*
+ * Limits how many trace_event calls user processes can create:
+ * Must be multiple of PAGE_SIZE.
+ */
+#define MAX_PAGES 1
+#define MAX_EVENTS (MAX_PAGES * PAGE_SIZE)
+
+/* Limit how long of an event name plus args within the subsystem. */
+#define MAX_EVENT_DESC 512
+#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
+#define MAX_FIELD_ARRAY_SIZE 1024
+
+static char *register_page_data;
+
+static DEFINE_MUTEX(reg_mutex);
+static DEFINE_HASHTABLE(register_table, 4);
+static DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
+
+/*
+ * Stores per-event properties, as users register events
+ * within a file a user_event might be created if it does not
+ * already exist. These are globally used and their lifetime
+ * is tied to the refcnt member. These cannot go away until the
+ * refcnt reaches zero.
+ */
+struct user_event {
+	struct tracepoint tracepoint;
+	struct trace_event_call call;
+	struct trace_event_class class;
+	struct dyn_event devent;
+	struct hlist_node node;
+	struct list_head fields;
+	atomic_t refcnt;
+	int index;
+	int flags;
+};
+
+/*
+ * Stores per-file events references, as users register events
+ * within a file this structure is modified and freed via RCU.
+ * The lifetime of this struct is tied to the lifetime of the file.
+ * These are not shared and only accessible by the file that created it.
+ */
+struct user_event_refs {
+	struct rcu_head rcu;
+	int count;
+	struct user_event *events[];
+};
+
+typedef void (*user_event_func_t) (struct user_event *user,
+				   void *data, u32 datalen,
+				   void *tpdata);
+
+static int user_event_parse(char *name, char *args, char *flags,
+			    struct user_event **newuser);
+
+static u32 user_event_key(char *name)
+{
+	return jhash(name, strlen(name), 0);
+}
+
+static struct list_head *user_event_get_fields(struct trace_event_call *call)
+{
+	struct user_event *user = (struct user_event *)call->data;
+
+	return &user->fields;
+}
+
+/*
+ * Parses a register command for user_events
+ * Format: event_name[:FLAG1[,FLAG2...]] [field1[;field2...]]
+ *
+ * Example event named 'test' with a 20 char 'msg' field with an unsigned int
+ * 'id' field after:
+ * test char[20] msg;unsigned int id
+ *
+ * NOTE: Offsets are from the user data perspective, they are not from the
+ * trace_entry/buffer perspective. We automatically add the common properties
+ * sizes to the offset for the user.
+ */
+static int user_event_parse_cmd(char *raw_command, struct user_event **newuser)
+{
+	char *name = raw_command;
+	char *args = strpbrk(name, " ");
+	char *flags;
+
+	if (args)
+		*args++ = '\0';
+
+	flags = strpbrk(name, ":");
+
+	if (flags)
+		*flags++ = '\0';
+
+	return user_event_parse(name, args, flags, newuser);
+}
+
+static int user_field_array_size(const char *type)
+{
+	const char *start = strchr(type, '[');
+	char val[8];
+	char *bracket;
+	int size = 0;
+
+	if (start == NULL)
+		return -EINVAL;
+
+	if (strscpy(val, start + 1, sizeof(val)) <= 0)
+		return -EINVAL;
+
+	bracket = strchr(val, ']');
+
+	if (!bracket)
+		return -EINVAL;
+
+	*bracket = '\0';
+
+	if (kstrtouint(val, 0, &size))
+		return -EINVAL;
+
+	if (size > MAX_FIELD_ARRAY_SIZE)
+		return -EINVAL;
+
+	return size;
+}
+
+static int user_field_size(const char *type)
+{
+	/* long is not allowed from a user, since it's ambigious in size */
+	if (strcmp(type, "s64") == 0)
+		return sizeof(s64);
+	if (strcmp(type, "u64") == 0)
+		return sizeof(u64);
+	if (strcmp(type, "s32") == 0)
+		return sizeof(s32);
+	if (strcmp(type, "u32") == 0)
+		return sizeof(u32);
+	if (strcmp(type, "int") == 0)
+		return sizeof(int);
+	if (strcmp(type, "unsigned int") == 0)
+		return sizeof(unsigned int);
+	if (strcmp(type, "s16") == 0)
+		return sizeof(s16);
+	if (strcmp(type, "u16") == 0)
+		return sizeof(u16);
+	if (strcmp(type, "short") == 0)
+		return sizeof(short);
+	if (strcmp(type, "unsigned short") == 0)
+		return sizeof(unsigned short);
+	if (strcmp(type, "s8") == 0)
+		return sizeof(s8);
+	if (strcmp(type, "u8") == 0)
+		return sizeof(u8);
+	if (strcmp(type, "char") == 0)
+		return sizeof(char);
+	if (strcmp(type, "unsigned char") == 0)
+		return sizeof(unsigned char);
+	if (str_has_prefix(type, "char["))
+		return user_field_array_size(type);
+	if (str_has_prefix(type, "unsigned char["))
+		return user_field_array_size(type);
+	if (str_has_prefix(type, "__data_loc "))
+		return sizeof(u32);
+	if (str_has_prefix(type, "__rel_loc "))
+		return sizeof(u32);
+
+	/* Uknown basic type, error */
+	return -EINVAL;
+}
+
+static void user_event_destroy_fields(struct user_event *user)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+
+	list_for_each_entry_safe(field, next, head, link) {
+		list_del(&field->link);
+		kfree(field);
+	}
+}
+
+static int user_event_add_field(struct user_event *user, const char *type,
+				const char *name, int offset, int size,
+				int is_signed, int filter_type)
+{
+	struct ftrace_event_field *field;
+
+	field = kmalloc(sizeof(*field), GFP_KERNEL);
+
+	if (!field)
+		return -ENOMEM;
+
+	field->type = type;
+	field->name = name;
+	field->offset = offset;
+	field->size = size;
+	field->is_signed = is_signed;
+	field->filter_type = filter_type;
+
+	list_add(&field->link, &user->fields);
+
+	return 0;
+}
+
+/*
+ * Parses the values of a field within the description
+ * Format: type name [size]
+ */
+static int user_event_parse_field(char *field, struct user_event *user,
+				  u32 *offset)
+{
+	char *part, *type, *name;
+	u32 depth = 0, saved_offset = *offset;
+	int len, size = -EINVAL;
+	bool is_struct = false;
+
+	field = skip_spaces(field);
+
+	if (*field == '\0')
+		return 0;
+
+	/* Handle types that have a space within */
+	len = str_has_prefix(field, "unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "struct ");
+	if (len) {
+		is_struct = true;
+		goto skip_next;
+	}
+
+	len = str_has_prefix(field, "__data_loc unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__data_loc ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__rel_loc unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__rel_loc ");
+	if (len)
+		goto skip_next;
+
+	goto parse;
+skip_next:
+	type = field;
+	field = strpbrk(field + len, " ");
+
+	if (field == NULL)
+		return -EINVAL;
+
+	*field++ = '\0';
+	depth++;
+parse:
+	while ((part = strsep(&field, " ")) != NULL) {
+		switch (depth++) {
+		case FIELD_DEPTH_TYPE:
+			type = part;
+			break;
+		case FIELD_DEPTH_NAME:
+			name = part;
+			break;
+		case FIELD_DEPTH_SIZE:
+			if (!is_struct)
+				return -EINVAL;
+
+			if (kstrtou32(part, 10, &size))
+				return -EINVAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (depth < FIELD_DEPTH_SIZE)
+		return -EINVAL;
+
+	if (depth == FIELD_DEPTH_SIZE)
+		size = user_field_size(type);
+
+	if (size == 0)
+		return -EINVAL;
+
+	if (size < 0)
+		return size;
+
+	*offset = saved_offset + size;
+
+	return user_event_add_field(user, type, name, saved_offset, size,
+				    type[0] != 'u', FILTER_OTHER);
+}
+
+static void user_event_parse_flags(struct user_event *user, char *flags)
+{
+	char *flag;
+
+	if (flags == NULL)
+		return;
+
+	while ((flag = strsep(&flags, ",")) != NULL) {
+		if (strcmp(flag, "BPF_ITER") == 0)
+			user->flags |= FLAG_BPF_ITER;
+	}
+}
+
+static int user_event_parse_fields(struct user_event *user, char *args)
+{
+	char *field;
+	u32 offset = sizeof(struct trace_entry);
+	int ret = -EINVAL;
+
+	if (args == NULL)
+		return 0;
+
+	while ((field = strsep(&args, ";")) != NULL) {
+		ret = user_event_parse_field(field, user, &offset);
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static struct trace_event_fields user_event_fields_array[1];
+
+static enum print_line_t user_event_print_trace(struct trace_iterator *iter,
+						int flags,
+						struct trace_event *event)
+{
+	/* Unsafe to try to decode user provided print_fmt, use hex */
+	trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16,
+				 1, iter->ent, iter->ent_size, true);
+
+	return trace_handle_return(&iter->seq);
+}
+
+static struct trace_event_functions user_event_funcs = {
+	.trace = user_event_print_trace,
+};
+
+static int destroy_user_event(struct user_event *user)
+{
+	int ret = 0;
+
+	/* Must destroy fields before call removal */
+	user_event_destroy_fields(user);
+
+	ret = trace_remove_event_call(&user->call);
+
+	if (ret)
+		return ret;
+
+	dyn_event_remove(&user->devent);
+
+	register_page_data[user->index] = 0;
+	clear_bit(user->index, page_bitmap);
+	hash_del(&user->node);
+
+	kfree(EVENT_NAME(user));
+	kfree(user);
+
+	return ret;
+}
+
+static struct user_event *find_user_event(char *name, u32 *outkey)
+{
+	struct user_event *user;
+	u32 key = user_event_key(name);
+
+	*outkey = key;
+
+	hash_for_each_possible(register_table, user, node, key)
+		if (!strcmp(EVENT_NAME(user), name))
+			return user;
+
+	return NULL;
+}
+
+/*
+ * Writes the user supplied payload out to a trace file.
+ */
+static void user_event_ftrace(struct user_event *user, void *data, u32 datalen,
+			      void *tpdata)
+{
+	struct trace_event_file *file;
+	struct trace_entry *entry;
+	struct trace_event_buffer event_buffer;
+
+	file = (struct trace_event_file *)tpdata;
+
+	if (!file ||
+	    !(file->flags & EVENT_FILE_FL_ENABLED) ||
+	    trace_trigger_soft_disabled(file))
+		return;
+
+	/* Allocates and fills trace_entry, + 1 of this is data payload */
+	entry = trace_event_buffer_reserve(&event_buffer, file,
+					   sizeof(*entry) + datalen);
+
+	if (unlikely(!entry))
+		return;
+
+	memcpy(entry + 1, data, datalen);
+
+	trace_event_buffer_commit(&event_buffer);
+}
+
+/*
+ * Update the register page that is shared between user processes.
+ */
+static void update_reg_page_for(struct user_event *user)
+{
+	struct tracepoint *tp = &user->tracepoint;
+	char status = 0;
+
+	if (atomic_read(&tp->key.enabled) > 0) {
+		struct tracepoint_func *probe_func_ptr;
+		user_event_func_t probe_func;
+
+		rcu_read_lock_sched();
+
+		probe_func_ptr = rcu_dereference_sched(tp->funcs);
+
+		if (probe_func_ptr) {
+			do {
+				probe_func = probe_func_ptr->func;
+
+				if (probe_func == user_event_ftrace)
+					status |= EVENT_STATUS_FTRACE;
+				else
+					status |= EVENT_STATUS_OTHER;
+			} while ((++probe_func_ptr)->func);
+		}
+
+		rcu_read_unlock_sched();
+	}
+
+	register_page_data[user->index] = status;
+}
+
+/*
+ * Register callback for our events from tracing sub-systems.
+ */
+static int user_event_reg(struct trace_event_call *call,
+			  enum trace_reg type,
+			  void *data)
+{
+	struct user_event *user = (struct user_event *)call->data;
+	int ret = 0;
+
+	if (!user)
+		return -ENOENT;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		ret = tracepoint_probe_register(call->tp,
+						call->class->probe,
+						data);
+		if (!ret)
+			goto inc;
+		break;
+
+	case TRACE_REG_UNREGISTER:
+		tracepoint_probe_unregister(call->tp,
+					    call->class->probe,
+					    data);
+		goto dec;
+
+	default:
+		break;
+	}
+
+	return ret;
+inc:
+	atomic_inc(&user->refcnt);
+	update_reg_page_for(user);
+	return 0;
+dec:
+	update_reg_page_for(user);
+	atomic_dec(&user->refcnt);
+	return 0;
+}
+
+static int user_event_create(const char *raw_command)
+{
+	struct user_event *user;
+	char *name;
+	int ret;
+
+	if (!str_has_prefix(raw_command, USER_EVENTS_PREFIX))
+		return -ECANCELED;
+
+	raw_command += USER_EVENTS_PREFIX_LEN;
+	raw_command = skip_spaces(raw_command);
+
+	name = kstrdup(raw_command, GFP_KERNEL);
+
+	if (!name)
+		return -ENOMEM;
+
+	mutex_lock(&reg_mutex);
+	ret = user_event_parse_cmd(name, &user);
+	mutex_unlock(&reg_mutex);
+
+	if (ret)
+		kfree(name);
+
+	return ret;
+}
+
+static int user_event_show(struct seq_file *m, struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+	struct ftrace_event_field *field, *next;
+	struct list_head *head;
+	int depth = 0;
+
+	seq_printf(m, "%s%s", USER_EVENTS_PREFIX, EVENT_NAME(user));
+
+	head = trace_get_fields(&user->call);
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (depth == 0)
+			seq_puts(m, " ");
+		else
+			seq_puts(m, "; ");
+
+		seq_printf(m, "%s %s", field->type, field->name);
+
+		if (str_has_prefix(field->type, "struct "))
+			seq_printf(m, " %d", field->size);
+
+		depth++;
+	}
+
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+static bool user_event_is_busy(struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	return atomic_read(&user->refcnt) != 0;
+}
+
+static int user_event_free(struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	if (atomic_read(&user->refcnt) != 0)
+		return -EBUSY;
+
+	return destroy_user_event(user);
+}
+
+static bool user_event_match(const char *system, const char *event,
+			     int argc, const char **argv, struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	return strcmp(EVENT_NAME(user), event) == 0 &&
+		(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+}
+
+static struct dyn_event_operations user_event_dops = {
+	.create = user_event_create,
+	.show = user_event_show,
+	.is_busy = user_event_is_busy,
+	.free = user_event_free,
+	.match = user_event_match,
+};
+
+static int user_event_trace_register(struct user_event *user)
+{
+	int ret;
+
+	ret = register_trace_event(&user->call.event);
+
+	if (!ret)
+		return -ENODEV;
+
+	ret = trace_add_event_call(&user->call);
+
+	if (ret)
+		unregister_trace_event(&user->call.event);
+
+	return ret;
+}
+
+/*
+ * Parses the event name, arguments and flags then registers if successful.
+ * The name buffer lifetime is owned by this method for success cases only.
+ */
+static int user_event_parse(char *name, char *args, char *flags,
+			    struct user_event **newuser)
+{
+	int ret;
+	int index;
+	u32 key;
+	struct user_event *user = find_user_event(name, &key);
+
+	if (user) {
+		*newuser = user;
+		/*
+		 * Name is allocated by caller, free it since it already exists.
+		 * Caller only worries about failure cases for freeing.
+		 */
+		kfree(name);
+		return 0;
+	}
+
+	index = find_first_zero_bit(page_bitmap, MAX_EVENTS);
+
+	if (index == MAX_EVENTS)
+		return -EMFILE;
+
+	user = kzalloc(sizeof(*user), GFP_KERNEL);
+
+	if (!user)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&user->class.fields);
+	INIT_LIST_HEAD(&user->fields);
+
+	user->tracepoint.name = name;
+
+	user_event_parse_flags(user, flags);
+
+	ret = user_event_parse_fields(user, args);
+
+	if (ret)
+		goto put_user;
+
+	/* Minimal print format */
+	user->call.print_fmt = "\"\"";
+
+	user->call.data = user;
+	user->call.class = &user->class;
+	user->call.name = name;
+	user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
+	user->call.tp = &user->tracepoint;
+	user->call.event.funcs = &user_event_funcs;
+
+	user->class.system = USER_EVENTS_SYSTEM;
+	user->class.fields_array = user_event_fields_array;
+	user->class.get_fields = user_event_get_fields;
+	user->class.reg = user_event_reg;
+	user->class.probe = user_event_ftrace;
+
+	mutex_lock(&event_mutex);
+	ret = user_event_trace_register(user);
+	mutex_unlock(&event_mutex);
+
+	if (ret)
+		goto put_user;
+
+	user->index = index;
+	dyn_event_init(&user->devent, &user_event_dops);
+	dyn_event_add(&user->devent, &user->call);
+	set_bit(user->index, page_bitmap);
+	hash_add(register_table, &user->node, key);
+
+	*newuser = user;
+	return 0;
+put_user:
+	user_event_destroy_fields(user);
+	kfree(user);
+	return ret;
+}
+
+/*
+ * Deletes a previously created event if it is no longer being used.
+ */
+static int delete_user_event(char *name)
+{
+	u32 key;
+	int ret;
+	struct user_event *user = find_user_event(name, &key);
+
+	if (!user)
+		return -ENOENT;
+
+	if (atomic_read(&user->refcnt) != 0)
+		return -EBUSY;
+
+	mutex_lock(&event_mutex);
+	ret = destroy_user_event(user);
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+/*
+ * Validates the user payload and writes via iterator.
+ */
+static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
+{
+	struct user_event_refs *refs;
+	struct user_event *user = NULL;
+	struct tracepoint *tp;
+	ssize_t ret = i->count;
+	int idx;
+
+	if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx)))
+		return -EFAULT;
+
+	rcu_read_lock_sched();
+
+	refs = rcu_dereference_sched(file->private_data);
+
+	/*
+	 * The refs->events array is protected by RCU, and new items may be
+	 * added. But the user retrieved from indexing into the events array
+	 * shall be immutable while the file is opened.
+	 */
+	if (likely(refs && idx < refs->count))
+		user = refs->events[idx];
+
+	rcu_read_unlock_sched();
+
+	if (unlikely(user == NULL))
+		return -ENOENT;
+
+	tp = &user->tracepoint;
+
+	/*
+	 * It's possible key.enabled disables after this check, however
+	 * we don't mind if a few events are included in this condition.
+	 */
+	if (likely(atomic_read(&tp->key.enabled) > 0)) {
+		struct tracepoint_func *probe_func_ptr;
+		user_event_func_t probe_func;
+		void *tpdata;
+		void *kdata;
+		u32 datalen;
+
+		kdata = kmalloc(i->count, GFP_KERNEL);
+
+		if (unlikely(!kdata))
+			return -ENOMEM;
+
+		datalen = copy_from_iter(kdata, i->count, i);
+
+		rcu_read_lock_sched();
+
+		probe_func_ptr = rcu_dereference_sched(tp->funcs);
+
+		if (probe_func_ptr) {
+			do {
+				probe_func = probe_func_ptr->func;
+				tpdata = probe_func_ptr->data;
+				probe_func(user, kdata, datalen, tpdata);
+			} while ((++probe_func_ptr)->func);
+		}
+
+		rcu_read_unlock_sched();
+
+		kfree(kdata);
+	}
+
+	return ret;
+}
+
+static ssize_t user_events_write(struct file *file, const char __user *ubuf,
+				 size_t count, loff_t *ppos)
+{
+	struct iovec iov;
+	struct iov_iter i;
+
+	if (unlikely(*ppos != 0))
+		return -EFAULT;
+
+	if (unlikely(import_single_range(READ, (char *)ubuf, count, &iov, &i)))
+		return -EFAULT;
+
+	return user_events_write_core(file, &i);
+}
+
+static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i)
+{
+	return user_events_write_core(kp->ki_filp, i);
+}
+
+static int user_events_ref_add(struct file *file, struct user_event *user)
+{
+	struct user_event_refs *refs, *new_refs;
+	int i, size, count = 0;
+
+	refs = rcu_dereference_protected(file->private_data,
+					 lockdep_is_held(&reg_mutex));
+
+	if (refs) {
+		count = refs->count;
+
+		for (i = 0; i < count; ++i)
+			if (refs->events[i] == user)
+				return i;
+	}
+
+	size = struct_size(refs, events, count + 1);
+
+	new_refs = kzalloc(size, GFP_KERNEL);
+
+	if (!new_refs)
+		return -ENOMEM;
+
+	new_refs->count = count + 1;
+
+	for (i = 0; i < count; ++i)
+		new_refs->events[i] = refs->events[i];
+
+	new_refs->events[i] = user;
+
+	atomic_inc(&user->refcnt);
+
+	rcu_assign_pointer(file->private_data, new_refs);
+
+	if (refs)
+		kfree_rcu(refs, rcu);
+
+	return i;
+}
+
+static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg)
+{
+	u32 size;
+	long ret;
+
+	ret = get_user(size, &ureg->size);
+
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)
+		return -E2BIG;
+
+	return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+}
+
+/*
+ * Registers a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_reg(struct file *file, unsigned long uarg)
+{
+	struct user_reg __user *ureg = (struct user_reg __user *)uarg;
+	struct user_reg reg;
+	struct user_event *user;
+	char *name;
+	long ret;
+
+	ret = user_reg_get(ureg, &reg);
+
+	if (ret)
+		return ret;
+
+	name = strndup_user((const char __user *)(uintptr_t)reg.name_args,
+			    MAX_EVENT_DESC);
+
+	if (IS_ERR(name)) {
+		ret = PTR_ERR(name);
+		return ret;
+	}
+
+	ret = user_event_parse_cmd(name, &user);
+
+	if (ret) {
+		kfree(name);
+		return ret;
+	}
+
+	ret = user_events_ref_add(file, user);
+
+	/* Positive number is index and valid */
+	if (ret < 0)
+		return ret;
+
+	put_user((u32)ret, &ureg->write_index);
+	put_user(user->index, &ureg->status_index);
+
+	return 0;
+}
+
+/*
+ * Deletes a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_del(struct file *file, unsigned long uarg)
+{
+	void __user *ubuf = (void __user *)uarg;
+	char *name;
+	long ret;
+
+	name = strndup_user(ubuf, MAX_EVENT_DESC);
+
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	ret = delete_user_event(name);
+
+	kfree(name);
+
+	return ret;
+}
+
+/*
+ * Handles the ioctl from user mode to register or alter operations.
+ */
+static long user_events_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long uarg)
+{
+	long ret = -ENOTTY;
+
+	switch (cmd) {
+	case DIAG_IOCSREG:
+		mutex_lock(&reg_mutex);
+		ret = user_events_ioctl_reg(file, uarg);
+		mutex_unlock(&reg_mutex);
+		break;
+
+	case DIAG_IOCSDEL:
+		mutex_lock(&reg_mutex);
+		ret = user_events_ioctl_del(file, uarg);
+		mutex_unlock(&reg_mutex);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Handles the final close of the file from user mode.
+ */
+static int user_events_release(struct inode *node, struct file *file)
+{
+	struct user_event_refs *refs;
+	struct user_event *user;
+	int i;
+
+	/*
+	 * Ensure refs cannot change under any situation by taking the
+	 * register mutex during the final freeing of the references.
+	 */
+	mutex_lock(&reg_mutex);
+
+	refs = file->private_data;
+
+	if (!refs)
+		goto out;
+
+	/*
+	 * The lifetime of refs has reached an end, it's tied to this file.
+	 * The underlying user_events are ref counted, and cannot be freed.
+	 * After this decrement, the user_events may be freed elsewhere.
+	 */
+	for (i = 0; i < refs->count; ++i) {
+		user = refs->events[i];
+
+		if (user)
+			atomic_dec(&user->refcnt);
+	}
+out:
+	file->private_data = NULL;
+
+	mutex_unlock(&reg_mutex);
+
+	kfree(refs);
+
+	return 0;
+}
+
+static const struct file_operations user_data_fops = {
+	.write = user_events_write,
+	.write_iter = user_events_write_iter,
+	.unlocked_ioctl	= user_events_ioctl,
+	.release = user_events_release,
+};
+
+/*
+ * Maps the shared page into the user process for checking if event is enabled.
+ */
+static int user_status_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	unsigned long size = vma->vm_end - vma->vm_start;
+
+	if (size != MAX_EVENTS)
+		return -EINVAL;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			       virt_to_phys(register_page_data) >> PAGE_SHIFT,
+			       size, vm_get_page_prot(VM_READ));
+}
+
+static void *user_seq_start(struct seq_file *m, loff_t *pos)
+{
+	if (*pos)
+		return NULL;
+
+	return (void *)1;
+}
+
+static void *user_seq_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	++*pos;
+	return NULL;
+}
+
+static void user_seq_stop(struct seq_file *m, void *p)
+{
+}
+
+static int user_seq_show(struct seq_file *m, void *p)
+{
+	struct user_event *user;
+	char status;
+	int i, active = 0, busy = 0, flags;
+
+	mutex_lock(&reg_mutex);
+
+	hash_for_each(register_table, i, user, node) {
+		status = register_page_data[user->index];
+		flags = user->flags;
+
+		seq_printf(m, "%d:%s", user->index, EVENT_NAME(user));
+
+		if (flags != 0 || status != 0)
+			seq_puts(m, " #");
+
+		if (status != 0) {
+			seq_puts(m, " Used by");
+			if (status & EVENT_STATUS_FTRACE)
+				seq_puts(m, " ftrace");
+			if (status & EVENT_STATUS_PERF)
+				seq_puts(m, " perf");
+			if (status & EVENT_STATUS_OTHER)
+				seq_puts(m, " other");
+			busy++;
+		}
+
+		if (flags & FLAG_BPF_ITER)
+			seq_puts(m, " FLAG:BPF_ITER");
+
+		seq_puts(m, "\n");
+		active++;
+	}
+
+	mutex_unlock(&reg_mutex);
+
+	seq_puts(m, "\n");
+	seq_printf(m, "Active: %d\n", active);
+	seq_printf(m, "Busy: %d\n", busy);
+	seq_printf(m, "Max: %ld\n", MAX_EVENTS);
+
+	return 0;
+}
+
+static const struct seq_operations user_seq_ops = {
+	.start = user_seq_start,
+	.next  = user_seq_next,
+	.stop  = user_seq_stop,
+	.show  = user_seq_show,
+};
+
+static int user_status_open(struct inode *node, struct file *file)
+{
+	return seq_open(file, &user_seq_ops);
+}
+
+static const struct file_operations user_status_fops = {
+	.open = user_status_open,
+	.mmap = user_status_mmap,
+	.read = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+/*
+ * Creates a set of tracefs files to allow user mode interactions.
+ */
+static int create_user_tracefs(void)
+{
+	struct dentry *edata, *emmap;
+
+	edata = tracefs_create_file("user_events_data", TRACE_MODE_WRITE,
+				    NULL, NULL, &user_data_fops);
+
+	if (!edata) {
+		pr_warn("Could not create tracefs 'user_events_data' entry\n");
+		goto err;
+	}
+
+	/* mmap with MAP_SHARED requires writable fd */
+	emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE,
+				    NULL, NULL, &user_status_fops);
+
+	if (!emmap) {
+		tracefs_remove(edata);
+		pr_warn("Could not create tracefs 'user_events_mmap' entry\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	return -ENODEV;
+}
+
+static void set_page_reservations(bool set)
+{
+	int page;
+
+	for (page = 0; page < MAX_PAGES; ++page) {
+		void *addr = register_page_data + (PAGE_SIZE * page);
+
+		if (set)
+			SetPageReserved(virt_to_page(addr));
+		else
+			ClearPageReserved(virt_to_page(addr));
+	}
+}
+
+static int __init trace_events_user_init(void)
+{
+	int ret;
+
+	/* Zero all bits beside 0 (which is reserved for failures) */
+	bitmap_zero(page_bitmap, MAX_EVENTS);
+	set_bit(0, page_bitmap);
+
+	register_page_data = kzalloc(MAX_EVENTS, GFP_KERNEL);
+
+	if (!register_page_data)
+		return -ENOMEM;
+
+	set_page_reservations(true);
+
+	ret = create_user_tracefs();
+
+	if (ret) {
+		pr_warn("user_events could not register with tracefs\n");
+		set_page_reservations(false);
+		kfree(register_page_data);
+		return ret;
+	}
+
+	if (dyn_event_register(&user_event_dops))
+		pr_warn("user_events could not register with dyn_events\n");
+
+	return 0;
+}
+
+fs_initcall(trace_events_user_init);
-- 
2.34.1

[for-next][PATCH 06/16] user_events: Add print_fmt generation support for basic types

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Addes print_fmt format generation for basic types that are supported for
user processes. Only supports sizes that are the same on 32 and 64 bit.

Link: https://lkml.kernel.org/r/20220118204326.2169-3-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 115 ++++++++++++++++++++++++++++++-
 1 file changed, 113 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 77105233115e..ddc5c3cf1bf8 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -359,6 +359,114 @@ static int user_event_parse_fields(struct user_event *user, char *args)
 
 static struct trace_event_fields user_event_fields_array[1];
 
+static const char *user_field_format(const char *type)
+{
+	if (strcmp(type, "s64") == 0)
+		return "%lld";
+	if (strcmp(type, "u64") == 0)
+		return "%llu";
+	if (strcmp(type, "s32") == 0)
+		return "%d";
+	if (strcmp(type, "u32") == 0)
+		return "%u";
+	if (strcmp(type, "int") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned int") == 0)
+		return "%u";
+	if (strcmp(type, "s16") == 0)
+		return "%d";
+	if (strcmp(type, "u16") == 0)
+		return "%u";
+	if (strcmp(type, "short") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned short") == 0)
+		return "%u";
+	if (strcmp(type, "s8") == 0)
+		return "%d";
+	if (strcmp(type, "u8") == 0)
+		return "%u";
+	if (strcmp(type, "char") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned char") == 0)
+		return "%u";
+	if (strstr(type, "char[") != 0)
+		return "%s";
+
+	/* Unknown, likely struct, allowed treat as 64-bit */
+	return "%llu";
+}
+
+static bool user_field_is_dyn_string(const char *type, const char **str_func)
+{
+	if (str_has_prefix(type, "__data_loc ")) {
+		*str_func = "__get_str";
+		goto check;
+	}
+
+	if (str_has_prefix(type, "__rel_loc ")) {
+		*str_func = "__get_rel_str";
+		goto check;
+	}
+
+	return false;
+check:
+	return strstr(type, "char") != 0;
+}
+
+#define LEN_OR_ZERO (len ? len - pos : 0)
+static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+	int pos = 0, depth = 0;
+	const char *str_func;
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (depth != 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s",
+				field->name, user_field_format(field->type));
+
+		depth++;
+	}
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (user_field_is_dyn_string(field->type, &str_func))
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", %s(%s)", str_func, field->name);
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", REC->%s", field->name);
+	}
+
+	return pos + 1;
+}
+#undef LEN_OR_ZERO
+
+static int user_event_create_print_fmt(struct user_event *user)
+{
+	char *print_fmt;
+	int len;
+
+	len = user_event_set_print_fmt(user, NULL, 0);
+
+	print_fmt = kmalloc(len, GFP_KERNEL);
+
+	if (!print_fmt)
+		return -ENOMEM;
+
+	user_event_set_print_fmt(user, print_fmt, len);
+
+	user->call.print_fmt = print_fmt;
+
+	return 0;
+}
+
 static enum print_line_t user_event_print_trace(struct trace_iterator *iter,
 						int flags,
 						struct trace_event *event)
@@ -392,6 +500,7 @@ static int destroy_user_event(struct user_event *user)
 	clear_bit(user->index, page_bitmap);
 	hash_del(&user->node);
 
+	kfree(user->call.print_fmt);
 	kfree(EVENT_NAME(user));
 	kfree(user);
 
@@ -669,8 +778,10 @@ static int user_event_parse(char *name, char *args, char *flags,
 	if (ret)
 		goto put_user;
 
-	/* Minimal print format */
-	user->call.print_fmt = "\"\"";
+	ret = user_event_create_print_fmt(user);
+
+	if (ret)
+		goto put_user;
 
 	user->call.data = user;
 	user->call.class = &user->class;
-- 
2.34.1

[for-next][PATCH 07/16] user_events: Handle matching arguments from dyn_events

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Ensures that when dynamic events requests a match with arguments that
they match what is in the user_event.

Link: https://lkml.kernel.org/r/20220118204326.2169-4-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 77 +++++++++++++++++++++++++++++++-
 1 file changed, 76 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index ddc5c3cf1bf8..a6794cb1f586 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -39,6 +39,7 @@
 #define MAX_EVENT_DESC 512
 #define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
 #define MAX_FIELD_ARRAY_SIZE 1024
+#define MAX_FIELD_ARG_NAME 256
 
 static char *register_page_data;
 
@@ -700,13 +701,87 @@ static int user_event_free(struct dyn_event *ev)
 	return destroy_user_event(user);
 }
 
+static bool user_field_match(struct ftrace_event_field *field, int argc,
+			     const char **argv, int *iout)
+{
+	char *field_name, *arg_name;
+	int len, pos, i = *iout;
+	bool colon = false, match = false;
+
+	if (i >= argc)
+		return false;
+
+	len = MAX_FIELD_ARG_NAME;
+	field_name = kmalloc(len, GFP_KERNEL);
+	arg_name = kmalloc(len, GFP_KERNEL);
+
+	if (!arg_name || !field_name)
+		goto out;
+
+	pos = 0;
+
+	for (; i < argc; ++i) {
+		if (i != *iout)
+			pos += snprintf(arg_name + pos, len - pos, " ");
+
+		pos += snprintf(arg_name + pos, len - pos, argv[i]);
+
+		if (strchr(argv[i], ';')) {
+			++i;
+			colon = true;
+			break;
+		}
+	}
+
+	pos = 0;
+
+	pos += snprintf(field_name + pos, len - pos, field->type);
+	pos += snprintf(field_name + pos, len - pos, " ");
+	pos += snprintf(field_name + pos, len - pos, field->name);
+
+	if (colon)
+		pos += snprintf(field_name + pos, len - pos, ";");
+
+	*iout = i;
+
+	match = strcmp(arg_name, field_name) == 0;
+out:
+	kfree(arg_name);
+	kfree(field_name);
+
+	return match;
+}
+
+static bool user_fields_match(struct user_event *user, int argc,
+			      const char **argv)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+	int i = 0;
+
+	list_for_each_entry_safe_reverse(field, next, head, link)
+		if (!user_field_match(field, argc, argv, &i))
+			return false;
+
+	if (i != argc)
+		return false;
+
+	return true;
+}
+
 static bool user_event_match(const char *system, const char *event,
 			     int argc, const char **argv, struct dyn_event *ev)
 {
 	struct user_event *user = container_of(ev, struct user_event, devent);
+	bool match;
 
-	return strcmp(EVENT_NAME(user), event) == 0 &&
+	match = strcmp(EVENT_NAME(user), event) == 0 &&
 		(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+
+	if (match && argc > 0)
+		match = user_fields_match(user, argc, argv);
+
+	return match;
 }
 
 static struct dyn_event_operations user_event_dops = {
-- 
2.34.1

[for-next][PATCH 08/16] user_events: Add basic perf and eBPF support

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Adds support to write out user_event data to perf_probe/perf files as
well as to any attached eBPF program.

Link: https://lkml.kernel.org/r/20220118204326.2169-5-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 72 +++++++++++++++++++++++++++++++-
 1 file changed, 71 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index a6794cb1f586..371f31472156 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -551,6 +551,50 @@ static void user_event_ftrace(struct user_event *user, void *data, u32 datalen,
 	trace_event_buffer_commit(&event_buffer);
 }
 
+#ifdef CONFIG_PERF_EVENTS
+/*
+ * Writes the user supplied payload out to perf ring buffer or eBPF program.
+ */
+static void user_event_perf(struct user_event *user, void *data, u32 datalen,
+			    void *tpdata)
+{
+	struct hlist_head *perf_head;
+
+	if (bpf_prog_array_valid(&user->call)) {
+		struct user_bpf_context context = {0};
+
+		context.data_len = datalen;
+		context.data_type = USER_BPF_DATA_KERNEL;
+		context.kdata = data;
+
+		trace_call_bpf(&user->call, &context);
+	}
+
+	perf_head = this_cpu_ptr(user->call.perf_events);
+
+	if (perf_head && !hlist_empty(perf_head)) {
+		struct trace_entry *perf_entry;
+		struct pt_regs *regs;
+		size_t size = sizeof(*perf_entry) + datalen;
+		int context;
+
+		perf_entry = perf_trace_buf_alloc(ALIGN(size, 8),
+						  &regs, &context);
+
+		if (unlikely(!perf_entry))
+			return;
+
+		perf_fetch_caller_regs(regs);
+
+		memcpy(perf_entry + 1, data, datalen);
+
+		perf_trace_buf_submit(perf_entry, size, context,
+				      user->call.event.type, 1, regs,
+				      perf_head, NULL);
+	}
+}
+#endif
+
 /*
  * Update the register page that is shared between user processes.
  */
@@ -573,6 +617,10 @@ static void update_reg_page_for(struct user_event *user)
 
 				if (probe_func == user_event_ftrace)
 					status |= EVENT_STATUS_FTRACE;
+#ifdef CONFIG_PERF_EVENTS
+				else if (probe_func == user_event_perf)
+					status |= EVENT_STATUS_PERF;
+#endif
 				else
 					status |= EVENT_STATUS_OTHER;
 			} while ((++probe_func_ptr)->func);
@@ -612,8 +660,27 @@ static int user_event_reg(struct trace_event_call *call,
 					    data);
 		goto dec;
 
-	default:
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		ret = tracepoint_probe_register(call->tp,
+						call->class->perf_probe,
+						data);
+		if (!ret)
+			goto inc;
+		break;
+
+	case TRACE_REG_PERF_UNREGISTER:
+		tracepoint_probe_unregister(call->tp,
+					    call->class->perf_probe,
+					    data);
+		goto dec;
+
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
 		break;
+#endif
 	}
 
 	return ret;
@@ -870,6 +937,9 @@ static int user_event_parse(char *name, char *args, char *flags,
 	user->class.get_fields = user_event_get_fields;
 	user->class.reg = user_event_reg;
 	user->class.probe = user_event_ftrace;
+#ifdef CONFIG_PERF_EVENTS
+	user->class.perf_probe = user_event_perf;
+#endif
 
 	mutex_lock(&event_mutex);
 	ret = user_event_trace_register(user);
-- 
2.34.1

[for-next][PATCH 09/16] user_events: Optimize writing events by only copying data once

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Pass iterator through to probes to allow copying data directly to the
probe buffers instead of taking multiple copies. Enables eBPF user and
raw iterator types out to programs for no-copy scenarios.

Link: https://lkml.kernel.org/r/20220118204326.2169-6-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 115 +++++++++++++++++++++++--------
 1 file changed, 85 insertions(+), 30 deletions(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 371f31472156..78b6b96c4cfa 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -41,6 +41,9 @@
 #define MAX_FIELD_ARRAY_SIZE 1024
 #define MAX_FIELD_ARG_NAME 256
 
+#define MAX_BPF_COPY_SIZE PAGE_SIZE
+#define MAX_STACK_BPF_DATA 512
+
 static char *register_page_data;
 
 static DEFINE_MUTEX(reg_mutex);
@@ -78,8 +81,7 @@ struct user_event_refs {
 	struct user_event *events[];
 };
 
-typedef void (*user_event_func_t) (struct user_event *user,
-				   void *data, u32 datalen,
+typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
 				   void *tpdata);
 
 static int user_event_parse(char *name, char *args, char *flags,
@@ -90,6 +92,20 @@ static u32 user_event_key(char *name)
 	return jhash(name, strlen(name), 0);
 }
 
+static __always_inline __must_check
+size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i)
+{
+	size_t ret;
+
+	pagefault_disable();
+
+	ret = copy_from_iter_nocache(addr, bytes, i);
+
+	pagefault_enable();
+
+	return ret;
+}
+
 static struct list_head *user_event_get_fields(struct trace_event_call *call)
 {
 	struct user_event *user = (struct user_event *)call->data;
@@ -525,7 +541,7 @@ static struct user_event *find_user_event(char *name, u32 *outkey)
 /*
  * Writes the user supplied payload out to a trace file.
  */
-static void user_event_ftrace(struct user_event *user, void *data, u32 datalen,
+static void user_event_ftrace(struct user_event *user, struct iov_iter *i,
 			      void *tpdata)
 {
 	struct trace_event_file *file;
@@ -541,41 +557,83 @@ static void user_event_ftrace(struct user_event *user, void *data, u32 datalen,
 
 	/* Allocates and fills trace_entry, + 1 of this is data payload */
 	entry = trace_event_buffer_reserve(&event_buffer, file,
-					   sizeof(*entry) + datalen);
+					   sizeof(*entry) + i->count);
 
 	if (unlikely(!entry))
 		return;
 
-	memcpy(entry + 1, data, datalen);
-
-	trace_event_buffer_commit(&event_buffer);
+	if (unlikely(!copy_nofault(entry + 1, i->count, i)))
+		__trace_event_discard_commit(event_buffer.buffer,
+					     event_buffer.event);
+	else
+		trace_event_buffer_commit(&event_buffer);
 }
 
 #ifdef CONFIG_PERF_EVENTS
+static void user_event_bpf(struct user_event *user, struct iov_iter *i)
+{
+	struct user_bpf_context context;
+	struct user_bpf_iter bpf_i;
+	char fast_data[MAX_STACK_BPF_DATA];
+	void *temp = NULL;
+
+	if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) {
+		/* Raw iterator */
+		context.data_type = USER_BPF_DATA_ITER;
+		context.data_len = i->count;
+		context.iter = &bpf_i;
+
+		bpf_i.iov_offset = i->iov_offset;
+		bpf_i.iov = i->iov;
+		bpf_i.nr_segs = i->nr_segs;
+	} else if (i->nr_segs == 1 && iter_is_iovec(i)) {
+		/* Single buffer from user */
+		context.data_type = USER_BPF_DATA_USER;
+		context.data_len = i->count;
+		context.udata = i->iov->iov_base + i->iov_offset;
+	} else {
+		/* Multi buffer from user */
+		struct iov_iter copy = *i;
+		size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE);
+
+		context.data_type = USER_BPF_DATA_KERNEL;
+		context.kdata = fast_data;
+
+		if (unlikely(copy_size > sizeof(fast_data))) {
+			temp = kmalloc(copy_size, GFP_NOWAIT);
+
+			if (temp)
+				context.kdata = temp;
+			else
+				copy_size = sizeof(fast_data);
+		}
+
+		context.data_len = copy_nofault(context.kdata,
+						copy_size, &copy);
+	}
+
+	trace_call_bpf(&user->call, &context);
+
+	kfree(temp);
+}
+
 /*
  * Writes the user supplied payload out to perf ring buffer or eBPF program.
  */
-static void user_event_perf(struct user_event *user, void *data, u32 datalen,
+static void user_event_perf(struct user_event *user, struct iov_iter *i,
 			    void *tpdata)
 {
 	struct hlist_head *perf_head;
 
-	if (bpf_prog_array_valid(&user->call)) {
-		struct user_bpf_context context = {0};
-
-		context.data_len = datalen;
-		context.data_type = USER_BPF_DATA_KERNEL;
-		context.kdata = data;
-
-		trace_call_bpf(&user->call, &context);
-	}
+	if (bpf_prog_array_valid(&user->call))
+		user_event_bpf(user, i);
 
 	perf_head = this_cpu_ptr(user->call.perf_events);
 
 	if (perf_head && !hlist_empty(perf_head)) {
 		struct trace_entry *perf_entry;
 		struct pt_regs *regs;
-		size_t size = sizeof(*perf_entry) + datalen;
+		size_t size = sizeof(*perf_entry) + i->count;
 		int context;
 
 		perf_entry = perf_trace_buf_alloc(ALIGN(size, 8),
@@ -586,7 +644,10 @@ static void user_event_perf(struct user_event *user, void *data, u32 datalen,
 
 		perf_fetch_caller_regs(regs);
 
-		memcpy(perf_entry + 1, data, datalen);
+		if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) {
+			perf_swevent_put_recursion_context(context);
+			return;
+		}
 
 		perf_trace_buf_submit(perf_entry, size, context,
 				      user->call.event.type, 1, regs,
@@ -1024,16 +1085,11 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 	if (likely(atomic_read(&tp->key.enabled) > 0)) {
 		struct tracepoint_func *probe_func_ptr;
 		user_event_func_t probe_func;
+		struct iov_iter copy;
 		void *tpdata;
-		void *kdata;
-		u32 datalen;
 
-		kdata = kmalloc(i->count, GFP_KERNEL);
-
-		if (unlikely(!kdata))
-			return -ENOMEM;
-
-		datalen = copy_from_iter(kdata, i->count, i);
+		if (unlikely(fault_in_iov_iter_readable(i, i->count)))
+			return -EFAULT;
 
 		rcu_read_lock_sched();
 
@@ -1041,15 +1097,14 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 
 		if (probe_func_ptr) {
 			do {
+				copy = *i;
 				probe_func = probe_func_ptr->func;
 				tpdata = probe_func_ptr->data;
-				probe_func(user, kdata, datalen, tpdata);
+				probe_func(user, &copy, tpdata);
 			} while ((++probe_func_ptr)->func);
 		}
 
 		rcu_read_unlock_sched();
-
-		kfree(kdata);
 	}
 
 	return ret;
-- 
2.34.1

[for-next][PATCH 10/16] user_events: Validate user payloads for size and null termination

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Add validation to ensure data is at or greater than the min size for the
fields of the event. If a dynamic array is used and is a type of char,
ensure null termination of the array exists.

Link: https://lkml.kernel.org/r/20220118204326.2169-7-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 147 ++++++++++++++++++++++++++++---
 1 file changed, 133 insertions(+), 14 deletions(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 78b6b96c4cfa..2b5e9fdb63a0 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -64,9 +64,11 @@ struct user_event {
 	struct dyn_event devent;
 	struct hlist_node node;
 	struct list_head fields;
+	struct list_head validators;
 	atomic_t refcnt;
 	int index;
 	int flags;
+	int min_size;
 };
 
 /*
@@ -81,8 +83,17 @@ struct user_event_refs {
 	struct user_event *events[];
 };
 
+#define VALIDATOR_ENSURE_NULL (1 << 0)
+#define VALIDATOR_REL (1 << 1)
+
+struct user_event_validator {
+	struct list_head link;
+	int offset;
+	int flags;
+};
+
 typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
-				   void *tpdata);
+				   void *tpdata, bool *faulted);
 
 static int user_event_parse(char *name, char *args, char *flags,
 			    struct user_event **newuser);
@@ -215,6 +226,17 @@ static int user_field_size(const char *type)
 	return -EINVAL;
 }
 
+static void user_event_destroy_validators(struct user_event *user)
+{
+	struct user_event_validator *validator, *next;
+	struct list_head *head = &user->validators;
+
+	list_for_each_entry_safe(validator, next, head, link) {
+		list_del(&validator->link);
+		kfree(validator);
+	}
+}
+
 static void user_event_destroy_fields(struct user_event *user)
 {
 	struct ftrace_event_field *field, *next;
@@ -230,13 +252,43 @@ static int user_event_add_field(struct user_event *user, const char *type,
 				const char *name, int offset, int size,
 				int is_signed, int filter_type)
 {
+	struct user_event_validator *validator;
 	struct ftrace_event_field *field;
+	int validator_flags = 0;
 
 	field = kmalloc(sizeof(*field), GFP_KERNEL);
 
 	if (!field)
 		return -ENOMEM;
 
+	if (str_has_prefix(type, "__data_loc "))
+		goto add_validator;
+
+	if (str_has_prefix(type, "__rel_loc ")) {
+		validator_flags |= VALIDATOR_REL;
+		goto add_validator;
+	}
+
+	goto add_field;
+
+add_validator:
+	if (strstr(type, "char") != 0)
+		validator_flags |= VALIDATOR_ENSURE_NULL;
+
+	validator = kmalloc(sizeof(*validator), GFP_KERNEL);
+
+	if (!validator) {
+		kfree(field);
+		return -ENOMEM;
+	}
+
+	validator->flags = validator_flags;
+	validator->offset = offset;
+
+	/* Want sequential access when validating */
+	list_add_tail(&validator->link, &user->validators);
+
+add_field:
 	field->type = type;
 	field->name = name;
 	field->offset = offset;
@@ -246,6 +298,12 @@ static int user_event_add_field(struct user_event *user, const char *type,
 
 	list_add(&field->link, &user->fields);
 
+	/*
+	 * Min size from user writes that are required, this does not include
+	 * the size of trace_entry (common fields).
+	 */
+	user->min_size = (offset + size) - sizeof(struct trace_entry);
+
 	return 0;
 }
 
@@ -517,6 +575,7 @@ static int destroy_user_event(struct user_event *user)
 	clear_bit(user->index, page_bitmap);
 	hash_del(&user->node);
 
+	user_event_destroy_validators(user);
 	kfree(user->call.print_fmt);
 	kfree(EVENT_NAME(user));
 	kfree(user);
@@ -538,15 +597,49 @@ static struct user_event *find_user_event(char *name, u32 *outkey)
 	return NULL;
 }
 
+static int user_event_validate(struct user_event *user, void *data, int len)
+{
+	struct list_head *head = &user->validators;
+	struct user_event_validator *validator;
+	void *pos, *end = data + len;
+	u32 loc, offset, size;
+
+	list_for_each_entry(validator, head, link) {
+		pos = data + validator->offset;
+
+		/* Already done min_size check, no bounds check here */
+		loc = *(u32 *)pos;
+		offset = loc & 0xffff;
+		size = loc >> 16;
+
+		if (likely(validator->flags & VALIDATOR_REL))
+			pos += offset + sizeof(loc);
+		else
+			pos = data + offset;
+
+		pos += size;
+
+		if (unlikely(pos > end))
+			return -EFAULT;
+
+		if (likely(validator->flags & VALIDATOR_ENSURE_NULL))
+			if (unlikely(*(char *)(pos - 1) != '\0'))
+				return -EFAULT;
+	}
+
+	return 0;
+}
+
 /*
  * Writes the user supplied payload out to a trace file.
  */
 static void user_event_ftrace(struct user_event *user, struct iov_iter *i,
-			      void *tpdata)
+			      void *tpdata, bool *faulted)
 {
 	struct trace_event_file *file;
 	struct trace_entry *entry;
 	struct trace_event_buffer event_buffer;
+	size_t size = sizeof(*entry) + i->count;
 
 	file = (struct trace_event_file *)tpdata;
 
@@ -556,17 +649,25 @@ static void user_event_ftrace(struct user_event *user, struct iov_iter *i,
 		return;
 
 	/* Allocates and fills trace_entry, + 1 of this is data payload */
-	entry = trace_event_buffer_reserve(&event_buffer, file,
-					   sizeof(*entry) + i->count);
+	entry = trace_event_buffer_reserve(&event_buffer, file, size);
 
 	if (unlikely(!entry))
 		return;
 
 	if (unlikely(!copy_nofault(entry + 1, i->count, i)))
-		__trace_event_discard_commit(event_buffer.buffer,
-					     event_buffer.event);
-	else
-		trace_event_buffer_commit(&event_buffer);
+		goto discard;
+
+	if (!list_empty(&user->validators) &&
+	    unlikely(user_event_validate(user, entry, size)))
+		goto discard;
+
+	trace_event_buffer_commit(&event_buffer);
+
+	return;
+discard:
+	*faulted = true;
+	__trace_event_discard_commit(event_buffer.buffer,
+				     event_buffer.event);
 }
 
 #ifdef CONFIG_PERF_EVENTS
@@ -621,7 +722,7 @@ static void user_event_bpf(struct user_event *user, struct iov_iter *i)
  * Writes the user supplied payload out to perf ring buffer or eBPF program.
  */
 static void user_event_perf(struct user_event *user, struct iov_iter *i,
-			    void *tpdata)
+			    void *tpdata, bool *faulted)
 {
 	struct hlist_head *perf_head;
 
@@ -644,14 +745,21 @@ static void user_event_perf(struct user_event *user, struct iov_iter *i,
 
 		perf_fetch_caller_regs(regs);
 
-		if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) {
-			perf_swevent_put_recursion_context(context);
-			return;
-		}
+		if (unlikely(!copy_nofault(perf_entry + 1, i->count, i)))
+			goto discard;
+
+		if (!list_empty(&user->validators) &&
+		    unlikely(user_event_validate(user, perf_entry, size)))
+			goto discard;
 
 		perf_trace_buf_submit(perf_entry, size, context,
 				      user->call.event.type, 1, regs,
 				      perf_head, NULL);
+
+		return;
+discard:
+		*faulted = true;
+		perf_swevent_put_recursion_context(context);
 	}
 }
 #endif
@@ -971,6 +1079,7 @@ static int user_event_parse(char *name, char *args, char *flags,
 
 	INIT_LIST_HEAD(&user->class.fields);
 	INIT_LIST_HEAD(&user->fields);
+	INIT_LIST_HEAD(&user->validators);
 
 	user->tracepoint.name = name;
 
@@ -1019,6 +1128,7 @@ static int user_event_parse(char *name, char *args, char *flags,
 	return 0;
 put_user:
 	user_event_destroy_fields(user);
+	user_event_destroy_validators(user);
 	kfree(user);
 	return ret;
 }
@@ -1076,6 +1186,9 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 	if (unlikely(user == NULL))
 		return -ENOENT;
 
+	if (unlikely(i->count < user->min_size))
+		return -EINVAL;
+
 	tp = &user->tracepoint;
 
 	/*
@@ -1087,10 +1200,13 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 		user_event_func_t probe_func;
 		struct iov_iter copy;
 		void *tpdata;
+		bool faulted;
 
 		if (unlikely(fault_in_iov_iter_readable(i, i->count)))
 			return -EFAULT;
 
+		faulted = false;
+
 		rcu_read_lock_sched();
 
 		probe_func_ptr = rcu_dereference_sched(tp->funcs);
@@ -1100,11 +1216,14 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 				copy = *i;
 				probe_func = probe_func_ptr->func;
 				tpdata = probe_func_ptr->data;
-				probe_func(user, &copy, tpdata);
+				probe_func(user, &copy, tpdata, &faulted);
 			} while ((++probe_func_ptr)->func);
 		}
 
 		rcu_read_unlock_sched();
+
+		if (unlikely(faulted))
+			return -EFAULT;
 	}
 
 	return ret;
-- 
2.34.1

[for-next][PATCH 11/16] user_events: Add self-test for ftrace integration

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Tests basic functionality of registering/deregistering, status and
writing data out via ftrace mechanisms within user_events.

Link: https://lkml.kernel.org/r/20220118204326.2169-8-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/testing/selftests/user_events/Makefile  |   9 +
 .../selftests/user_events/ftrace_test.c       | 387 ++++++++++++++++++
 tools/testing/selftests/user_events/settings  |   1 +
 3 files changed, 397 insertions(+)
 create mode 100644 tools/testing/selftests/user_events/Makefile
 create mode 100644 tools/testing/selftests/user_events/ftrace_test.c
 create mode 100644 tools/testing/selftests/user_events/settings

diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile
new file mode 100644
index 000000000000..d66c551a6fe3
--- /dev/null
+++ b/tools/testing/selftests/user_events/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include
+LDLIBS += -lrt -lpthread -lm
+
+TEST_GEN_PROGS = ftrace_test
+
+TEST_FILES := settings
+
+include ../lib.mk
diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c
new file mode 100644
index 000000000000..68010fd7b719
--- /dev/null
+++ b/tools/testing/selftests/user_events/ftrace_test.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events FTrace Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable";
+const char *trace_file = "/sys/kernel/debug/tracing/trace";
+const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format";
+
+static int trace_bytes(void)
+{
+	int fd = open(trace_file, O_RDONLY);
+	char buf[256];
+	int bytes = 0, got;
+
+	if (fd == -1)
+		return -1;
+
+	while (true) {
+		got = read(fd, buf, sizeof(buf));
+
+		if (got == -1)
+			return -1;
+
+		if (got == 0)
+			break;
+
+		bytes += got;
+	}
+
+	close(fd);
+
+	return bytes;
+}
+
+static int skip_until_empty_line(FILE *fp)
+{
+	int c, last = 0;
+
+	while (true) {
+		c = getc(fp);
+
+		if (c == EOF)
+			break;
+
+		if (last == '\n' && c == '\n')
+			return 0;
+
+		last = c;
+	}
+
+	return -1;
+}
+
+static int get_print_fmt(char *buffer, int len)
+{
+	FILE *fp = fopen(fmt_file, "r");
+	char *newline;
+
+	if (!fp)
+		return -1;
+
+	/* Read until empty line (Skip Common) */
+	if (skip_until_empty_line(fp) < 0)
+		goto err;
+
+	/* Read until empty line (Skip Properties) */
+	if (skip_until_empty_line(fp) < 0)
+		goto err;
+
+	/* Read in print_fmt: */
+	if (fgets(buffer, len, fp) == NULL)
+		goto err;
+
+	newline = strchr(buffer, '\n');
+
+	if (newline)
+		*newline = '\0';
+
+	fclose(fp);
+
+	return 0;
+err:
+	fclose(fp);
+
+	return -1;
+}
+
+static int clear(void)
+{
+	int fd = open(data_file, O_RDWR);
+
+	if (fd == -1)
+		return -1;
+
+	if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1)
+		if (errno != ENOENT)
+			return -1;
+
+	close(fd);
+
+	return 0;
+}
+
+static int check_print_fmt(const char *event, const char *expected)
+{
+	struct user_reg reg = {0};
+	char print_fmt[256];
+	int ret;
+	int fd;
+
+	/* Ensure cleared */
+	ret = clear();
+
+	if (ret != 0)
+		return ret;
+
+	fd = open(data_file, O_RDWR);
+
+	if (fd == -1)
+		return fd;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)event;
+
+	/* Register should work */
+	ret = ioctl(fd, DIAG_IOCSREG, &reg);
+
+	close(fd);
+
+	if (ret != 0)
+		return ret;
+
+	/* Ensure correct print_fmt */
+	ret = get_print_fmt(print_fmt, sizeof(print_fmt));
+
+	if (ret != 0)
+		return ret;
+
+	return strcmp(print_fmt, expected);
+}
+
+FIXTURE(user) {
+	int status_fd;
+	int data_fd;
+	int enable_fd;
+};
+
+FIXTURE_SETUP(user) {
+	self->status_fd = open(status_file, O_RDONLY);
+	ASSERT_NE(-1, self->status_fd);
+
+	self->data_fd = open(data_file, O_RDWR);
+	ASSERT_NE(-1, self->data_fd);
+
+	self->enable_fd = -1;
+}
+
+FIXTURE_TEARDOWN(user) {
+	close(self->status_fd);
+	close(self->data_fd);
+
+	if (self->enable_fd != -1) {
+		write(self->enable_fd, "0", sizeof("0"));
+		close(self->enable_fd);
+	}
+
+	ASSERT_EQ(0, clear());
+}
+
+TEST_F(user, register_events) {
+	struct user_reg reg = {0};
+	int page_size = sysconf(_SC_PAGESIZE);
+	char *status_page;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+	status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED,
+			   self->status_fd, 0);
+
+	/* Register should work */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+
+	/* Multiple registers should result in same index */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+
+	/* Ensure disabled */
+	self->enable_fd = open(enable_file, O_RDWR);
+	ASSERT_NE(-1, self->enable_fd);
+	ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0")))
+
+	/* MMAP should work and be zero'd */
+	ASSERT_NE(MAP_FAILED, status_page);
+	ASSERT_NE(NULL, status_page);
+	ASSERT_EQ(0, status_page[reg.status_index]);
+
+	/* Enable event and ensure bits updated in status */
+	ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+	ASSERT_EQ(EVENT_STATUS_FTRACE, status_page[reg.status_index]);
+
+	/* Disable event and ensure bits updated in status */
+	ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0")))
+	ASSERT_EQ(0, status_page[reg.status_index]);
+
+	/* File still open should return -EBUSY for delete */
+	ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event"));
+	ASSERT_EQ(EBUSY, errno);
+
+	/* Delete should work only after close */
+	close(self->data_fd);
+	self->data_fd = open(data_file, O_RDWR);
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event"));
+
+	/* Unmap should work */
+	ASSERT_EQ(0, munmap(status_page, page_size));
+}
+
+TEST_F(user, write_events) {
+	struct user_reg reg = {0};
+	struct iovec io[3];
+	__u32 field1, field2;
+	int before = 0, after = 0;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+	field1 = 1;
+	field2 = 2;
+
+	io[0].iov_base = &reg.write_index;
+	io[0].iov_len = sizeof(reg.write_index);
+	io[1].iov_base = &field1;
+	io[1].iov_len = sizeof(field1);
+	io[2].iov_base = &field2;
+	io[2].iov_len = sizeof(field2);
+
+	/* Register should work */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+
+	/* Write should fail on invalid slot with ENOENT */
+	io[0].iov_base = &field2;
+	io[0].iov_len = sizeof(field2);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(ENOENT, errno);
+	io[0].iov_base = &reg.write_index;
+	io[0].iov_len = sizeof(reg.write_index);
+
+	/* Enable event */
+	self->enable_fd = open(enable_file, O_RDWR);
+	ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+
+	/* Write should make it out to ftrace buffers */
+	before = trace_bytes();
+	ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	after = trace_bytes();
+	ASSERT_GT(after, before);
+}
+
+TEST_F(user, write_fault) {
+	struct user_reg reg = {0};
+	struct iovec io[2];
+	int l = sizeof(__u64);
+	void *anon;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)"__test_event u64 anon";
+
+	anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, anon);
+
+	io[0].iov_base = &reg.write_index;
+	io[0].iov_len = sizeof(reg.write_index);
+	io[1].iov_base = anon;
+	io[1].iov_len = l;
+
+	/* Register should work */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+
+	/* Write should work normally */
+	ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2));
+
+	/* Faulted data should zero fill and work */
+	ASSERT_EQ(0, madvise(anon, l, MADV_DONTNEED));
+	ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2));
+	ASSERT_EQ(0, munmap(anon, l));
+}
+
+TEST_F(user, print_fmt) {
+	int ret;
+
+	ret = check_print_fmt("__test_event __rel_loc char[] data",
+			      "print fmt: \"data=%s\", __get_rel_str(data)");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event __data_loc char[] data",
+			      "print fmt: \"data=%s\", __get_str(data)");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event s64 data",
+			      "print fmt: \"data=%lld\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event u64 data",
+			      "print fmt: \"data=%llu\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event s32 data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event u32 data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event int data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event unsigned int data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event s16 data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event u16 data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event short data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event unsigned short data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event s8 data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event u8 data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event char data",
+			      "print fmt: \"data=%d\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event unsigned char data",
+			      "print fmt: \"data=%u\", REC->data");
+	ASSERT_EQ(0, ret);
+
+	ret = check_print_fmt("__test_event char[4] data",
+			      "print fmt: \"data=%s\", REC->data");
+	ASSERT_EQ(0, ret);
+}
+
+int main(int argc, char **argv)
+{
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/user_events/settings b/tools/testing/selftests/user_events/settings
new file mode 100644
index 000000000000..ba4d85f74cd6
--- /dev/null
+++ b/tools/testing/selftests/user_events/settings
@@ -0,0 +1 @@
+timeout=90
-- 
2.34.1

[for-next][PATCH 12/16] user_events: Add self-test for dynamic_events integration

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Tests matching deletes, creation of basic and complex types. Ensures
common patterns work correctly when interacting with dynamic_events
file.

Link: https://lkml.kernel.org/r/20220118204326.2169-9-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/testing/selftests/user_events/Makefile  |   2 +-
 .../testing/selftests/user_events/dyn_test.c  | 130 ++++++++++++++++++
 2 files changed, 131 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/user_events/dyn_test.c

diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile
index d66c551a6fe3..e824b9c2cae7 100644
--- a/tools/testing/selftests/user_events/Makefile
+++ b/tools/testing/selftests/user_events/Makefile
@@ -2,7 +2,7 @@
 CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include
 LDLIBS += -lrt -lpthread -lm
 
-TEST_GEN_PROGS = ftrace_test
+TEST_GEN_PROGS = ftrace_test dyn_test
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c
new file mode 100644
index 000000000000..d6265d14cd51
--- /dev/null
+++ b/tools/testing/selftests/user_events/dyn_test.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events Dyn Events Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events";
+const char *clear = "!u:__test_event";
+
+static int Append(const char *value)
+{
+	int fd = open(dyn_file, O_RDWR | O_APPEND);
+	int ret = write(fd, value, strlen(value));
+
+	close(fd);
+	return ret;
+}
+
+#define CLEAR() \
+do { \
+	int ret = Append(clear); \
+	if (ret == -1) \
+		ASSERT_EQ(ENOENT, errno); \
+} while (0)
+
+#define TEST_PARSE(x) \
+do { \
+	ASSERT_NE(-1, Append(x)); \
+	CLEAR(); \
+} while (0)
+
+#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x))
+
+FIXTURE(user) {
+};
+
+FIXTURE_SETUP(user) {
+	CLEAR();
+}
+
+FIXTURE_TEARDOWN(user) {
+	CLEAR();
+}
+
+TEST_F(user, basic_types) {
+	/* All should work */
+	TEST_PARSE("u:__test_event u64 a");
+	TEST_PARSE("u:__test_event u32 a");
+	TEST_PARSE("u:__test_event u16 a");
+	TEST_PARSE("u:__test_event u8 a");
+	TEST_PARSE("u:__test_event char a");
+	TEST_PARSE("u:__test_event unsigned char a");
+	TEST_PARSE("u:__test_event int a");
+	TEST_PARSE("u:__test_event unsigned int a");
+	TEST_PARSE("u:__test_event short a");
+	TEST_PARSE("u:__test_event unsigned short a");
+	TEST_PARSE("u:__test_event char[20] a");
+	TEST_PARSE("u:__test_event unsigned char[20] a");
+	TEST_PARSE("u:__test_event char[0x14] a");
+	TEST_PARSE("u:__test_event unsigned char[0x14] a");
+	/* Bad size format should fail */
+	TEST_NPARSE("u:__test_event char[aa] a");
+	/* Large size should fail */
+	TEST_NPARSE("u:__test_event char[9999] a");
+	/* Long size string should fail */
+	TEST_NPARSE("u:__test_event char[0x0000000000001] a");
+}
+
+TEST_F(user, loc_types) {
+	/* All should work */
+	TEST_PARSE("u:__test_event __data_loc char[] a");
+	TEST_PARSE("u:__test_event __data_loc unsigned char[] a");
+	TEST_PARSE("u:__test_event __rel_loc char[] a");
+	TEST_PARSE("u:__test_event __rel_loc unsigned char[] a");
+}
+
+TEST_F(user, size_types) {
+	/* Should work */
+	TEST_PARSE("u:__test_event struct custom a 20");
+	/* Size not specified on struct should fail */
+	TEST_NPARSE("u:__test_event struct custom a");
+	/* Size specified on non-struct should fail */
+	TEST_NPARSE("u:__test_event char a 20");
+}
+
+TEST_F(user, flags) {
+	/* Should work */
+	TEST_PARSE("u:__test_event:BPF_ITER u32 a");
+	/* Forward compat */
+	TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a");
+}
+
+TEST_F(user, matching) {
+	/* Register */
+	ASSERT_NE(-1, Append("u:__test_event struct custom a 20"));
+	/* Should not match */
+	TEST_NPARSE("!u:__test_event struct custom b");
+	/* Should match */
+	TEST_PARSE("!u:__test_event struct custom a");
+	/* Multi field reg */
+	ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b"));
+	/* Non matching cases */
+	TEST_NPARSE("!u:__test_event u32 a");
+	TEST_NPARSE("!u:__test_event u32 b");
+	TEST_NPARSE("!u:__test_event u32 a; u32 ");
+	TEST_NPARSE("!u:__test_event u32 a; u32 a");
+	/* Matching case */
+	TEST_PARSE("!u:__test_event u32 a; u32 b");
+	/* Register */
+	ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b"));
+	/* Ensure trailing semi-colon case */
+	TEST_PARSE("!u:__test_event u32 a; u32 b;");
+}
+
+int main(int argc, char **argv)
+{
+	return test_harness_run(argc, argv);
+}
-- 
2.34.1

[for-next][PATCH 13/16] user_events: Add self-test for perf_event integration

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Tests perf can be attached to and written out correctly. Ensures attach
updates status bits in user programs.

Link: https://lkml.kernel.org/r/20220118204326.2169-10-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/testing/selftests/user_events/Makefile  |   2 +-
 .../testing/selftests/user_events/perf_test.c | 168 ++++++++++++++++++
 2 files changed, 169 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/user_events/perf_test.c

diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile
index e824b9c2cae7..c765d8635d9a 100644
--- a/tools/testing/selftests/user_events/Makefile
+++ b/tools/testing/selftests/user_events/Makefile
@@ -2,7 +2,7 @@
 CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include
 LDLIBS += -lrt -lpthread -lm
 
-TEST_GEN_PROGS = ftrace_test dyn_test
+TEST_GEN_PROGS = ftrace_test dyn_test perf_test
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c
new file mode 100644
index 000000000000..26851d51d6bb
--- /dev/null
+++ b/tools/testing/selftests/user_events/perf_test.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events Perf Events Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <linux/perf_event.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id";
+const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format";
+
+struct event {
+	__u32 index;
+	__u32 field1;
+	__u32 field2;
+};
+
+static long perf_event_open(struct perf_event_attr *pe, pid_t pid,
+			    int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags);
+}
+
+static int get_id(void)
+{
+	FILE *fp = fopen(id_file, "r");
+	int ret, id = 0;
+
+	if (!fp)
+		return -1;
+
+	ret = fscanf(fp, "%d", &id);
+	fclose(fp);
+
+	if (ret != 1)
+		return -1;
+
+	return id;
+}
+
+static int get_offset(void)
+{
+	FILE *fp = fopen(fmt_file, "r");
+	int ret, c, last = 0, offset = 0;
+
+	if (!fp)
+		return -1;
+
+	/* Read until empty line */
+	while (true) {
+		c = getc(fp);
+
+		if (c == EOF)
+			break;
+
+		if (last == '\n' && c == '\n')
+			break;
+
+		last = c;
+	}
+
+	ret = fscanf(fp, "\tfield:u32 field1;\toffset:%d;", &offset);
+	fclose(fp);
+
+	if (ret != 1)
+		return -1;
+
+	return offset;
+}
+
+FIXTURE(user) {
+	int status_fd;
+	int data_fd;
+};
+
+FIXTURE_SETUP(user) {
+	self->status_fd = open(status_file, O_RDONLY);
+	ASSERT_NE(-1, self->status_fd);
+
+	self->data_fd = open(data_file, O_RDWR);
+	ASSERT_NE(-1, self->data_fd);
+}
+
+FIXTURE_TEARDOWN(user) {
+	close(self->status_fd);
+	close(self->data_fd);
+}
+
+TEST_F(user, perf_write) {
+	struct perf_event_attr pe = {0};
+	struct user_reg reg = {0};
+	int page_size = sysconf(_SC_PAGESIZE);
+	char *status_page;
+	struct event event;
+	struct perf_event_mmap_page *perf_page;
+	int id, fd, offset;
+	__u32 *val;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+	status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED,
+			   self->status_fd, 0);
+	ASSERT_NE(MAP_FAILED, status_page);
+
+	/* Register should work */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+	ASSERT_EQ(0, status_page[reg.status_index]);
+
+	/* Id should be there */
+	id = get_id();
+	ASSERT_NE(-1, id);
+	offset = get_offset();
+	ASSERT_NE(-1, offset);
+
+	pe.type = PERF_TYPE_TRACEPOINT;
+	pe.size = sizeof(pe);
+	pe.config = id;
+	pe.sample_type = PERF_SAMPLE_RAW;
+	pe.sample_period = 1;
+	pe.wakeup_events = 1;
+
+	/* Tracepoint attach should work */
+	fd = perf_event_open(&pe, 0, -1, -1, 0);
+	ASSERT_NE(-1, fd);
+
+	perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0);
+	ASSERT_NE(MAP_FAILED, perf_page);
+
+	/* Status should be updated */
+	ASSERT_EQ(EVENT_STATUS_PERF, status_page[reg.status_index]);
+
+	event.index = reg.write_index;
+	event.field1 = 0xc001;
+	event.field2 = 0xc01a;
+
+	/* Ensure write shows up at correct offset */
+	ASSERT_NE(-1, write(self->data_fd, &event, sizeof(event)));
+	val = (void *)(((char *)perf_page) + perf_page->data_offset);
+	ASSERT_EQ(PERF_RECORD_SAMPLE, *val);
+	/* Skip over header and size, move to offset */
+	val += 3;
+	val = (void *)((char *)val) + offset;
+	/* Ensure correct */
+	ASSERT_EQ(event.field1, *val++);
+	ASSERT_EQ(event.field2, *val++);
+}
+
+int main(int argc, char **argv)
+{
+	return test_harness_run(argc, argv);
+}
-- 
2.34.1

[for-next][PATCH 14/16] user_events: Add self-test for validator boundaries

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Tests to ensure validator boundary cases are working correctly within
close and far bounds. Ensures __data_loc and __rel_loc strings are
null terminated and within range. Ensures min size checks work as
expected.

Link: https://lkml.kernel.org/r/20220118204326.2169-11-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../selftests/user_events/ftrace_test.c       | 65 +++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c
index 68010fd7b719..a80fb5ef61d5 100644
--- a/tools/testing/selftests/user_events/ftrace_test.c
+++ b/tools/testing/selftests/user_events/ftrace_test.c
@@ -309,6 +309,71 @@ TEST_F(user, write_fault) {
 	ASSERT_EQ(0, munmap(anon, l));
 }
 
+TEST_F(user, write_validator) {
+	struct user_reg reg = {0};
+	struct iovec io[3];
+	int loc, bytes;
+	char data[8];
+	int before = 0, after = 0;
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)"__test_event __rel_loc char[] data";
+
+	/* Register should work */
+	ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+	ASSERT_EQ(0, reg.write_index);
+	ASSERT_NE(0, reg.status_index);
+
+	io[0].iov_base = &reg.write_index;
+	io[0].iov_len = sizeof(reg.write_index);
+	io[1].iov_base = &loc;
+	io[1].iov_len = sizeof(loc);
+	io[2].iov_base = data;
+	bytes = snprintf(data, sizeof(data), "Test") + 1;
+	io[2].iov_len = bytes;
+
+	/* Undersized write should fail */
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 1));
+	ASSERT_EQ(EINVAL, errno);
+
+	/* Enable event */
+	self->enable_fd = open(enable_file, O_RDWR);
+	ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+
+	/* Full in-bounds write should work */
+	before = trace_bytes();
+	loc = DYN_LOC(0, bytes);
+	ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	after = trace_bytes();
+	ASSERT_GT(after, before);
+
+	/* Out of bounds write should fault (offset way out) */
+	loc = DYN_LOC(1024, bytes);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(EFAULT, errno);
+
+	/* Out of bounds write should fault (offset 1 byte out) */
+	loc = DYN_LOC(1, bytes);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(EFAULT, errno);
+
+	/* Out of bounds write should fault (size way out) */
+	loc = DYN_LOC(0, bytes + 1024);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(EFAULT, errno);
+
+	/* Out of bounds write should fault (size 1 byte out) */
+	loc = DYN_LOC(0, bytes + 1);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(EFAULT, errno);
+
+	/* Non-Null should fault */
+	memset(data, 'A', sizeof(data));
+	loc = DYN_LOC(0, bytes);
+	ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+	ASSERT_EQ(EFAULT, errno);
+}
+
 TEST_F(user, print_fmt) {
 	int ret;
 
-- 
2.34.1

[for-next][PATCH 15/16] user_events: Add sample code for typical usage

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Add sample code for user_events typical usage to show how to register
and monitor status, as well as to write out data.

Link: https://lkml.kernel.org/r/20220118204326.2169-12-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 samples/user_events/Makefile  |  5 ++
 samples/user_events/example.c | 91 +++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)
 create mode 100644 samples/user_events/Makefile
 create mode 100644 samples/user_events/example.c

diff --git a/samples/user_events/Makefile b/samples/user_events/Makefile
new file mode 100644
index 000000000000..7252b589db57
--- /dev/null
+++ b/samples/user_events/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wl,-no-as-needed -Wall -I../../usr/include
+
+example: example.o
+example.o: example.c
diff --git a/samples/user_events/example.c b/samples/user_events/example.c
new file mode 100644
index 000000000000..4f5778e441c0
--- /dev/null
+++ b/samples/user_events/example.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/user_events.h>
+
+/* Assumes debugfs is mounted */
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+
+static int event_status(char **status)
+{
+	int fd = open(status_file, O_RDONLY);
+
+	*status = mmap(NULL, sysconf(_SC_PAGESIZE), PROT_READ,
+		       MAP_SHARED, fd, 0);
+
+	close(fd);
+
+	if (*status == MAP_FAILED)
+		return -1;
+
+	return 0;
+}
+
+static int event_reg(int fd, const char *command, int *status, int *write)
+{
+	struct user_reg reg = {0};
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)command;
+
+	if (ioctl(fd, DIAG_IOCSREG, &reg) == -1)
+		return -1;
+
+	*status = reg.status_index;
+	*write = reg.write_index;
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int data_fd, status, write;
+	char *status_page;
+	struct iovec io[2];
+	__u32 count = 0;
+
+	if (event_status(&status_page) == -1)
+		return errno;
+
+	data_fd = open(data_file, O_RDWR);
+
+	if (event_reg(data_fd, "test u32 count", &status, &write) == -1)
+		return errno;
+
+	/* Setup iovec */
+	io[0].iov_base = &write;
+	io[0].iov_len = sizeof(write);
+	io[1].iov_base = &count;
+	io[1].iov_len = sizeof(count);
+
+ask:
+	printf("Press enter to check status...\n");
+	getchar();
+
+	/* Check if anyone is listening */
+	if (status_page[status]) {
+		/* Yep, trace out our data */
+		writev(data_fd, (const struct iovec *)io, 2);
+
+		/* Increase the count */
+		count++;
+
+		printf("Something was attached, wrote data\n");
+	}
+
+	goto ask;
+
+	return 0;
+}
-- 
2.34.1

[for-next][PATCH 16/16] user_events: Add documentation file

[Steven Rostedt]

From: Beau Belgrave <beaub@linux.microsoft.com>

Add a documentation file about user_events with example code, etc.
explaining how it may be used.

Link: https://lkml.kernel.org/r/20220118204326.2169-13-beaub@linux.microsoft.com

Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/index.rst       |   1 +
 Documentation/trace/user_events.rst | 216 ++++++++++++++++++++++++++++
 2 files changed, 217 insertions(+)
 create mode 100644 Documentation/trace/user_events.rst

diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst
index 3769b9b7aed8..3a47aa8341c6 100644
--- a/Documentation/trace/index.rst
+++ b/Documentation/trace/index.rst
@@ -30,3 +30,4 @@ Linux Tracing Technologies
    stm
    sys-t
    coresight/index
+   user_events
diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst
new file mode 100644
index 000000000000..bddedabaca80
--- /dev/null
+++ b/Documentation/trace/user_events.rst
@@ -0,0 +1,216 @@
+=========================================
+user_events: User-based Event Tracing
+=========================================
+
+:Author: Beau Belgrave
+
+Overview
+--------
+User based trace events allow user processes to create events and trace data
+that can be viewed via existing tools, such as ftrace, perf and eBPF.
+To enable this feature, build your kernel with CONFIG_USER_EVENTS=y.
+
+Programs can view status of the events via
+/sys/kernel/debug/tracing/user_events_status and can both register and write
+data out via /sys/kernel/debug/tracing/user_events_data.
+
+Programs can also use /sys/kernel/debug/tracing/dynamic_events to register and
+delete user based events via the u: prefix. The format of the command to
+dynamic_events is the same as the ioctl with the u: prefix applied.
+
+Typically programs will register a set of events that they wish to expose to
+tools that can read trace_events (such as ftrace and perf). The registration
+process gives back two ints to the program for each event. The first int is the
+status index. This index describes which byte in the
+/sys/kernel/debug/tracing/user_events_status file represents this event. The
+second int is the write index. This index describes the data when a write() or
+writev() is called on the /sys/kernel/debug/tracing/user_events_data file.
+
+The structures referenced in this document are contained with the
+/include/uap/linux/user_events.h file in the source tree.
+
+**NOTE:** *Both user_events_status and user_events_data are under the tracefs
+filesystem and may be mounted at different paths than above.*
+
+Registering
+-----------
+Registering within a user process is done via ioctl() out to the
+/sys/kernel/debug/tracing/user_events_data file. The command to issue is
+DIAG_IOCSREG.
+
+This command takes a struct user_reg as an argument::
+
+  struct user_reg {
+        u32 size;
+        u64 name_args;
+        u32 status_index;
+        u32 write_index;
+  };
+
+The struct user_reg requires two inputs, the first is the size of the structure
+to ensure forward and backward compatibility. The second is the command string
+to issue for registering. Upon success two outputs are set, the status index
+and the write index.
+
+User based events show up under tracefs like any other event under the
+subsystem named "user_events". This means tools that wish to attach to the
+events need to use /sys/kernel/debug/tracing/events/user_events/[name]/enable
+or perf record -e user_events:[name] when attaching/recording.
+
+**NOTE:** *The write_index returned is only valid for the FD that was used*
+
+Command Format
+^^^^^^^^^^^^^^
+The command string format is as follows::
+
+  name[:FLAG1[,FLAG2...]] [Field1[;Field2...]]
+
+Supported Flags
+^^^^^^^^^^^^^^^
+**BPF_ITER** - EBPF programs attached to this event will get the raw iovec
+struct instead of any data copies for max performance.
+
+Field Format
+^^^^^^^^^^^^
+::
+
+  type name [size]
+
+Basic types are supported (__data_loc, u32, u64, int, char, char[20], etc).
+User programs are encouraged to use clearly sized types like u32.
+
+**NOTE:** *Long is not supported since size can vary between user and kernel.*
+
+The size is only valid for types that start with a struct prefix.
+This allows user programs to describe custom structs out to tools, if required.
+
+For example, a struct in C that looks like this::
+
+  struct mytype {
+    char data[20];
+  };
+
+Would be represented by the following field::
+
+  struct mytype myname 20
+
+Deleting
+-----------
+Deleting an event from within a user process is done via ioctl() out to the
+/sys/kernel/debug/tracing/user_events_data file. The command to issue is
+DIAG_IOCSDEL.
+
+This command only requires a single string specifying the event to delete by
+its name. Delete will only succeed if there are no references left to the
+event (in both user and kernel space). User programs should use a separate file
+to request deletes than the one used for registration due to this.
+
+Status
+------
+When tools attach/record user based events the status of the event is updated
+in realtime. This allows user programs to only incur the cost of the write() or
+writev() calls when something is actively attached to the event.
+
+User programs call mmap() on /sys/kernel/debug/tracing/user_events_status to
+check the status for each event that is registered. The byte to check in the
+file is given back after the register ioctl() via user_reg.status_index.
+Currently the size of user_events_status is a single page, however, custom
+kernel configurations can change this size to allow more user based events. In
+all cases the size of the file is a multiple of a page size.
+
+For example, if the register ioctl() gives back a status_index of 3 you would
+check byte 3 of the returned mmap data to see if anything is attached to that
+event.
+
+Administrators can easily check the status of all registered events by reading
+the user_events_status file directly via a terminal. The output is as follows::
+
+  Byte:Name [# Comments]
+  ...
+
+  Active: ActiveCount
+  Busy: BusyCount
+  Max: MaxCount
+
+For example, on a system that has a single event the output looks like this::
+
+  1:test
+
+  Active: 1
+  Busy: 0
+  Max: 4096
+
+If a user enables the user event via ftrace, the output would change to this::
+
+  1:test # Used by ftrace
+
+  Active: 1
+  Busy: 1
+  Max: 4096
+
+**NOTE:** *A status index of 0 will never be returned. This allows user
+programs to have an index that can be used on error cases.*
+
+Status Bits
+^^^^^^^^^^^
+The byte being checked will be non-zero if anything is attached. Programs can
+check specific bits in the byte to see what mechanism has been attached.
+
+The following values are defined to aid in checking what has been attached:
+
+**EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0).
+
+**EVENT_STATUS_PERF** - Bit set if perf/eBPF has been attached (Bit 1).
+
+Writing Data
+------------
+After registering an event the same fd that was used to register can be used
+to write an entry for that event. The write_index returned must be at the start
+of the data, then the remaining data is treated as the payload of the event.
+
+For example, if write_index returned was 1 and I wanted to write out an int
+payload of the event. Then the data would have to be 8 bytes (2 ints) in size,
+with the first 4 bytes being equal to 1 and the last 4 bytes being equal to the
+value I want as the payload.
+
+In memory this would look like this::
+
+  int index;
+  int payload;
+
+User programs might have well known structs that they wish to use to emit out
+as payloads. In those cases writev() can be used, with the first vector being
+the index and the following vector(s) being the actual event payload.
+
+For example, if I have a struct like this::
+
+  struct payload {
+        int src;
+        int dst;
+        int flags;
+  };
+
+It's advised for user programs to do the following::
+
+  struct iovec io[2];
+  struct payload e;
+
+  io[0].iov_base = &write_index;
+  io[0].iov_len = sizeof(write_index);
+  io[1].iov_base = &e;
+  io[1].iov_len = sizeof(e);
+
+  writev(fd, (const struct iovec*)io, 2);
+
+**NOTE:** *The write_index is not emitted out into the trace being recorded.*
+
+EBPF
+----
+EBPF programs that attach to a user-based event tracepoint are given a pointer
+to a struct user_bpf_context. The bpf context contains the data type (which can
+be a user or kernel buffer, or can be a pointer to the iovec) and the data
+length that was emitted (minus the write_index).
+
+Example Code
+------------
+See sample code in samples/user_events.
-- 
2.34.1