OpenCloudOS-Kernel/include/linux/sysctl.h

231 lines
7.1 KiB
C
Raw Normal View History

/*
* 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;
typedef int proc_handler (struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
extern int proc_dostring(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
sysctl: handle error writing UINT_MAX to u32 fields We have scripts which write to certain fields on 3.18 kernels but this seems to be failing on 4.4 kernels. An entry which we write to here is xfrm_aevent_rseqth which is u32. echo 4294967295 > /proc/sys/net/core/xfrm_aevent_rseqth Commit 230633d109e3 ("kernel/sysctl.c: detect overflows when converting to int") prevented writing to sysctl entries when integer overflow occurs. However, this does not apply to unsigned integers. Heinrich suggested that we introduce a new option to handle 64 bit limits and set min as 0 and max as UINT_MAX. This might not work as it leads to issues similar to __do_proc_doulongvec_minmax. Alternatively, we would need to change the datatype of the entry to 64 bit. static int __do_proc_doulongvec_minmax(void *data, struct ctl_table { i = (unsigned long *) data; //This cast is causing to read beyond the size of data (u32) vleft = table->maxlen / sizeof(unsigned long); //vleft is 0 because maxlen is sizeof(u32) which is lesser than sizeof(unsigned long) on x86_64. Introduce a new proc handler proc_douintvec. Individual proc entries will need to be updated to use the new handler. [akpm@linux-foundation.org: coding-style fixes] Fixes: 230633d109e3 ("kernel/sysctl.c:detect overflows when converting to int") Link: http://lkml.kernel.org/r/1471479806-5252-1-git-send-email-subashab@codeaurora.org Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> Cc: Heinrich Schuchardt <xypron.glpk@gmx.de> Cc: Kees Cook <keescook@chromium.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ingo Molnar <mingo@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-26 06:16:51 +08:00
extern int proc_douintvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_douintvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int proc_dointvec_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_ms_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_doulongvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
void __user *, size_t *, loff_t *);
extern int proc_do_large_bitmap(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
/*
* 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;
proc: Fix proc_sys_prune_dcache to hold a sb reference Andrei Vagin writes: FYI: This bug has been reproduced on 4.11.7 > BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo} still in use (1) [unmount of proc proc] > ------------[ cut here ]------------ > WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80 > CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1 > Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015 > Workqueue: events proc_cleanup_work > Call Trace: > dump_stack+0x63/0x86 > __warn+0xcb/0xf0 > warn_slowpath_null+0x1d/0x20 > umount_check+0x6e/0x80 > d_walk+0xc6/0x270 > ? dentry_free+0x80/0x80 > do_one_tree+0x26/0x40 > shrink_dcache_for_umount+0x2d/0x90 > generic_shutdown_super+0x1f/0xf0 > kill_anon_super+0x12/0x20 > proc_kill_sb+0x40/0x50 > deactivate_locked_super+0x43/0x70 > deactivate_super+0x5a/0x60 > cleanup_mnt+0x3f/0x90 > mntput_no_expire+0x13b/0x190 > kern_unmount+0x3e/0x50 > pid_ns_release_proc+0x15/0x20 > proc_cleanup_work+0x15/0x20 > process_one_work+0x197/0x450 > worker_thread+0x4e/0x4a0 > kthread+0x109/0x140 > ? process_one_work+0x450/0x450 > ? kthread_park+0x90/0x90 > ret_from_fork+0x2c/0x40 > ---[ end trace e1c109611e5d0b41 ]--- > VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds. Have a nice day... > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: _raw_spin_lock+0xc/0x30 > PGD 0 Fix this by taking a reference to the super block in proc_sys_prune_dcache. The superblock reference is the core of the fix however the sysctl_inodes list is converted to a hlist so that hlist_del_init_rcu may be used. This allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while not causing problems for proc_sys_evict_inode when if it later choses to remove the inode from the sysctl_inodes list. Removing inodes from the sysctl_inodes list allows proc_sys_prune_dcache to have a progress guarantee, while still being able to drop all locks. The fact that head->unregistering is set in start_unregistering ensures that no more inodes will be added to the the sysctl_inodes list. Previously the code did a dance where it delayed calling iput until the next entry in the list was being considered to ensure the inode remained on the sysctl_inodes list until the next entry was walked to. The structure of the loop in this patch does not need that so is much easier to understand and maintain. Cc: stable@vger.kernel.org Reported-by: Andrei Vagin <avagin@gmail.com> Tested-by: Andrei Vagin <avagin@openvz.org> Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.") Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering") Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2017-07-06 21:41:06 +08:00
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);
[PATCH] sysctl: remove insert_at_head from register_sysctl The semantic effect of insert_at_head is that it would allow new registered sysctl entries to override existing sysctl entries of the same name. Which is pain for caching and the proc interface never implemented. I have done an audit and discovered that none of the current users of register_sysctl care as (excpet for directories) they do not register duplicate sysctl entries. So this patch simply removes the support for overriding existing entries in the sys_sysctl interface since no one uses it or cares and it makes future enhancments harder. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: David Howells <dhowells@redhat.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Corey Minyard <minyard@acm.org> Cc: Neil Brown <neilb@suse.de> Cc: "John W. Linville" <linville@tuxdriver.com> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Jan Kara <jack@ucw.cz> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-14 16:34:09 +08:00
void unregister_sysctl_table(struct ctl_table_header * table);
extern int sysctl_init(void);
extern struct ctl_table sysctl_mount_point[];
#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 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 *))
{
}
#endif /* CONFIG_SYSCTL */
int sysctl_max_threads(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif /* _LINUX_SYSCTL_H */