Recording stacktraces is very useful, but the size of 16 deep is very
restrictive. For example, in seeing where tasks schedule out in a non
running state, the following can be used:
~# cd /sys/kernel/tracing
~# echo 'hist:keys=common_stacktrace:vals=hitcount if prev_state & 3' > events/sched/sched_switch/trigger
~# cat events/sched/sched_switch/hist
[..]
{ common_stacktrace:
__schedule+0xdc0/0x1860
schedule+0x27/0xd0
schedule_timeout+0xb5/0x100
wait_for_completion+0x8a/0x140
xfs_buf_iowait+0x20/0xd0 [xfs]
xfs_buf_read_map+0x103/0x250 [xfs]
xfs_trans_read_buf_map+0x161/0x310 [xfs]
xfs_btree_read_buf_block+0xa0/0x120 [xfs]
xfs_btree_lookup_get_block+0xa3/0x1e0 [xfs]
xfs_btree_lookup+0xea/0x530 [xfs]
xfs_alloc_fixup_trees+0x72/0x570 [xfs]
xfs_alloc_ag_vextent_size+0x67f/0x800 [xfs]
xfs_alloc_vextent_iterate_ags.constprop.0+0x52/0x230 [xfs]
xfs_alloc_vextent_start_ag+0x9d/0x1b0 [xfs]
xfs_bmap_btalloc+0x2af/0x680 [xfs]
xfs_bmapi_allocate+0xdb/0x2c0 [xfs]
} hitcount: 1
[..]
The above stops at 16 functions where knowing more would be useful. As the
allocated storage for stacks is the same for strings, and that size is 256
bytes, there is a lot of space not being used for stacktraces.
16 * 8 = 128
Up the size to 31 (it requires the last slot to be zero, so it can't be 32).
Also change the BUILD_BUG_ON() to allow the size of the stacktrace storage
to be equal to the max size. One slot is used to hold the number of
elements in the stack.
BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX);
Change that from ">=" to just ">", as now they are equal.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260123105415.2be26bf4@gandalf.local.home
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When debugging the synthetic events, being able to function trace its
functions is very useful (now that CONFIG_FUNCTION_SELF_TRACING is
available). For some reason trace_event_raw_event_synth() was marked as
"notrace", which was totally unnecessary as all of the tracing directory
had function tracing disabled until the recent FUNCTION_SELF_TRACING was
added.
Remove the notrace annotation from trace_event_raw_event_synth() as
there's no reason to not trace it when tracing synthetic event functions.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260122204526.068a98c9@gandalf.local.home
Acked-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When CONFIG_HIST_TRIGGERS_DEBUG is enabled, each trace event has a
"hist_debug" file that explains the histogram internal data. This is very
useful for debugging histograms.
One bit of data that was missing from this file was what function a
histogram field uses to process its data. The hist_field structure now has
a fn_num that is used by a switch statement in hist_fn_call() to call a
function directly (to avoid spectre mitigations).
Instead of displaying that number, create a string array that maps to the
histogram function enums so that the function for a field may be
displayed:
~# cat /sys/kernel/tracing/events/sched/sched_switch/hist_debug
[..]
hist_data: 0000000043d62762
n_vals: 2
n_keys: 1
n_fields: 3
val fields:
hist_data->fields[0]:
flags:
VAL: HIST_FIELD_FL_HITCOUNT
type: u64
size: 8
is_signed: 0
function: hist_field_counter()
hist_data->fields[1]:
flags:
HIST_FIELD_FL_VAR
var.name: __arg_3921_2
var.idx (into tracing_map_elt.vars[]): 0
type: unsigned long[]
size: 128
is_signed: 0
function: hist_field_nop()
key fields:
hist_data->fields[2]:
flags:
HIST_FIELD_FL_KEY
ftrace_event_field name: prev_pid
type: pid_t
size: 8
is_signed: 1
function: hist_field_s32()
The "function:" field above is added.
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260122203822.58df4d80@gandalf.local.home
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Tested-by: Tom Zanussi <zanussi@kernel.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In enable_boot_kprobe_events(), it returns directly when trace kprobes is
empty, thereby reducing the function's execution time. This function may
otherwise wait for the event_mutex lock for tens of milliseconds on certain
machines, which is unnecessary when trace kprobes is empty.
Link: https://lore.kernel.org/all/20260127053848.108473-1-sunliming@linux.dev/
Signed-off-by: sunliming <sunliming@kylinos.cn>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Using single ftrace_ops for direct calls update instead of allocating
ftrace_ops object for each trampoline.
With single ftrace_ops object we can use update_ftrace_direct_* api
that allows multiple ip sites updates on single ftrace_ops object.
Adding HAVE_SINGLE_FTRACE_DIRECT_OPS config option to be enabled on
each arch that supports this.
At the moment we can enable this only on x86 arch, because arm relies
on ftrace_ops object representing just single trampoline image (stored
in ftrace_ops::direct_call). Archs that do not support this will continue
to use *_ftrace_direct api.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20251230145010.103439-10-jolsa@kernel.org
Adding update_ftrace_direct_mod function that modifies all entries
(ip -> direct) provided in hash argument to direct ftrace ops and
updates its attachments.
The difference to current modify_ftrace_direct is:
- hash argument that allows to modify multiple ip -> direct
entries at once
This change will allow us to have simple ftrace_ops for all bpf
direct interface users in following changes.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20251230145010.103439-7-jolsa@kernel.org
Adding update_ftrace_direct_del function that removes all entries
(ip -> addr) provided in hash argument to direct ftrace ops and
updates its attachments.
The difference to current unregister_ftrace_direct is
- hash argument that allows to unregister multiple ip -> direct
entries at once
- we can call update_ftrace_direct_del multiple times on the
same ftrace_ops object, becase we do not need to unregister
all entries at once, we can do it gradualy with the help of
ftrace_update_ops function
This change will allow us to have simple ftrace_ops for all bpf
direct interface users in following changes.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20251230145010.103439-6-jolsa@kernel.org
Adding update_ftrace_direct_add function that adds all entries
(ip -> addr) provided in hash argument to direct ftrace ops
and updates its attachments.
The difference to current register_ftrace_direct is
- hash argument that allows to register multiple ip -> direct
entries at once
- we can call update_ftrace_direct_add multiple times on the
same ftrace_ops object, becase after first registration with
register_ftrace_function_nolock, it uses ftrace_update_ops to
update the ftrace_ops object
This change will allow us to have simple ftrace_ops for all bpf
direct interface users in following changes.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20251230145010.103439-5-jolsa@kernel.org
At the moment the we allow the jmp attach only for ftrace_ops that
has FTRACE_OPS_FL_JMP set. This conflicts with following changes
where we use single ftrace_ops object for all direct call sites,
so all could be be attached via just call or jmp.
We already limit the jmp attach support with config option and bit
(LSB) set on the trampoline address. It turns out that's actually
enough to limit the jmp attach for architecture and only for chosen
addresses (with LSB bit set).
Each user of register_ftrace_direct or modify_ftrace_direct can set
the trampoline bit (LSB) to indicate it has to be attached by jmp.
The bpf trampoline generation code uses trampoline flags to generate
jmp-attach specific code and ftrace inner code uses the trampoline
bit (LSB) to handle return from jmp attachment, so there's no harm
to remove the FTRACE_OPS_FL_JMP bit.
The fexit/fmodret performance stays the same (did not drop),
current code:
fentry : 77.904 ± 0.546M/s
fexit : 62.430 ± 0.554M/s
fmodret : 66.503 ± 0.902M/s
with this change:
fentry : 80.472 ± 0.061M/s
fexit : 63.995 ± 0.127M/s
fmodret : 67.362 ± 0.175M/s
Fixes: 25e4e3565d ("ftrace: Introduce FTRACE_OPS_FL_JMP")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20251230145010.103439-2-jolsa@kernel.org
When /proc/sys/kernel/traceoff_on_warning is set to 1, the top level
tracing buffer is disabled when a warning happens. This is very useful
when debugging and want the tracing buffer to stop taking new data when a
warning triggers keeping the events that lead up to the warning from being
overwritten.
Now that there is also a persistent ring buffer and an option to have
trace_printk go to that buffer, the same holds true for that buffer. A
warning could happen just before a crash but still write enough events to
lose the events that lead up to the first warning that was the reason for
the crash.
When /proc/sys/kernel/traceoff_on_warning is set to 1 and a warning is
triggered, not only disable the top level tracing buffer, but also disable
the buffer that trace_printk()s are written to.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://patch.msgid.link/20260121093858.5c5d7e7b@gandalf.local.home
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
By doing:
# trace-cmd sqlhist -e -n futex_wait select TIMESTAMP_DELTA_USECS as lat from sys_enter_futex as start join sys_exit_futex as end on start.common_pid = end.common_pid
and
# trace-cmd start -e futex_wait -f 'lat > 100' -e page_pool_state_release -f 'pfn == 1'
The output of the show_event_trigger and show_event_filter files are well
aligned because of the inconsistent 'tab' spacing:
~# cat /sys/kernel/tracing/show_event_triggers
syscalls:sys_exit_futex hist:keys=common_pid:vals=hitcount:__lat_12046_2=common_timestamp.usecs-$__arg_12046_1:sort=hitcount:size=2048:clock=global:onmatch(syscalls.sys_enter_futex).trace(futex_wait,$__lat_12046_2) [active]
syscalls:sys_enter_futex hist:keys=common_pid:vals=hitcount:__arg_12046_1=common_timestamp.usecs:sort=hitcount:size=2048:clock=global [active]
~# cat /sys/kernel/tracing/show_event_filters
synthetic:futex_wait (lat > 100)
page_pool:page_pool_state_release (pfn == 1)
This makes it not so easy to read. Instead, force the spacing to be at
least 32 bytes from the beginning (one space if the system:event is longer
than 30 bytes):
~# cat /sys/kernel/tracing/show_event_triggers
syscalls:sys_exit_futex hist:keys=common_pid:vals=hitcount:__lat_8125_2=common_timestamp.usecs-$__arg_8125_1:sort=hitcount:size=2048:clock=global:onmatch(syscalls.sys_enter_futex).trace(futex_wait,$__lat_8125_2) [active]
syscalls:sys_enter_futex hist:keys=common_pid:vals=hitcount:__arg_8125_1=common_timestamp.usecs:sort=hitcount:size=2048:clock=global [active]
~# cat /sys/kernel/tracing/show_event_filters
synthetic:futex_wait (lat > 100)
page_pool:page_pool_state_release (pfn == 1)
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260112153408.18373e73@gandalf.local.home
Reviewed-by: Aaron Tomlin <atomlin@atomlin.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Avoid running the wakeup irq_work on an isolated CPU. Since the wakeup can
run on any CPU, let's pick a housekeeping CPU to do the job.
This change reduces additional noise when tracing isolated CPUs. For
example, the following ipi_send_cpu stack trace was captured with
nohz_full=2 on the isolated CPU:
<idle>-0 [002] d.h4. 1255.379293: ipi_send_cpu: cpu=2 callsite=irq_work_queue+0x2d/0x50 callback=rb_wake_up_waiters+0x0/0x80
<idle>-0 [002] d.h4. 1255.379329: <stack trace>
=> trace_event_raw_event_ipi_send_cpu
=> __irq_work_queue_local
=> irq_work_queue
=> ring_buffer_unlock_commit
=> trace_buffer_unlock_commit_regs
=> trace_event_buffer_commit
=> trace_event_raw_event_x86_irq_vector
=> __sysvec_apic_timer_interrupt
=> sysvec_apic_timer_interrupt
=> asm_sysvec_apic_timer_interrupt
=> pv_native_safe_halt
=> default_idle
=> default_idle_call
=> do_idle
=> cpu_startup_entry
=> start_secondary
=> common_startup_64
The IRQ work interrupt alone adds considerable noise, but the impact can
get even worse with PREEMPT_RT, because the IRQ work interrupt is then
handled by a separate kernel thread. This requires a task switch and makes
tracing useless for analyzing latency on an isolated CPU.
After applying the patch, the trace is similar, but ipi_send_cpu always
targets a non-isolated CPU.
Unfortunately, irq_work_queue_on() is not NMI-safe. When running in NMI
context, fall back to queuing the irq work on the local CPU.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Clark Williams <clrkwllms@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Link: https://patch.msgid.link/20260108132132.2473515-1-ptesarik@suse.com
Signed-off-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
To audit active event triggers, userspace currently must traverse the
events/ directory and read each individual trigger file. This is
cumbersome for system-wide auditing or debugging.
Introduce "show_event_triggers" at the trace root directory. This file
displays all events that currently have one or more triggers applied,
alongside the trigger configuration, in a consolidated
system:event [tab] trigger format.
The implementation leverages the existing trace_event_file iterators
and uses the trigger's own print() operation to ensure output
consistency with the per-event trigger files.
Link: https://patch.msgid.link/20260105142939.2655342-3-atomlin@atomlin.com
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Currently, to audit active Ftrace event filters, userspace must
recursively traverse the events/ directory and read each individual
filter file. This is inefficient for monitoring tools and debugging.
Introduce "show_event_filters" at the trace root directory. This file
displays all events that currently have a filter applied, alongside the
actual filter string, in a consolidated system:event [tab] filter
format.
The implementation reuses the existing trace_event_file iterators to
ensure atomic traversal of the event list and utilises guard(rcu)() for
automatic, scope-based protection when accessing volatile filter
strings.
Link: https://patch.msgid.link/20260105142939.2655342-2-atomlin@atomlin.com
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This patch continues the effort to refactor workqueue APIs, which has begun
with the changes introducing new workqueues and a new alloc_workqueue flag:
commit 128ea9f6cc ("workqueue: Add system_percpu_wq and system_dfl_wq")
commit 930c2ea566 ("workqueue: Add new WQ_PERCPU flag")
The point of the refactoring is to eventually alter the default behavior of
workqueues to become unbound by default so that their workload placement is
optimized by the scheduler.
Before that to happen after a careful review and conversion of each individual
case, workqueue users must be converted to the better named new workqueues with
no intended behaviour changes:
system_wq -> system_percpu_wq
system_unbound_wq -> system_dfl_wq
This specific workflow has no benefits being per-cpu, so instead of
system_percpu_wq the new unbound workqueue has been used (system_dfl_wq).
This way the old obsolete workqueues (system_wq, system_unbound_wq) can be
removed in the future.
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251230142820.173712-1-marco.crivellari@suse.com
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Add support for displaying bitmasks in human-readable list format (e.g.,
0,2-5,7) in addition to the default hexadecimal bitmap representation.
This is particularly useful when tracing CPU masks and other large
bitmasks where individual bit positions are more meaningful than their
hexadecimal encoding.
When the "bitmask-list" option is enabled, the printk "%*pbl" format
specifier is used to render bitmasks as comma-separated ranges, making
trace output easier to interpret for complex CPU configurations and
large bitmask values.
Link: https://patch.msgid.link/20251226160724.2246493-2-atomlin@atomlin.com
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Memory allocated with trigger_data_alloc() requires trigger_data_free()
for proper cleanup.
Replace kfree() with trigger_data_free() to fix this.
Found via static analysis and code review.
This isn't a real bug due to the current code basically being an open
coded version of trigger_data_free() without the synchronization. The
synchronization isn't needed as this is the error path of creation and
there's nothing to synchronize against yet. Replace the kfree() to be
consistent with the allocation.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Tom Zanussi <zanussi@kernel.org>
Link: https://patch.msgid.link/20251211100058.2381268-1-linmq006@gmail.com
Fixes: e1f187d09e ("tracing: Have existing event_command.parse() implementations use helpers")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
If fsession exists, we will use the bit (1 << BPF_TRAMP_IS_RETURN_SHIFT)
in ((u64 *)ctx)[-1] to store the "is_return" flag.
The logic of bpf_session_is_return() for fsession is implemented in the
verifier by inline following code:
bool bpf_session_is_return(void *ctx)
{
return (((u64 *)ctx)[-1] >> BPF_TRAMP_IS_RETURN_SHIFT) & 1;
}
Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Co-developed-by: Leon Hwang <leon.hwang@linux.dev>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20260124062008.8657-5-dongml2@chinatelecom.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
For now, ((u64 *)ctx)[-1] is used to store the nr_args in the trampoline.
However, 1 byte is enough to store such information. Therefore, we use
only the least significant byte of ((u64 *)ctx)[-1] to store the nr_args,
and reserve the rest for other usages.
Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Link: https://lore.kernel.org/r/20260124062008.8657-3-dongml2@chinatelecom.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When funcgraph-args and funcgraph-retaddr are both enabled, many kernel
functions display invalid parameters in trace logs.
The issue occurs because print_graph_retval() passes a mismatched args
pointer to print_function_args(). Fix this by retrieving the correct
args pointer using the FGRAPH_ENTRY_ARGS() macro.
Link: https://patch.msgid.link/20260112021601.1300479-1-dolinux.peng@gmail.com
Fixes: f83ac7544f ("function_graph: Enable funcgraph-args and funcgraph-retaddr to work simultaneously")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Donglin Peng <pengdonglin@xiaomi.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When creating a synthetic event based on an existing synthetic event that
had a stacktrace field and the new synthetic event used that field a
kernel crash occurred:
~# cd /sys/kernel/tracing
~# echo 's:stack unsigned long stack[];' > dynamic_events
~# echo 'hist:keys=prev_pid:s0=common_stacktrace if prev_state & 3' >> events/sched/sched_switch/trigger
~# echo 'hist:keys=next_pid:s1=$s0:onmatch(sched.sched_switch).trace(stack,$s1)' >> events/sched/sched_switch/trigger
The above creates a synthetic event that takes a stacktrace when a task
schedules out in a non-running state and passes that stacktrace to the
sched_switch event when that task schedules back in. It triggers the
"stack" synthetic event that has a stacktrace as its field (called "stack").
~# echo 's:syscall_stack s64 id; unsigned long stack[];' >> dynamic_events
~# echo 'hist:keys=common_pid:s2=stack' >> events/synthetic/stack/trigger
~# echo 'hist:keys=common_pid:s3=$s2,i0=id:onmatch(synthetic.stack).trace(syscall_stack,$i0,$s3)' >> events/raw_syscalls/sys_exit/trigger
The above makes another synthetic event called "syscall_stack" that
attaches the first synthetic event (stack) to the sys_exit trace event and
records the stacktrace from the stack event with the id of the system call
that is exiting.
When enabling this event (or using it in a historgram):
~# echo 1 > events/synthetic/syscall_stack/enable
Produces a kernel crash!
BUG: unable to handle page fault for address: 0000000000400010
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP PTI
CPU: 6 UID: 0 PID: 1257 Comm: bash Not tainted 6.16.3+deb14-amd64 #1 PREEMPT(lazy) Debian 6.16.3-1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
RIP: 0010:trace_event_raw_event_synth+0x90/0x380
Code: c5 00 00 00 00 85 d2 0f 84 e1 00 00 00 31 db eb 34 0f 1f 00 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 2e 0f 1f 84 00 00 00 00 00 <49> 8b 04 24 48 83 c3 01 8d 0c c5 08 00 00 00 01 cd 41 3b 5d 40 0f
RSP: 0018:ffffd2670388f958 EFLAGS: 00010202
RAX: ffff8ba1065cc100 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000001 RSI: fffff266ffda7b90 RDI: ffffd2670388f9b0
RBP: 0000000000000010 R08: ffff8ba104e76000 R09: ffffd2670388fa50
R10: ffff8ba102dd42e0 R11: ffffffff9a908970 R12: 0000000000400010
R13: ffff8ba10a246400 R14: ffff8ba10a710220 R15: fffff266ffda7b90
FS: 00007fa3bc63f740(0000) GS:ffff8ba2e0f48000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000400010 CR3: 0000000107f9e003 CR4: 0000000000172ef0
Call Trace:
<TASK>
? __tracing_map_insert+0x208/0x3a0
action_trace+0x67/0x70
event_hist_trigger+0x633/0x6d0
event_triggers_call+0x82/0x130
trace_event_buffer_commit+0x19d/0x250
trace_event_raw_event_sys_exit+0x62/0xb0
syscall_exit_work+0x9d/0x140
do_syscall_64+0x20a/0x2f0
? trace_event_raw_event_sched_switch+0x12b/0x170
? save_fpregs_to_fpstate+0x3e/0x90
? _raw_spin_unlock+0xe/0x30
? finish_task_switch.isra.0+0x97/0x2c0
? __rseq_handle_notify_resume+0xad/0x4c0
? __schedule+0x4b8/0xd00
? restore_fpregs_from_fpstate+0x3c/0x90
? switch_fpu_return+0x5b/0xe0
? do_syscall_64+0x1ef/0x2f0
? do_fault+0x2e9/0x540
? __handle_mm_fault+0x7d1/0xf70
? count_memcg_events+0x167/0x1d0
? handle_mm_fault+0x1d7/0x2e0
? do_user_addr_fault+0x2c3/0x7f0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
The reason is that the stacktrace field is not labeled as such, and is
treated as a normal field and not as a dynamic event that it is.
In trace_event_raw_event_synth() the event is field is still treated as a
dynamic array, but the retrieval of the data is considered a normal field,
and the reference is just the meta data:
// Meta data is retrieved instead of a dynamic array
str_val = (char *)(long)var_ref_vals[val_idx];
// Then when it tries to process it:
len = *((unsigned long *)str_val) + 1;
It triggers a kernel page fault.
To fix this, first when defining the fields of the first synthetic event,
set the filter type to FILTER_STACKTRACE. This is used later by the second
synthetic event to know that this field is a stacktrace. When creating
the field of the new synthetic event, have it use this FILTER_STACKTRACE
to know to create a stacktrace field to copy the stacktrace into.
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Tom Zanussi <zanussi@kernel.org>
Link: https://patch.msgid.link/20260122194824.6905a38e@gandalf.local.home
Fixes: 00cf3d672a ("tracing: Allow synthetic events to pass around stacktraces")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
For now, bpf_get_func_arg() and bpf_get_func_arg_cnt() is not supported by
the BPF_TRACE_RAW_TP, which is not convenient to get the argument of the
tracepoint, especially for the case that the position of the arguments in
a tracepoint can change.
The target tracepoint BTF type id is specified during loading time,
therefore we can get the function argument count from the function
prototype instead of the stack.
Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20260121044348.113201-2-dongml2@chinatelecom.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
After commit 37cce22dbd ("bpf: verifier: Refactor helper access type tracking"),
the verifier started relying on the access type flags in helper
function prototypes to perform memory access optimizations.
Currently, several helper functions utilizing ARG_PTR_TO_MEM lack the
corresponding MEM_RDONLY or MEM_WRITE flags. This omission causes the
verifier to incorrectly assume that the buffer contents are unchanged
across the helper call. Consequently, the verifier may optimize away
subsequent reads based on this wrong assumption, leading to correctness
issues.
For bpf_get_stack_proto_raw_tp, the original MEM_RDONLY was incorrect
since the helper writes to the buffer. Change it to ARG_PTR_TO_UNINIT_MEM
which correctly indicates write access to potentially uninitialized memory.
Similar issues were recently addressed for specific helpers in commit
ac44dcc788 ("bpf: Fix verifier assumptions of bpf_d_path's output buffer")
and commit 2eb7648558 ("bpf: Specify access type of bpf_sysctl_get_name args").
Fix these prototypes by adding the correct memory access flags.
Fixes: 37cce22dbd ("bpf: verifier: Refactor helper access type tracking")
Co-developed-by: Shuran Liu <electronlsr@gmail.com>
Signed-off-by: Shuran Liu <electronlsr@gmail.com>
Co-developed-by: Peili Gao <gplhust955@gmail.com>
Signed-off-by: Peili Gao <gplhust955@gmail.com>
Co-developed-by: Haoran Ni <haoran.ni.cs@gmail.com>
Signed-off-by: Haoran Ni <haoran.ni.cs@gmail.com>
Signed-off-by: Zesen Liu <ftyghome@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260120-helper_proto-v3-1-27b0180b4e77@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add __force annotations to casts that convert between __user and kernel
address spaces. These casts are intentional:
- In bpf_send_signal_common(), the value is stored in si_value.sival_ptr
which is typed as void __user *, but the value comes from a BPF
program parameter.
- In the bpf_*_dynptr() kfuncs, user pointers are cast to const void *
before being passed to copy helper functions that correctly handle
the user address space through copy_from_user variants.
Without __force, sparse reports:
warning: cast removes address space '__user' of expression
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20260115184509.3585759-1-mykyta.yatsenko5@gmail.com
Closes: https://lore.kernel.org/oe-kbuild-all/202601131740.6C3BdBaB-lkp@intel.com/
Mahe reported issue with bpf_override_return helper not working when
executed from kprobe.multi bpf program on arm.
The problem is that on arm we use alternate storage for pt_regs object
that is passed to bpf_prog_run and if any register is changed (which
is the case of bpf_override_return) it's not propagated back to actual
pt_regs object.
Fixing this by introducing and calling ftrace_partial_regs_update function
to propagate the values of changed registers (ip and stack).
Reported-by: Mahe Tardy <mahe.tardy@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/bpf/20260112121157.854473-1-jolsa@kernel.org
The pg_remaining calculation in ftrace_process_locs() assumes that
ENTRIES_PER_PAGE multiplied by 2^order equals the actual capacity of the
allocated page group. However, ENTRIES_PER_PAGE is PAGE_SIZE / ENTRY_SIZE
(integer division). When PAGE_SIZE is not a multiple of ENTRY_SIZE (e.g.
4096 / 24 = 170 with remainder 16), high-order allocations (like 256 pages)
have significantly more capacity than 256 * 170. This leads to pg_remaining
being underestimated, which in turn makes skip (derived from skipped -
pg_remaining) larger than expected, causing the WARN(skip != remaining)
to trigger.
Extra allocated pages for ftrace: 2 with 654 skipped
WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:7295 ftrace_process_locs+0x5bf/0x5e0
A similar problem in ftrace_allocate_records() can result in allocating
too many pages. This can trigger the second warning in
ftrace_process_locs().
Extra allocated pages for ftrace
WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:7276 ftrace_process_locs+0x548/0x580
Use the actual capacity of a page group to determine the number of pages
to allocate. Have ftrace_allocate_pages() return the number of allocated
pages to avoid having to calculate it. Use the actual page group capacity
when validating the number of unused pages due to skipped entries.
Drop the definition of ENTRIES_PER_PAGE since it is no longer used.
Cc: stable@vger.kernel.org
Fixes: 4a3efc6baf ("ftrace: Update the mcount_loc check of skipped entries")
Link: https://patch.msgid.link/20260113152243.3557219-1-linux@roeck-us.net
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cross-merge BPF and other fixes after downstream PR.
No conflicts.
Adjacent:
Auto-merging MAINTAINERS
Auto-merging Makefile
Auto-merging kernel/bpf/verifier.c
Auto-merging kernel/sched/ext.c
Auto-merging mm/memcontrol.c
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The header files generated by dot2c currently create enums for states
and events assigning the first element to 0. This is superfluous as it
happens automatically if no value is specified.
Also it doesn't add a comma to the last enum elements, which slightly
complicates the diff if states or events are added.
Remove the assignment to 0 and add a comma to last elements, this
simplifies the logic for the code generator.
Reviewed-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/r/20251126104241.291258-8-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
The da_monitor helper functions are generated from macros of the type:
DECLARE_DA_FUNCTION(name, type) \
static void da_func_x_##name(type arg) {} \
static void da_func_y_##name(type arg) {} \
This is good to minimise code duplication but the long macros made of
skipped end of lines is rather hard to parse. Since functions are
static, the advantage of naming them differently for each monitor is
minimal.
Refactor the da_monitor.h file to minimise macros, instead of declaring
functions from macros, we simply declare them with the same name for all
monitors (e.g. da_func_x) and for any remaining reference to the monitor
name (e.g. tracepoints, enums, global variables) we use the CONCATENATE
macro.
In this way the file is much easier to maintain while keeping the same
generality.
Functions depending on the monitor types are now conditionally compiled
according to the value of RV_MON_TYPE, which must be defined in the
monitor source.
The monitor type can be specified as in the original implementation,
although it's best to keep the default implementation (unsigned char) as
not all parts of code support larger data types, and likely there's no
need.
We keep the empty macro definitions to ease review of this change with
diff tools, but cleanup is required.
Also adapt existing monitors to keep the build working.
Reviewed-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/r/20251126104241.291258-2-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
When user resize all trace ring buffer through file 'buffer_size_kb',
then in ring_buffer_resize(), kernel allocates buffer pages for each
cpu in a loop.
If the kernel preemption model is PREEMPT_NONE and there are many cpus
and there are many buffer pages to be freed, it may not give up cpu
for a long time and finally cause a softlockup.
To avoid it, call cond_resched() after each cpu buffer free as Commit
f6bd2c9248 ("ring-buffer: Avoid softlockup in ring_buffer_resize()")
does.
Detailed call trace as follow:
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: 24-....: (14837 ticks this GP) idle=521c/1/0x4000000000000000 softirq=230597/230597 fqs=5329
rcu: (t=15004 jiffies g=26003221 q=211022 ncpus=96)
CPU: 24 UID: 0 PID: 11253 Comm: bash Kdump: loaded Tainted: G EL 6.18.2+ #278 NONE
pc : arch_local_irq_restore+0x8/0x20
arch_local_irq_restore+0x8/0x20 (P)
free_frozen_page_commit+0x28c/0x3b0
__free_frozen_pages+0x1c0/0x678
___free_pages+0xc0/0xe0
free_pages+0x3c/0x50
ring_buffer_resize.part.0+0x6a8/0x880
ring_buffer_resize+0x3c/0x58
__tracing_resize_ring_buffer.part.0+0x34/0xd8
tracing_resize_ring_buffer+0x8c/0xd0
tracing_entries_write+0x74/0xd8
vfs_write+0xcc/0x288
ksys_write+0x74/0x118
__arm64_sys_write+0x24/0x38
Cc: <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251228065008.2396573-1-mawupeng1@huawei.com
Signed-off-by: Wupeng Ma <mawupeng1@huawei.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Pull tracing fixes from Steven Rostedt:
- Add Documentation/core-api/tracepoint.rst to TRACING in MAINTAINERS
file
Updates to the tracepoint.rst document should be reviewed by the
tracing maintainers.
- Fix warning triggered by perf attaching to synthetic events
The synthetic events do not add a function to be registered when perf
attaches to them. This causes a warning when perf registers a
synthetic event and passes a NULL pointer to the tracepoint register
function.
Ideally synthetic events should be updated to work with perf, but as
that's a feature and not a bug fix, simply now return -ENODEV when
perf tries to register an event that has a NULL pointer for its
function. This no longer causes a kernel warning and simply causes
the perf code to fail with an error message.
- Fix 32bit overflow in option flag test
The option's flags changed from 32 bits in size to 64 bits in size.
Fix one of the places that shift 1 by the option bit number to to be
1ULL.
- Fix the output of printing the direct jmp functions
The enabled_functions that shows how functions are being attached by
ftrace wasn't updated to accommodate the new direct jmp trampolines
that set the LSB of the pointer, and outputs garbage. Update the
output to handle the direct jmp trampolines.
* tag 'trace-v6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
ftrace: Fix address for jmp mode in t_show()
tracing: Fix UBSAN warning in __remove_instance()
tracing: Do not register unsupported perf events
MAINTAINERS: add tracepoint core-api doc files to TRACING
Synthetic events currently do not have a function to register perf events.
This leads to calling the tracepoint register functions with a NULL
function pointer which triggers:
------------[ cut here ]------------
WARNING: kernel/tracepoint.c:175 at tracepoint_add_func+0x357/0x370, CPU#2: perf/2272
Modules linked in: kvm_intel kvm irqbypass
CPU: 2 UID: 0 PID: 2272 Comm: perf Not tainted 6.18.0-ftest-11964-ge022764176fc-dirty #323 PREEMPTLAZY
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
RIP: 0010:tracepoint_add_func+0x357/0x370
Code: 28 9c e8 4c 0b f5 ff eb 0f 4c 89 f7 48 c7 c6 80 4d 28 9c e8 ab 89 f4 ff 31 c0 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc <0f> 0b 49 c7 c6 ea ff ff ff e9 ee fe ff ff 0f 0b e9 f9 fe ff ff 0f
RSP: 0018:ffffabc0c44d3c40 EFLAGS: 00010246
RAX: 0000000000000001 RBX: ffff9380aa9e4060 RCX: 0000000000000000
RDX: 000000000000000a RSI: ffffffff9e1d4a98 RDI: ffff937fcf5fd6c8
RBP: 0000000000000001 R08: 0000000000000007 R09: ffff937fcf5fc780
R10: 0000000000000003 R11: ffffffff9c193910 R12: 000000000000000a
R13: ffffffff9e1e5888 R14: 0000000000000000 R15: ffffabc0c44d3c78
FS: 00007f6202f5f340(0000) GS:ffff93819f00f000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055d3162281a8 CR3: 0000000106a56003 CR4: 0000000000172ef0
Call Trace:
<TASK>
tracepoint_probe_register+0x5d/0x90
synth_event_reg+0x3c/0x60
perf_trace_event_init+0x204/0x340
perf_trace_init+0x85/0xd0
perf_tp_event_init+0x2e/0x50
perf_try_init_event+0x6f/0x230
? perf_event_alloc+0x4bb/0xdc0
perf_event_alloc+0x65a/0xdc0
__se_sys_perf_event_open+0x290/0x9f0
do_syscall_64+0x93/0x7b0
? entry_SYSCALL_64_after_hwframe+0x76/0x7e
? trace_hardirqs_off+0x53/0xc0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Instead, have the code return -ENODEV, which doesn't warn and has perf
error out with:
# perf record -e synthetic:futex_wait
Error:
The sys_perf_event_open() syscall returned with 19 (No such device) for event (synthetic:futex_wait).
"dmesg | grep -i perf" may provide additional information.
Ideally perf should support synthetic events, but for now just fix the
warning. The support can come later.
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://patch.msgid.link/20251216182440.147e4453@gandalf.local.home
Fixes: 4b147936fa ("tracing: Add support for 'synthetic' events")
Reported-by: Ian Rogers <irogers@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
