diff options
Diffstat (limited to 'kernel/sysctl.c')
| -rw-r--r-- | kernel/sysctl.c | 1676 |
1 files changed, 183 insertions, 1493 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 137d4abe3eda..2cd767b9680e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1,87 +1,27 @@ // SPDX-License-Identifier: GPL-2.0-only /* * sysctl.c: General linux system control interface - * - * Begun 24 March 1995, Stephen Tweedie - * Added /proc support, Dec 1995 - * Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas. - * Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver. - * Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver. - * Dynamic registration fixes, Stephen Tweedie. - * Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn. - * Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris - * Horn. - * Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer. - * Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer. - * Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill - * Wendling. - * The list_for_each() macro wasn't appropriate for the sysctl loop. - * Removed it and replaced it with older style, 03/23/00, Bill Wendling */ -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/slab.h> #include <linux/sysctl.h> #include <linux/bitmap.h> -#include <linux/signal.h> -#include <linux/panic.h> -#include <linux/printk.h> #include <linux/proc_fs.h> -#include <linux/security.h> #include <linux/ctype.h> -#include <linux/kmemleak.h> -#include <linux/filter.h> -#include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kobject.h> -#include <linux/net.h> -#include <linux/sysrq.h> #include <linux/highuid.h> #include <linux/writeback.h> -#include <linux/ratelimit.h> -#include <linux/compaction.h> -#include <linux/hugetlb.h> #include <linux/initrd.h> -#include <linux/key.h> -#include <linux/times.h> #include <linux/limits.h> -#include <linux/dcache.h> #include <linux/syscalls.h> -#include <linux/vmstat.h> -#include <linux/nfs_fs.h> -#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> -#include <linux/binfmts.h> -#include <linux/sched/sysctl.h> -#include <linux/mount.h> -#include <linux/userfaultfd_k.h> -#include <linux/pid.h> #include "../lib/kstrtox.h" #include <linux/uaccess.h> #include <asm/processor.h> -#ifdef CONFIG_X86 -#include <asm/nmi.h> -#include <asm/stacktrace.h> -#include <asm/io.h> -#endif -#ifdef CONFIG_SPARC -#include <asm/setup.h> -#endif -#ifdef CONFIG_RT_MUTEXES -#include <linux/rtmutex.h> -#endif - /* shared constants to be used in various sysctls */ const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 }; EXPORT_SYMBOL(sysctl_vals); @@ -92,12 +32,6 @@ 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; @@ -120,7 +54,8 @@ static const int cap_last_cap = CAP_LAST_CAP; * to the buffer. * * These write modes control how current file position affects the behavior of - * updating sysctl values through the proc interface on each write. + * updating internal kernel (SYSCTL_USER_TO_KERN) sysctl values through the proc + * interface on each write. */ enum sysctl_writes_mode { SYSCTL_WRITES_LEGACY = -1, @@ -130,12 +65,6 @@ enum sysctl_writes_mode { static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT; #endif /* CONFIG_PROC_SYSCTL */ - -#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ - defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) -int sysctl_legacy_va_layout; -#endif - #endif /* CONFIG_SYSCTL */ /* @@ -144,7 +73,7 @@ int sysctl_legacy_va_layout; #ifdef CONFIG_PROC_SYSCTL -static int _proc_do_string(char *data, int maxlen, int write, +static int _proc_do_string(char *data, int maxlen, int dir, char *buffer, size_t *lenp, loff_t *ppos) { size_t len; @@ -155,7 +84,7 @@ static int _proc_do_string(char *data, int maxlen, int write, return 0; } - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) { /* Only continue writes not past the end of buffer. */ len = strlen(data); @@ -206,7 +135,7 @@ static int _proc_do_string(char *data, int maxlen, int write, return 0; } -static void warn_sysctl_write(struct ctl_table *table) +static void warn_sysctl_write(const struct ctl_table *table) { pr_warn_once("%s wrote to %s when file position was not 0!\n" "This will not be supported in the future. To silence this\n" @@ -224,7 +153,7 @@ static void warn_sysctl_write(struct ctl_table *table) * handlers can ignore the return value. */ static bool proc_first_pos_non_zero_ignore(loff_t *ppos, - struct ctl_table *table) + const struct ctl_table *table) { if (!*ppos) return false; @@ -243,7 +172,7 @@ static bool proc_first_pos_non_zero_ignore(loff_t *ppos, /** * proc_dostring - read a string sysctl * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -257,13 +186,13 @@ static bool proc_first_pos_non_zero_ignore(loff_t *ppos, * * Returns 0 on success. */ -int proc_dostring(struct ctl_table *table, int write, +int proc_dostring(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - if (write) + if (SYSCTL_USER_TO_KERN(dir)) proc_first_pos_non_zero_ignore(ppos, table); - return _proc_do_string(table->data, table->maxlen, write, buffer, lenp, + return _proc_do_string(table->data, table->maxlen, dir, buffer, lenp, ppos); } @@ -425,89 +354,55 @@ static void proc_put_char(void **buf, size_t *size, char c) } } -static int do_proc_dobool_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - *(bool *)valp = *lvalp; - } else { - int val = *(bool *)valp; +static SYSCTL_USER_TO_KERN_INT_CONV(, SYSCTL_CONV_IDENTITY) +static SYSCTL_KERN_TO_USER_INT_CONV(, SYSCTL_CONV_IDENTITY) - *lvalp = (unsigned long)val; - *negp = false; - } - return 0; -} +static SYSCTL_INT_CONV_CUSTOM(, sysctl_user_to_kern_int_conv, + sysctl_kern_to_user_int_conv, false) +static SYSCTL_INT_CONV_CUSTOM(_minmax, sysctl_user_to_kern_int_conv, + sysctl_kern_to_user_int_conv, true) -static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - if (*negp) { - if (*lvalp > (unsigned long) INT_MAX + 1) - return -EINVAL; - WRITE_ONCE(*valp, -*lvalp); - } else { - if (*lvalp > (unsigned long) INT_MAX) - return -EINVAL; - WRITE_ONCE(*valp, *lvalp); - } - } else { - int val = READ_ONCE(*valp); - if (val < 0) { - *negp = true; - *lvalp = -(unsigned long)val; - } else { - *negp = false; - *lvalp = (unsigned long)val; - } - } - return 0; -} -static int do_proc_douintvec_conv(unsigned long *lvalp, - unsigned int *valp, - int write, void *data) +static SYSCTL_USER_TO_KERN_UINT_CONV(, SYSCTL_CONV_IDENTITY) + +int sysctl_kern_to_user_uint_conv(unsigned long *u_ptr, + const unsigned int *k_ptr) { - if (write) { - if (*lvalp > UINT_MAX) - return -EINVAL; - WRITE_ONCE(*valp, *lvalp); - } else { - unsigned int val = READ_ONCE(*valp); - *lvalp = (unsigned long)val; - } + unsigned int val = READ_ONCE(*k_ptr); + *u_ptr = (unsigned long)val; return 0; } +static SYSCTL_UINT_CONV_CUSTOM(, sysctl_user_to_kern_uint_conv, + sysctl_kern_to_user_uint_conv, false) +static SYSCTL_UINT_CONV_CUSTOM(_minmax, sysctl_user_to_kern_uint_conv, + sysctl_kern_to_user_uint_conv, true) + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; -static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, - int write, void *buffer, - size_t *lenp, loff_t *ppos, - int (*conv)(bool *negp, unsigned long *lvalp, int *valp, - int write, void *data), - void *data) +static int do_proc_dointvec(const struct ctl_table *table, int dir, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr, + int dir, const struct ctl_table *table)) { int *i, vleft, first = 1, err = 0; size_t left; char *p; - if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + if (!table->data || !table->maxlen || !*lenp || + (*ppos && SYSCTL_KERN_TO_USER(dir))) { *lenp = 0; return 0; } - i = (int *) tbl_data; + i = (int *) table->data; vleft = table->maxlen / sizeof(*i); left = *lenp; if (!conv) - conv = do_proc_dointvec_conv; + conv = do_proc_int_conv; - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { if (proc_first_pos_non_zero_ignore(ppos, table)) goto out; @@ -520,7 +415,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, unsigned long lval; bool neg; - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { proc_skip_spaces(&p, &left); if (!left) @@ -530,12 +425,12 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, sizeof(proc_wspace_sep), NULL); if (err) break; - if (conv(&neg, &lval, i, 1, data)) { + if (conv(&neg, &lval, i, 1, table)) { err = -EINVAL; break; } } else { - if (conv(&neg, &lval, i, 0, data)) { + if (conv(&neg, &lval, i, 0, table)) { err = -EINVAL; break; } @@ -545,11 +440,11 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, } } - if (!write && !first && left && !err) + if (SYSCTL_KERN_TO_USER(dir) && !first && left && !err) proc_put_char(&buffer, &left, '\n'); - if (write && !err && left) + if (SYSCTL_USER_TO_KERN(dir) && !err && left) proc_skip_spaces(&p, &left); - if (write && first) + if (SYSCTL_USER_TO_KERN(dir) && first) return err ? : -EINVAL; *lenp -= left; out: @@ -557,24 +452,11 @@ out: return err; } -static int do_proc_dointvec(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(bool *negp, unsigned long *lvalp, int *valp, - int write, void *data), - void *data) -{ - return __do_proc_dointvec(table->data, table, write, - buffer, lenp, ppos, conv, data); -} - -static int do_proc_douintvec_w(unsigned int *tbl_data, - struct ctl_table *table, - void *buffer, +static int do_proc_douintvec_w(const struct ctl_table *table, void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) + int (*conv)(unsigned long *u_ptr, + unsigned int *k_ptr, int dir, + const struct ctl_table *table)) { unsigned long lval; int err = 0; @@ -604,7 +486,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, goto out_free; } - if (conv(&lval, tbl_data, 1, data)) { + if (conv(&lval, (unsigned int *) table->data, 1, table)) { err = -EINVAL; goto out_free; } @@ -618,18 +500,16 @@ out_free: return 0; - /* This is in keeping with old __do_proc_dointvec() */ bail_early: *ppos += *lenp; return err; } -static int do_proc_douintvec_r(unsigned int *tbl_data, void *buffer, +static int do_proc_douintvec_r(const struct ctl_table *table, void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) + int (*conv)(unsigned long *u_ptr, + unsigned int *k_ptr, int dir, + const struct ctl_table *table)) { unsigned long lval; int err = 0; @@ -637,7 +517,7 @@ static int do_proc_douintvec_r(unsigned int *tbl_data, void *buffer, left = *lenp; - if (conv(&lval, tbl_data, 0, data)) { + if (conv(&lval, (unsigned int *) table->data, 0, table)) { err = -EINVAL; goto out; } @@ -655,23 +535,21 @@ out: return err; } -static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, - int write, void *buffer, - size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) +static int do_proc_douintvec(const struct ctl_table *table, int dir, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *u_ptr, + unsigned int *k_ptr, int dir, + const struct ctl_table *table)) { - unsigned int *i, vleft; + unsigned int vleft; - if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + if (!table->data || !table->maxlen || !*lenp || + (*ppos && SYSCTL_KERN_TO_USER(dir))) { *lenp = 0; return 0; } - i = (unsigned int *) tbl_data; - vleft = table->maxlen / sizeof(*i); + vleft = table->maxlen / sizeof(unsigned int); /* * Arrays are not supported, keep this simple. *Do not* add @@ -683,49 +561,66 @@ static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, } if (!conv) - conv = do_proc_douintvec_conv; + conv = do_proc_uint_conv; - if (write) - return do_proc_douintvec_w(i, table, buffer, lenp, ppos, - conv, data); - return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); + if (SYSCTL_USER_TO_KERN(dir)) + return do_proc_douintvec_w(table, buffer, lenp, ppos, conv); + return do_proc_douintvec_r(table, buffer, lenp, ppos, conv); } -int do_proc_douintvec(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) +int proc_douintvec_conv(const struct ctl_table *table, int dir, void *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *u_ptr, unsigned int *k_ptr, + int dir, const struct ctl_table *table)) { - return __do_proc_douintvec(table->data, table, write, - buffer, lenp, ppos, conv, data); + return do_proc_douintvec(table, dir, buffer, lenp, ppos, conv); } + /** * proc_dobool - read/write a bool * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position * - * Reads/writes up to table->maxlen/sizeof(unsigned int) integer - * values from/to the user buffer, treated as an ASCII string. + * Reads/writes one integer value from/to the user buffer, + * treated as an ASCII string. + * + * table->data must point to a bool variable and table->maxlen must + * be sizeof(bool). * * Returns 0 on success. */ -int proc_dobool(struct ctl_table *table, int write, void *buffer, +int proc_dobool(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dobool_conv, NULL); + struct ctl_table tmp; + bool *data = table->data; + int res, val; + + /* Do not support arrays yet. */ + if (table->maxlen != sizeof(bool)) + return -EINVAL; + + tmp = *table; + tmp.maxlen = sizeof(val); + tmp.data = &val; + + val = READ_ONCE(*data); + res = proc_dointvec(&tmp, dir, buffer, lenp, ppos); + if (res) + return res; + if (SYSCTL_USER_TO_KERN(dir)) + WRITE_ONCE(*data, val); + return 0; } /** * proc_dointvec - read a vector of integers * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -735,37 +630,16 @@ int proc_dobool(struct ctl_table *table, int write, void *buffer, * * Returns 0 on success. */ -int proc_dointvec(struct ctl_table *table, int write, void *buffer, +int proc_dointvec(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); + return do_proc_dointvec(table, dir, buffer, lenp, ppos, NULL); } -#ifdef CONFIG_COMPACTION -static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, - int write, void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret, old; - - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - old = *(int *)table->data; - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret) - return ret; - if (old != *(int *)table->data) - pr_warn_once("sysctl attribute %s changed by %s[%d]\n", - table->procname, current->comm, - task_pid_nr(current)); - return ret; -} -#endif - /** * proc_douintvec - read a vector of unsigned integers * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -775,100 +649,17 @@ static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, * * Returns 0 on success. */ -int proc_douintvec(struct ctl_table *table, int write, void *buffer, +int proc_douintvec(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_douintvec_conv, NULL); -} - -/* - * Taint values can only be increased - * This means we can safely use a temporary. - */ -static int proc_taint(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - struct ctl_table t; - unsigned long tmptaint = get_taint(); - int err; - - if (write && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - t = *table; - t.data = &tmptaint; - err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); - if (err < 0) - return err; - - if (write) { - int i; - - /* - * If we are relying on panic_on_taint not producing - * false positives due to userspace input, bail out - * before setting the requested taint flags. - */ - if (panic_on_taint_nousertaint && (tmptaint & panic_on_taint)) - return -EINVAL; - - /* - * Poor man's atomic or. Not worth adding a primitive - * to everyone's atomic.h for this - */ - for (i = 0; i < TAINT_FLAGS_COUNT; i++) - if ((1UL << i) & tmptaint) - add_taint(i, LOCKDEP_STILL_OK); - } - - return err; -} - -/** - * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure - * @min: pointer to minimum allowable value - * @max: pointer to maximum allowable value - * - * The do_proc_dointvec_minmax_conv_param structure provides the - * minimum and maximum values for doing range checking for those sysctl - * parameters that use the proc_dointvec_minmax() handler. - */ -struct do_proc_dointvec_minmax_conv_param { - int *min; - int *max; -}; - -static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - int tmp, ret; - struct do_proc_dointvec_minmax_conv_param *param = data; - /* - * If writing, first do so via a temporary local int so we can - * bounds-check it before touching *valp. - */ - int *ip = write ? &tmp : valp; - - ret = do_proc_dointvec_conv(negp, lvalp, ip, write, data); - if (ret) - return ret; - - if (write) { - if ((param->min && *param->min > tmp) || - (param->max && *param->max < tmp)) - return -EINVAL; - WRITE_ONCE(*valp, tmp); - } - - return 0; + return do_proc_douintvec(table, dir, buffer, lenp, ppos, + do_proc_uint_conv); } /** * proc_dointvec_minmax - read a vector of integers with min/max values * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -879,62 +670,20 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, * This routine will ensure the values are within the range specified by * table->extra1 (min) and table->extra2 (max). * - * Returns 0 on success or -EINVAL on write when the range check fails. + * Returns 0 on success or -EINVAL when the range check fails and + * SYSCTL_USER_TO_KERN(dir) == true */ -int proc_dointvec_minmax(struct ctl_table *table, int write, +int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - struct do_proc_dointvec_minmax_conv_param param = { - .min = (int *) table->extra1, - .max = (int *) table->extra2, - }; - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dointvec_minmax_conv, ¶m); -} - -/** - * struct do_proc_douintvec_minmax_conv_param - proc_douintvec_minmax() range checking structure - * @min: pointer to minimum allowable value - * @max: pointer to maximum allowable value - * - * The do_proc_douintvec_minmax_conv_param structure provides the - * minimum and maximum values for doing range checking for those sysctl - * parameters that use the proc_douintvec_minmax() handler. - */ -struct do_proc_douintvec_minmax_conv_param { - unsigned int *min; - unsigned int *max; -}; - -static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, - unsigned int *valp, - int write, void *data) -{ - int ret; - unsigned int tmp; - struct do_proc_douintvec_minmax_conv_param *param = data; - /* write via temporary local uint for bounds-checking */ - unsigned int *up = write ? &tmp : valp; - - ret = do_proc_douintvec_conv(lvalp, up, write, data); - if (ret) - return ret; - - if (write) { - if ((param->min && *param->min > tmp) || - (param->max && *param->max < tmp)) - return -ERANGE; - - WRITE_ONCE(*valp, tmp); - } - - return 0; + return do_proc_dointvec(table, dir, buffer, lenp, ppos, + do_proc_int_conv_minmax); } /** * proc_douintvec_minmax - read a vector of unsigned ints with min/max values * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -948,23 +697,20 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, * check for UINT_MAX to avoid having to support wrap around uses from * userspace. * - * Returns 0 on success or -ERANGE on write when the range check fails. + * Returns 0 on success or -ERANGE when range check failes and + * SYSCTL_USER_TO_KERN(dir) == true */ -int proc_douintvec_minmax(struct ctl_table *table, int write, +int proc_douintvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - struct do_proc_douintvec_minmax_conv_param param = { - .min = (unsigned int *) table->extra1, - .max = (unsigned int *) table->extra2, - }; - return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_douintvec_minmax_conv, ¶m); + return do_proc_douintvec(table, dir, buffer, lenp, ppos, + do_proc_uint_conv_minmax); } /** * proc_dou8vec_minmax - read a vector of unsigned chars with min/max values * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -976,91 +722,64 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, * This routine will ensure the values are within the range specified by * table->extra1 (min) and table->extra2 (max). * - * Returns 0 on success or an error on write when the range check fails. + * Returns 0 on success or an error on SYSCTL_USER_TO_KERN(dir) == true + * and the range check fails. */ -int proc_dou8vec_minmax(struct ctl_table *table, int write, +int proc_dou8vec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp; unsigned int min = 0, max = 255U, val; u8 *data = table->data; - struct do_proc_douintvec_minmax_conv_param param = { - .min = &min, - .max = &max, - }; int res; /* Do not support arrays yet. */ if (table->maxlen != sizeof(u8)) return -EINVAL; - if (table->extra1) { - min = *(unsigned int *) table->extra1; - if (min > 255U) - return -EINVAL; - } - if (table->extra2) { - max = *(unsigned int *) table->extra2; - if (max > 255U) - return -EINVAL; - } - tmp = *table; tmp.maxlen = sizeof(val); tmp.data = &val; + if (!tmp.extra1) + tmp.extra1 = (unsigned int *) &min; + if (!tmp.extra2) + tmp.extra2 = (unsigned int *) &max; + val = READ_ONCE(*data); - res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos, - do_proc_douintvec_minmax_conv, ¶m); + res = do_proc_douintvec(&tmp, dir, buffer, lenp, ppos, + do_proc_uint_conv_minmax); if (res) return res; - if (write) + if (SYSCTL_USER_TO_KERN(dir)) WRITE_ONCE(*data, val); return 0; } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); -#ifdef CONFIG_MAGIC_SYSRQ -static int sysrq_sysctl_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int tmp, ret; - - tmp = sysrq_mask(); - - ret = __do_proc_dointvec(&tmp, table, write, buffer, - lenp, ppos, NULL, NULL); - if (ret || !write) - return ret; - - if (write) - sysrq_toggle_support(tmp); - - return 0; -} -#endif - -static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, - int write, void *buffer, size_t *lenp, loff_t *ppos, - unsigned long convmul, unsigned long convdiv) +static int do_proc_doulongvec_minmax(const struct ctl_table *table, int dir, + void *buffer, size_t *lenp, loff_t *ppos, + unsigned long convmul, + unsigned long convdiv) { unsigned long *i, *min, *max; int vleft, first = 1, err = 0; size_t left; char *p; - if (!data || !table->maxlen || !*lenp || (*ppos && !write)) { + if (!table->data || !table->maxlen || !*lenp || + (*ppos && SYSCTL_KERN_TO_USER(dir))) { *lenp = 0; return 0; } - i = data; + i = table->data; min = table->extra1; max = table->extra2; vleft = table->maxlen / sizeof(unsigned long); left = *lenp; - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { if (proc_first_pos_non_zero_ignore(ppos, table)) goto out; @@ -1072,7 +791,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, for (; left && vleft--; i++, first = 0) { unsigned long val; - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { bool neg; proc_skip_spaces(&p, &left); @@ -1101,11 +820,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, } } - if (!write && !first && left && !err) + if (SYSCTL_KERN_TO_USER(dir) && !first && left && !err) proc_put_char(&buffer, &left, '\n'); - if (write && !err) + if (SYSCTL_USER_TO_KERN(dir) && !err) proc_skip_spaces(&p, &left); - if (write && first) + if (SYSCTL_USER_TO_KERN(dir) && first) return err ? : -EINVAL; *lenp -= left; out: @@ -1113,18 +832,18 @@ out: return err; } -static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, - unsigned long convdiv) +int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir, + void *buffer, size_t *lenp, loff_t *ppos, + unsigned long convmul, unsigned long convdiv) { - return __do_proc_doulongvec_minmax(table->data, table, write, - buffer, lenp, ppos, convmul, convdiv); + return do_proc_doulongvec_minmax(table, dir, buffer, lenp, ppos, + convmul, convdiv); } /** * proc_doulongvec_minmax - read a vector of long integers with min/max values * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -1137,239 +856,24 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_minmax(struct ctl_table *table, int write, +int proc_doulongvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l); -} - -/** - * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: file position - * - * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long - * values from/to the user buffer, treated as an ASCII string. The values - * are treated as milliseconds, and converted to jiffies when they are stored. - * - * This routine will ensure the values are within the range specified by - * table->extra1 (min) and table->extra2 (max). - * - * Returns 0 on success. - */ -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_doulongvec_minmax(table, write, buffer, - lenp, ppos, HZ, 1000l); -} - - -static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - if (*lvalp > INT_MAX / HZ) - return 1; - if (*negp) - WRITE_ONCE(*valp, -*lvalp * HZ); - else - WRITE_ONCE(*valp, *lvalp * HZ); - } else { - int val = READ_ONCE(*valp); - unsigned long lval; - if (val < 0) { - *negp = true; - lval = -(unsigned long)val; - } else { - *negp = false; - lval = (unsigned long)val; - } - *lvalp = lval / HZ; - } - return 0; -} - -static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ) - return 1; - *valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp); - } else { - int val = *valp; - unsigned long lval; - if (val < 0) { - *negp = true; - lval = -(unsigned long)val; - } else { - *negp = false; - lval = (unsigned long)val; - } - *lvalp = jiffies_to_clock_t(lval); - } - return 0; -} - -static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); - - if (jif > INT_MAX) - return 1; - WRITE_ONCE(*valp, (int)jif); - } else { - int val = READ_ONCE(*valp); - unsigned long lval; - if (val < 0) { - *negp = true; - lval = -(unsigned long)val; - } else { - *negp = false; - lval = (unsigned long)val; - } - *lvalp = jiffies_to_msecs(lval); - } - return 0; -} - -static int do_proc_dointvec_ms_jiffies_minmax_conv(bool *negp, unsigned long *lvalp, - int *valp, int write, void *data) -{ - int tmp, ret; - struct do_proc_dointvec_minmax_conv_param *param = data; - /* - * If writing, first do so via a temporary local int so we can - * bounds-check it before touching *valp. - */ - int *ip = write ? &tmp : valp; - - ret = do_proc_dointvec_ms_jiffies_conv(negp, lvalp, ip, write, data); - if (ret) - return ret; - - if (write) { - if ((param->min && *param->min > tmp) || - (param->max && *param->max < tmp)) - return -EINVAL; - *valp = tmp; - } - return 0; -} - -/** - * proc_dointvec_jiffies - read a vector of integers as seconds - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: file position - * - * 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 seconds, and are converted into - * jiffies. - * - * Returns 0 on success. - */ -int proc_dointvec_jiffies(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_dointvec(table,write,buffer,lenp,ppos, - do_proc_dointvec_jiffies_conv,NULL); -} - -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - struct do_proc_dointvec_minmax_conv_param param = { - .min = (int *) table->extra1, - .max = (int *) table->extra2, - }; - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dointvec_ms_jiffies_minmax_conv, ¶m); -} - -/** - * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: pointer to the file position - * - * 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/USER_HZ seconds, and - * are converted into jiffies. - * - * Returns 0 on success. - */ -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dointvec_userhz_jiffies_conv, NULL); -} - -/** - * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: file position - * @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 - * are converted into jiffies. - * - * Returns 0 on success. - */ -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) -{ - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dointvec_ms_jiffies_conv, NULL); + return proc_doulongvec_minmax_conv(table, dir, buffer, lenp, ppos, 1l, 1l); } -static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr, + int dir, const struct ctl_table *table)) { - struct pid *new_pid; - pid_t tmp; - int r; - - tmp = pid_vnr(cad_pid); - - r = __do_proc_dointvec(&tmp, table, write, buffer, - lenp, ppos, NULL, NULL); - if (r || !write) - return r; - - new_pid = find_get_pid(tmp); - if (!new_pid) - return -ESRCH; - - put_pid(xchg(&cad_pid, new_pid)); - return 0; + return do_proc_dointvec(table, dir, buffer, lenp, ppos, conv); } /** * proc_do_large_bitmap - read/write from/to a large bitmap * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file + * @dir: %TRUE if this is a write to the sysctl file * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -1383,7 +887,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer, * * Returns 0 on success. */ -int proc_do_large_bitmap(struct ctl_table *table, int write, +int proc_do_large_bitmap(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { int err = 0; @@ -1393,12 +897,12 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, unsigned long *tmp_bitmap = NULL; char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c; - if (!bitmap || !bitmap_len || !left || (*ppos && !write)) { + if (!bitmap || !bitmap_len || !left || (*ppos && SYSCTL_KERN_TO_USER(dir))) { *lenp = 0; return 0; } - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { char *p = buffer; size_t skipped = 0; @@ -1499,7 +1003,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, } if (!err) { - if (write) { + if (SYSCTL_USER_TO_KERN(dir)) { if (*ppos) bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len); else @@ -1515,85 +1019,70 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, #else /* CONFIG_PROC_SYSCTL */ -int proc_dostring(struct ctl_table *table, int write, +int proc_dostring(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dobool(struct ctl_table *table, int write, +int proc_dobool(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec(struct ctl_table *table, int write, +int proc_dointvec(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_douintvec(struct ctl_table *table, int write, +int proc_douintvec(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_minmax(struct ctl_table *table, int write, +int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_douintvec_minmax(struct ctl_table *table, int write, +int proc_douintvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dou8vec_minmax(struct ctl_table *table, int write, +int proc_dou8vec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_jiffies(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, +int proc_doulongvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_doulongvec_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir, + void *buffer, size_t *lenp, loff_t *ppos, + unsigned long convmul, unsigned long convdiv) { return -ENOSYS; } -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr, + int dir, const struct ctl_table *table)) { return -ENOSYS; } -int proc_do_large_bitmap(struct ctl_table *table, int write, +int proc_do_large_bitmap(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; @@ -1602,7 +1091,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, #endif /* CONFIG_PROC_SYSCTL */ #if defined(CONFIG_SYSCTL) -int proc_do_static_key(struct ctl_table *table, int write, +int proc_do_static_key(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; @@ -1616,13 +1105,13 @@ int proc_do_static_key(struct ctl_table *table, int write, .extra2 = SYSCTL_ONE, }; - if (write && !capable(CAP_SYS_ADMIN)) + if (SYSCTL_USER_TO_KERN(dir) && !capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&static_key_mutex); val = static_key_enabled(key); - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); - if (write && !ret) { + ret = proc_dointvec_minmax(&tmp, dir, buffer, lenp, ppos); + if (SYSCTL_USER_TO_KERN(dir) && !ret) { if (val) static_key_enable(key); else @@ -1632,22 +1121,9 @@ int proc_do_static_key(struct ctl_table *table, int write, return ret; } -static struct ctl_table kern_table[] = { - { - .procname = "panic", - .data = &panic_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, +static const struct ctl_table sysctl_subsys_table[] = { #ifdef CONFIG_PROC_SYSCTL { - .procname = "tainted", - .maxlen = sizeof(long), - .mode = 0644, - .proc_handler = proc_taint, - }, - { .procname = "sysctl_writes_strict", .data = &sysctl_writes_strict, .maxlen = sizeof(int), @@ -1658,203 +1134,6 @@ static struct ctl_table kern_table[] = { }, #endif { - .procname = "print-fatal-signals", - .data = &print_fatal_signals, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#ifdef CONFIG_SPARC - { - .procname = "reboot-cmd", - .data = reboot_command, - .maxlen = 256, - .mode = 0644, - .proc_handler = proc_dostring, - }, - { - .procname = "stop-a", - .data = &stop_a_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "scons-poweroff", - .data = &scons_pwroff, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_SPARC64 - { - .procname = "tsb-ratio", - .data = &sysctl_tsb_ratio, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_PARISC - { - .procname = "soft-power", - .data = &pwrsw_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW - { - .procname = "unaligned-trap", - .data = &unaligned_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_STACK_TRACER - { - .procname = "stack_tracer_enabled", - .data = &stack_tracer_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = stack_trace_sysctl, - }, -#endif -#ifdef CONFIG_TRACING - { - .procname = "ftrace_dump_on_oops", - .data = &ftrace_dump_on_oops, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "traceoff_on_warning", - .data = &__disable_trace_on_warning, - .maxlen = sizeof(__disable_trace_on_warning), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tracepoint_printk", - .data = &tracepoint_printk, - .maxlen = sizeof(tracepoint_printk), - .mode = 0644, - .proc_handler = tracepoint_printk_sysctl, - }, -#endif -#ifdef CONFIG_MODULES - { - .procname = "modprobe", - .data = &modprobe_path, - .maxlen = KMOD_PATH_LEN, - .mode = 0644, - .proc_handler = proc_dostring, - }, - { - .procname = "modules_disabled", - .data = &modules_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_UEVENT_HELPER - { - .procname = "hotplug", - .data = &uevent_helper, - .maxlen = UEVENT_HELPER_PATH_LEN, - .mode = 0644, - .proc_handler = proc_dostring, - }, -#endif -#ifdef CONFIG_MAGIC_SYSRQ - { - .procname = "sysrq", - .data = NULL, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = sysrq_sysctl_handler, - }, -#endif -#ifdef CONFIG_PROC_SYSCTL - { - .procname = "cad_pid", - .data = NULL, - .maxlen = sizeof (int), - .mode = 0600, - .proc_handler = proc_do_cad_pid, - }, -#endif - { - .procname = "threads-max", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sysctl_max_threads, - }, - { - .procname = "usermodehelper", - .mode = 0555, - .child = usermodehelper_table, - }, - { - .procname = "overflowuid", - .data = &overflowuid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_MAXOLDUID, - }, - { - .procname = "overflowgid", - .data = &overflowgid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_MAXOLDUID, - }, -#ifdef CONFIG_S390 - { - .procname = "userprocess_debug", - .data = &show_unhandled_signals, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif - { - .procname = "pid_max", - .data = &pid_max, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &pid_max_min, - .extra2 = &pid_max_max, - }, - { - .procname = "panic_on_oops", - .data = &panic_on_oops, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "panic_print", - .data = &panic_print, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { .procname = "ngroups_max", .data = (void *)&ngroups_max, .maxlen = sizeof (int), @@ -1868,90 +1147,15 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) - { - .procname = "unknown_nmi_panic", - .data = &unknown_nmi_panic, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif - -#if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \ - defined(CONFIG_DEBUG_STACKOVERFLOW) - { - .procname = "panic_on_stackoverflow", - .data = &sysctl_panic_on_stackoverflow, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#if defined(CONFIG_X86) - { - .procname = "panic_on_unrecovered_nmi", - .data = &panic_on_unrecovered_nmi, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "panic_on_io_nmi", - .data = &panic_on_io_nmi, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "bootloader_type", - .data = &bootloader_type, - .maxlen = sizeof (int), - .mode = 0444, - .proc_handler = proc_dointvec, - }, - { - .procname = "bootloader_version", - .data = &bootloader_version, - .maxlen = sizeof (int), - .mode = 0444, - .proc_handler = proc_dointvec, - }, - { - .procname = "io_delay_type", - .data = &io_delay_type, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#if defined(CONFIG_MMU) +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW { - .procname = "randomize_va_space", - .data = &randomize_va_space, + .procname = "unaligned-trap", + .data = &unaligned_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif -#if defined(CONFIG_S390) && defined(CONFIG_SMP) - { - .procname = "spin_retry", - .data = &spin_retry, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) - { - .procname = "acpi_video_flags", - .data = &acpi_realmode_flags, - .maxlen = sizeof (unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, -#endif #ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN { .procname = "ignore-unaligned-usertrap", @@ -1961,521 +1165,11 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_IA64 - { - .procname = "unaligned-dump-stack", - .data = &unaligned_dump_stack, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_RT_MUTEXES - { - .procname = "max_lock_depth", - .data = &max_lock_depth, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_KEYS - { - .procname = "keys", - .mode = 0555, - .child = key_sysctls, - }, -#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_proc_update_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", - .data = &panic_on_warn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#ifdef CONFIG_TREE_RCU - { - .procname = "panic_on_rcu_stall", - .data = &sysctl_panic_on_rcu_stall, - .maxlen = sizeof(sysctl_panic_on_rcu_stall), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "max_rcu_stall_to_panic", - .data = &sysctl_max_rcu_stall_to_panic, - .maxlen = sizeof(sysctl_max_rcu_stall_to_panic), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_INT_MAX, - }, -#endif - { } }; -static struct ctl_table vm_table[] = { - { - .procname = "overcommit_memory", - .data = &sysctl_overcommit_memory, - .maxlen = sizeof(sysctl_overcommit_memory), - .mode = 0644, - .proc_handler = overcommit_policy_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, - { - .procname = "overcommit_ratio", - .data = &sysctl_overcommit_ratio, - .maxlen = sizeof(sysctl_overcommit_ratio), - .mode = 0644, - .proc_handler = overcommit_ratio_handler, - }, - { - .procname = "overcommit_kbytes", - .data = &sysctl_overcommit_kbytes, - .maxlen = sizeof(sysctl_overcommit_kbytes), - .mode = 0644, - .proc_handler = overcommit_kbytes_handler, - }, - { - .procname = "page-cluster", - .data = &page_cluster, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&page_cluster_max, - }, - { - .procname = "dirtytime_expire_seconds", - .data = &dirtytime_expire_interval, - .maxlen = sizeof(dirtytime_expire_interval), - .mode = 0644, - .proc_handler = dirtytime_interval_handler, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "swappiness", - .data = &vm_swappiness, - .maxlen = sizeof(vm_swappiness), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .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", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_sysctl_handler, - }, -#ifdef CONFIG_NUMA - { - .procname = "nr_hugepages_mempolicy", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = &hugetlb_mempolicy_sysctl_handler, - }, -#endif - { - .procname = "hugetlb_shm_group", - .data = &sysctl_hugetlb_shm_group, - .maxlen = sizeof(gid_t), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nr_overcommit_hugepages", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_overcommit_handler, - }, -#endif - { - .procname = "lowmem_reserve_ratio", - .data = &sysctl_lowmem_reserve_ratio, - .maxlen = sizeof(sysctl_lowmem_reserve_ratio), - .mode = 0644, - .proc_handler = lowmem_reserve_ratio_sysctl_handler, - }, - { - .procname = "drop_caches", - .data = &sysctl_drop_caches, - .maxlen = sizeof(int), - .mode = 0200, - .proc_handler = drop_caches_sysctl_handler, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_FOUR, - }, -#ifdef CONFIG_COMPACTION - { - .procname = "compact_memory", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0200, - .proc_handler = sysctl_compaction_handler, - }, - { - .procname = "compaction_proactiveness", - .data = &sysctl_compaction_proactiveness, - .maxlen = sizeof(sysctl_compaction_proactiveness), - .mode = 0644, - .proc_handler = compaction_proactiveness_sysctl_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "extfrag_threshold", - .data = &sysctl_extfrag_threshold, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_THOUSAND, - }, - { - .procname = "compact_unevictable_allowed", - .data = &sysctl_compact_unevictable_allowed, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_warn_RT_change, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - -#endif /* CONFIG_COMPACTION */ - { - .procname = "min_free_kbytes", - .data = &min_free_kbytes, - .maxlen = sizeof(min_free_kbytes), - .mode = 0644, - .proc_handler = min_free_kbytes_sysctl_handler, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "watermark_boost_factor", - .data = &watermark_boost_factor, - .maxlen = sizeof(watermark_boost_factor), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "watermark_scale_factor", - .data = &watermark_scale_factor, - .maxlen = sizeof(watermark_scale_factor), - .mode = 0644, - .proc_handler = watermark_scale_factor_sysctl_handler, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_THREE_THOUSAND, - }, - { - .procname = "percpu_pagelist_high_fraction", - .data = &percpu_pagelist_high_fraction, - .maxlen = sizeof(percpu_pagelist_high_fraction), - .mode = 0644, - .proc_handler = percpu_pagelist_high_fraction_sysctl_handler, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "page_lock_unfairness", - .data = &sysctl_page_lock_unfairness, - .maxlen = sizeof(sysctl_page_lock_unfairness), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, -#ifdef CONFIG_MMU - { - .procname = "max_map_count", - .data = &sysctl_max_map_count, - .maxlen = sizeof(sysctl_max_map_count), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, -#else - { - .procname = "nr_trim_pages", - .data = &sysctl_nr_trim_pages, - .maxlen = sizeof(sysctl_nr_trim_pages), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, -#endif - { - .procname = "vfs_cache_pressure", - .data = &sysctl_vfs_cache_pressure, - .maxlen = sizeof(sysctl_vfs_cache_pressure), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, -#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ - defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) - { - .procname = "legacy_va_layout", - .data = &sysctl_legacy_va_layout, - .maxlen = sizeof(sysctl_legacy_va_layout), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, -#endif -#ifdef CONFIG_NUMA - { - .procname = "zone_reclaim_mode", - .data = &node_reclaim_mode, - .maxlen = sizeof(node_reclaim_mode), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "min_unmapped_ratio", - .data = &sysctl_min_unmapped_ratio, - .maxlen = sizeof(sysctl_min_unmapped_ratio), - .mode = 0644, - .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "min_slab_ratio", - .data = &sysctl_min_slab_ratio, - .maxlen = sizeof(sysctl_min_slab_ratio), - .mode = 0644, - .proc_handler = sysctl_min_slab_ratio_sysctl_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, -#endif -#ifdef CONFIG_SMP - { - .procname = "stat_interval", - .data = &sysctl_stat_interval, - .maxlen = sizeof(sysctl_stat_interval), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "stat_refresh", - .data = NULL, - .maxlen = 0, - .mode = 0600, - .proc_handler = vmstat_refresh, - }, -#endif -#ifdef CONFIG_MMU - { - .procname = "mmap_min_addr", - .data = &dac_mmap_min_addr, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = mmap_min_addr_handler, - }, -#endif -#ifdef CONFIG_NUMA - { - .procname = "numa_zonelist_order", - .data = &numa_zonelist_order, - .maxlen = NUMA_ZONELIST_ORDER_LEN, - .mode = 0644, - .proc_handler = numa_zonelist_order_handler, - }, -#endif -#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \ - (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) - { - .procname = "vdso_enabled", -#ifdef CONFIG_X86_32 - .data = &vdso32_enabled, - .maxlen = sizeof(vdso32_enabled), -#else - .data = &vdso_enabled, - .maxlen = sizeof(vdso_enabled), -#endif - .mode = 0644, - .proc_handler = proc_dointvec, - .extra1 = SYSCTL_ZERO, - }, -#endif -#ifdef CONFIG_MEMORY_FAILURE - { - .procname = "memory_failure_early_kill", - .data = &sysctl_memory_failure_early_kill, - .maxlen = sizeof(sysctl_memory_failure_early_kill), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "memory_failure_recovery", - .data = &sysctl_memory_failure_recovery, - .maxlen = sizeof(sysctl_memory_failure_recovery), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif - { - .procname = "user_reserve_kbytes", - .data = &sysctl_user_reserve_kbytes, - .maxlen = sizeof(sysctl_user_reserve_kbytes), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "admin_reserve_kbytes", - .data = &sysctl_admin_reserve_kbytes, - .maxlen = sizeof(sysctl_admin_reserve_kbytes), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, -#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS - { - .procname = "mmap_rnd_bits", - .data = &mmap_rnd_bits, - .maxlen = sizeof(mmap_rnd_bits), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)&mmap_rnd_bits_min, - .extra2 = (void *)&mmap_rnd_bits_max, - }, -#endif -#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS - { - .procname = "mmap_rnd_compat_bits", - .data = &mmap_rnd_compat_bits, - .maxlen = sizeof(mmap_rnd_compat_bits), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)&mmap_rnd_compat_bits_min, - .extra2 = (void *)&mmap_rnd_compat_bits_max, - }, -#endif -#ifdef CONFIG_USERFAULTFD - { - .procname = "unprivileged_userfaultfd", - .data = &sysctl_unprivileged_userfaultfd, - .maxlen = sizeof(sysctl_unprivileged_userfaultfd), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif - { } -}; - -static struct ctl_table debug_table[] = { -#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE - { - .procname = "exception-trace", - .data = &show_unhandled_signals, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, -#endif - { } -}; - -static struct ctl_table dev_table[] = { - { } -}; - -DECLARE_SYSCTL_BASE(kernel, kern_table); -DECLARE_SYSCTL_BASE(vm, vm_table); -DECLARE_SYSCTL_BASE(debug, debug_table); -DECLARE_SYSCTL_BASE(dev, dev_table); - int __init sysctl_init_bases(void) { - register_sysctl_base(kernel); - register_sysctl_base(vm); - register_sysctl_base(debug); - register_sysctl_base(dev); + register_sysctl_init("kernel", sysctl_subsys_table); return 0; } @@ -2487,12 +1181,8 @@ int __init sysctl_init_bases(void) EXPORT_SYMBOL(proc_dobool); EXPORT_SYMBOL(proc_dointvec); EXPORT_SYMBOL(proc_douintvec); -EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL_GPL(proc_douintvec_minmax); -EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); -EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); EXPORT_SYMBOL(proc_doulongvec_minmax); -EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); EXPORT_SYMBOL(proc_do_large_bitmap); |
