diff options
Diffstat (limited to 'kernel/sysctl.c')
| -rw-r--r-- | kernel/sysctl.c | 3021 |
1 files changed, 1444 insertions, 1577 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a176d8727a3..e961286d0e14 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -68,6 +68,9 @@ #include <linux/bpf.h> #include <linux/mount.h> #include <linux/userfaultfd_k.h> +#include <linux/coredump.h> +#include <linux/latencytop.h> +#include <linux/pid.h> #include "../lib/kstrtox.h" @@ -103,22 +106,6 @@ #if defined(CONFIG_SYSCTL) -/* External variables not in a header file. */ -extern int suid_dumpable; -#ifdef CONFIG_COREDUMP -extern int core_uses_pid; -extern char core_pattern[]; -extern unsigned int core_pipe_limit; -#endif -extern int pid_max; -extern int pid_max_min, pid_max_max; -extern int percpu_pagelist_fraction; -extern int latencytop_enabled; -extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; -#ifndef CONFIG_MMU -extern int sysctl_nr_trim_pages; -#endif - /* Constants used for minimum and maximum */ #ifdef CONFIG_LOCKUP_DETECTOR static int sixty = 60; @@ -160,24 +147,6 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #ifdef CONFIG_INOTIFY_USER #include <linux/inotify.h> #endif -#ifdef CONFIG_SPARC -#endif - -#ifdef CONFIG_PARISC -extern int pwrsw_enabled; -#endif - -#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW -extern int unaligned_enabled; -#endif - -#ifdef CONFIG_IA64 -extern int unaligned_dump_stack; -#endif - -#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN -extern int no_unaligned_warning; -#endif #ifdef CONFIG_PROC_SYSCTL @@ -207,102 +176,1438 @@ 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 + +#ifdef CONFIG_SCHED_DEBUG +static int min_sched_granularity_ns = 100000; /* 100 usecs */ +static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ +static int min_wakeup_granularity_ns; /* 0 usecs */ +static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ +#ifdef CONFIG_SMP +static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; +static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; +#endif /* CONFIG_SMP */ +#endif /* CONFIG_SCHED_DEBUG */ -static int proc_do_cad_pid(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -static int proc_taint(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_COMPACTION -static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, - int write, void __user *buffer, - size_t *lenp, loff_t *ppos); +static int min_extfrag_threshold; +static int max_extfrag_threshold = 1000; #endif + +#endif /* CONFIG_SYSCTL */ + +/* + * /proc/sys support + */ + +#ifdef CONFIG_PROC_SYSCTL + +static int _proc_do_string(char *data, int maxlen, int write, + char *buffer, size_t *lenp, loff_t *ppos) +{ + size_t len; + char c, *p; + + if (!data || !maxlen || !*lenp) { + *lenp = 0; + return 0; + } + + if (write) { + if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) { + /* Only continue writes not past the end of buffer. */ + len = strlen(data); + if (len > maxlen - 1) + len = maxlen - 1; + + if (*ppos > len) + return 0; + len = *ppos; + } else { + /* Start writing from beginning of buffer. */ + len = 0; + } + + *ppos += *lenp; + p = buffer; + while ((p - buffer) < *lenp && len < maxlen - 1) { + c = *(p++); + if (c == 0 || c == '\n') + break; + data[len++] = c; + } + data[len] = 0; + } else { + len = strlen(data); + if (len > maxlen) + len = maxlen; + + if (*ppos > len) { + *lenp = 0; + return 0; + } + + data += *ppos; + len -= *ppos; + + if (len > *lenp) + len = *lenp; + if (len) + memcpy(buffer, data, len); + if (len < *lenp) { + buffer[len] = '\n'; + len++; + } + *lenp = len; + *ppos += len; + } + return 0; +} + +static void warn_sysctl_write(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" + "warning, set kernel.sysctl_writes_strict = -1\n", + current->comm, table->procname); +} + +/** + * proc_first_pos_non_zero_ignore - check if first position is allowed + * @ppos: file position + * @table: the sysctl table + * + * Returns true if the first position is non-zero and the sysctl_writes_strict + * mode indicates this is not allowed for numeric input types. String proc + * handlers can ignore the return value. + */ +static bool proc_first_pos_non_zero_ignore(loff_t *ppos, + struct ctl_table *table) +{ + if (!*ppos) + return false; + + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + return true; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + return false; + default: + return false; + } +} + +/** + * proc_dostring - read a string sysctl + * @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 a string from/to the user buffer. If the kernel + * buffer provided is not large enough to hold the string, the + * string is truncated. The copied string is %NULL-terminated. + * If the string is being read by the user process, it is copied + * and a newline '\n' is added. It is truncated if the buffer is + * not large enough. + * + * Returns 0 on success. + */ +int proc_dostring(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + if (write) + proc_first_pos_non_zero_ignore(ppos, table); + + return _proc_do_string(table->data, table->maxlen, write, buffer, lenp, + ppos); +} + +static size_t proc_skip_spaces(char **buf) +{ + size_t ret; + char *tmp = skip_spaces(*buf); + ret = tmp - *buf; + *buf = tmp; + return ret; +} + +static void proc_skip_char(char **buf, size_t *size, const char v) +{ + while (*size) { + if (**buf != v) + break; + (*size)--; + (*buf)++; + } +} + +/** + * strtoul_lenient - parse an ASCII formatted integer from a buffer and only + * fail on overflow + * + * @cp: kernel buffer containing the string to parse + * @endp: pointer to store the trailing characters + * @base: the base to use + * @res: where the parsed integer will be stored + * + * In case of success 0 is returned and @res will contain the parsed integer, + * @endp will hold any trailing characters. + * This function will fail the parse on overflow. If there wasn't an overflow + * the function will defer the decision what characters count as invalid to the + * caller. + */ +static int strtoul_lenient(const char *cp, char **endp, unsigned int base, + unsigned long *res) +{ + unsigned long long result; + unsigned int rv; + + cp = _parse_integer_fixup_radix(cp, &base); + rv = _parse_integer(cp, base, &result); + if ((rv & KSTRTOX_OVERFLOW) || (result != (unsigned long)result)) + return -ERANGE; + + cp += rv; + + if (endp) + *endp = (char *)cp; + + *res = (unsigned long)result; + return 0; +} + +#define TMPBUFLEN 22 +/** + * proc_get_long - reads an ASCII formatted integer from a user buffer + * + * @buf: a kernel buffer + * @size: size of the kernel buffer + * @val: this is where the number will be stored + * @neg: set to %TRUE if number is negative + * @perm_tr: a vector which contains the allowed trailers + * @perm_tr_len: size of the perm_tr vector + * @tr: pointer to store the trailer character + * + * In case of success %0 is returned and @buf and @size are updated with + * the amount of bytes read. If @tr is non-NULL and a trailing + * character exists (size is non-zero after returning from this + * function), @tr is updated with the trailing character. + */ +static int proc_get_long(char **buf, size_t *size, + unsigned long *val, bool *neg, + const char *perm_tr, unsigned perm_tr_len, char *tr) +{ + int len; + char *p, tmp[TMPBUFLEN]; + + if (!*size) + return -EINVAL; + + len = *size; + if (len > TMPBUFLEN - 1) + len = TMPBUFLEN - 1; + + memcpy(tmp, *buf, len); + + tmp[len] = 0; + p = tmp; + if (*p == '-' && *size > 1) { + *neg = true; + p++; + } else + *neg = false; + if (!isdigit(*p)) + return -EINVAL; + + if (strtoul_lenient(p, &p, 0, val)) + return -EINVAL; + + len = p - tmp; + + /* We don't know if the next char is whitespace thus we may accept + * invalid integers (e.g. 1234...a) or two integers instead of one + * (e.g. 123...1). So lets not allow such large numbers. */ + if (len == TMPBUFLEN - 1) + return -EINVAL; + + if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len)) + return -EINVAL; + + if (tr && (len < *size)) + *tr = *p; + + *buf += len; + *size -= len; + + return 0; +} + +/** + * proc_put_long - converts an integer to a decimal ASCII formatted string + * + * @buf: the user buffer + * @size: the size of the user buffer + * @val: the integer to be converted + * @neg: sign of the number, %TRUE for negative + * + * In case of success @buf and @size are updated with the amount of bytes + * written. + */ +static void proc_put_long(void **buf, size_t *size, unsigned long val, bool neg) +{ + int len; + char tmp[TMPBUFLEN], *p = tmp; + + sprintf(p, "%s%lu", neg ? "-" : "", val); + len = strlen(tmp); + if (len > *size) + len = *size; + memcpy(*buf, tmp, len); + *size -= len; + *buf += len; +} +#undef TMPBUFLEN + +static void proc_put_char(void **buf, size_t *size, char c) +{ + if (*size) { + char **buffer = (char **)buf; + **buffer = c; + + (*size)--; + (*buffer)++; + *buf = *buffer; + } +} + +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; + *valp = -*lvalp; + } else { + if (*lvalp > (unsigned long) INT_MAX) + return -EINVAL; + *valp = *lvalp; + } + } else { + int val = *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) +{ + if (write) { + if (*lvalp > UINT_MAX) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + +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) +{ + int *i, vleft, first = 1, err = 0; + size_t left; + char *p; + + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (int *) tbl_data; + vleft = table->maxlen / sizeof(*i); + left = *lenp; + + if (!conv) + conv = do_proc_dointvec_conv; + + if (write) { + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + p = buffer; + } + + for (; left && vleft--; i++, first=0) { + unsigned long lval; + bool neg; + + if (write) { + left -= proc_skip_spaces(&p); + + if (!left) + break; + err = proc_get_long(&p, &left, &lval, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err) + break; + if (conv(&neg, &lval, i, 1, data)) { + err = -EINVAL; + break; + } + } else { + if (conv(&neg, &lval, i, 0, data)) { + err = -EINVAL; + break; + } + if (!first) + proc_put_char(&buffer, &left, '\t'); + proc_put_long(&buffer, &left, lval, neg); + } + } + + if (!write && !first && left && !err) + proc_put_char(&buffer, &left, '\n'); + if (write && !err && left) + left -= proc_skip_spaces(&p); + if (write && first) + return err ? : -EINVAL; + *lenp -= left; +out: + *ppos += *lenp; + 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, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + bool neg; + char *p = buffer; + + left = *lenp; + + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto bail_early; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + + left -= proc_skip_spaces(&p); + if (!left) { + err = -EINVAL; + goto out_free; + } + + err = proc_get_long(&p, &left, &lval, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err || neg) { + err = -EINVAL; + goto out_free; + } + + if (conv(&lval, tbl_data, 1, data)) { + err = -EINVAL; + goto out_free; + } + + if (!err && left) + left -= proc_skip_spaces(&p); + +out_free: + if (err) + return -EINVAL; + + 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, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + + left = *lenp; + + if (conv(&lval, tbl_data, 0, data)) { + err = -EINVAL; + goto out; + } + + proc_put_long(&buffer, &left, lval, false); + if (!left) + goto out; + + proc_put_char(&buffer, &left, '\n'); + +out: + *lenp -= left; + *ppos += *lenp; + + 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) +{ + unsigned int *i, vleft; + + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (unsigned int *) tbl_data; + vleft = table->maxlen / sizeof(*i); + + /* + * Arrays are not supported, keep this simple. *Do not* add + * support for them. + */ + if (vleft != 1) { + *lenp = 0; + return -EINVAL; + } + + if (!conv) + conv = do_proc_douintvec_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); +} + +static 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) +{ + return __do_proc_douintvec(table->data, table, write, + buffer, lenp, ppos, conv, data); +} + +/** + * proc_dointvec - read a vector of integers + * @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. + * + * Returns 0 on success. + */ +int proc_dointvec(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, 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 + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, 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) { + /* + * Poor man's atomic or. Not worth adding a primitive + * to everyone's atomic.h for this + */ + int i; + for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) { + if ((tmptaint >> i) & 1) + add_taint(i, LOCKDEP_STILL_OK); + } + } + + return err; +} + #ifdef CONFIG_PRINTK static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} #endif +/** + * 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; + *valp = tmp; + } + + return 0; +} + +/** + * 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 + * @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. + * + * 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. + */ +int proc_dointvec_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_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; + + *valp = tmp; + } + + return 0; +} + +/** + * 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 + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. Negative + * strings are not allowed. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). There is a final sanity + * 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. + */ +int proc_douintvec_minmax(struct ctl_table *table, int write, + 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); +} + +static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + if (write) { + unsigned int val; + + val = round_pipe_size(*lvalp); + if (val == 0) + return -EINVAL; + + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_dopipe_max_size_conv, NULL); +} + +static void validate_coredump_safety(void) +{ +#ifdef CONFIG_COREDUMP + if (suid_dumpable == SUID_DUMP_ROOT && + core_pattern[0] != '/' && core_pattern[0] != '|') { + printk(KERN_WARNING +"Unsafe core_pattern used with fs.suid_dumpable=2.\n" +"Pipe handler or fully qualified core dump path required.\n" +"Set kernel.core_pattern before fs.suid_dumpable.\n" + ); + } +#endif +} + static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} + #ifdef CONFIG_COREDUMP static int proc_dostring_coredump(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dostring(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} #endif -static int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ static int sysrq_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -#endif + void *buffer, size_t *lenp, loff_t *ppos) +{ + int tmp, ret; -static struct ctl_table kern_table[]; -static struct ctl_table vm_table[]; -static struct ctl_table fs_table[]; -static struct ctl_table debug_table[]; -static struct ctl_table dev_table[]; -extern struct ctl_table random_table[]; -#ifdef CONFIG_EPOLL -extern struct ctl_table epoll_table[]; -#endif + tmp = sysrq_mask(); -#ifdef CONFIG_FW_LOADER_USER_HELPER -extern struct ctl_table firmware_config_table[]; -#endif + ret = __do_proc_dointvec(&tmp, table, write, buffer, + lenp, ppos, NULL, NULL); + if (ret || !write) + return ret; -#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ - defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) -int sysctl_legacy_va_layout; + if (write) + sysrq_toggle_support(tmp); + + return 0; +} #endif -/* The default sysctl tables: */ +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) +{ + unsigned long *i, *min, *max; + int vleft, first = 1, err = 0; + size_t left; + char *p; -static struct ctl_table sysctl_base_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kern_table, - }, - { - .procname = "vm", - .mode = 0555, - .child = vm_table, - }, - { - .procname = "fs", - .mode = 0555, - .child = fs_table, - }, - { - .procname = "debug", - .mode = 0555, - .child = debug_table, - }, - { - .procname = "dev", - .mode = 0555, - .child = dev_table, - }, - { } -}; + if (!data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } -#ifdef CONFIG_SCHED_DEBUG -static int min_sched_granularity_ns = 100000; /* 100 usecs */ -static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ -static int min_wakeup_granularity_ns; /* 0 usecs */ -static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ -#ifdef CONFIG_SMP -static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; -static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -#endif /* CONFIG_SMP */ -#endif /* CONFIG_SCHED_DEBUG */ + i = (unsigned long *) data; + min = (unsigned long *) table->extra1; + max = (unsigned long *) table->extra2; + vleft = table->maxlen / sizeof(unsigned long); + left = *lenp; -#ifdef CONFIG_COMPACTION -static int min_extfrag_threshold; -static int max_extfrag_threshold = 1000; -#endif + if (write) { + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + p = buffer; + } + + for (; left && vleft--; i++, first = 0) { + unsigned long val; + + if (write) { + bool neg; + + left -= proc_skip_spaces(&p); + if (!left) + break; + + err = proc_get_long(&p, &left, &val, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err) + break; + if (neg) + continue; + val = convmul * val / convdiv; + if ((min && val < *min) || (max && val > *max)) { + err = -EINVAL; + break; + } + *i = val; + } else { + val = convdiv * (*i) / convmul; + if (!first) + proc_put_char(&buffer, &left, '\t'); + proc_put_long(&buffer, &left, val, false); + } + } + + if (!write && !first && left && !err) + proc_put_char(&buffer, &left, '\n'); + if (write && !err) + left -= proc_skip_spaces(&p); + if (write && first) + return err ? : -EINVAL; + *lenp -= left; +out: + *ppos += *lenp; + 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) +{ + return __do_proc_doulongvec_minmax(table->data, table, write, + 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 + * @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. + * + * 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_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, 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; + *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ); + } else { + int val = *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; + *valp = (int)jif; + } 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_msecs(lval); + } + 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(uns |