linux/ipc/ipc_sysctl.c
Linus Torvalds eb6a9339ef Mainly singleton patches, documented in their respective changelogs.
Notable series include:
 
 - Some maintenance and performance work for ocfs2 in Heming Zhao's
   series "improve write IO performance when fragmentation is high".
 
 - Some ocfs2 bugfixes from Su Yue in the series "ocfs2 bugs fixes
   exposed by fstests".
 
 - kfifo header rework from Andy Shevchenko in the series "kfifo: Clean
   up kfifo.h".
 
 - GDB script fixes from Florian Rommel in the series "scripts/gdb: Fixes
   for $lx_current and $lx_per_cpu".
 
 - After much discussion, a coding-style update from Barry Song
   explaining one reason why inline functions are preferred over macros.
   The series is "codingstyle: avoid unused parameters for a function-like
   macro".
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZkpLYQAKCRDdBJ7gKXxA
 jo9NAQDctSD3TMXqxqCHLaEpCaYTYzi6TGAVHjgkqGzOt7tYjAD/ZIzgcmRwthjP
 R7SSiSgZ7UnP9JRn16DQILmFeaoG1gs=
 =lYhr
 -----END PGP SIGNATURE-----

Merge tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-mm updates from Andrew Morton:
 "Mainly singleton patches, documented in their respective changelogs.
  Notable series include:

   - Some maintenance and performance work for ocfs2 in Heming Zhao's
     series "improve write IO performance when fragmentation is high".

   - Some ocfs2 bugfixes from Su Yue in the series "ocfs2 bugs fixes
     exposed by fstests".

   - kfifo header rework from Andy Shevchenko in the series "kfifo:
     Clean up kfifo.h".

   - GDB script fixes from Florian Rommel in the series "scripts/gdb:
     Fixes for $lx_current and $lx_per_cpu".

   - After much discussion, a coding-style update from Barry Song
     explaining one reason why inline functions are preferred over
     macros. The series is "codingstyle: avoid unused parameters for a
     function-like macro""

* tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (62 commits)
  fs/proc: fix softlockup in __read_vmcore
  nilfs2: convert BUG_ON() in nilfs_finish_roll_forward() to WARN_ON()
  scripts: checkpatch: check unused parameters for function-like macro
  Documentation: coding-style: ask function-like macros to evaluate parameters
  nilfs2: use __field_struct() for a bitwise field
  selftests/kcmp: remove unused open mode
  nilfs2: remove calls to folio_set_error() and folio_clear_error()
  kernel/watchdog_perf.c: tidy up kerneldoc
  watchdog: allow nmi watchdog to use raw perf event
  watchdog: handle comma separated nmi_watchdog command line
  nilfs2: make superblock data array index computation sparse friendly
  squashfs: remove calls to set the folio error flag
  squashfs: convert squashfs_symlink_read_folio to use folio APIs
  scripts/gdb: fix detection of current CPU in KGDB
  scripts/gdb: make get_thread_info accept pointers
  scripts/gdb: fix parameter handling in $lx_per_cpu
  scripts/gdb: fix failing KGDB detection during probe
  kfifo: don't use "proxy" headers
  media: stih-cec: add missing io.h
  media: rc: add missing io.h
  ...
2024-05-19 14:02:03 -07:00

334 lines
8 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2007
*
* Author: Eric Biederman <ebiederm@xmision.com>
*/
#include <linux/module.h>
#include <linux/ipc.h>
#include <linux/nsproxy.h>
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <linux/capability.h>
#include <linux/ipc_namespace.h>
#include <linux/msg.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include "util.h"
static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ipc_namespace *ns =
container_of(table->data, struct ipc_namespace, shm_rmid_forced);
int err;
err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (err < 0)
return err;
if (ns->shm_rmid_forced)
shm_destroy_orphaned(ns);
return err;
}
static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
int dummy = 0;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = &dummy;
if (write)
pr_info_once("writing to auto_msgmni has no effect");
return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
}
static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ipc_namespace *ns =
container_of(table->data, struct ipc_namespace, sem_ctls);
int ret, semmni;
semmni = ns->sem_ctls[3];
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret)
ret = sem_check_semmni(ns);
/*
* Reset the semmni value if an error happens.
*/
if (ret)
ns->sem_ctls[3] = semmni;
return ret;
}
int ipc_mni = IPCMNI;
int ipc_mni_shift = IPCMNI_SHIFT;
int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
static struct ctl_table ipc_sysctls[] = {
{
.procname = "shmmax",
.data = &init_ipc_ns.shm_ctlmax,
.maxlen = sizeof(init_ipc_ns.shm_ctlmax),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "shmall",
.data = &init_ipc_ns.shm_ctlall,
.maxlen = sizeof(init_ipc_ns.shm_ctlall),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "shmmni",
.data = &init_ipc_ns.shm_ctlmni,
.maxlen = sizeof(init_ipc_ns.shm_ctlmni),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = &ipc_mni,
},
{
.procname = "shm_rmid_forced",
.data = &init_ipc_ns.shm_rmid_forced,
.maxlen = sizeof(init_ipc_ns.shm_rmid_forced),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax_orphans,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "msgmax",
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof(init_ipc_ns.msg_ctlmax),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "msgmni",
.data = &init_ipc_ns.msg_ctlmni,
.maxlen = sizeof(init_ipc_ns.msg_ctlmni),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = &ipc_mni,
},
{
.procname = "auto_msgmni",
.data = NULL,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_ipc_auto_msgmni,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "msgmnb",
.data = &init_ipc_ns.msg_ctlmnb,
.maxlen = sizeof(init_ipc_ns.msg_ctlmnb),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "sem",
.data = &init_ipc_ns.sem_ctls,
.maxlen = 4*sizeof(int),
.mode = 0644,
.proc_handler = proc_ipc_sem_dointvec,
},
#ifdef CONFIG_CHECKPOINT_RESTORE
{
.procname = "sem_next_id",
.data = &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
.mode = 0444,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "msg_next_id",
.data = &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
.mode = 0444,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
{
.procname = "shm_next_id",
.data = &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
.mode = 0444,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_INT_MAX,
},
#endif
};
static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
{
return &current->nsproxy->ipc_ns->ipc_set;
}
static int set_is_seen(struct ctl_table_set *set)
{
return &current->nsproxy->ipc_ns->ipc_set == set;
}
static void ipc_set_ownership(struct ctl_table_header *head,
kuid_t *uid, kgid_t *gid)
{
struct ipc_namespace *ns =
container_of(head->set, struct ipc_namespace, ipc_set);
kuid_t ns_root_uid = make_kuid(ns->user_ns, 0);
kgid_t ns_root_gid = make_kgid(ns->user_ns, 0);
*uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID;
*gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID;
}
static int ipc_permissions(struct ctl_table_header *head, const struct ctl_table *table)
{
int mode = table->mode;
#ifdef CONFIG_CHECKPOINT_RESTORE
struct ipc_namespace *ns =
container_of(head->set, struct ipc_namespace, ipc_set);
if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) ||
(table->data == &ns->ids[IPC_MSG_IDS].next_id) ||
(table->data == &ns->ids[IPC_SHM_IDS].next_id)) &&
checkpoint_restore_ns_capable(ns->user_ns))
mode = 0666;
else
#endif
{
kuid_t ns_root_uid;
kgid_t ns_root_gid;
ipc_set_ownership(head, &ns_root_uid, &ns_root_gid);
if (uid_eq(current_euid(), ns_root_uid))
mode >>= 6;
else if (in_egroup_p(ns_root_gid))
mode >>= 3;
}
mode &= 7;
return (mode << 6) | (mode << 3) | mode;
}
static struct ctl_table_root set_root = {
.lookup = set_lookup,
.permissions = ipc_permissions,
.set_ownership = ipc_set_ownership,
};
bool setup_ipc_sysctls(struct ipc_namespace *ns)
{
struct ctl_table *tbl;
setup_sysctl_set(&ns->ipc_set, &set_root, set_is_seen);
tbl = kmemdup(ipc_sysctls, sizeof(ipc_sysctls), GFP_KERNEL);
if (tbl) {
int i;
for (i = 0; i < ARRAY_SIZE(ipc_sysctls); i++) {
if (tbl[i].data == &init_ipc_ns.shm_ctlmax)
tbl[i].data = &ns->shm_ctlmax;
else if (tbl[i].data == &init_ipc_ns.shm_ctlall)
tbl[i].data = &ns->shm_ctlall;
else if (tbl[i].data == &init_ipc_ns.shm_ctlmni)
tbl[i].data = &ns->shm_ctlmni;
else if (tbl[i].data == &init_ipc_ns.shm_rmid_forced)
tbl[i].data = &ns->shm_rmid_forced;
else if (tbl[i].data == &init_ipc_ns.msg_ctlmax)
tbl[i].data = &ns->msg_ctlmax;
else if (tbl[i].data == &init_ipc_ns.msg_ctlmni)
tbl[i].data = &ns->msg_ctlmni;
else if (tbl[i].data == &init_ipc_ns.msg_ctlmnb)
tbl[i].data = &ns->msg_ctlmnb;
else if (tbl[i].data == &init_ipc_ns.sem_ctls)
tbl[i].data = &ns->sem_ctls;
#ifdef CONFIG_CHECKPOINT_RESTORE
else if (tbl[i].data == &init_ipc_ns.ids[IPC_SEM_IDS].next_id)
tbl[i].data = &ns->ids[IPC_SEM_IDS].next_id;
else if (tbl[i].data == &init_ipc_ns.ids[IPC_MSG_IDS].next_id)
tbl[i].data = &ns->ids[IPC_MSG_IDS].next_id;
else if (tbl[i].data == &init_ipc_ns.ids[IPC_SHM_IDS].next_id)
tbl[i].data = &ns->ids[IPC_SHM_IDS].next_id;
#endif
else
tbl[i].data = NULL;
}
ns->ipc_sysctls = __register_sysctl_table(&ns->ipc_set, "kernel", tbl,
ARRAY_SIZE(ipc_sysctls));
}
if (!ns->ipc_sysctls) {
kfree(tbl);
retire_sysctl_set(&ns->ipc_set);
return false;
}
return true;
}
void retire_ipc_sysctls(struct ipc_namespace *ns)
{
const struct ctl_table *tbl;
tbl = ns->ipc_sysctls->ctl_table_arg;
unregister_sysctl_table(ns->ipc_sysctls);
retire_sysctl_set(&ns->ipc_set);
kfree(tbl);
}
static int __init ipc_sysctl_init(void)
{
if (!setup_ipc_sysctls(&init_ipc_ns)) {
pr_warn("ipc sysctl registration failed\n");
return -ENOMEM;
}
return 0;
}
device_initcall(ipc_sysctl_init);
static int __init ipc_mni_extend(char *str)
{
ipc_mni = IPCMNI_EXTEND;
ipc_mni_shift = IPCMNI_EXTEND_SHIFT;
ipc_min_cycle = IPCMNI_EXTEND_MIN_CYCLE;
pr_info("IPCMNI extended to %d.\n", ipc_mni);
return 0;
}
early_param("ipcmni_extend", ipc_mni_extend);