aboutsummaryrefslogtreecommitdiff
path: root/kernel/sysctl.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sysctl.c')
-rw-r--r--kernel/sysctl.c447
1 files changed, 31 insertions, 416 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 830aaf8ca08e..35d034219513 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -61,13 +61,9 @@
#include <linux/capability.h>
#include <linux/binfmts.h>
#include <linux/sched/sysctl.h>
-#include <linux/kexec.h>
-#include <linux/bpf.h>
#include <linux/mount.h>
#include <linux/userfaultfd_k.h>
-#include <linux/latencytop.h>
#include <linux/pid.h>
-#include <linux/delayacct.h>
#include "../lib/kstrtox.h"
@@ -82,15 +78,9 @@
#ifdef CONFIG_SPARC
#include <asm/setup.h>
#endif
-#ifdef CONFIG_BSD_PROCESS_ACCT
-#include <linux/acct.h>
-#endif
#ifdef CONFIG_RT_MUTEXES
#include <linux/rtmutex.h>
#endif
-#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
-#include <linux/lockdep.h>
-#endif
#if defined(CONFIG_SYSCTL)
@@ -100,8 +90,6 @@
static const int six_hundred_forty_kb = 640 * 1024;
#endif
-/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
-static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
static const int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
@@ -148,66 +136,6 @@ static const int max_extfrag_threshold = 1000;
#endif /* CONFIG_SYSCTL */
-#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
-static int bpf_stats_handler(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
-{
- struct static_key *key = (struct static_key *)table->data;
- static int saved_val;
- int val, ret;
- struct ctl_table tmp = {
- .data = &val,
- .maxlen = sizeof(val),
- .mode = table->mode,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- };
-
- if (write && !capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- mutex_lock(&bpf_stats_enabled_mutex);
- val = saved_val;
- ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
- if (write && !ret && val != saved_val) {
- if (val)
- static_key_slow_inc(key);
- else
- static_key_slow_dec(key);
- saved_val = val;
- }
- mutex_unlock(&bpf_stats_enabled_mutex);
- return ret;
-}
-
-void __weak unpriv_ebpf_notify(int new_state)
-{
-}
-
-static int bpf_unpriv_handler(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
-{
- int ret, unpriv_enable = *(int *)table->data;
- bool locked_state = unpriv_enable == 1;
- struct ctl_table tmp = *table;
-
- if (write && !capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- tmp.data = &unpriv_enable;
- ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
- if (write && !ret) {
- if (locked_state && unpriv_enable != 1)
- return -EPERM;
- *(int *)table->data = unpriv_enable;
- }
-
- unpriv_ebpf_notify(unpriv_enable);
-
- return ret;
-}
-#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */
-
/*
* /proc/sys support
*/
@@ -518,14 +446,14 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
if (*negp) {
if (*lvalp > (unsigned long) INT_MAX + 1)
return -EINVAL;
- *valp = -*lvalp;
+ WRITE_ONCE(*valp, -*lvalp);
} else {
if (*lvalp > (unsigned long) INT_MAX)
return -EINVAL;
- *valp = *lvalp;
+ WRITE_ONCE(*valp, *lvalp);
}
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
if (val < 0) {
*negp = true;
*lvalp = -(unsigned long)val;
@@ -544,9 +472,9 @@ static int do_proc_douintvec_conv(unsigned long *lvalp,
if (write) {
if (*lvalp > UINT_MAX)
return -EINVAL;
- *valp = *lvalp;
+ WRITE_ONCE(*valp, *lvalp);
} else {
- unsigned int val = *valp;
+ unsigned int val = READ_ONCE(*valp);
*lvalp = (unsigned long)val;
}
return 0;
@@ -929,7 +857,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
if ((param->min && *param->min > tmp) ||
(param->max && *param->max < tmp))
return -EINVAL;
- *valp = tmp;
+ WRITE_ONCE(*valp, tmp);
}
return 0;
@@ -995,7 +923,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
(param->max && *param->max < tmp))
return -ERANGE;
- *valp = tmp;
+ WRITE_ONCE(*valp, tmp);
}
return 0;
@@ -1079,13 +1007,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write,
tmp.maxlen = sizeof(val);
tmp.data = &val;
- val = *data;
+ val = READ_ONCE(*data);
res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos,
do_proc_douintvec_minmax_conv, &param);
if (res)
return res;
if (write)
- *data = val;
+ WRITE_ONCE(*data, val);
return 0;
}
EXPORT_SYMBOL_GPL(proc_dou8vec_minmax);
@@ -1162,9 +1090,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
err = -EINVAL;
break;
}
- *i = val;
+ WRITE_ONCE(*i, val);
} else {
- val = convdiv * (*i) / convmul;
+ val = convdiv * READ_ONCE(*i) / convmul;
if (!first)
proc_put_char(&buffer, &left, '\t');
proc_put_long(&buffer, &left, val, false);
@@ -1245,9 +1173,12 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
if (write) {
if (*lvalp > INT_MAX / HZ)
return 1;
- *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
+ if (*negp)
+ WRITE_ONCE(*valp, -*lvalp * HZ);
+ else
+ WRITE_ONCE(*valp, *lvalp * HZ);
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
unsigned long lval;
if (val < 0) {
*negp = true;
@@ -1293,9 +1224,9 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
if (jif > INT_MAX)
return 1;
- *valp = (int)jif;
+ WRITE_ONCE(*valp, (int)jif);
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
unsigned long lval;
if (val < 0) {
*negp = true;
@@ -1363,8 +1294,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
* @ppos: the current position in the file
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string.
- * The values read are assumed to be in 1/1000 seconds, and
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in 1/1000 seconds, and
* are converted into jiffies.
*
* Returns 0 on success.
@@ -1659,35 +1590,6 @@ int proc_do_static_key(struct ctl_table *table, int write,
}
static struct ctl_table kern_table[] = {
- {
- .procname = "sched_child_runs_first",
- .data = &sysctl_sched_child_runs_first,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#ifdef CONFIG_SCHEDSTATS
- {
- .procname = "sched_schedstats",
- .data = NULL,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sysctl_schedstats,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif /* CONFIG_SCHEDSTATS */
-#ifdef CONFIG_TASK_DELAY_ACCT
- {
- .procname = "task_delayacct",
- .data = NULL,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sysctl_delayacct,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif /* CONFIG_TASK_DELAY_ACCT */
#ifdef CONFIG_NUMA_BALANCING
{
.procname = "numa_balancing",
@@ -1700,103 +1602,6 @@ static struct ctl_table kern_table[] = {
},
#endif /* CONFIG_NUMA_BALANCING */
{
- .procname = "sched_rt_period_us",
- .data = &sysctl_sched_rt_period,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_rt_handler,
- },
- {
- .procname = "sched_rt_runtime_us",
- .data = &sysctl_sched_rt_runtime,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = sched_rt_handler,
- },
- {
- .procname = "sched_deadline_period_max_us",
- .data = &sysctl_sched_dl_period_max,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sched_deadline_period_min_us",
- .data = &sysctl_sched_dl_period_min,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sched_rr_timeslice_ms",
- .data = &sysctl_sched_rr_timeslice,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = sched_rr_handler,
- },
-#ifdef CONFIG_UCLAMP_TASK
- {
- .procname = "sched_util_clamp_min",
- .data = &sysctl_sched_uclamp_util_min,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sysctl_sched_uclamp_handler,
- },
- {
- .procname = "sched_util_clamp_max",
- .data = &sysctl_sched_uclamp_util_max,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sysctl_sched_uclamp_handler,
- },
- {
- .procname = "sched_util_clamp_min_rt_default",
- .data = &sysctl_sched_uclamp_util_min_rt_default,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sysctl_sched_uclamp_handler,
- },
-#endif
-#ifdef CONFIG_CFS_BANDWIDTH
- {
- .procname = "sched_cfs_bandwidth_slice_us",
- .data = &sysctl_sched_cfs_bandwidth_slice,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ONE,
- },
-#endif
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
- {
- .procname = "sched_energy_aware",
- .data = &sysctl_sched_energy_aware,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_energy_aware_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif
-#ifdef CONFIG_PROVE_LOCKING
- {
- .procname = "prove_locking",
- .data = &prove_locking,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
-#ifdef CONFIG_LOCK_STAT
- {
- .procname = "lock_stat",
- .data = &lock_stat,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
- {
.procname = "panic",
.data = &panic_timeout,
.maxlen = sizeof(int),
@@ -1820,24 +1625,6 @@ static struct ctl_table kern_table[] = {
.extra2 = SYSCTL_ONE,
},
#endif
-#ifdef CONFIG_LATENCYTOP
- {
- .procname = "latencytop",
- .data = &latencytop_enabled,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = sysctl_latencytop,
- },
-#endif
-#ifdef CONFIG_BLK_DEV_INITRD
- {
- .procname = "real-root-dev",
- .data = &real_root_dev,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
{
.procname = "print-fatal-signals",
.data = &print_fatal_signals,
@@ -1895,22 +1682,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
- {
- .procname = "ctrl-alt-del",
- .data = &C_A_D,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#ifdef CONFIG_FUNCTION_TRACER
- {
- .procname = "ftrace_enabled",
- .data = &ftrace_enabled,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = ftrace_enable_sysctl,
- },
-#endif
#ifdef CONFIG_STACK_TRACER
{
.procname = "stack_tracer_enabled",
@@ -1943,18 +1714,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = tracepoint_printk_sysctl,
},
#endif
-#ifdef CONFIG_KEXEC_CORE
- {
- .procname = "kexec_load_disabled",
- .data = &kexec_load_disabled,
- .maxlen = sizeof(int),
- .mode = 0644,
- /* only handle a transition from default "0" to "1" */
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ONE,
- .extra2 = SYSCTL_ONE,
- },
-#endif
#ifdef CONFIG_MODULES
{
.procname = "modprobe",
@@ -1983,15 +1742,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dostring,
},
#endif
-#ifdef CONFIG_BSD_PROCESS_ACCT
- {
- .procname = "acct",
- .data = &acct_parm,
- .maxlen = 3*sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
#ifdef CONFIG_MAGIC_SYSRQ
{
.procname = "sysrq",
@@ -2049,17 +1799,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef CONFIG_SMP
- {
- .procname = "oops_all_cpu_backtrace",
- .data = &sysctl_oops_all_cpu_backtrace,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif /* CONFIG_SMP */
{
.procname = "pid_max",
.data = &pid_max,
@@ -2208,13 +1947,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
- {
- .procname = "poweroff_cmd",
- .data = &poweroff_cmd,
- .maxlen = POWEROFF_CMD_PATH_LEN,
- .mode = 0644,
- .proc_handler = proc_dostring,
- },
#ifdef CONFIG_KEYS
{
.procname = "keys",
@@ -2288,35 +2020,6 @@ static struct ctl_table kern_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
- {
- .procname = "timer_migration",
- .data = &sysctl_timer_migration,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = timer_migration_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif
-#ifdef CONFIG_BPF_SYSCALL
- {
- .procname = "unprivileged_bpf_disabled",
- .data = &sysctl_unprivileged_bpf_disabled,
- .maxlen = sizeof(sysctl_unprivileged_bpf_disabled),
- .mode = 0644,
- .proc_handler = bpf_unpriv_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_TWO,
- },
- {
- .procname = "bpf_stats_enabled",
- .data = &bpf_stats_enabled_key.key,
- .maxlen = sizeof(bpf_stats_enabled_key),
- .mode = 0644,
- .proc_handler = bpf_stats_handler,
- },
-#endif
#if defined(CONFIG_TREE_RCU)
{
.procname = "panic_on_rcu_stall",
@@ -2353,29 +2056,6 @@ static struct ctl_table vm_table[] = {
.extra2 = SYSCTL_TWO,
},
{
- .procname = "panic_on_oom",
- .data = &sysctl_panic_on_oom,
- .maxlen = sizeof(sysctl_panic_on_oom),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_TWO,
- },
- {
- .procname = "oom_kill_allocating_task",
- .data = &sysctl_oom_kill_allocating_task,
- .maxlen = sizeof(sysctl_oom_kill_allocating_task),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "oom_dump_tasks",
- .data = &sysctl_oom_dump_tasks,
- .maxlen = sizeof(sysctl_oom_dump_tasks),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "overcommit_ratio",
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
@@ -2398,55 +2078,6 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ZERO,
},
{
- .procname = "dirty_background_ratio",
- .data = &dirty_background_ratio,
- .maxlen = sizeof(dirty_background_ratio),
- .mode = 0644,
- .proc_handler = dirty_background_ratio_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE_HUNDRED,
- },
- {
- .procname = "dirty_background_bytes",
- .data = &dirty_background_bytes,
- .maxlen = sizeof(dirty_background_bytes),
- .mode = 0644,
- .proc_handler = dirty_background_bytes_handler,
- .extra1 = SYSCTL_LONG_ONE,
- },
- {
- .procname = "dirty_ratio",
- .data = &vm_dirty_ratio,
- .maxlen = sizeof(vm_dirty_ratio),
- .mode = 0644,
- .proc_handler = dirty_ratio_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE_HUNDRED,
- },
- {
- .procname = "dirty_bytes",
- .data = &vm_dirty_bytes,
- .maxlen = sizeof(vm_dirty_bytes),
- .mode = 0644,
- .proc_handler = dirty_bytes_handler,
- .extra1 = (void *)&dirty_bytes_min,
- },
- {
- .procname = "dirty_writeback_centisecs",
- .data = &dirty_writeback_interval,
- .maxlen = sizeof(dirty_writeback_interval),
- .mode = 0644,
- .proc_handler = dirty_writeback_centisecs_handler,
- },
- {
- .procname = "dirty_expire_centisecs",
- .data = &dirty_expire_interval,
- .maxlen = sizeof(dirty_expire_interval),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- },
- {
.procname = "dirtytime_expire_seconds",
.data = &dirtytime_expire_interval,
.maxlen = sizeof(dirtytime_expire_interval),
@@ -2463,6 +2094,17 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO_HUNDRED,
},
+#ifdef CONFIG_NUMA
+ {
+ .procname = "numa_stat",
+ .data = &sysctl_vm_numa_stat,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = sysctl_vm_numa_stat_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+#endif
#ifdef CONFIG_HUGETLB_PAGE
{
.procname = "nr_hugepages",
@@ -2479,15 +2121,6 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &hugetlb_mempolicy_sysctl_handler,
},
- {
- .procname = "numa_stat",
- .data = &sysctl_vm_numa_stat,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = sysctl_vm_numa_stat_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
#endif
{
.procname = "hugetlb_shm_group",
@@ -2618,13 +2251,6 @@ static struct ctl_table vm_table[] = {
},
#endif
{
- .procname = "laptop_mode",
- .data = &laptop_mode,
- .maxlen = sizeof(laptop_mode),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- {
.procname = "vfs_cache_pressure",
.data = &sysctl_vfs_cache_pressure,
.maxlen = sizeof(sysctl_vfs_cache_pressure),
@@ -2721,17 +2347,6 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ZERO,
},
#endif
-#ifdef CONFIG_HIGHMEM
- {
- .procname = "highmem_is_dirtyable",
- .data = &vm_highmem_is_dirtyable,
- .maxlen = sizeof(vm_highmem_is_dirtyable),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
-#endif
#ifdef CONFIG_MEMORY_FAILURE
{
.procname = "memory_failure_early_kill",
Powered by cgit, Gruvboxed by Blaster4385.