mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
![Vlastimil Babka](/assets/img/avatar_default.png)
Patch series "support setting sysctl parameters from kernel command line", v3. This series adds support for something that seems like many people always wanted but nobody added it yet, so here's the ability to set sysctl parameters via kernel command line options in the form of sysctl.vm.something=1 The important part is Patch 1. The second, not so important part is an attempt to clean up legacy one-off parameters that do the same thing as a sysctl. I don't want to remove them completely for compatibility reasons, but with generic sysctl support the idea is to remove the one-off param handlers and treat the parameters as aliases for the sysctl variants. I have identified several parameters that mention sysctl counterparts in Documentation/admin-guide/kernel-parameters.txt but there might be more. The conversion also has varying level of success: - numa_zonelist_order is converted in Patch 2 together with adding the necessary infrastructure. It's easy as it doesn't really do anything but warn on deprecated value these days. - hung_task_panic is converted in Patch 3, but there's a downside that now it only accepts 0 and 1, while previously it was any integer value - nmi_watchdog maps to two sysctls nmi_watchdog and hardlockup_panic, so there's no straighforward conversion possible - traceoff_on_warning is a flag without value and it would be required to handle that somehow in the conversion infractructure, which seems pointless for a single flag This patch (of 5): A recently proposed patch to add vm_swappiness command line parameter in addition to existing sysctl [1] made me wonder why we don't have a general support for passing sysctl parameters via command line. Googling found only somebody else wondering the same [2], but I haven't found any prior discussion with reasons why not to do this. Settings the vm_swappiness issue aside (the underlying issue might be solved in a different way), quick search of kernel-parameters.txt shows there are already some that exist as both sysctl and kernel parameter - hung_task_panic, nmi_watchdog, numa_zonelist_order, traceoff_on_warning. A general mechanism would remove the need to add more of those one-offs and might be handy in situations where configuration by e.g. /etc/sysctl.d/ is impractical. Hence, this patch adds a new parse_args() pass that looks for parameters prefixed by 'sysctl.' and tries to interpret them as writes to the corresponding sys/ files using an temporary in-kernel procfs mount. This mechanism was suggested by Eric W. Biederman [3], as it handles all dynamically registered sysctl tables, even though we don't handle modular sysctls. Errors due to e.g. invalid parameter name or value are reported in the kernel log. The processing is hooked right before the init process is loaded, as some handlers might be more complicated than simple setters and might need some subsystems to be initialized. At the moment the init process can be started and eventually execute a process writing to /proc/sys/ then it should be also fine to do that from the kernel. Sysctls registered later on module load time are not set by this mechanism - it's expected that in such scenarios, setting sysctl values from userspace is practical enough. [1] https://lore.kernel.org/r/BL0PR02MB560167492CA4094C91589930E9FC0@BL0PR02MB5601.namprd02.prod.outlook.com/ [2] https://unix.stackexchange.com/questions/558802/how-to-set-sysctl-using-kernel-command-line-parameter [3] https://lore.kernel.org/r/87bloj2skm.fsf@x220.int.ebiederm.org/ Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Iurii Zaikin <yzaikin@google.com> Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: "Eric W . Biederman" <ebiederm@xmission.com> Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Christian Brauner <christian.brauner@ubuntu.com> Link: http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz Link: http://lkml.kernel.org/r/20200427180433.7029-2-vbabka@suse.cz Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
247 lines
7.6 KiB
C
247 lines
7.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* sysctl.h: General linux system control interface
|
|
*
|
|
* Begun 24 March 1995, Stephen Tweedie
|
|
*
|
|
****************************************************************
|
|
****************************************************************
|
|
**
|
|
** WARNING:
|
|
** The values in this file are exported to user space via
|
|
** the sysctl() binary interface. Do *NOT* change the
|
|
** numbering of any existing values here, and do not change
|
|
** any numbers within any one set of values. If you have to
|
|
** redefine an existing interface, use a new number for it.
|
|
** The kernel will then return -ENOTDIR to any application using
|
|
** the old binary interface.
|
|
**
|
|
****************************************************************
|
|
****************************************************************
|
|
*/
|
|
#ifndef _LINUX_SYSCTL_H
|
|
#define _LINUX_SYSCTL_H
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/uidgid.h>
|
|
#include <uapi/linux/sysctl.h>
|
|
|
|
/* For the /proc/sys support */
|
|
struct completion;
|
|
struct ctl_table;
|
|
struct nsproxy;
|
|
struct ctl_table_root;
|
|
struct ctl_table_header;
|
|
struct ctl_dir;
|
|
|
|
/* Keep the same order as in fs/proc/proc_sysctl.c */
|
|
#define SYSCTL_ZERO ((void *)&sysctl_vals[0])
|
|
#define SYSCTL_ONE ((void *)&sysctl_vals[1])
|
|
#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2])
|
|
|
|
extern const int sysctl_vals[];
|
|
|
|
typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer,
|
|
size_t *lenp, loff_t *ppos);
|
|
|
|
int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer,
|
|
size_t *lenp, loff_t *ppos);
|
|
int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *,
|
|
loff_t *);
|
|
int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *,
|
|
loff_t *);
|
|
int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *,
|
|
size_t *, loff_t *);
|
|
int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *);
|
|
int proc_do_static_key(struct ctl_table *table, int write, void *buffer,
|
|
size_t *lenp, loff_t *ppos);
|
|
|
|
/*
|
|
* Register a set of sysctl names by calling register_sysctl_table
|
|
* with an initialised array of struct ctl_table's. An entry with
|
|
* NULL procname terminates the table. table->de will be
|
|
* set up by the registration and need not be initialised in advance.
|
|
*
|
|
* sysctl names can be mirrored automatically under /proc/sys. The
|
|
* procname supplied controls /proc naming.
|
|
*
|
|
* The table's mode will be honoured both for sys_sysctl(2) and
|
|
* proc-fs access.
|
|
*
|
|
* Leaf nodes in the sysctl tree will be represented by a single file
|
|
* under /proc; non-leaf nodes will be represented by directories. A
|
|
* null procname disables /proc mirroring at this node.
|
|
*
|
|
* sysctl(2) can automatically manage read and write requests through
|
|
* the sysctl table. The data and maxlen fields of the ctl_table
|
|
* struct enable minimal validation of the values being written to be
|
|
* performed, and the mode field allows minimal authentication.
|
|
*
|
|
* There must be a proc_handler routine for any terminal nodes
|
|
* mirrored under /proc/sys (non-terminals are handled by a built-in
|
|
* directory handler). Several default handlers are available to
|
|
* cover common cases.
|
|
*/
|
|
|
|
/* Support for userspace poll() to watch for changes */
|
|
struct ctl_table_poll {
|
|
atomic_t event;
|
|
wait_queue_head_t wait;
|
|
};
|
|
|
|
static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
|
|
{
|
|
return (void *)(unsigned long)atomic_read(&poll->event);
|
|
}
|
|
|
|
#define __CTL_TABLE_POLL_INITIALIZER(name) { \
|
|
.event = ATOMIC_INIT(0), \
|
|
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
|
|
|
|
#define DEFINE_CTL_TABLE_POLL(name) \
|
|
struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
|
|
|
|
/* A sysctl table is an array of struct ctl_table: */
|
|
struct ctl_table {
|
|
const char *procname; /* Text ID for /proc/sys, or zero */
|
|
void *data;
|
|
int maxlen;
|
|
umode_t mode;
|
|
struct ctl_table *child; /* Deprecated */
|
|
proc_handler *proc_handler; /* Callback for text formatting */
|
|
struct ctl_table_poll *poll;
|
|
void *extra1;
|
|
void *extra2;
|
|
} __randomize_layout;
|
|
|
|
struct ctl_node {
|
|
struct rb_node node;
|
|
struct ctl_table_header *header;
|
|
};
|
|
|
|
/* struct ctl_table_header is used to maintain dynamic lists of
|
|
struct ctl_table trees. */
|
|
struct ctl_table_header {
|
|
union {
|
|
struct {
|
|
struct ctl_table *ctl_table;
|
|
int used;
|
|
int count;
|
|
int nreg;
|
|
};
|
|
struct rcu_head rcu;
|
|
};
|
|
struct completion *unregistering;
|
|
struct ctl_table *ctl_table_arg;
|
|
struct ctl_table_root *root;
|
|
struct ctl_table_set *set;
|
|
struct ctl_dir *parent;
|
|
struct ctl_node *node;
|
|
struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
|
|
};
|
|
|
|
struct ctl_dir {
|
|
/* Header must be at the start of ctl_dir */
|
|
struct ctl_table_header header;
|
|
struct rb_root root;
|
|
};
|
|
|
|
struct ctl_table_set {
|
|
int (*is_seen)(struct ctl_table_set *);
|
|
struct ctl_dir dir;
|
|
};
|
|
|
|
struct ctl_table_root {
|
|
struct ctl_table_set default_set;
|
|
struct ctl_table_set *(*lookup)(struct ctl_table_root *root);
|
|
void (*set_ownership)(struct ctl_table_header *head,
|
|
struct ctl_table *table,
|
|
kuid_t *uid, kgid_t *gid);
|
|
int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
|
|
};
|
|
|
|
/* struct ctl_path describes where in the hierarchy a table is added */
|
|
struct ctl_path {
|
|
const char *procname;
|
|
};
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
void proc_sys_poll_notify(struct ctl_table_poll *poll);
|
|
|
|
extern void setup_sysctl_set(struct ctl_table_set *p,
|
|
struct ctl_table_root *root,
|
|
int (*is_seen)(struct ctl_table_set *));
|
|
extern void retire_sysctl_set(struct ctl_table_set *set);
|
|
|
|
struct ctl_table_header *__register_sysctl_table(
|
|
struct ctl_table_set *set,
|
|
const char *path, struct ctl_table *table);
|
|
struct ctl_table_header *__register_sysctl_paths(
|
|
struct ctl_table_set *set,
|
|
const struct ctl_path *path, struct ctl_table *table);
|
|
struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table);
|
|
struct ctl_table_header *register_sysctl_table(struct ctl_table * table);
|
|
struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
|
|
struct ctl_table *table);
|
|
|
|
void unregister_sysctl_table(struct ctl_table_header * table);
|
|
|
|
extern int sysctl_init(void);
|
|
void do_sysctl_args(void);
|
|
|
|
extern int pwrsw_enabled;
|
|
extern int unaligned_enabled;
|
|
extern int unaligned_dump_stack;
|
|
extern int no_unaligned_warning;
|
|
|
|
extern struct ctl_table sysctl_mount_point[];
|
|
extern struct ctl_table random_table[];
|
|
extern struct ctl_table firmware_config_table[];
|
|
extern struct ctl_table epoll_table[];
|
|
|
|
#else /* CONFIG_SYSCTL */
|
|
static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct ctl_table_header *register_sysctl_paths(
|
|
const struct ctl_path *path, struct ctl_table *table)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void unregister_sysctl_table(struct ctl_table_header * table)
|
|
{
|
|
}
|
|
|
|
static inline void setup_sysctl_set(struct ctl_table_set *p,
|
|
struct ctl_table_root *root,
|
|
int (*is_seen)(struct ctl_table_set *))
|
|
{
|
|
}
|
|
|
|
static inline void do_sysctl_args(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SYSCTL */
|
|
|
|
int sysctl_max_threads(struct ctl_table *table, int write, void *buffer,
|
|
size_t *lenp, loff_t *ppos);
|
|
|
|
#endif /* _LINUX_SYSCTL_H */
|