* Re: [PATCH] blk-mq: use NOIO context to prevent deadlock during debugfs creation
From: Ming Lei @ 2026-02-13 4:43 UTC (permalink / raw)
To: Yu Kuai
Cc: Jens Axboe, nilay, hch, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Yi Zhang, Shinichiro Kawasaki, Keith Busch,
Sagi Grimberg, linux-block, linux-nvme, linux-trace-kernel,
linux-kernel
In-Reply-To: <20260212080135.1673063-1-yukuai@fnnas.com>
On Thu, Feb 12, 2026 at 04:01:35PM +0800, Yu Kuai wrote:
> Creating debugfs entries can trigger fs reclaim, which can enter back
> into the block layer request_queue. This can cause deadlock if the
> queue is frozen.
>
> Previously, a WARN_ON_ONCE check was used in debugfs_create_files()
> to detect this condition, but it was racy since the queue can be frozen
> from another context at any time.
debugfs lock doesn't depend on queue freeze, so the implied deadlock isn't
obvious.
Can you explain a bit why freeze from another context may cause dead lock?
Thanks,
Ming
^ permalink raw reply
* Re: [PATCH] blk-mq: use NOIO context to prevent deadlock during debugfs creation
From: Yu Kuai @ 2026-02-13 5:39 UTC (permalink / raw)
To: Ming Lei
Cc: Jens Axboe, nilay, hch, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Yi Zhang, Shinichiro Kawasaki, Keith Busch,
Sagi Grimberg, linux-block, linux-nvme, linux-trace-kernel,
linux-kernel, yukuai
In-Reply-To: <aY6sDstii_R_zOfs@fedora>
Hi,
在 2026/2/13 12:43, Ming Lei 写道:
> On Thu, Feb 12, 2026 at 04:01:35PM +0800, Yu Kuai wrote:
>> Creating debugfs entries can trigger fs reclaim, which can enter back
>> into the block layer request_queue. This can cause deadlock if the
>> queue is frozen.
>>
>> Previously, a WARN_ON_ONCE check was used in debugfs_create_files()
>> to detect this condition, but it was racy since the queue can be frozen
>> from another context at any time.
> debugfs lock doesn't depend on queue freeze, so the implied deadlock isn't
> obvious.
>
> Can you explain a bit why freeze from another context may cause dead lock?
It's probably fine to freeze from another context concurrently, I mean the
checking will cause the false warning like:
Re: [bug report] WARNING: block/blk-mq-debugfs.c:620 at
debugfs_create_files.isra.0+0x54/0x60, CPU#220: kworker/u1036:7/70421 -
Shinichiro Kawasaki <https://lore.kernel.org/all/aYWQR7CtYdk3K39g@shinmob/>
So checking itself is racy and should be removed, meanwhile there are two options:
1) use noio for debugfs creation;
2) move debugfs creation out of queue frozen from nvme target;
BTW, I added the blk_queue_enter/exit() protection for 2 because I think it's
safe, and can prevent deadlock if there are any implied deadlock related to
queue frozen.
>
>
> Thanks,
> Ming
>
>
--
Thansk,
Kuai
^ permalink raw reply
* [PATCH RESEND] function_graph: restore direct mode when callbacks drop to one
From: hu.shengming @ 2026-02-13 6:29 UTC (permalink / raw)
To: rostedt, mhiramat
Cc: mark.rutland, mathieu.desnoyers, linux-kernel, linux-trace-kernel,
zhang.run, yang.tao172, yang.yang29
From: Shengming Hu <hu.shengming@zte.com.cn>
When registering a second fgraph callback, direct path is disabled
and array loop is used instead.
When ftrace_graph_active falls back to one, we try to re-enable direct
mode via ftrace_graph_enable_direct(true, ...).
But ftrace_graph_enable_direct() incorrectly disables the static key
rather than enabling it.
This leaves fgraph_do_direct permanently off after first multi-callback
transition, so direct fast mode is never restored.
Fixes: cc60ee813b503 ("function_graph: Use static_call and branch to optimize entry function")
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
---
kernel/trace/fgraph.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index cc48d16be43e..4df766c690f9 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1303,7 +1303,7 @@ static void ftrace_graph_enable_direct(bool enable_branch, struct fgraph_ops *go
static_call_update(fgraph_func, func);
static_call_update(fgraph_retfunc, retfunc);
if (enable_branch)
- static_branch_disable(&fgraph_do_direct);
+ static_branch_enable(&fgraph_do_direct);
}
static void ftrace_graph_disable_direct(bool disable_branch)
--
2.25.1
^ permalink raw reply related
* Re: [PATCH] function_graph: restore direct mode when callbacks drop to one
From: hu.shengming @ 2026-02-13 6:34 UTC (permalink / raw)
To: rostedt
Cc: mhiramat, mark.rutland, mathieu.desnoyers, linux-kernel,
linux-trace-kernel, zhang.run, yang.tao172, yang.yang29
In-Reply-To: <20260212224752.4311a58d@fedora>
> On Fri, 13 Feb 2026 10:34:24 +0800 (CST)
> <hu.shengming@zte.com.cn> wrote:
>
> > From: Shengming Hu <hu.shengming@zte.com.cn>
> >
> > When registering a second fgraph callback, direct path is disabled
> > and array loop is used instead.
> > When ftrace_graph_active falls back to one, we try to re-enable direct
> > mode via ftrace_graph_enable_direct(true, ...).
> > But ftrace_graph_enable_direct() incorrectly disables the static key
> > rather than enabling it.
> > This leaves fgraph_do_direct permanently off after first multi-callback
> > transition, so direct fast mode is never restored.
>
> Good catch!
>
> >
> > Fixes: cc60ee813b503 ("function_graph: Use static_call and branch to optimize entry function")
> > Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
> > ---
> > kernel/trace/fgraph.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
> > index cc48d16be43e..4df766c690f9 100644
> > --- a/kernel/trace/fgraph.c
> > +++ b/kernel/trace/fgraph.c
> > @@ -1303,7 +1303,7 @@ static void ftrace_graph_enable_direct(bool enable_branch, struct fgraph_ops *go
> > static_call_update(fgraph_func, func);
> > static_call_update(fgraph_retfunc, retfunc);
> > if (enable_branch)
> > - static_branch_disable(&fgraph_do_direct);
> > + static_branch_enable(&fgraph_do_direct);
> > }
>
> Your email client killed your patch. it has huge white-space damage.
> But because it's such a trivial change, I'll fix it up for you. But
> next time please make sure your email client doesn't corrupt your
> patches.
>
> Thanks,
>
> -- Steve
Hi Steve,
I’ve identified the cause of the email formatting issue and have resent the patch.
https://lore.kernel.org/linux-trace-kernel/20260213142932519cuWSpEXeS4-UnCvNXnK2P@zte.com.cn/T/#u
Thank you very much for the reminder.
--
With Best Regards,
Shengming
>
> >
> > static void ftrace_graph_disable_direct(bool disable_branch)
> > --
> > 2.25.1
>
^ permalink raw reply
* [PATCH] ring-buffer: Fix possible dereference of uninitialized pointer
From: Daniil Dulov @ 2026-02-13 10:01 UTC (permalink / raw)
To: Steven Rostedt
Cc: Daniil Dulov, Masami Hiramatsu, Mathieu Desnoyers,
open list:TRACING, open list:TRACING, lvc-project,
kernel test robot, Dan Carpenter
There is a pointer head_page in rb_meta_validate_events() which is not
initialized at the beginning of a function. This pointer can be dereferenced
if there is a failure during reader page validation. In this case the control
is passed to "invalid" label where the pointer is dereferenced in a loop.
To fix the issue initialize orig_head and head_page before calling
rb_validate_buffer.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202406130130.JtTGRf7W-lkp@intel.com/
Fixes: 5f3b6e839f3c ("ring-buffer: Validate boot range memory events")
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
---
kernel/trace/ring_buffer.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 630221b00838..ad08430347b0 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1918,6 +1918,8 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
if (!meta || !meta->head_buffer)
return;
+ orig_head = head_page = cpu_buffer->head_page;
+
/* Do the reader page first */
ret = rb_validate_buffer(cpu_buffer->reader_page->page, cpu_buffer->cpu);
if (ret < 0) {
@@ -1928,7 +1930,6 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
entry_bytes += local_read(&cpu_buffer->reader_page->page->commit);
local_set(&cpu_buffer->reader_page->entries, ret);
- orig_head = head_page = cpu_buffer->head_page;
ts = head_page->page->time_stamp;
/*
--
2.34.1
^ permalink raw reply related
* [PATCH v3 0/5] tools/rtla: Consolidate nr_cpus usage
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
sysconf(_SC_NPROCESSORS_CONF) (via get_nprocs_conf) reflects
cpu_possible_mask, which is fixed at boot time, so querying it
repeatedly is unnecessary.
Replace multiple calls to sysconf(_SC_NPROCESSORS_CONF) with a single
global nr_cpus variable initialized once at startup.
V3:
- Remove unneeded cpus parameter from timerlat BPF functions as
requested by Wander Costa.
v2:
- Add `#pragma once` in timerlat_u.h to avoid redefinition errors with
pre-C23 compilers.
Costa Shulyupin (5):
tools/rtla: Consolidate nr_cpus usage across all tools
tools/rtla: Remove unneeded nr_cpus arguments
tools/rtla: Remove unneeded nr_cpus members
tools/rtla: Remove unneeded nr_cpus from for_each_monitored_cpu
tools/rtla: Remove unneeded cpus parameter from timerlat BPF functions
tools/tracing/rtla/src/common.c | 7 ++-
tools/tracing/rtla/src/common.h | 4 +-
tools/tracing/rtla/src/osnoise_hist.c | 26 +++++------
tools/tracing/rtla/src/osnoise_top.c | 16 ++-----
tools/tracing/rtla/src/timerlat.c | 9 ++--
tools/tracing/rtla/src/timerlat_aa.c | 11 ++---
tools/tracing/rtla/src/timerlat_bpf.c | 19 ++++----
tools/tracing/rtla/src/timerlat_bpf.h | 12 ++---
tools/tracing/rtla/src/timerlat_hist.c | 62 +++++++++++---------------
tools/tracing/rtla/src/timerlat_top.c | 47 +++++++------------
tools/tracing/rtla/src/timerlat_u.c | 9 ++--
tools/tracing/rtla/src/timerlat_u.h | 1 +
tools/tracing/rtla/src/utils.c | 10 +----
13 files changed, 88 insertions(+), 145 deletions(-)
--
2.52.0
^ permalink raw reply
* [PATCH v3 1/5] tools/rtla: Consolidate nr_cpus usage across all tools
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
sysconf(_SC_NPROCESSORS_CONF) (via get_nprocs_conf) reflects
cpu_possible_mask, which is fixed at boot time, so querying it
repeatedly is unnecessary.
Replace multiple calls to sysconf(_SC_NPROCESSORS_CONF) with a single
global nr_cpus variable initialized once at startup.
`#pragma once` in timerlat_u.h is needed for pre-C23 compilers to avoid
redefinition errors.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
tools/tracing/rtla/src/common.c | 7 +++++--
tools/tracing/rtla/src/common.h | 2 ++
tools/tracing/rtla/src/osnoise_hist.c | 3 ---
tools/tracing/rtla/src/osnoise_top.c | 7 -------
tools/tracing/rtla/src/timerlat.c | 5 +----
tools/tracing/rtla/src/timerlat_aa.c | 1 -
tools/tracing/rtla/src/timerlat_hist.c | 3 ---
tools/tracing/rtla/src/timerlat_top.c | 7 -------
tools/tracing/rtla/src/timerlat_u.c | 3 +--
tools/tracing/rtla/src/timerlat_u.h | 1 +
tools/tracing/rtla/src/utils.c | 10 +---------
11 files changed, 11 insertions(+), 38 deletions(-)
diff --git a/tools/tracing/rtla/src/common.c b/tools/tracing/rtla/src/common.c
index ceff76a62a30..e4cf30a65e82 100644
--- a/tools/tracing/rtla/src/common.c
+++ b/tools/tracing/rtla/src/common.c
@@ -5,12 +5,14 @@
#include <signal.h>
#include <stdlib.h>
#include <string.h>
-#include <unistd.h>
#include <getopt.h>
+#include <sys/sysinfo.h>
+
#include "common.h"
struct trace_instance *trace_inst;
volatile int stop_tracing;
+int nr_cpus;
static void stop_trace(int sig)
{
@@ -135,7 +137,7 @@ common_apply_config(struct osnoise_tool *tool, struct common_params *params)
}
if (!params->cpus) {
- for (i = 0; i < sysconf(_SC_NPROCESSORS_CONF); i++)
+ for (i = 0; i < nr_cpus; i++)
CPU_SET(i, ¶ms->monitored_cpus);
}
@@ -183,6 +185,7 @@ int run_tool(struct tool_ops *ops, int argc, char *argv[])
bool stopped;
int retval;
+ nr_cpus = get_nprocs_conf();
params = ops->parse_args(argc, argv);
if (!params)
exit(1);
diff --git a/tools/tracing/rtla/src/common.h b/tools/tracing/rtla/src/common.h
index 7602c5593ef5..32f9c1351209 100644
--- a/tools/tracing/rtla/src/common.h
+++ b/tools/tracing/rtla/src/common.h
@@ -107,6 +107,8 @@ struct common_params {
struct timerlat_u_params user;
};
+extern int nr_cpus;
+
#define for_each_monitored_cpu(cpu, nr_cpus, common) \
for (cpu = 0; cpu < nr_cpus; cpu++) \
if (!(common)->cpus || CPU_ISSET(cpu, &(common)->monitored_cpus))
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 9d70ea34807f..03ebff34fff4 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -647,9 +647,6 @@ static struct osnoise_tool
*osnoise_init_hist(struct common_params *params)
{
struct osnoise_tool *tool;
- int nr_cpus;
-
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
tool = osnoise_init_tool("osnoise_hist");
if (!tool)
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index d54d47947fb4..7dcd2e318205 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -232,12 +232,8 @@ osnoise_print_stats(struct osnoise_tool *top)
{
struct osnoise_params *params = to_osnoise_params(top->params);
struct trace_instance *trace = &top->trace;
- static int nr_cpus = -1;
int i;
- if (nr_cpus == -1)
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
-
if (!params->common.quiet)
clear_terminal(trace->seq);
@@ -495,9 +491,6 @@ osnoise_top_apply_config(struct osnoise_tool *tool)
struct osnoise_tool *osnoise_init_top(struct common_params *params)
{
struct osnoise_tool *tool;
- int nr_cpus;
-
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
tool = osnoise_init_tool("osnoise_top");
if (!tool)
diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c
index 8f8811f7a13b..69856f677fce 100644
--- a/tools/tracing/rtla/src/timerlat.c
+++ b/tools/tracing/rtla/src/timerlat.c
@@ -99,7 +99,7 @@ timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_params *params)
int timerlat_enable(struct osnoise_tool *tool)
{
struct timerlat_params *params = to_timerlat_params(tool->params);
- int retval, nr_cpus, i;
+ int retval, i;
if (params->dma_latency >= 0) {
dma_latency_fd = set_cpu_dma_latency(params->dma_latency);
@@ -115,8 +115,6 @@ int timerlat_enable(struct osnoise_tool *tool)
return -1;
}
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
-
for_each_monitored_cpu(i, nr_cpus, ¶ms->common) {
if (save_cpu_idle_disable_state(i) < 0) {
err_msg("Could not save cpu idle state.\n");
@@ -214,7 +212,6 @@ void timerlat_analyze(struct osnoise_tool *tool, bool stopped)
void timerlat_free(struct osnoise_tool *tool)
{
struct timerlat_params *params = to_timerlat_params(tool->params);
- int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
int i;
timerlat_aa_destroy();
diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c
index 31e66ea2b144..5766d58709eb 100644
--- a/tools/tracing/rtla/src/timerlat_aa.c
+++ b/tools/tracing/rtla/src/timerlat_aa.c
@@ -1022,7 +1022,6 @@ void timerlat_aa_destroy(void)
*/
int timerlat_aa_init(struct osnoise_tool *tool, int dump_tasks)
{
- int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
struct timerlat_aa_context *taa_ctx;
int retval;
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 4e8c38a61197..841118ed84f2 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -1031,9 +1031,6 @@ static struct osnoise_tool
*timerlat_init_hist(struct common_params *params)
{
struct osnoise_tool *tool;
- int nr_cpus;
-
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
tool = osnoise_init_tool("timerlat_hist");
if (!tool)
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 284b74773c2b..3e395ce4fa9f 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -442,15 +442,11 @@ timerlat_print_stats(struct osnoise_tool *top)
struct timerlat_params *params = to_timerlat_params(top->params);
struct trace_instance *trace = &top->trace;
struct timerlat_top_cpu summary;
- static int nr_cpus = -1;
int i;
if (params->common.aa_only)
return;
- if (nr_cpus == -1)
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
-
if (!params->common.quiet)
clear_terminal(trace->seq);
@@ -781,9 +777,6 @@ static struct osnoise_tool
*timerlat_init_top(struct common_params *params)
{
struct osnoise_tool *top;
- int nr_cpus;
-
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
top = osnoise_init_tool("timerlat_top");
if (!top)
diff --git a/tools/tracing/rtla/src/timerlat_u.c b/tools/tracing/rtla/src/timerlat_u.c
index ce68e39d25fd..a569fe7f93aa 100644
--- a/tools/tracing/rtla/src/timerlat_u.c
+++ b/tools/tracing/rtla/src/timerlat_u.c
@@ -16,7 +16,7 @@
#include <sys/wait.h>
#include <sys/prctl.h>
-#include "utils.h"
+#include "common.h"
#include "timerlat_u.h"
/*
@@ -131,7 +131,6 @@ static int timerlat_u_send_kill(pid_t *procs, int nr_cpus)
*/
void *timerlat_u_dispatcher(void *data)
{
- int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
struct timerlat_u_params *params = data;
char proc_name[128];
int procs_count = 0;
diff --git a/tools/tracing/rtla/src/timerlat_u.h b/tools/tracing/rtla/src/timerlat_u.h
index 661511908957..a692331bd1c7 100644
--- a/tools/tracing/rtla/src/timerlat_u.h
+++ b/tools/tracing/rtla/src/timerlat_u.h
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#pragma once
/*
* Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
*/
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index 0da3b2470c31..8cd1b374b035 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -19,7 +19,7 @@
#include <stdio.h>
#include <limits.h>
-#include "utils.h"
+#include "common.h"
#define MAX_MSG_LENGTH 1024
int config_debug;
@@ -119,14 +119,11 @@ int parse_cpu_set(char *cpu_list, cpu_set_t *set)
{
const char *p;
int end_cpu;
- int nr_cpus;
int cpu;
int i;
CPU_ZERO(set);
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
-
for (p = cpu_list; *p; ) {
cpu = atoi(p);
if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus)
@@ -559,7 +556,6 @@ int save_cpu_idle_disable_state(unsigned int cpu)
unsigned int nr_states;
unsigned int state;
int disabled;
- int nr_cpus;
nr_states = cpuidle_state_count(cpu);
@@ -567,7 +563,6 @@ int save_cpu_idle_disable_state(unsigned int cpu)
return 0;
if (saved_cpu_idle_disable_state == NULL) {
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
saved_cpu_idle_disable_state = calloc(nr_cpus, sizeof(unsigned int *));
if (!saved_cpu_idle_disable_state)
return -1;
@@ -644,13 +639,10 @@ int restore_cpu_idle_disable_state(unsigned int cpu)
void free_cpu_idle_disable_states(void)
{
int cpu;
- int nr_cpus;
if (!saved_cpu_idle_disable_state)
return;
- nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
-
for (cpu = 0; cpu < nr_cpus; cpu++) {
free(saved_cpu_idle_disable_state[cpu]);
saved_cpu_idle_disable_state[cpu] = NULL;
--
2.52.0
^ permalink raw reply related
* [PATCH v3 2/5] tools/rtla: Remove unneeded nr_cpus arguments
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
nr_cpus does not change at runtime, so passing it through function
arguments is unnecessary.
Use the global nr_cpus instead of propagating it via parameters.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
tools/tracing/rtla/src/osnoise_hist.c | 4 ++--
tools/tracing/rtla/src/osnoise_top.c | 4 ++--
tools/tracing/rtla/src/timerlat_bpf.c | 5 ++---
tools/tracing/rtla/src/timerlat_bpf.h | 6 ++----
tools/tracing/rtla/src/timerlat_hist.c | 19 +++++++------------
tools/tracing/rtla/src/timerlat_top.c | 19 +++++++------------
tools/tracing/rtla/src/timerlat_u.c | 6 +++---
7 files changed, 25 insertions(+), 38 deletions(-)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 03ebff34fff4..d83ee047a5f5 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -62,7 +62,7 @@ static void osnoise_free_hist_tool(struct osnoise_tool *tool)
* osnoise_alloc_histogram - alloc runtime data
*/
static struct osnoise_hist_data
-*osnoise_alloc_histogram(int nr_cpus, int entries, int bucket_size)
+*osnoise_alloc_histogram(int entries, int bucket_size)
{
struct osnoise_hist_data *data;
int cpu;
@@ -652,7 +652,7 @@ static struct osnoise_tool
if (!tool)
return NULL;
- tool->data = osnoise_alloc_histogram(nr_cpus, params->hist.entries,
+ tool->data = osnoise_alloc_histogram(params->hist.entries,
params->hist.bucket_size);
if (!tool->data)
goto out_err;
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index 7dcd2e318205..73b3ac0dd43b 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -51,7 +51,7 @@ static void osnoise_free_top_tool(struct osnoise_tool *tool)
/*
* osnoise_alloc_histogram - alloc runtime data
*/
-static struct osnoise_top_data *osnoise_alloc_top(int nr_cpus)
+static struct osnoise_top_data *osnoise_alloc_top(void)
{
struct osnoise_top_data *data;
@@ -496,7 +496,7 @@ struct osnoise_tool *osnoise_init_top(struct common_params *params)
if (!tool)
return NULL;
- tool->data = osnoise_alloc_top(nr_cpus);
+ tool->data = osnoise_alloc_top();
if (!tool->data) {
osnoise_destroy_tool(tool);
return NULL;
diff --git a/tools/tracing/rtla/src/timerlat_bpf.c b/tools/tracing/rtla/src/timerlat_bpf.c
index 05adf18303df..8d5c3a095e41 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.c
+++ b/tools/tracing/rtla/src/timerlat_bpf.c
@@ -191,13 +191,12 @@ int timerlat_bpf_get_hist_value(int key,
int timerlat_bpf_get_summary_value(enum summary_field key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus)
+ long long *value_user)
{
return get_value(bpf->maps.summary_irq,
bpf->maps.summary_thread,
bpf->maps.summary_user,
- key, value_irq, value_thread, value_user, cpus);
+ key, value_irq, value_thread, value_user, nr_cpus);
}
/*
diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h
index 169abeaf4363..f4a5476f2abb 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.h
+++ b/tools/tracing/rtla/src/timerlat_bpf.h
@@ -28,8 +28,7 @@ int timerlat_bpf_get_hist_value(int key,
int timerlat_bpf_get_summary_value(enum summary_field key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus);
+ long long *value_user);
int timerlat_load_bpf_action_program(const char *program_path);
static inline int have_libbpf_support(void) { return 1; }
#else
@@ -53,8 +52,7 @@ static inline int timerlat_bpf_get_hist_value(int key,
static inline int timerlat_bpf_get_summary_value(enum summary_field key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus)
+ long long *value_user)
{
return -1;
}
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 841118ed84f2..dee5fbf622c3 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -83,7 +83,7 @@ static void timerlat_free_histogram_tool(struct osnoise_tool *tool)
* timerlat_alloc_histogram - alloc runtime data
*/
static struct timerlat_hist_data
-*timerlat_alloc_histogram(int nr_cpus, int entries, int bucket_size)
+*timerlat_alloc_histogram(int entries, int bucket_size)
{
struct timerlat_hist_data *data;
int cpu;
@@ -223,8 +223,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
/* Pull summary */
err = timerlat_bpf_get_summary_value(SUMMARY_COUNT,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -234,8 +233,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_MIN,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -245,8 +243,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_MAX,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -256,8 +253,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_SUM,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -267,8 +263,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_OVERFLOW,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -1036,7 +1031,7 @@ static struct osnoise_tool
if (!tool)
return NULL;
- tool->data = timerlat_alloc_histogram(nr_cpus, params->hist.entries,
+ tool->data = timerlat_alloc_histogram(params->hist.entries,
params->hist.bucket_size);
if (!tool->data)
goto out_err;
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 3e395ce4fa9f..25b4d81b4fe0 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -62,7 +62,7 @@ static void timerlat_free_top_tool(struct osnoise_tool *tool)
/*
* timerlat_alloc_histogram - alloc runtime data
*/
-static struct timerlat_top_data *timerlat_alloc_top(int nr_cpus)
+static struct timerlat_top_data *timerlat_alloc_top(void)
{
struct timerlat_top_data *data;
int cpu;
@@ -196,8 +196,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
/* Pull summary */
err = timerlat_bpf_get_summary_value(SUMMARY_CURRENT,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -207,8 +206,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_COUNT,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -218,8 +216,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_MIN,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -229,8 +226,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_MAX,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -240,8 +236,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
}
err = timerlat_bpf_get_summary_value(SUMMARY_SUM,
- value_irq, value_thread, value_user,
- data->nr_cpus);
+ value_irq, value_thread, value_user);
if (err)
return err;
for (i = 0; i < data->nr_cpus; i++) {
@@ -782,7 +777,7 @@ static struct osnoise_tool
if (!top)
return NULL;
- top->data = timerlat_alloc_top(nr_cpus);
+ top->data = timerlat_alloc_top();
if (!top->data)
goto out_err;
diff --git a/tools/tracing/rtla/src/timerlat_u.c b/tools/tracing/rtla/src/timerlat_u.c
index a569fe7f93aa..03b4e68e8b1e 100644
--- a/tools/tracing/rtla/src/timerlat_u.c
+++ b/tools/tracing/rtla/src/timerlat_u.c
@@ -99,7 +99,7 @@ static int timerlat_u_main(int cpu, struct timerlat_u_params *params)
*
* Return the number of processes that received the kill.
*/
-static int timerlat_u_send_kill(pid_t *procs, int nr_cpus)
+static int timerlat_u_send_kill(pid_t *procs)
{
int killed = 0;
int i, retval;
@@ -169,7 +169,7 @@ void *timerlat_u_dispatcher(void *data)
/* parent */
if (pid == -1) {
- timerlat_u_send_kill(procs, nr_cpus);
+ timerlat_u_send_kill(procs);
debug_msg("Failed to create child processes");
pthread_exit(&retval);
}
@@ -196,7 +196,7 @@ void *timerlat_u_dispatcher(void *data)
sleep(1);
}
- timerlat_u_send_kill(procs, nr_cpus);
+ timerlat_u_send_kill(procs);
while (procs_count) {
pid = waitpid(-1, &wstatus, 0);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 3/5] tools/rtla: Remove unneeded nr_cpus members
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
nr_cpus does not change at runtime, so keeping it in struct members is
unnecessary.
Use the global nr_cpus instead of struct members.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
tools/tracing/rtla/src/osnoise_hist.c | 18 ++++++------
tools/tracing/rtla/src/osnoise_top.c | 3 --
tools/tracing/rtla/src/timerlat_aa.c | 10 +++----
tools/tracing/rtla/src/timerlat_hist.c | 40 ++++++++++++--------------
tools/tracing/rtla/src/timerlat_top.c | 19 ++++++------
5 files changed, 39 insertions(+), 51 deletions(-)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index d83ee047a5f5..90291504a1aa 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -29,7 +29,6 @@ struct osnoise_hist_data {
struct osnoise_hist_cpu *hist;
int entries;
int bucket_size;
- int nr_cpus;
};
/*
@@ -41,7 +40,7 @@ osnoise_free_histogram(struct osnoise_hist_data *data)
int cpu;
/* one histogram for IRQ and one for thread, per CPU */
- for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
if (data->hist[cpu].samples)
free(data->hist[cpu].samples);
}
@@ -73,7 +72,6 @@ static struct osnoise_hist_data
data->entries = entries;
data->bucket_size = bucket_size;
- data->nr_cpus = nr_cpus;
data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
if (!data->hist)
@@ -246,7 +244,7 @@ static void osnoise_hist_header(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(s, "Index");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -275,7 +273,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "count:");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -287,7 +285,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "min: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -300,7 +298,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "avg: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -316,7 +314,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "max: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -351,7 +349,7 @@ osnoise_print_stats(struct osnoise_tool *tool)
trace_seq_printf(trace->seq, "%-6d",
bucket * data->bucket_size);
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -387,7 +385,7 @@ osnoise_print_stats(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "over: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index 73b3ac0dd43b..6fb3e72d74f2 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -31,7 +31,6 @@ struct osnoise_top_cpu {
struct osnoise_top_data {
struct osnoise_top_cpu *cpu_data;
- int nr_cpus;
};
/*
@@ -59,8 +58,6 @@ static struct osnoise_top_data *osnoise_alloc_top(void)
if (!data)
return NULL;
- data->nr_cpus = nr_cpus;
-
/* one set of histograms per CPU */
data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
if (!data->cpu_data)
diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c
index 5766d58709eb..59b219a1503e 100644
--- a/tools/tracing/rtla/src/timerlat_aa.c
+++ b/tools/tracing/rtla/src/timerlat_aa.c
@@ -102,7 +102,6 @@ struct timerlat_aa_data {
* The analysis context and system wide view
*/
struct timerlat_aa_context {
- int nr_cpus;
int dump_tasks;
/* per CPU data */
@@ -738,7 +737,7 @@ void timerlat_auto_analysis(int irq_thresh, int thread_thresh)
irq_thresh = irq_thresh * 1000;
thread_thresh = thread_thresh * 1000;
- for (cpu = 0; cpu < taa_ctx->nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
taa_data = timerlat_aa_get_data(taa_ctx, cpu);
if (irq_thresh && taa_data->tlat_irq_latency >= irq_thresh) {
@@ -766,7 +765,7 @@ void timerlat_auto_analysis(int irq_thresh, int thread_thresh)
printf("\n");
printf("Printing CPU tasks:\n");
- for (cpu = 0; cpu < taa_ctx->nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
taa_data = timerlat_aa_get_data(taa_ctx, cpu);
tep = taa_ctx->tool->trace.tep;
@@ -792,7 +791,7 @@ static void timerlat_aa_destroy_seqs(struct timerlat_aa_context *taa_ctx)
if (!taa_ctx->taa_data)
return;
- for (i = 0; i < taa_ctx->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
taa_data = timerlat_aa_get_data(taa_ctx, i);
if (taa_data->prev_irqs_seq) {
@@ -842,7 +841,7 @@ static int timerlat_aa_init_seqs(struct timerlat_aa_context *taa_ctx)
struct timerlat_aa_data *taa_data;
int i;
- for (i = 0; i < taa_ctx->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
taa_data = timerlat_aa_get_data(taa_ctx, i);
@@ -1031,7 +1030,6 @@ int timerlat_aa_init(struct osnoise_tool *tool, int dump_tasks)
__timerlat_aa_ctx = taa_ctx;
- taa_ctx->nr_cpus = nr_cpus;
taa_ctx->tool = tool;
taa_ctx->dump_tasks = dump_tasks;
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index dee5fbf622c3..4bf1489cad23 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -44,7 +44,6 @@ struct timerlat_hist_data {
struct timerlat_hist_cpu *hist;
int entries;
int bucket_size;
- int nr_cpus;
};
/*
@@ -56,7 +55,7 @@ timerlat_free_histogram(struct timerlat_hist_data *data)
int cpu;
/* one histogram for IRQ and one for thread, per CPU */
- for (cpu = 0; cpu < data->nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
if (data->hist[cpu].irq)
free(data->hist[cpu].irq);
@@ -94,7 +93,6 @@ static struct timerlat_hist_data
data->entries = entries;
data->bucket_size = bucket_size;
- data->nr_cpus = nr_cpus;
/* one set of histograms per CPU */
data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
@@ -204,17 +202,17 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
{
struct timerlat_hist_data *data = tool->data;
int i, j, err;
- long long value_irq[data->nr_cpus],
- value_thread[data->nr_cpus],
- value_user[data->nr_cpus];
+ long long value_irq[nr_cpus],
+ value_thread[nr_cpus],
+ value_user[nr_cpus];
/* Pull histogram */
for (i = 0; i < data->entries; i++) {
err = timerlat_bpf_get_hist_value(i, value_irq, value_thread,
- value_user, data->nr_cpus);
+ value_user, nr_cpus);
if (err)
return err;
- for (j = 0; j < data->nr_cpus; j++) {
+ for (j = 0; j < nr_cpus; j++) {
data->hist[j].irq[i] = value_irq[j];
data->hist[j].thread[i] = value_thread[j];
data->hist[j].user[i] = value_user[j];
@@ -226,7 +224,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->hist[i].irq_count = value_irq[i];
data->hist[i].thread_count = value_thread[i];
data->hist[i].user_count = value_user[i];
@@ -236,7 +234,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->hist[i].min_irq = value_irq[i];
data->hist[i].min_thread = value_thread[i];
data->hist[i].min_user = value_user[i];
@@ -246,7 +244,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->hist[i].max_irq = value_irq[i];
data->hist[i].max_thread = value_thread[i];
data->hist[i].max_user = value_user[i];
@@ -256,7 +254,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->hist[i].sum_irq = value_irq[i];
data->hist[i].sum_thread = value_thread[i];
data->hist[i].sum_user = value_user[i];
@@ -266,7 +264,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->hist[i].irq[data->entries] = value_irq[i];
data->hist[i].thread[data->entries] = value_thread[i];
data->hist[i].user[data->entries] = value_user[i];
@@ -300,7 +298,7 @@ static void timerlat_hist_header(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(s, "Index");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -352,7 +350,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "count:");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -374,7 +372,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "min: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -402,7 +400,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "avg: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -430,7 +428,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "max: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -475,7 +473,7 @@ timerlat_print_stats_all(struct timerlat_params *params,
sum.min_thread = ~0;
sum.min_user = ~0;
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -622,7 +620,7 @@ timerlat_print_stats(struct osnoise_tool *tool)
trace_seq_printf(trace->seq, "%-6d",
bucket * data->bucket_size);
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -660,7 +658,7 @@ timerlat_print_stats(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "over: ");
- for_each_monitored_cpu(cpu, data->nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 25b4d81b4fe0..4eb820fe1f21 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -41,7 +41,6 @@ struct timerlat_top_cpu {
struct timerlat_top_data {
struct timerlat_top_cpu *cpu_data;
- int nr_cpus;
};
/*
@@ -71,8 +70,6 @@ static struct timerlat_top_data *timerlat_alloc_top(void)
if (!data)
return NULL;
- data->nr_cpus = nr_cpus;
-
/* one set of histograms per CPU */
data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
if (!data->cpu_data)
@@ -190,16 +187,16 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
{
struct timerlat_top_data *data = tool->data;
int i, err;
- long long value_irq[data->nr_cpus],
- value_thread[data->nr_cpus],
- value_user[data->nr_cpus];
+ long long value_irq[nr_cpus],
+ value_thread[nr_cpus],
+ value_user[nr_cpus];
/* Pull summary */
err = timerlat_bpf_get_summary_value(SUMMARY_CURRENT,
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->cpu_data[i].cur_irq = value_irq[i];
data->cpu_data[i].cur_thread = value_thread[i];
data->cpu_data[i].cur_user = value_user[i];
@@ -209,7 +206,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->cpu_data[i].irq_count = value_irq[i];
data->cpu_data[i].thread_count = value_thread[i];
data->cpu_data[i].user_count = value_user[i];
@@ -219,7 +216,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->cpu_data[i].min_irq = value_irq[i];
data->cpu_data[i].min_thread = value_thread[i];
data->cpu_data[i].min_user = value_user[i];
@@ -229,7 +226,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->cpu_data[i].max_irq = value_irq[i];
data->cpu_data[i].max_thread = value_thread[i];
data->cpu_data[i].max_user = value_user[i];
@@ -239,7 +236,7 @@ static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
value_irq, value_thread, value_user);
if (err)
return err;
- for (i = 0; i < data->nr_cpus; i++) {
+ for (i = 0; i < nr_cpus; i++) {
data->cpu_data[i].sum_irq = value_irq[i];
data->cpu_data[i].sum_thread = value_thread[i];
data->cpu_data[i].sum_user = value_user[i];
--
2.52.0
^ permalink raw reply related
* [PATCH v3 4/5] tools/rtla: Remove unneeded nr_cpus from for_each_monitored_cpu
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
nr_cpus does not change at runtime, so passing it through the macro
argument is unnecessary.
Remove the argument and use the global nr_cpus instead.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
tools/tracing/rtla/src/common.h | 2 +-
tools/tracing/rtla/src/osnoise_hist.c | 15 +++++++--------
tools/tracing/rtla/src/osnoise_top.c | 2 +-
tools/tracing/rtla/src/timerlat.c | 4 ++--
tools/tracing/rtla/src/timerlat_hist.c | 16 ++++++++--------
tools/tracing/rtla/src/timerlat_top.c | 2 +-
6 files changed, 20 insertions(+), 21 deletions(-)
diff --git a/tools/tracing/rtla/src/common.h b/tools/tracing/rtla/src/common.h
index 32f9c1351209..28d258d6d178 100644
--- a/tools/tracing/rtla/src/common.h
+++ b/tools/tracing/rtla/src/common.h
@@ -109,7 +109,7 @@ struct common_params {
extern int nr_cpus;
-#define for_each_monitored_cpu(cpu, nr_cpus, common) \
+#define for_each_monitored_cpu(cpu, common) \
for (cpu = 0; cpu < nr_cpus; cpu++) \
if (!(common)->cpus || CPU_ISSET(cpu, &(common)->monitored_cpus))
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 90291504a1aa..e8f07108d39a 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -244,7 +244,7 @@ static void osnoise_hist_header(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(s, "Index");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -273,8 +273,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "count:");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
-
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -285,7 +284,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "min: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -298,7 +297,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "avg: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -314,7 +313,7 @@ osnoise_print_summary(struct osnoise_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "max: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -349,7 +348,7 @@ osnoise_print_stats(struct osnoise_tool *tool)
trace_seq_printf(trace->seq, "%-6d",
bucket * data->bucket_size);
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
@@ -385,7 +384,7 @@ osnoise_print_stats(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "over: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].count)
continue;
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index 6fb3e72d74f2..ab5db35f21ae 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -236,7 +236,7 @@ osnoise_print_stats(struct osnoise_tool *top)
osnoise_top_header(top);
- for_each_monitored_cpu(i, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(i, ¶ms->common) {
osnoise_top_print(top, i);
}
diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c
index 69856f677fce..ec14abd45fff 100644
--- a/tools/tracing/rtla/src/timerlat.c
+++ b/tools/tracing/rtla/src/timerlat.c
@@ -115,7 +115,7 @@ int timerlat_enable(struct osnoise_tool *tool)
return -1;
}
- for_each_monitored_cpu(i, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(i, ¶ms->common) {
if (save_cpu_idle_disable_state(i) < 0) {
err_msg("Could not save cpu idle state.\n");
return -1;
@@ -218,7 +218,7 @@ void timerlat_free(struct osnoise_tool *tool)
if (dma_latency_fd >= 0)
close(dma_latency_fd);
if (params->deepest_idle_state >= -1) {
- for_each_monitored_cpu(i, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(i, ¶ms->common) {
restore_cpu_idle_disable_state(i);
}
}
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 4bf1489cad23..db66312ec966 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -298,7 +298,7 @@ static void timerlat_hist_header(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(s, "Index");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -350,7 +350,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "count:");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -372,7 +372,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "min: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -400,7 +400,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "avg: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -428,7 +428,7 @@ timerlat_print_summary(struct timerlat_params *params,
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "max: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -473,7 +473,7 @@ timerlat_print_stats_all(struct timerlat_params *params,
sum.min_thread = ~0;
sum.min_user = ~0;
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -620,7 +620,7 @@ timerlat_print_stats(struct osnoise_tool *tool)
trace_seq_printf(trace->seq, "%-6d",
bucket * data->bucket_size);
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
@@ -658,7 +658,7 @@ timerlat_print_stats(struct osnoise_tool *tool)
if (!params->common.hist.no_index)
trace_seq_printf(trace->seq, "over: ");
- for_each_monitored_cpu(cpu, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(cpu, ¶ms->common) {
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 4eb820fe1f21..ed3d3d1c8956 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -446,7 +446,7 @@ timerlat_print_stats(struct osnoise_tool *top)
timerlat_top_header(params, top);
- for_each_monitored_cpu(i, nr_cpus, ¶ms->common) {
+ for_each_monitored_cpu(i, ¶ms->common) {
timerlat_top_print(top, i);
timerlat_top_update_sum(top, i, &summary);
}
--
2.52.0
^ permalink raw reply related
* [PATCH v3 5/5] tools/rtla: Remove unneeded cpus parameter from timerlat BPF functions
From: Costa Shulyupin @ 2026-02-13 11:52 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Costa Shulyupin, Crystal Wood,
Wander Lairson Costa, Ivan Pravdin, John Kacur, Tiezhu Yang,
linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
nr_cpus is a global variable available throughout the codebase, so
passing it as a function parameter is unnecessary.
Remove the cpus parameter from timerlat_bpf_get_hist_value() and
get_value(), using the global nr_cpus directly.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
tools/tracing/rtla/src/timerlat_bpf.c | 16 +++++++---------
tools/tracing/rtla/src/timerlat_bpf.h | 6 ++----
tools/tracing/rtla/src/timerlat_hist.c | 2 +-
3 files changed, 10 insertions(+), 14 deletions(-)
diff --git a/tools/tracing/rtla/src/timerlat_bpf.c b/tools/tracing/rtla/src/timerlat_bpf.c
index 8d5c3a095e41..dd3cf71d74e5 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.c
+++ b/tools/tracing/rtla/src/timerlat_bpf.c
@@ -147,24 +147,23 @@ static int get_value(struct bpf_map *map_irq,
int key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus)
+ long long *value_user)
{
int err;
err = bpf_map__lookup_elem(map_irq, &key,
sizeof(unsigned int), value_irq,
- sizeof(long long) * cpus, 0);
+ sizeof(long long) * nr_cpus, 0);
if (err)
return err;
err = bpf_map__lookup_elem(map_thread, &key,
sizeof(unsigned int), value_thread,
- sizeof(long long) * cpus, 0);
+ sizeof(long long) * nr_cpus, 0);
if (err)
return err;
err = bpf_map__lookup_elem(map_user, &key,
sizeof(unsigned int), value_user,
- sizeof(long long) * cpus, 0);
+ sizeof(long long) * nr_cpus, 0);
if (err)
return err;
return 0;
@@ -176,13 +175,12 @@ static int get_value(struct bpf_map *map_irq,
int timerlat_bpf_get_hist_value(int key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus)
+ long long *value_user)
{
return get_value(bpf->maps.hist_irq,
bpf->maps.hist_thread,
bpf->maps.hist_user,
- key, value_irq, value_thread, value_user, cpus);
+ key, value_irq, value_thread, value_user);
}
/*
@@ -196,7 +194,7 @@ int timerlat_bpf_get_summary_value(enum summary_field key,
return get_value(bpf->maps.summary_irq,
bpf->maps.summary_thread,
bpf->maps.summary_user,
- key, value_irq, value_thread, value_user, nr_cpus);
+ key, value_irq, value_thread, value_user);
}
/*
diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h
index f4a5476f2abb..531c9ef16f51 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.h
+++ b/tools/tracing/rtla/src/timerlat_bpf.h
@@ -23,8 +23,7 @@ int timerlat_bpf_restart_tracing(void);
int timerlat_bpf_get_hist_value(int key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus);
+ long long *value_user);
int timerlat_bpf_get_summary_value(enum summary_field key,
long long *value_irq,
long long *value_thread,
@@ -44,8 +43,7 @@ static inline int timerlat_bpf_restart_tracing(void) { return -1; };
static inline int timerlat_bpf_get_hist_value(int key,
long long *value_irq,
long long *value_thread,
- long long *value_user,
- int cpus)
+ long long *value_user)
{
return -1;
}
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index db66312ec966..1c4702948532 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -209,7 +209,7 @@ static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
/* Pull histogram */
for (i = 0; i < data->entries; i++) {
err = timerlat_bpf_get_hist_value(i, value_irq, value_thread,
- value_user, nr_cpus);
+ value_user);
if (err)
return err;
for (j = 0; j < nr_cpus; j++) {
--
2.52.0
^ permalink raw reply related
* Re: [PATCH v3 0/5] tools/rtla: Consolidate nr_cpus usage
From: Wander Lairson Costa @ 2026-02-13 13:54 UTC (permalink / raw)
To: Costa Shulyupin
Cc: Steven Rostedt, Tomas Glozar, Crystal Wood, Ivan Pravdin,
John Kacur, Tiezhu Yang, linux-trace-kernel, linux-kernel, bpf
In-Reply-To: <20260213115234.430232-1-costa.shul@redhat.com>
On Fri, Feb 13, 2026 at 01:52:29PM +0200, Costa Shulyupin wrote:
> sysconf(_SC_NPROCESSORS_CONF) (via get_nprocs_conf) reflects
> cpu_possible_mask, which is fixed at boot time, so querying it
> repeatedly is unnecessary.
>
> Replace multiple calls to sysconf(_SC_NPROCESSORS_CONF) with a single
> global nr_cpus variable initialized once at startup.
Reviewed-by: Wander Lairson Costa <wander@redhat.com>
>
> V3:
> - Remove unneeded cpus parameter from timerlat BPF functions as
> requested by Wander Costa.
> v2:
> - Add `#pragma once` in timerlat_u.h to avoid redefinition errors with
> pre-C23 compilers.
>
> Costa Shulyupin (5):
> tools/rtla: Consolidate nr_cpus usage across all tools
> tools/rtla: Remove unneeded nr_cpus arguments
> tools/rtla: Remove unneeded nr_cpus members
> tools/rtla: Remove unneeded nr_cpus from for_each_monitored_cpu
> tools/rtla: Remove unneeded cpus parameter from timerlat BPF functions
>
> tools/tracing/rtla/src/common.c | 7 ++-
> tools/tracing/rtla/src/common.h | 4 +-
> tools/tracing/rtla/src/osnoise_hist.c | 26 +++++------
> tools/tracing/rtla/src/osnoise_top.c | 16 ++-----
> tools/tracing/rtla/src/timerlat.c | 9 ++--
> tools/tracing/rtla/src/timerlat_aa.c | 11 ++---
> tools/tracing/rtla/src/timerlat_bpf.c | 19 ++++----
> tools/tracing/rtla/src/timerlat_bpf.h | 12 ++---
> tools/tracing/rtla/src/timerlat_hist.c | 62 +++++++++++---------------
> tools/tracing/rtla/src/timerlat_top.c | 47 +++++++------------
> tools/tracing/rtla/src/timerlat_u.c | 9 ++--
> tools/tracing/rtla/src/timerlat_u.h | 1 +
> tools/tracing/rtla/src/utils.c | 10 +----
> 13 files changed, 88 insertions(+), 145 deletions(-)
>
> --
> 2.52.0
>
^ permalink raw reply
* [PATCH v6 0/3] mm: vmscan: add PID and cgroup ID to vmscan tracepoints
From: Thomas Ballasi @ 2026-02-13 18:15 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260122182510.2126-1-tballasi@linux.microsoft.com>
Changes in v6:
- Updated Steven's patch with sign-off
- Passed memcg pointers as arguments in tracepoints instead of memcg_id
Link to v5:
https://lore.kernel.org/linux-trace-kernel/20260122182510.2126-1-tballasi@linux.microsoft.com/
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
Steven Rostedt (1):
tracing: Add __event_in_*irq() helpers
Thomas Ballasi (2):
mm: vmscan: add cgroup IDs to vmscan tracepoints
mm: vmscan: add PIDs to vmscan tracepoints
include/trace/events/vmscan.h | 104 +++++++++++++--------
include/trace/stages/stage3_trace_output.h | 8 ++
include/trace/stages/stage7_class_define.h | 19 ++++
mm/shrinker.c | 6 +-
mm/vmscan.c | 17 ++--
5 files changed, 106 insertions(+), 48 deletions(-)
--
2.33.8
^ permalink raw reply
* [PATCH v6 1/3] tracing: Add __event_in_*irq() helpers
From: Thomas Ballasi @ 2026-02-13 18:15 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260213181537.54350-1-tballasi@linux.microsoft.com>
From: Steven Rostedt <rostedt@goodmis.org>
Some trace events want to expose in their output if they were triggered in
an interrupt or softirq context. Instead of recording this in the event
structure itself, as this information is stored in the flags portion of
the event header, add helper macros that can be used in the print format:
TP_printk("val=%d %s", __entry->val, __entry_in_irq() ? "(in-irq)" : "")
This will output "(in-irq)" for the event in the trace data if the event
was triggered in hard or soft interrupt context.
Link: https://lore.kernel.org/all/20251229132942.31a2b583@gandalf.local.home/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/stages/stage3_trace_output.h | 8 ++++++++
include/trace/stages/stage7_class_define.h | 19 +++++++++++++++++++
2 files changed, 27 insertions(+)
diff --git a/include/trace/stages/stage3_trace_output.h b/include/trace/stages/stage3_trace_output.h
index 1e7b0bef95f52..53a23988a3b8a 100644
--- a/include/trace/stages/stage3_trace_output.h
+++ b/include/trace/stages/stage3_trace_output.h
@@ -150,3 +150,11 @@
#undef __get_buf
#define __get_buf(len) trace_seq_acquire(p, (len))
+
+#undef __event_in_hardirq
+#undef __event_in_softirq
+#undef __event_in_irq
+
+#define __event_in_hardirq() (__entry->ent.flags & TRACE_FLAG_HARDIRQ)
+#define __event_in_softirq() (__entry->ent.flags & TRACE_FLAG_SOFTIRQ)
+#define __event_in_irq() (__entry->ent.flags & (TRACE_FLAG_HARDIRQ | TRACE_FLAG_SOFTIRQ))
diff --git a/include/trace/stages/stage7_class_define.h b/include/trace/stages/stage7_class_define.h
index fcd564a590f43..47008897a7956 100644
--- a/include/trace/stages/stage7_class_define.h
+++ b/include/trace/stages/stage7_class_define.h
@@ -26,6 +26,25 @@
#undef __print_hex_dump
#undef __get_buf
+#undef __event_in_hardirq
+#undef __event_in_softirq
+#undef __event_in_irq
+
+/*
+ * The TRACE_FLAG_* are enums. Instead of using TRACE_DEFINE_ENUM(),
+ * use their hardcoded values. These values are parsed by user space
+ * tooling elsewhere so they will never change.
+ *
+ * See "enum trace_flag_type" in linux/trace_events.h:
+ * TRACE_FLAG_HARDIRQ
+ * TRACE_FLAG_SOFTIRQ
+ */
+
+/* This is what is displayed in the format files */
+#define __event_in_hardirq() (REC->common_flags & 0x8)
+#define __event_in_softirq() (REC->common_flags & 0x10)
+#define __event_in_irq() (REC->common_flags & 0x18)
+
/*
* The below is not executed in the kernel. It is only what is
* displayed in the print format for userspace to parse.
--
2.33.8
^ permalink raw reply related
* [PATCH v6 2/3] mm: vmscan: add cgroup IDs to vmscan tracepoints
From: Thomas Ballasi @ 2026-02-13 18:15 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260213181537.54350-1-tballasi@linux.microsoft.com>
Memory reclaim events are currently difficult to attribute to
specific cgroups, making debugging memory pressure issues
challenging. This patch adds memory cgroup ID (memcg_id) to key
vmscan tracepoints to enable better correlation and analysis.
For operations not associated with a specific cgroup, the field
is defaulted to 0.
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/events/vmscan.h | 83 ++++++++++++++++++++---------------
mm/shrinker.c | 6 ++-
mm/vmscan.c | 17 +++----
3 files changed, 61 insertions(+), 45 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 490958fa10dee..1212f6a7c223e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -114,85 +114,92 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags),
+ TP_ARGS(gfp_flags, order, memcg),
TP_STRUCT__entry(
- __field( int, order )
__field( unsigned long, gfp_flags )
+ __field( u64, memcg_id )
+ __field( int, order )
),
TP_fast_assign(
- __entry->order = order;
__entry->gfp_flags = (__force unsigned long)gfp_flags;
+ __entry->order = order;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("order=%d gfp_flags=%s",
+ TP_printk("order=%d gfp_flags=%s memcg_id=%llu",
__entry->order,
- show_gfp_flags(__entry->gfp_flags))
+ show_gfp_flags(__entry->gfp_flags),
+ __entry->memcg_id)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
#ifdef CONFIG_MEMCG
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
#endif /* CONFIG_MEMCG */
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed),
+ TP_ARGS(nr_reclaimed, memcg),
TP_STRUCT__entry(
__field( unsigned long, nr_reclaimed )
+ __field( u64, memcg_id )
),
TP_fast_assign(
__entry->nr_reclaimed = nr_reclaimed;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed)
+ TP_printk("nr_reclaimed=%lu memcg_id=%llu",
+ __entry->nr_reclaimed,
+ __entry->memcg_id)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
#ifdef CONFIG_MEMCG
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
#endif /* CONFIG_MEMCG */
@@ -200,39 +207,42 @@ TRACE_EVENT(mm_shrink_slab_start,
TP_PROTO(struct shrinker *shr, struct shrink_control *sc,
long nr_objects_to_shrink, unsigned long cache_items,
unsigned long long delta, unsigned long total_scan,
- int priority),
+ int priority, struct mem_cgroup *memcg),
TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan,
- priority),
+ priority, memcg),
TP_STRUCT__entry(
__field(struct shrinker *, shr)
__field(void *, shrink)
- __field(int, nid)
__field(long, nr_objects_to_shrink)
__field(unsigned long, gfp_flags)
__field(unsigned long, cache_items)
__field(unsigned long long, delta)
__field(unsigned long, total_scan)
__field(int, priority)
+ __field(int, nid)
+ __field(u64, memcg_id)
),
TP_fast_assign(
__entry->shr = shr;
__entry->shrink = shr->scan_objects;
- __entry->nid = sc->nid;
__entry->nr_objects_to_shrink = nr_objects_to_shrink;
__entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
__entry->cache_items = cache_items;
__entry->delta = delta;
__entry->total_scan = total_scan;
__entry->priority = priority;
+ __entry->nid = sc->nid;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
+ TP_printk("%pS %p: nid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->memcg_id,
__entry->nr_objects_to_shrink,
show_gfp_flags(__entry->gfp_flags),
__entry->cache_items,
@@ -243,35 +253,38 @@ TRACE_EVENT(mm_shrink_slab_start,
TRACE_EVENT(mm_shrink_slab_end,
TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval,
- long unused_scan_cnt, long new_scan_cnt, long total_scan),
+ long unused_scan_cnt, long new_scan_cnt, long total_scan, struct mem_cgroup *memcg),
TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt,
- total_scan),
+ total_scan, memcg),
TP_STRUCT__entry(
__field(struct shrinker *, shr)
- __field(int, nid)
__field(void *, shrink)
__field(long, unused_scan)
__field(long, new_scan)
- __field(int, retval)
__field(long, total_scan)
+ __field(int, nid)
+ __field(int, retval)
+ __field(u64, memcg_id)
),
TP_fast_assign(
__entry->shr = shr;
- __entry->nid = nid;
__entry->shrink = shr->scan_objects;
__entry->unused_scan = unused_scan_cnt;
__entry->new_scan = new_scan_cnt;
- __entry->retval = shrinker_retval;
__entry->total_scan = total_scan;
+ __entry->nid = nid;
+ __entry->retval = shrinker_retval;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
+ TP_printk("%pS %p: nid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->memcg_id,
__entry->unused_scan,
__entry->new_scan,
__entry->total_scan,
@@ -504,9 +517,9 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
TRACE_EVENT(mm_vmscan_throttled,
diff --git a/mm/shrinker.c b/mm/shrinker.c
index 4a93fd433689a..ddf784f996a59 100644
--- a/mm/shrinker.c
+++ b/mm/shrinker.c
@@ -410,7 +410,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
total_scan = min(total_scan, (2 * freeable));
trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
- freeable, delta, total_scan, priority);
+ freeable, delta, total_scan, priority,
+ shrinkctl->memcg);
/*
* Normally, we should not scan less than batch_size objects in one
@@ -461,7 +462,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
*/
new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);
- trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
+ trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan,
+ shrinkctl->memcg);
return freed;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 614ccf39fe3fa..9d512fb354fcd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6603,11 +6603,11 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
return 1;
set_task_reclaim_state(current, &sc.reclaim_state);
- trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
+ trace_mm_vmscan_direct_reclaim_begin(sc.gfp_mask, order, 0);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
- trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+ trace_mm_vmscan_direct_reclaim_end(nr_reclaimed, 0);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
@@ -6636,8 +6636,9 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
- trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
- sc.gfp_mask);
+ trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.gfp_mask,
+ sc.order,
+ memcg);
/*
* NOTE: Although we can get the priority field, using it
@@ -6648,7 +6649,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
*/
shrink_lruvec(lruvec, &sc);
- trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
+ trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed, memcg);
*nr_scanned = sc.nr_scanned;
@@ -6684,13 +6685,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
set_task_reclaim_state(current, &sc.reclaim_state);
- trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
+ trace_mm_vmscan_memcg_reclaim_begin(sc.gfp_mask, 0, memcg);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
memalloc_noreclaim_restore(noreclaim_flag);
- trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+ trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed, memcg);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
@@ -7642,7 +7643,7 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask,
delayacct_freepages_end();
psi_memstall_leave(&pflags);
- trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed);
+ trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed, 0);
return sc->nr_reclaimed;
}
--
2.33.8
^ permalink raw reply related
* [PATCH v6 3/3] mm: vmscan: add PIDs to vmscan tracepoints
From: Thomas Ballasi @ 2026-02-13 18:15 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260213181537.54350-1-tballasi@linux.microsoft.com>
The changes aims at adding additionnal tracepoints variables to help
debuggers attribute them to specific processes.
The PID field uses in_task() to reliably detect when we're in process
context and can safely access current->pid. When not in process
context (such as in interrupt or in an asynchronous RCU context), the
field is set to -1 as a sentinel value.
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/events/vmscan.h | 35 +++++++++++++++++++++++++----------
1 file changed, 25 insertions(+), 10 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 1212f6a7c223e..a68b712ef757a 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -122,18 +122,22 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
__field( unsigned long, gfp_flags )
__field( u64, memcg_id )
__field( int, order )
+ __field( int, pid )
),
TP_fast_assign(
__entry->gfp_flags = (__force unsigned long)gfp_flags;
__entry->order = order;
+ __entry->pid = current->pid;
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("order=%d gfp_flags=%s memcg_id=%llu",
+ TP_printk("order=%d gfp_flags=%s pid=%d memcg_id=%llu %s",
__entry->order,
show_gfp_flags(__entry->gfp_flags),
- __entry->memcg_id)
+ __entry->pid,
+ __entry->memcg_id,
+ __event_in_irq() ? "(in-irq)" : "")
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
@@ -168,16 +172,20 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
TP_STRUCT__entry(
__field( unsigned long, nr_reclaimed )
__field( u64, memcg_id )
+ __field( int, pid )
),
TP_fast_assign(
__entry->nr_reclaimed = nr_reclaimed;
__entry->memcg_id = mem_cgroup_id(memcg);
+ __entry->pid = current->pid;
),
- TP_printk("nr_reclaimed=%lu memcg_id=%llu",
+ TP_printk("nr_reclaimed=%lu pid=%d memcg_id=%llu %s",
__entry->nr_reclaimed,
- __entry->memcg_id)
+ __entry->pid,
+ __entry->memcg_id,
+ __event_in_irq() ? "(in-irq)" : "")
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
@@ -220,9 +228,10 @@ TRACE_EVENT(mm_shrink_slab_start,
__field(unsigned long, cache_items)
__field(unsigned long long, delta)
__field(unsigned long, total_scan)
+ __field(u64, memcg_id)
__field(int, priority)
__field(int, nid)
- __field(u64, memcg_id)
+ __field(int, pid)
),
TP_fast_assign(
@@ -236,19 +245,22 @@ TRACE_EVENT(mm_shrink_slab_start,
__entry->priority = priority;
__entry->nid = sc->nid;
__entry->memcg_id = mem_cgroup_id(memcg);
+ __entry->pid = current->pid;
),
- TP_printk("%pS %p: nid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
+ TP_printk("%pS %p: nid: %d pid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d %s",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->pid,
__entry->memcg_id,
__entry->nr_objects_to_shrink,
show_gfp_flags(__entry->gfp_flags),
__entry->cache_items,
__entry->delta,
__entry->total_scan,
- __entry->priority)
+ __entry->priority,
+ __event_in_irq() ? "(in-irq)" : "")
);
TRACE_EVENT(mm_shrink_slab_end,
@@ -266,29 +278,32 @@ TRACE_EVENT(mm_shrink_slab_end,
__field(long, total_scan)
__field(int, nid)
__field(int, retval)
+ __field(int, pid)
__field(u64, memcg_id)
),
TP_fast_assign(
__entry->shr = shr;
- __entry->shrink = shr->scan_objects;
__entry->unused_scan = unused_scan_cnt;
__entry->new_scan = new_scan_cnt;
__entry->total_scan = total_scan;
__entry->nid = nid;
__entry->retval = shrinker_retval;
+ __entry->pid = current->pid;
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
+ TP_printk("%pS %p: nid: %d pid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d %s",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->pid,
__entry->memcg_id,
__entry->unused_scan,
__entry->new_scan,
__entry->total_scan,
- __entry->retval)
+ __entry->retval,
+ __event_in_irq() ? "(in-irq)" : "")
);
TRACE_EVENT(mm_vmscan_lru_isolate,
--
2.33.8
^ permalink raw reply related
* [PATCH v2] blk-mq: use NOIO context to prevent deadlock during debugfs creation
From: Yu Kuai @ 2026-02-14 5:43 UTC (permalink / raw)
To: axboe, nilay, ming.lei, hch
Cc: yi.zhang, shinichiro.kawasaki, kbusch, rostedt, mhiramat,
mathieu.desnoyers, linux-block, linux-kernel, linux-trace-kernel
Creating debugfs entries can trigger fs reclaim, which can enter back
into the block layer request_queue. This can cause deadlock if the
queue is frozen.
Previously, a WARN_ON_ONCE check was used in debugfs_create_files()
to detect this condition, but it was racy since the queue can be frozen
from another context at any time.
Introduce blk_debugfs_lock()/blk_debugfs_unlock() helpers that combine
the debugfs_mutex with memalloc_noio_save()/restore() to prevent fs
reclaim from triggering block I/O. Also add blk_debugfs_lock_nomemsave()
and blk_debugfs_unlock_nomemrestore() variants for callers that don't
need NOIO protection (e.g., debugfs removal or read-only operations).
Replace all raw debugfs_mutex lock/unlock pairs with these helpers,
using the _nomemsave/_nomemrestore variants where appropriate.
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/all/CAHj4cs9gNKEYAPagD9JADfO5UH+OiCr4P7OO2wjpfOYeM-RV=A@mail.gmail.com/
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Closes: https://lore.kernel.org/all/aYWQR7CtYdk3K39g@shinmob/
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
block/blk-mq-debugfs.c | 10 +++-------
block/blk-mq-sched.c | 9 +++++----
block/blk-sysfs.c | 9 +++++----
block/blk-wbt.c | 10 ++++++----
block/blk.h | 31 +++++++++++++++++++++++++++++++
kernel/trace/blktrace.c | 38 +++++++++++++++++++++-----------------
6 files changed, 71 insertions(+), 36 deletions(-)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index faeaa1fc86a7..28167c9baa55 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -613,11 +613,6 @@ static void debugfs_create_files(struct request_queue *q, struct dentry *parent,
const struct blk_mq_debugfs_attr *attr)
{
lockdep_assert_held(&q->debugfs_mutex);
- /*
- * Creating new debugfs entries with queue freezed has the risk of
- * deadlock.
- */
- WARN_ON_ONCE(q->mq_freeze_depth != 0);
/*
* debugfs_mutex should not be nested under other locks that can be
* grabbed while queue is frozen.
@@ -693,12 +688,13 @@ void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
void blk_mq_debugfs_register_hctxs(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
+ unsigned int memflags;
unsigned long i;
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_debugfs_register_hctx(q, hctx);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
}
void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index e26898128a7e..97c3c8f45a9b 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -390,13 +390,14 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int fla
void blk_mq_sched_reg_debugfs(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
+ unsigned int memflags;
unsigned long i;
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
blk_mq_debugfs_register_sched(q);
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_debugfs_register_sched_hctx(q, hctx);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
}
void blk_mq_sched_unreg_debugfs(struct request_queue *q)
@@ -404,11 +405,11 @@ void blk_mq_sched_unreg_debugfs(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
unsigned long i;
- mutex_lock(&q->debugfs_mutex);
+ blk_debugfs_lock_nomemsave(q);
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_debugfs_unregister_sched_hctx(hctx);
blk_mq_debugfs_unregister_sched(q);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock_nomemrestore(q);
}
void blk_mq_free_sched_tags(struct elevator_tags *et,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 003aa684e854..f3b1968c80ce 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -892,13 +892,13 @@ static void blk_debugfs_remove(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
- mutex_lock(&q->debugfs_mutex);
+ blk_debugfs_lock_nomemsave(q);
blk_trace_shutdown(q);
debugfs_remove_recursive(q->debugfs_dir);
q->debugfs_dir = NULL;
q->sched_debugfs_dir = NULL;
q->rqos_debugfs_dir = NULL;
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock_nomemrestore(q);
}
/**
@@ -908,6 +908,7 @@ static void blk_debugfs_remove(struct gendisk *disk)
int blk_register_queue(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
+ unsigned int memflags;
int ret;
ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue");
@@ -921,11 +922,11 @@ int blk_register_queue(struct gendisk *disk)
}
mutex_lock(&q->sysfs_lock);
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
q->debugfs_dir = debugfs_create_dir(disk->disk_name, blk_debugfs_root);
if (queue_is_mq(q))
blk_mq_debugfs_register(q);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
ret = disk_register_independent_access_ranges(disk);
if (ret)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 1415f2bf8611..6dba71e87387 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -776,6 +776,7 @@ void wbt_init_enable_default(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
struct rq_wb *rwb;
+ unsigned int memflags;
if (!__wbt_enable_default(disk))
return;
@@ -789,9 +790,9 @@ void wbt_init_enable_default(struct gendisk *disk)
return;
}
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
blk_mq_debugfs_register_rq_qos(q);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
}
static u64 wbt_default_latency_nsec(struct request_queue *q)
@@ -1015,9 +1016,10 @@ int wbt_set_lat(struct gendisk *disk, s64 val)
blk_mq_unquiesce_queue(q);
out:
blk_mq_unfreeze_queue(q, memflags);
- mutex_lock(&q->debugfs_mutex);
+
+ memflags = blk_debugfs_lock(q);
blk_mq_debugfs_register_rq_qos(q);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
return ret;
}
diff --git a/block/blk.h b/block/blk.h
index 401d19ed08a6..68cef70e84e6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -740,4 +740,35 @@ static inline void blk_unfreeze_release_lock(struct request_queue *q)
}
#endif
+/*
+ * debugfs directory and file creation can trigger fs reclaim, which can enter
+ * back into the block layer request_queue. This can cause deadlock if the
+ * queue is frozen. Use NOIO context together with debugfs_mutex to prevent fs
+ * reclaim from triggering block I/O.
+ */
+static inline void blk_debugfs_lock_nomemsave(struct request_queue *q)
+{
+ mutex_lock(&q->debugfs_mutex);
+}
+
+static inline void blk_debugfs_unlock_nomemrestore(struct request_queue *q)
+{
+ mutex_unlock(&q->debugfs_mutex);
+}
+
+static inline unsigned int __must_check blk_debugfs_lock(struct request_queue *q)
+{
+ unsigned int memflags = memalloc_noio_save();
+
+ blk_debugfs_lock_nomemsave(q);
+ return memflags;
+}
+
+static inline void blk_debugfs_unlock(struct request_queue *q,
+ unsigned int memflags)
+{
+ blk_debugfs_unlock_nomemrestore(q);
+ memalloc_noio_restore(memflags);
+}
+
#endif /* BLK_INTERNAL_H */
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c4db5c2e7103..a3d8a68f8683 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -559,9 +559,9 @@ int blk_trace_remove(struct request_queue *q)
{
int ret;
- mutex_lock(&q->debugfs_mutex);
+ blk_debugfs_lock_nomemsave(q);
ret = __blk_trace_remove(q);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock_nomemrestore(q);
return ret;
}
@@ -767,6 +767,7 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
struct blk_user_trace_setup2 buts2;
struct blk_user_trace_setup buts;
struct blk_trace *bt;
+ unsigned int memflags;
int ret;
ret = copy_from_user(&buts, arg, sizeof(buts));
@@ -785,16 +786,16 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
.pid = buts.pid,
};
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
bt = blk_trace_setup_prepare(q, name, dev, buts.buf_size, buts.buf_nr,
bdev);
if (IS_ERR(bt)) {
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
return PTR_ERR(bt);
}
blk_trace_setup_finalize(q, name, 1, bt, &buts2);
strscpy(buts.name, buts2.name, BLKTRACE_BDEV_SIZE);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
if (copy_to_user(arg, &buts, sizeof(buts))) {
blk_trace_remove(q);
@@ -809,6 +810,7 @@ static int blk_trace_setup2(struct request_queue *q, char *name, dev_t dev,
{
struct blk_user_trace_setup2 buts2;
struct blk_trace *bt;
+ unsigned int memflags;
if (copy_from_user(&buts2, arg, sizeof(buts2)))
return -EFAULT;
@@ -819,15 +821,15 @@ static int blk_trace_setup2(struct request_queue *q, char *name, dev_t dev,
if (buts2.flags != 0)
return -EINVAL;
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
bt = blk_trace_setup_prepare(q, name, dev, buts2.buf_size, buts2.buf_nr,
bdev);
if (IS_ERR(bt)) {
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
return PTR_ERR(bt);
}
blk_trace_setup_finalize(q, name, 2, bt, &buts2);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
if (copy_to_user(arg, &buts2, sizeof(buts2))) {
blk_trace_remove(q);
@@ -844,6 +846,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
struct blk_user_trace_setup2 buts2;
struct compat_blk_user_trace_setup cbuts;
struct blk_trace *bt;
+ unsigned int memflags;
if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
return -EFAULT;
@@ -860,15 +863,15 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
.pid = cbuts.pid,
};
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
bt = blk_trace_setup_prepare(q, name, dev, buts2.buf_size, buts2.buf_nr,
bdev);
if (IS_ERR(bt)) {
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
return PTR_ERR(bt);
}
blk_trace_setup_finalize(q, name, 1, bt, &buts2);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
if (copy_to_user(arg, &buts2.name, ARRAY_SIZE(buts2.name))) {
blk_trace_remove(q);
@@ -898,9 +901,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
{
int ret;
- mutex_lock(&q->debugfs_mutex);
+ blk_debugfs_lock_nomemsave(q);
ret = __blk_trace_startstop(q, start);
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock_nomemrestore(q);
return ret;
}
@@ -2020,7 +2023,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct blk_trace *bt;
ssize_t ret = -ENXIO;
- mutex_lock(&q->debugfs_mutex);
+ blk_debugfs_lock_nomemsave(q);
bt = rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex));
@@ -2041,7 +2044,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
ret = sprintf(buf, "%llu\n", bt->end_lba);
out_unlock_bdev:
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock_nomemrestore(q);
return ret;
}
@@ -2052,6 +2055,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
struct block_device *bdev = dev_to_bdev(dev);
struct request_queue *q = bdev_get_queue(bdev);
struct blk_trace *bt;
+ unsigned int memflags;
u64 value;
ssize_t ret = -EINVAL;
@@ -2071,7 +2075,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
goto out;
}
- mutex_lock(&q->debugfs_mutex);
+ memflags = blk_debugfs_lock(q);
bt = rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex));
@@ -2106,7 +2110,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
}
out_unlock_bdev:
- mutex_unlock(&q->debugfs_mutex);
+ blk_debugfs_unlock(q, memflags);
out:
return ret ? ret : count;
}
--
2.51.0
^ permalink raw reply related
* Enhancing Conditional Filtering for Function Graph Tracer
From: Donglin Peng @ 2026-02-14 10:36 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: linux-trace-kernel, Linux Kernel Mailing List
Hi Steve and Masami,
I recently had an idea while using the function graph tracer.
Currently, it supports basic
filtering via set_ftrace_pid(PID-based) and
set_graph_function(function name-based).
However, this filtering mechanism feels somewhat limited. Given that
we already have
features like funcgraph-args, I wonder if we could enhance filtering by allowing
conditional tracking based on function parameters — similar to how
trace events support
filters/triggers.
To simplify implementation, I propose extending a new trigger type
(e.g., "funcgraph").
In ftrace_graph_ignore_func, we could look up the corresponding trace_fprobe and
trace_event_file based on trace->func, then decide whether to trace
the function using
a helper like the following:
static bool ftrace_graph_filter(struct trace_fprobe *tf, struct
ftrace_regs *fregs,
struct trace_event_file *trace_file)
{
struct fentry_trace_entry_head *entry;
struct trace_event_buffer fbuffer;
struct event_trigger_data *data;
int dsize;
dsize = __get_data_size(&tf->tp, fregs, NULL);
entry = trace_event_buffer_reserve(&fbuffer, trace_file,
sizeof(*entry) + tf->tp.size + dsize);
if (!entry)
return false;
entry = ring_buffer_event_data(fbuffer.event);
store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize);
list_for_each_entry_rcu(data, &trace_file->triggers, list) {
if (data->cmd_ops->trigger_type == TRIGGER_TYPE_FUNCGRAPH) {
struct event_filter *filter = rcu_dereference_sched(data->filter);
if (filter && filter_match_preds(filter, entry))
return true; // Allow tracing
}
}
return false; // Skip tracing
}
Does this approach make sense? Any suggestions or concerns?
Thanks,
Donglin
^ permalink raw reply
* Re: [RFC PATCH v2 33/37] KVM: selftests: Make TEST_EXPECT_SIGBUS thread-safe
From: Ackerley Tng @ 2026-02-14 19:49 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-trace-kernel,
x86
Cc: aik, andrew.jones, binbin.wu, bp, brauner, chao.p.peng,
chao.p.peng, chenhuacai, corbet, dave.hansen, david, hpa,
ira.weiny, jgg, jmattson, jroedel, jthoughton, maobibo,
mathieu.desnoyers, maz, mhiramat, michael.roth, mingo, mlevitsk,
oupton, pankaj.gupta, pbonzini, prsampat, qperret, ricarkol,
rick.p.edgecombe, rientjes, rostedt, seanjc, shivankg, shuah,
steven.price, tabba, tglx, vannapurve, vbabka, willy, wyihan,
yan.y.zhao
In-Reply-To: <995398ca18fcb192444799a520cab5ea8e43df7b.1770071243.git.ackerleytng@google.com>
Ackerley Tng <ackerleytng@google.com> writes:
> The TEST_EXPECT_SIGBUS macro is not thread-safe as it uses a global
> sigjmp_buf and installs a global SIGBUS signal handler. If multiple threads
> execute the macro concurrently, they will race on installing the signal
> handler and stomp on other threads' jump buffers, leading to incorrect test
> behavior.
>
> Make TEST_EXPECT_SIGBUS thread-safe with the following changes:
>
> Share the KVM tests' global signal handler. sigaction() applies to all
> threads; without sharing a global signal handler, one thread may have
> removed the signal handler that another thread added, hence leading to
> unexpected signals.
>
> The alternative of layering signal handlers was considered, but calling
> sigaction() within TEST_EXPECT_SIGBUS() necessarily creates a race. To
> avoid adding new setup and teardown routines to do sigaction() and keep
> usage of TEST_EXPECT_SIGBUS() simple, share the KVM tests' global signal
> handler.
>
> Opportunistically rename report_unexpected_signal to
> catchall_signal_handler.
>
> To continue to only expect SIGBUS within specific regions of code, use a
> thread-specific variable, expecting_sigbus, to replace installing and
> removing signal handlers.
>
> Make the execution environment for the thread, sigjmp_buf, a
> thread-specific variable.
>
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> ---
> .../testing/selftests/kvm/include/test_util.h | 29 +++++++++----------
> tools/testing/selftests/kvm/lib/kvm_util.c | 18 ++++++++----
> tools/testing/selftests/kvm/lib/test_util.c | 7 -----
> 3 files changed, 26 insertions(+), 28 deletions(-)
>
> diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
> index 2871a4292847..0e4e6f7dab8f 100644
> --- a/tools/testing/selftests/kvm/include/test_util.h
> +++ b/tools/testing/selftests/kvm/include/test_util.h
> @@ -80,22 +80,19 @@ do { \
> __builtin_unreachable(); \
> } while (0)
>
> -extern sigjmp_buf expect_sigbus_jmpbuf;
> -void expect_sigbus_handler(int signum);
> -
> -#define TEST_EXPECT_SIGBUS(action) \
> -do { \
> - struct sigaction sa_old, sa_new = { \
> - .sa_handler = expect_sigbus_handler, \
> - }; \
> - \
> - sigaction(SIGBUS, &sa_new, &sa_old); \
> - if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \
> - action; \
> - TEST_FAIL("'%s' should have triggered SIGBUS", #action); \
> - } \
> - sigaction(SIGBUS, &sa_old, NULL); \
> -} while (0)
> +extern __thread sigjmp_buf expect_sigbus_jmpbuf;
> +extern __thread bool expecting_sigbus;
> +
> +#define TEST_EXPECT_SIGBUS(action) \
> + do { \
> + expecting_sigbus = true; \
> + if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \
> + action; \
> + TEST_FAIL("'%s' should have triggered SIGBUS", \
> + #action); \
> + } \
> + expecting_sigbus = false; \
> + } while (0)
>
> size_t parse_size(const char *size);
>
> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
> index aec7b24418ab..18ced8bdde36 100644
> --- a/tools/testing/selftests/kvm/lib/kvm_util.c
> +++ b/tools/testing/selftests/kvm/lib/kvm_util.c
> @@ -2314,13 +2314,20 @@ __weak void kvm_selftest_arch_init(void)
> {
> }
>
> -static void report_unexpected_signal(int signum)
> +__thread sigjmp_buf expect_sigbus_jmpbuf;
> +__thread bool expecting_sigbus;
> +
> +static void catchall_signal_handler(int signum)
> {
> + switch (signum) {
> + case SIGBUS: {
> + if (expecting_sigbus)
Transferring/summarizing an internal comment from Sean upstream:
This assumes that tests are indeed using the catchall_signal_handler as
the global signal handler.
In the next revision, I will make TEST_EXPECT_SIGBUS() assert that the
default signal handler is installed, so that developers get a clear,
explicit failure if/when something goes wrong.
> + siglongjmp(expect_sigbus_jmpbuf, 1);
> +
> + TEST_FAIL("Unexpected SIGBUS (%d)\n", signum);
> + }
> #define KVM_CASE_SIGNUM(sig) \
> case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum)
> -
> - switch (signum) {
> - KVM_CASE_SIGNUM(SIGBUS);
> KVM_CASE_SIGNUM(SIGSEGV);
> KVM_CASE_SIGNUM(SIGILL);
> KVM_CASE_SIGNUM(SIGFPE);
> @@ -2332,12 +2339,13 @@ static void report_unexpected_signal(int signum)
> void __attribute((constructor)) kvm_selftest_init(void)
> {
> struct sigaction sig_sa = {
> - .sa_handler = report_unexpected_signal,
> + .sa_handler = catchall_signal_handler,
> };
>
> /* Tell stdout not to buffer its content. */
> setbuf(stdout, NULL);
>
> + expecting_sigbus = false;
> sigaction(SIGBUS, &sig_sa, NULL);
> sigaction(SIGSEGV, &sig_sa, NULL);
> sigaction(SIGILL, &sig_sa, NULL);
> diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
> index 8a1848586a85..03eb99af9b8d 100644
> --- a/tools/testing/selftests/kvm/lib/test_util.c
> +++ b/tools/testing/selftests/kvm/lib/test_util.c
> @@ -18,13 +18,6 @@
>
> #include "test_util.h"
>
> -sigjmp_buf expect_sigbus_jmpbuf;
> -
> -void __attribute__((used)) expect_sigbus_handler(int signum)
> -{
> - siglongjmp(expect_sigbus_jmpbuf, 1);
> -}
> -
> /*
> * Random number generator that is usable from guest code. This is the
> * Park-Miller LCG using standard constants.
> --
> 2.53.0.rc1.225.gd81095ad13-goog
^ permalink raw reply
* Re: [RFC PATCH v2 09/37] KVM: guest_memfd: Add support for KVM_SET_MEMORY_ATTRIBUTES2
From: Ackerley Tng @ 2026-02-14 20:09 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-trace-kernel,
x86
Cc: aik, andrew.jones, binbin.wu, bp, brauner, chao.p.peng,
chao.p.peng, chenhuacai, corbet, dave.hansen, david, hpa,
ira.weiny, jgg, jmattson, jroedel, jthoughton, maobibo,
mathieu.desnoyers, maz, mhiramat, michael.roth, mingo, mlevitsk,
oupton, pankaj.gupta, pbonzini, prsampat, qperret, ricarkol,
rick.p.edgecombe, rientjes, rostedt, seanjc, shivankg, shuah,
steven.price, tabba, tglx, vannapurve, vbabka, willy, wyihan,
yan.y.zhao
In-Reply-To: <86ad28b767524e1e654b9c960e39ca8bfb24c114.1770071243.git.ackerleytng@google.com>
Ackerley Tng <ackerleytng@google.com> writes:
>
> [...snip...]
>
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index 23ec0b0c3e22..26e80745c8b4 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -117,7 +117,7 @@ description:
> x86 includes both i386 and x86_64.
>
> Type:
> - system, vm, or vcpu.
> + system, vm, vcpu or guest_memfd.
>
> Parameters:
> what parameters are accepted by the ioctl.
> @@ -6523,11 +6523,22 @@ the capability to be present.
> ---------------------------------
>
> :Capability: KVM_CAP_MEMORY_ATTRIBUTES2
> -:Architectures: x86
> -:Type: vm ioctl
> +:Architectures: all
> +:Type: vm, guest_memfd ioctl
> :Parameters: struct kvm_memory_attributes2 (in/out)
> :Returns: 0 on success, <0 on error
>
> +Errors:
> +
> + ========== ===============================================================
> + EINVAL The specified `offset` or `size` were invalid (e.g. not
> + page aligned, causes an overflow, or size is zero).
> + EFAULT The parameter address was invalid.
> + EAGAIN Some page within requested range had unexpected refcounts. The
> + offset of the page will be returned in `error_offset`.
> + ENOMEM Ran out of memory trying to track private/shared state
> + ========== ===============================================================
> +
> KVM_SET_MEMORY_ATTRIBUTES2 is an extension to
> KVM_SET_MEMORY_ATTRIBUTES that supports returning (writing) values to
> userspace. The original (pre-extension) fields are shared with
> @@ -6538,15 +6549,42 @@ Attribute values are shared with KVM_SET_MEMORY_ATTRIBUTES.
> ::
>
> struct kvm_memory_attributes2 {
> - __u64 address;
> + /* in */
> + union {
> + __u64 address;
> + __u64 offset;
> + };
> __u64 size;
> __u64 attributes;
> __u64 flags;
> - __u64 reserved[12];
> + /* out */
> + __u64 error_offset;
> + __u64 reserved[11];
> };
>
> #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
>
> +Set attributes for a range of offsets within a guest_memfd to
> +KVM_MEMORY_ATTRIBUTE_PRIVATE to limit the specified guest_memfd backed
> +memory range for guest_use. Even if KVM_CAP_GUEST_MEMFD_MMAP is
> +supported, after a successful call to set
> +KVM_MEMORY_ATTRIBUTE_PRIVATE, the requested range will not be mappable
> +into host userspace and will only be mappable by the guest.
> +
> +To allow the range to be mappable into host userspace again, call
> +KVM_SET_MEMORY_ATTRIBUTES2 on the guest_memfd again with
> +KVM_MEMORY_ATTRIBUTE_PRIVATE unset.
> +
> +If this ioctl returns -EAGAIN, the offset of the page with unexpected
> +refcounts will be returned in `error_offset`. This can occur if there
> +are transient refcounts on the pages, taken by other parts of the
> +kernel.
> +
> +Userspace is expected to figure out how to remove all known refcounts
> +on the shared pages, such as refcounts taken by get_user_pages(), and
> +try the ioctl again. A possible source of these long term refcounts is
> +if the guest_memfd memory was pinned in IOMMU page tables.
> +
> See also: :ref: `KVM_SET_MEMORY_ATTRIBUTES`.
>
Transferring/re-summarizing an internal comment from Sean upstream here!
We can also follow up on this topic at the next guest_memfd biweekly.
Before this lands, Sean wants, at the very minimum, an in-principle
agreement on guest_memfd behavior with respect to whether or not memory
should be preserved on conversion.
Sean is against deferring whether to preserve memory to the underlying
hardware because that is letting (effectively) micro-architectural
behavior to define KVM's ABI. KVM's uAPI cannot let behavior be
undefined, or be based on vendor, and maybe even on firmware version.
Sean says that all decisions that affect guest data must be made by
userspace. The architecture can restrict what is possible, e.g. neither
SNP nor TDX currently support "generic" in-place conversion, but whether
or not data is to be preserved must be an explicit request from
userspace. If preserving data is impossible, then KVM needs to reject
the request.
(Vendor specific ioctls are out-of-scope, SNP and TDX cases were brought
up purely to highlight that there's nothing that fundamentally prevents
preserving data on conversion.)
I suggested a few uAPI options for configuring content preservation on
conversion:
1. guest_memfd creation time flag like
GUEST_MEMFD_FLAG_PRESERVE_CONTENTS. This can be valid only if the
kernel and vendor support content preservation
This was rejected because we should not assume all current and future
use cases will want the same content preservation config for a given
guest_memfd.
2. KConfig: automatically select to preserve contents if the
architecture supports content preservation
This was rejected because it's not a decision explicitly made by
userspace.
3. KVM module param to configure content preservation.
This was rejected because the configuration may not generalize across
all VMs on the same host.
4. guest_memfd ioctl flag
SET_MEMORY_ATTRIBUTES2_FLAG_PRESERVE_CONTENTS. -EINVAL if kernel and
vendor don't support content preservation
Specifying a flag to choose whether content should be preserved at
conversion-time is the current best suggestion.
What does the rest of the community think of a conversion ioctl flag to
choose whether to preserve memory contents on conversion?
Fuad, I think you also made a related comment on an earlier internal
version we were working on. What do you/pKVM think?
>
> [...snip...]
>
^ permalink raw reply
* [PATCH v1] Documentation/rtla: Add hwnoise to main page
From: Costa Shulyupin @ 2026-02-15 13:12 UTC (permalink / raw)
To: Steven Rostedt, Tomas Glozar, Jonathan Corbet, linux-trace-kernel,
linux-kernel, linux-doc
Cc: Costa Shulyupin
Add hwnoise to the command list and SEE ALSO section. The command list
is ordered from low level to high level.
Signed-off-by: Costa Shulyupin <costa.shul@redhat.com>
---
Documentation/tools/rtla/rtla.rst | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/Documentation/tools/rtla/rtla.rst b/Documentation/tools/rtla/rtla.rst
index 2a5fb7004ad4..6df1296b8cc1 100644
--- a/Documentation/tools/rtla/rtla.rst
+++ b/Documentation/tools/rtla/rtla.rst
@@ -21,6 +21,10 @@ results.
COMMANDS
========
+**hwnoise**
+
+ Detect and quantify hardware-related noise.
+
**osnoise**
Gives information about the operating system noise (osnoise).
@@ -39,7 +43,7 @@ For other options, see the man page for the corresponding command.
SEE ALSO
========
-**rtla-osnoise**\(1), **rtla-timerlat**\(1)
+**rtla-hwnoise**\(1), **rtla-osnoise**\(1), **rtla-timerlat**\(1)
AUTHOR
======
--
2.53.0
^ permalink raw reply related
* Re: [PATCH v2] blk-mq: use NOIO context to prevent deadlock during debugfs creation
From: Nilay Shroff @ 2026-02-15 13:34 UTC (permalink / raw)
To: Yu Kuai, axboe, ming.lei, hch
Cc: yi.zhang, shinichiro.kawasaki, kbusch, rostedt, mhiramat,
mathieu.desnoyers, linux-block, linux-kernel, linux-trace-kernel
In-Reply-To: <20260214054350.2322436-1-yukuai@fnnas.com>
On 2/14/26 11:13 AM, Yu Kuai wrote:
> Creating debugfs entries can trigger fs reclaim, which can enter back
> into the block layer request_queue. This can cause deadlock if the
> queue is frozen.
>
> Previously, a WARN_ON_ONCE check was used in debugfs_create_files()
> to detect this condition, but it was racy since the queue can be frozen
> from another context at any time.
>
> Introduce blk_debugfs_lock()/blk_debugfs_unlock() helpers that combine
> the debugfs_mutex with memalloc_noio_save()/restore() to prevent fs
> reclaim from triggering block I/O. Also add blk_debugfs_lock_nomemsave()
> and blk_debugfs_unlock_nomemrestore() variants for callers that don't
> need NOIO protection (e.g., debugfs removal or read-only operations).
>
> Replace all raw debugfs_mutex lock/unlock pairs with these helpers,
> using the _nomemsave/_nomemrestore variants where appropriate.
>
> Reported-by: Yi Zhang <yi.zhang@redhat.com>
> Closes: https://lore.kernel.org/all/CAHj4cs9gNKEYAPagD9JADfO5UH+OiCr4P7OO2wjpfOYeM-RV=A@mail.gmail.com/
> Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
> Closes: https://lore.kernel.org/all/aYWQR7CtYdk3K39g@shinmob/
> Suggested-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Yu Kuai <yukuai@fnnas.com>
Looks good to me:
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
^ permalink raw reply
* Re: [syzbot] [block?] [trace?] INFO: task hung in blk_trace_startstop
From: syzbot @ 2026-02-15 14:17 UTC (permalink / raw)
To: axboe, linux-block, linux-kernel, linux-trace-kernel,
mathieu.desnoyers, mhiramat, rostedt, syzkaller-bugs
In-Reply-To: <691367ae.a70a0220.22f260.0141.GAE@google.com>
syzbot has found a reproducer for the following issue on:
HEAD commit: 635c467cc14e Add linux-next specific files for 20260213
git tree: linux-next
console output: https://syzkaller.appspot.com/x/log.txt?x=14d8ec02580000
kernel config: https://syzkaller.appspot.com/x/.config?x=f09eec269f9f4746
dashboard link: https://syzkaller.appspot.com/bug?extid=774863666ef5b025c9d0
compiler: Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
syz repro: https://syzkaller.appspot.com/x/repro.syz?x=12cc2ffa580000
Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/24870d51cbd0/disk-635c467c.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/49283c738806/vmlinux-635c467c.xz
kernel image: https://storage.googleapis.com/syzbot-assets/8c5f9d1da977/bzImage-635c467c.xz
mounted in repro: https://storage.googleapis.com/syzbot-assets/b01c09978893/mount_0.gz
fsck result: OK (log: https://syzkaller.appspot.com/x/fsck.log?x=163e915a580000)
IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+774863666ef5b025c9d0@syzkaller.appspotmail.com
INFO: task syz.3.20:6102 blocked for more than 143 seconds.
Not tainted syzkaller #0
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:syz.3.20 state:D stack:28368 pid:6102 tgid:6087 ppid:5957 task_flags:0x400040 flags:0x00080002
Call Trace:
<TASK>
context_switch kernel/sched/core.c:5295 [inline]
__schedule+0x1585/0x5340 kernel/sched/core.c:6907
__schedule_loop kernel/sched/core.c:6989 [inline]
schedule+0x164/0x360 kernel/sched/core.c:7004
schedule_preempt_disabled+0x13/0x30 kernel/sched/core.c:7061
__mutex_lock_common kernel/locking/mutex.c:692 [inline]
__mutex_lock+0x7fe/0x1300 kernel/locking/mutex.c:776
blk_trace_startstop+0x8f/0x610 kernel/trace/blktrace.c:901
blk_trace_ioctl+0x315/0x740 kernel/trace/blktrace.c:947
blkdev_common_ioctl+0x13a7/0x3250 block/ioctl.c:724
blkdev_ioctl+0x528/0x740 block/ioctl.c:798
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:597 [inline]
__se_sys_ioctl+0xfc/0x170 fs/ioctl.c:583
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f530c39bf79
RSP: 002b:00007f530d2e4028 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007f530c616180 RCX: 00007f530c39bf79
RDX: 0000000000000000 RSI: 0000000000001275 RDI: 0000000000000007
RBP: 00007f530c4327e0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f530c616218 R14: 00007f530c616180 R15: 00007ffdd027c568
</TASK>
INFO: task syz.2.19:6109 blocked for more than 150 seconds.
Not tainted syzkaller #0
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:syz.2.19 state:D stack:26720 pid:6109 tgid:6091 ppid:5955 task_flags:0x400140 flags:0x00080002
Call Trace:
<TASK>
context_switch kernel/sched/core.c:5295 [inline]
__schedule+0x1585/0x5340 kernel/sched/core.c:6907
__schedule_loop kernel/sched/core.c:6989 [inline]
schedule+0x164/0x360 kernel/sched/core.c:7004
schedule_preempt_disabled+0x13/0x30 kernel/sched/core.c:7061
__mutex_lock_common kernel/locking/mutex.c:692 [inline]
__mutex_lock+0x7fe/0x1300 kernel/locking/mutex.c:776
relay_open+0x3b8/0x920 kernel/relay.c:516
blk_trace_setup_prepare+0x425/0x5a0 kernel/trace/blktrace.c:716
blk_trace_setup+0x2c0/0x430 kernel/trace/blktrace.c:789
blk_trace_ioctl+0x380/0x740 kernel/trace/blktrace.c:935
---
If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.
^ permalink raw reply
* [PATCH AUTOSEL 6.19-5.15] tracing: Fix false sharing in hwlat get_sample()
From: Sasha Levin @ 2026-02-15 15:03 UTC (permalink / raw)
To: patches, stable
Cc: Colin Lord, Masami Hiramatsu, Mathieu Desnoyers,
Steven Rostedt (Google), Sasha Levin, linux-kernel,
linux-trace-kernel
In-Reply-To: <20260215150333.2150455-1-sashal@kernel.org>
From: Colin Lord <clord@mykolab.com>
[ Upstream commit f743435f988cb0cf1f521035aee857851b25e06d ]
The get_sample() function in the hwlat tracer assumes the caller holds
hwlat_data.lock, but this is not actually happening. The result is
unprotected data access to hwlat_data, and in per-cpu mode can result in
false sharing which may show up as false positive latency events.
The specific case of false sharing observed was primarily between
hwlat_data.sample_width and hwlat_data.count. These are separated by
just 8B and are therefore likely to share a cache line. When one thread
modifies count, the cache line is in a modified state so when other
threads read sample_width in the main latency detection loop, they fetch
the modified cache line. On some systems, the fetch itself may be slow
enough to count as a latency event, which could set up a self
reinforcing cycle of latency events as each event increments count which
then causes more latency events, continuing the cycle.
The other result of the unprotected data access is that hwlat_data.count
can end up with duplicate or missed values, which was observed on some
systems in testing.
Convert hwlat_data.count to atomic64_t so it can be safely modified
without locking, and prevent false sharing by pulling sample_width into
a local variable.
One system this was tested on was a dual socket server with 32 CPUs on
each numa node. With settings of 1us threshold, 1000us width, and
2000us window, this change reduced the number of latency events from
500 per second down to approximately 1 event per minute. Some machines
tested did not exhibit measurable latency from the false sharing.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260210074810.6328-1-clord@mykolab.com
Signed-off-by: Colin Lord <clord@mykolab.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
LLM Generated explanations, may be completely bogus:
## Analysis of the Commit
### 1. Commit Message Analysis
The commit message is very detailed and clearly describes:
- **The bug**: `get_sample()` assumes `hwlat_data.lock` is held, but
it's not actually held. This leads to unprotected data access and
false sharing in per-cpu mode.
- **The specific false sharing**: `hwlat_data.sample_width` and
`hwlat_data.count` are 8 bytes apart, likely sharing a cache line.
When one thread modifies `count`, other threads reading `sample_width`
in the latency detection loop fetch the modified cache line, causing
measurable latency.
- **The self-reinforcing cycle**: The latency from cache line fetch
triggers a latency event, which increments `count`, which causes more
cache line invalidation, which causes more latency events — a vicious
cycle.
- **The data race**: `hwlat_data.count` can end up with duplicate or
missed values due to unprotected concurrent access.
- **Concrete test results**: On a dual-socket 32-CPUs-per-node server,
latency events dropped from 500/sec to ~1/min.
Keywords: "false sharing", "false positive latency events", "unprotected
data access", "duplicate or missed values."
### 2. Code Change Analysis
The changes are minimal and surgical:
1. **`hwlat_data.count` converted from `u64` to `atomic64_t`**: This
fixes a real data race where multiple threads could concurrently
increment `count` without synchronization, leading to lost updates
(duplicate/missed values). The `atomic64_inc_return()` replaces
`hwlat_data.count++; s.seqnum = hwlat_data.count;` with a single
atomic operation.
2. **`sample_width` pulled into a local variable with `READ_ONCE()`**:
`u64 sample_width = READ_ONCE(hwlat_data.sample_width);` is used
instead of reading `hwlat_data.sample_width` in the hot loop (`do {
... } while (total <= sample_width)`). This:
- Prevents the CPU from repeatedly fetching a cache line that may be
bouncing between cores
- Eliminates the false sharing between `sample_width` and `count`
- Uses `READ_ONCE()` for proper load semantics
3. **Init path updated**: `hwlat_data.count = 0` →
`atomic64_set(&hwlat_data.count, 0)` — consistent with the type
change.
4. **Comment fix**: Removes the incorrect claim that `get_sample()` is
"called with hwlat_data.lock held."
### 3. Bug Classification
This commit fixes **multiple real bugs**:
1. **Data race on `hwlat_data.count`**: Concurrent unsynchronized access
to a shared counter. This is a real correctness bug — sequence
numbers can be duplicated or skipped.
2. **False sharing causing false positive latency detection**: The hwlat
tracer is producing bogus results (500 events/sec vs 1/min). This is
a **functional correctness bug** — the tracer is reporting phantom
hardware latency that doesn't exist. Users relying on hwlat tracer
results would be misled.
3. **Self-reinforcing feedback loop**: The false sharing creates a
pathological cycle that makes the tracer practically unusable on some
multi-socket systems.
### 4. Scope and Risk Assessment
- **Lines changed**: ~15 lines of actual code changes across 4 hunks in
a single file
- **Files touched**: 1 (`kernel/trace/trace_hwlat.c`)
- **Risk**: Very low. The changes are:
- Converting a counter to atomic (well-understood primitive)
- Caching a value in a local variable (safe, the value doesn't need to
be re-read)
- Using `READ_ONCE()` (standard kernel pattern)
- **Subsystem**: Tracing — self-contained, well-maintained by Steven
Rostedt
- **Could it break something?**: Extremely unlikely. The atomic64
operations are well-tested primitives, and caching sample_width is
semantically equivalent (the width doesn't change during a sample).
### 5. User Impact
- **Who is affected**: Anyone using the hwlat tracer in per-cpu mode on
multi-socket systems
- **Severity**: The tracer produces wildly incorrect results (500x false
positives) on affected systems
- **Real-world impact**: Users trying to validate hardware latency
characteristics for real-time workloads would get completely
misleading data
- **The data race on count**: Could cause sequence number issues that
affect trace analysis tooling
### 6. Stability Indicators
- **Signed-off by Steven Rostedt** (tracing subsystem maintainer) — high
confidence
- **Concrete test data** provided showing dramatic improvement
- **Link to mailing list** discussion provided
- The fix uses standard kernel primitives (atomic64_t, READ_ONCE) —
well-understood patterns
### 7. Dependency Check
- No dependencies on other commits
- `atomic64_t` and `READ_ONCE()` are available in all stable kernel
versions
- The hwlat tracer exists in all recent stable trees (introduced in
v4.9)
### Stable Kernel Rules Assessment
1. **Obviously correct and tested**: Yes — tested on real hardware with
measurable improvement
2. **Fixes a real bug**: Yes — data race + false sharing causing
incorrect tracer output
3. **Important issue**: Yes — tracer producing 500x false positive
latency events, plus data race on counter
4. **Small and contained**: Yes — ~15 lines in one file
5. **No new features**: Correct — this is a pure bug fix
6. **Applies cleanly**: Should apply cleanly to recent stable trees
### Risk vs Benefit
- **Risk**: Near zero — atomic counter and local variable caching are
trivially safe changes
- **Benefit**: High — fixes a data race and makes the hwlat tracer
produce correct results on multi-socket systems
**YES**
kernel/trace/trace_hwlat.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 2f7b94e98317c..3fe274b84f1c2 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -102,9 +102,9 @@ struct hwlat_sample {
/* keep the global state somewhere. */
static struct hwlat_data {
- struct mutex lock; /* protect changes */
+ struct mutex lock; /* protect changes */
- u64 count; /* total since reset */
+ atomic64_t count; /* total since reset */
u64 sample_window; /* total sampling window (on+off) */
u64 sample_width; /* active sampling portion of window */
@@ -193,8 +193,7 @@ void trace_hwlat_callback(bool enter)
* get_sample - sample the CPU TSC and look for likely hardware latencies
*
* Used to repeatedly capture the CPU TSC (or similar), looking for potential
- * hardware-induced latency. Called with interrupts disabled and with
- * hwlat_data.lock held.
+ * hardware-induced latency. Called with interrupts disabled.
*/
static int get_sample(void)
{
@@ -204,6 +203,7 @@ static int get_sample(void)
time_type start, t1, t2, last_t2;
s64 diff, outer_diff, total, last_total = 0;
u64 sample = 0;
+ u64 sample_width = READ_ONCE(hwlat_data.sample_width);
u64 thresh = tracing_thresh;
u64 outer_sample = 0;
int ret = -1;
@@ -267,7 +267,7 @@ static int get_sample(void)
if (diff > sample)
sample = diff; /* only want highest value */
- } while (total <= hwlat_data.sample_width);
+ } while (total <= sample_width);
barrier(); /* finish the above in the view for NMIs */
trace_hwlat_callback_enabled = false;
@@ -285,8 +285,7 @@ static int get_sample(void)
if (kdata->nmi_total_ts)
do_div(kdata->nmi_total_ts, NSEC_PER_USEC);
- hwlat_data.count++;
- s.seqnum = hwlat_data.count;
+ s.seqnum = atomic64_inc_return(&hwlat_data.count);
s.duration = sample;
s.outer_duration = outer_sample;
s.nmi_total_ts = kdata->nmi_total_ts;
@@ -832,7 +831,7 @@ static int hwlat_tracer_init(struct trace_array *tr)
hwlat_trace = tr;
- hwlat_data.count = 0;
+ atomic64_set(&hwlat_data.count, 0);
tr->max_latency = 0;
save_tracing_thresh = tracing_thresh;
--
2.51.0
^ permalink raw reply related
* [PATCH] pstore: fix ftrace dump, when ECC is enabled
From: Andrey Skvortsov @ 2026-02-15 18:51 UTC (permalink / raw)
To: Kees Cook, Tony Luck, Guilherme G. Piccoli, linux-hardening,
linux-kernel, Steven Rostedt, Masami Hiramatsu, Mark Rutland,
linux-trace-kernel
Cc: Andrey Skvortsov
total_size is sum of record->size and record->ecc_notice_size (ECC: No
errors detected). When ECC is not used, then there is no problem.
When ECC is enabled, then ftrace dump is decoded incorrectly after
restart.
First this affects starting offset calculation, that breaks
reading of all ftrace records.
CPU:66 ts:51646260179894273 3818ffff80008002 fe00ffff800080f0 0x3818ffff80008002 <- 0xfe00ffff800080f0
CPU:66 ts:56589664458375169 3818ffff80008002 ff02ffff800080f0 0x3818ffff80008002 <- 0xff02ffff800080f0
CPU:67 ts:13194139533313 afe4ffff80008002 1ffff800080f0 0xafe4ffff80008002 <- 0x1ffff800080f0
CPU:67 ts:13194139533313 b7d0ffff80008001 100ffff80008002 0xb7d0ffff80008001 <- 0x100ffff80008002
CPU:67 ts:51646260179894273 8de0ffff80008001 202ffff80008002 0x8de0ffff80008001 <- 0x202ffff80008002
Second ECC notice message is printed like ftrace record and as a
result couple of last records are completely wrong.
For example, when the starting offset is fixed:
CPU:0 ts:113 ffffffc00879bd04 ffffffc0080dc08c cpuidle_enter <- do_idle+0x20c/0x290
CPU:0 ts:114 ffffffc00879bd04 ffffffc0080dc08c cpuidle_enter <- do_idle+0x20c/0x290
CPU:100 ts:28259048229270629 6f4e203a4343450a 2073726f72726520 0x6f4e203a4343450a <- 0x2073726f72726520
Signed-off-by: Andrey Skvortsov <andrej.skvortzov@gmail.com>
---
fs/pstore/inode.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index b4e55c90f8dc2..9c2d5e5f31d65 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -74,9 +74,9 @@ static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
if (!data)
return NULL;
- data->off = ps->total_size % REC_SIZE;
+ data->off = ps->record->size % REC_SIZE;
data->off += *pos * REC_SIZE;
- if (data->off + REC_SIZE > ps->total_size)
+ if (data->off + REC_SIZE > ps->record->size)
return NULL;
return_ptr(data);
@@ -94,7 +94,7 @@ static void *pstore_ftrace_seq_next(struct seq_file *s, void *v, loff_t *pos)
(*pos)++;
data->off += REC_SIZE;
- if (data->off + REC_SIZE > ps->total_size)
+ if (data->off + REC_SIZE > ps->record->size)
return NULL;
return data;
--
2.51.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox