Commit 8aeacf25 authored by Joel Granados's avatar Joel Granados Committed by Ingo Molnar
Browse files

perf/core: Move perf_event sysctls into kernel/events 



Move ctl tables to two files:

 - perf_event_{paranoid,mlock_kb,max_sample_rate} and
   perf_cpu_time_max_percent into kernel/events/core.c

 - perf_event_max_{stack,context_per_stack} into
   kernel/events/callchain.c

Make static variables and functions that are fully contained in core.c
and callchain.cand remove them from include/linux/perf_event.h.
Additionally six_hundred_forty_kb is moved to callchain.c.

Two new sysctl tables are added ({callchain,events_core}_sysctl_table)
with their respective sysctl registration functions.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kerenel/sysctl.c.

Signed-off-by: default avatarJoel Granados <joel.granados@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250218-jag-mv_ctltables-v1-5-cd3698ab8d29@kernel.org
parent e6e21a9a

include/linux/perf_event.h

+0 −9
Original line number Diff line number Diff line
@@ -1652,19 +1652,10 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 
}



extern int sysctl_perf_event_paranoid;

extern int sysctl_perf_event_mlock;

extern int sysctl_perf_event_sample_rate;

extern int sysctl_perf_cpu_time_max_percent;



extern void perf_sample_event_took(u64 sample_len_ns);



int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,

		void *buffer, size_t *lenp, loff_t *ppos);

int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,

		void *buffer, size_t *lenp, loff_t *ppos);

int perf_event_max_stack_handler(const struct ctl_table *table, int write,

		void *buffer, size_t *lenp, loff_t *ppos);



/* Access to perf_event_open(2) syscall. */

#define PERF_SECURITY_OPEN		0

kernel/events/callchain.c

+32 −6
Original line number Diff line number Diff line
@@ -22,6 +22,7 @@ struct callchain_cpus_entries { 


int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;

int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK;

static const int six_hundred_forty_kb = 640 * 1024;



static inline size_t perf_callchain_entry__sizeof(void)

{
@@ -266,11 +267,7 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, 
	return entry;

}



/*

 * Used for sysctl_perf_event_max_stack and

 * sysctl_perf_event_max_contexts_per_stack.

 */

int perf_event_max_stack_handler(const struct ctl_table *table, int write,

static int perf_event_max_stack_handler(const struct ctl_table *table, int write,

					void *buffer, size_t *lenp, loff_t *ppos)

{

	int *value = table->data;
@@ -292,3 +289,32 @@ int perf_event_max_stack_handler(const struct ctl_table *table, int write, 


	return ret;

}



static const struct ctl_table callchain_sysctl_table[] = {

	{

		.procname	= "perf_event_max_stack",

		.data		= &sysctl_perf_event_max_stack,

		.maxlen		= sizeof(sysctl_perf_event_max_stack),

		.mode		= 0644,

		.proc_handler	= perf_event_max_stack_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= (void *)&six_hundred_forty_kb,

	},

	{

		.procname	= "perf_event_max_contexts_per_stack",

		.data		= &sysctl_perf_event_max_contexts_per_stack,

		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),

		.mode		= 0644,

		.proc_handler	= perf_event_max_stack_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= SYSCTL_ONE_THOUSAND,

	},

};



static int __init init_callchain_sysctls(void)

{

	register_sysctl_init("kernel", callchain_sysctl_table);

	return 0;

}

core_initcall(init_callchain_sysctls);

kernel/events/core.c

+51 −6
Original line number Diff line number Diff line
@@ -452,8 +452,8 @@ static struct kmem_cache *perf_event_cache; 
 */

int sysctl_perf_event_paranoid __read_mostly = 2;



/* Minimum for 512 kiB + 1 user control page */

int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */

/* Minimum for 512 kiB + 1 user control page. 'free' kiB per user. */

static int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024);



/*

 * max perf event sample rate
@@ -463,6 +463,7 @@ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' 
#define DEFAULT_CPU_TIME_MAX_PERCENT	25



int sysctl_perf_event_sample_rate __read_mostly	= DEFAULT_MAX_SAMPLE_RATE;

static int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;



static int max_samples_per_tick __read_mostly	= DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);

static int perf_sample_period_ns __read_mostly	= DEFAULT_SAMPLE_PERIOD_NS;
@@ -484,7 +485,7 @@ static void update_perf_cpu_limits(void) 


static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);



int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,

static int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,

				       void *buffer, size_t *lenp, loff_t *ppos)

{

	int ret;
@@ -506,9 +507,7 @@ int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, 
	return 0;

}



int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;



int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,

static int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,

		void *buffer, size_t *lenp, loff_t *ppos)

{

	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -528,6 +527,52 @@ int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, 
	return 0;

}



static const struct ctl_table events_core_sysctl_table[] = {

	/*

	 * User-space relies on this file as a feature check for

	 * perf_events being enabled. It's an ABI, do not remove!

	 */

	{

		.procname	= "perf_event_paranoid",

		.data		= &sysctl_perf_event_paranoid,

		.maxlen		= sizeof(sysctl_perf_event_paranoid),

		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

	{

		.procname	= "perf_event_mlock_kb",

		.data		= &sysctl_perf_event_mlock,

		.maxlen		= sizeof(sysctl_perf_event_mlock),

		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

	{

		.procname	= "perf_event_max_sample_rate",

		.data		= &sysctl_perf_event_sample_rate,

		.maxlen		= sizeof(sysctl_perf_event_sample_rate),

		.mode		= 0644,

		.proc_handler	= perf_event_max_sample_rate_handler,

		.extra1		= SYSCTL_ONE,

	},

	{

		.procname	= "perf_cpu_time_max_percent",

		.data		= &sysctl_perf_cpu_time_max_percent,

		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),

		.mode		= 0644,

		.proc_handler	= perf_cpu_time_max_percent_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= SYSCTL_ONE_HUNDRED,

	},

};



static int __init init_events_core_sysctls(void)

{

	register_sysctl_init("kernel", events_core_sysctl_table);

	return 0;

}

core_initcall(init_events_core_sysctls);





/*

 * perf samples are done in some very critical code paths (NMIs).

 * If they take too much CPU time, the system can lock up and not

kernel/sysctl.c

+0 −64
Original line number Diff line number Diff line
@@ -54,7 +54,6 @@ 
#include <linux/acpi.h>

#include <linux/reboot.h>

#include <linux/ftrace.h>

#include <linux/perf_event.h>

#include <linux/oom.h>

#include <linux/kmod.h>

#include <linux/capability.h>
@@ -91,12 +90,6 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals); 
#if defined(CONFIG_SYSCTL)



/* Constants used for minimum and maximum */



#ifdef CONFIG_PERF_EVENTS

static const int six_hundred_forty_kb = 640 * 1024;

#endif





static const int ngroups_max = NGROUPS_MAX;

static const int cap_last_cap = CAP_LAST_CAP;
@@ -1932,63 +1925,6 @@ static const struct ctl_table kern_table[] = { 
		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

#endif

#ifdef CONFIG_PERF_EVENTS

	/*

	 * User-space scripts rely on the existence of this file

	 * as a feature check for perf_events being enabled.

	 *

	 * So it's an ABI, do not remove!

	 */

	{

		.procname	= "perf_event_paranoid",

		.data		= &sysctl_perf_event_paranoid,

		.maxlen		= sizeof(sysctl_perf_event_paranoid),

		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

	{

		.procname	= "perf_event_mlock_kb",

		.data		= &sysctl_perf_event_mlock,

		.maxlen		= sizeof(sysctl_perf_event_mlock),

		.mode		= 0644,

		.proc_handler	= proc_dointvec,

	},

	{

		.procname	= "perf_event_max_sample_rate",

		.data		= &sysctl_perf_event_sample_rate,

		.maxlen		= sizeof(sysctl_perf_event_sample_rate),

		.mode		= 0644,

		.proc_handler	= perf_event_max_sample_rate_handler,

		.extra1		= SYSCTL_ONE,

	},

	{

		.procname	= "perf_cpu_time_max_percent",

		.data		= &sysctl_perf_cpu_time_max_percent,

		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),

		.mode		= 0644,

		.proc_handler	= perf_cpu_time_max_percent_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= SYSCTL_ONE_HUNDRED,

	},

	{

		.procname	= "perf_event_max_stack",

		.data		= &sysctl_perf_event_max_stack,

		.maxlen		= sizeof(sysctl_perf_event_max_stack),

		.mode		= 0644,

		.proc_handler	= perf_event_max_stack_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= (void *)&six_hundred_forty_kb,

	},

	{

		.procname	= "perf_event_max_contexts_per_stack",

		.data		= &sysctl_perf_event_max_contexts_per_stack,

		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),

		.mode		= 0644,

		.proc_handler	= perf_event_max_stack_handler,

		.extra1		= SYSCTL_ZERO,

		.extra2		= SYSCTL_ONE_THOUSAND,

	},

#endif

	{

		.procname	= "panic_on_warn",