tracing/user_events: Introduce multi-format events

Currently user_events supports 1 event with the same name and must have
the exact same format when referenced by multiple programs. This opens
an opportunity for malicious or poorly thought through programs to
create events that others use with different formats. Another scenario
is user programs wishing to use the same event name but add more fields
later when the software updates. Various versions of a program may be
running side-by-side, which is prevented by the current single format
requirement.

Add a new register flag (USER_EVENT_REG_MULTI_FORMAT) which indicates
the user program wishes to use the same user_event name, but may have
several different formats of the event. When this flag is used, create
the underlying tracepoint backing the user_event with a unique name
per-version of the format. It's important that existing ABI users do
not get this logic automatically, even if one of the multi format
events matches the format. This ensures existing programs that create
events and assume the tracepoint name will match exactly continue to
work as expected. Add logic to only check multi-format events with
other multi-format events and single-format events to only check
single-format events during find.

Change system name of the multi-format event tracepoint to ensure that
multi-format events are isolated completely from single-format events.
This prevents single-format names from conflicting with multi-format
events if they end with the same suffix as the multi-format events.

Add a register_name (reg_name) to the user_event struct which allows for
split naming of events. We now have the name that was used to register
within user_events as well as the unique name for the tracepoint. Upon
registering events ensure matches based on first the reg_name, followed
by the fields and format of the event. This allows for multiple events
with the same registered name to have different formats. The underlying
tracepoint will have a unique name in the format of {reg_name}.{unique_id}.

For example, if both "test u32 value" and "test u64 value" are used with
the USER_EVENT_REG_MULTI_FORMAT the system would have 2 unique
tracepoints. The dynamic_events file would then show the following:
u:test u64 count
u:test u32 count

The actual tracepoint names look like this:
test.0
test.1

Both would be under the new user_events_multi system name to prevent the
older ABI from being used to squat on multi-formatted events and block
their use.

Deleting events via "!u:test u64 count" would only delete the first
tracepoint that matched that format. When the delete ABI is used all
events with the same name will be attempted to be deleted. If
per-version deletion is required, user programs should either not use
persistent events or delete them via dynamic_events.

Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-3-beaub@linux.microsoft.com

Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

tracing/user_events: Allow events to persist for perfmon_capable users

There are several scenarios that have come up where having a user_event
persist even if the process that registered it exits. The main one is
having a daemon create events on bootup that shouldn't get deleted if
the daemon has to exit or reload. Another is within OpenTelemetry
exporters, they wish to potentially check if a user_event exists on the
system to determine if exporting the data out should occur. The
user_event in this case must exist even in the absence of the owning
process running (such as the above daemon case).

Expose the previously internal flag USER_EVENT_REG_PERSIST to user
processes. Upon register or delete of events with this flag, ensure the
user is perfmon_capable to prevent random user processes with access to
tracefs from creating events that persist after exit.

Link: https://lkml.kernel.org/r/20230912180704.1284-2-beaub@linux.microsoft.com

Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

tracing/user_events: Align structs with tabs for readability

Add tabs to make struct members easier to read and unify the style of
the code.

Link: https://lkml.kernel.org/r/20230328235219.203-13-beaub@linux.microsoft.com

Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

tracing/user_events: Add ioctl for disabling addresses

Enablements are now tracked by the lifetime of the task/mm. User
processes need to be able to disable their addresses if tracing is
requested to be turned off. Before unmapping the page would suffice.
However, we now need a stronger contract. Add an ioctl to enable this.

A new flag bit is added, freeing, to user_event_enabler to ensure that
if the event is attempted to be removed while a fault is being handled
that the remove is delayed until after the fault is reattempted.

Link: https://lkml.kernel.org/r/20230328235219.203-6-beaub@linux.microsoft.com

Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

tracing/user_events: Use remote writes for event enablement

As part of the discussions for user_events aligned with user space
tracers, it was determined that user programs should register a aligned
value to set or clear a bit when an event becomes enabled. Currently a
shared page is being used that requires mmap(). Remove the shared page
implementation and move to a user registered address implementation.

In this new model during the event registration from user programs 3 new
values are specified. The first is the address to update when the event
is either enabled or disabled. The second is the bit to set/clear to
reflect the event being enabled. The third is the size of the value at
the specified address.

This allows for a local 32/64-bit value in user programs to support
both kernel and user tracers. As an example, setting bit 31 for kernel
tracers when the event becomes enabled allows for user tracers to use
the other bits for ref counts or other flags. The kernel side updates
the bit atomically, user programs need to also update these values
atomically.

User provided addresses must be aligned on a natural boundary, this
allows for single page checking and prevents odd behaviors such as a
enable value straddling 2 pages instead of a single page. Currently
page faults are only logged, future patches will handle these.

Link: https://lkml.kernel.org/r/20230328235219.203-4-beaub@linux.microsoft.com

Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

tracing/user_events: Split header into uapi and kernel

The UAPI parts need to be split out from the kernel parts of user_events
now that other parts of the kernel will reference it. Do so by moving
the existing include/linux/user_events.h into
include/uapi/linux/user_events.h.

Link: https://lkml.kernel.org/r/20230328235219.203-2-beaub@linux.microsoft.com

Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

user_events: Add minimal support for trace_event into ftrace

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>