linux-brain/ipc/ipc_sysctl.c
Manfred Spraul 99db46ea29 ipc: do cyclic id allocation for the ipc object.
For ipcmni_extend mode, the sequence number space is only 7 bits.  So
the chance of id reuse is relatively high compared with the non-extended
mode.

To alleviate this id reuse problem, this patch enables cyclic allocation
for the index to the radix tree (idx).  The disadvantage is that this
can cause a slight slow-down of the fast path, as the radix tree could
be higher than necessary.

To limit the radix tree height, I have chosen the following limits:
 1) The cycling is done over in_use*1.5.
 2) At least, the cycling is done over
   "normal" ipcnmi mode: RADIX_TREE_MAP_SIZE elements
   "ipcmni_extended": 4096 elements

Result:
- for normal mode:
	No change for <= 42 active ipc elements. With more than 42
	active ipc elements, a 2nd level would be added to the radix
	tree.
	Without cyclic allocation, a 2nd level would be added only with
	more than 63 active elements.

- for extended mode:
	Cycling creates always at least a 2-level radix tree.
	With more than 2730 active objects, a 3rd level would be
	added, instead of > 4095 active objects until the 3rd level
	is added without cyclic allocation.

For a 2-level radix tree compared to a 1-level radix tree, I have
observed < 1% performance impact.

Notes:
1) Normal "x=semget();y=semget();" is unaffected: Then the idx
  is e.g. a and a+1, regardless if idr_alloc() or idr_alloc_cyclic()
  is used.

2) The -1% happens in a microbenchmark after this situation:
	x=semget();
	for(i=0;i<4000;i++) {t=semget();semctl(t,0,IPC_RMID);}
	y=semget();
	Now perform semget calls on x and y that do not sleep.

3) The worst-case reuse cycle time is unfortunately unaffected:
   If you have 2^24-1 ipc objects allocated, and get/remove the last
   possible element in a loop, then the id is reused after 128
   get/remove pairs.

Performance check:
A microbenchmark that performes no-op semop() randomly on two IDs,
with only these two IDs allocated.
The IDs were set using /proc/sys/kernel/sem_next_id.
The test was run 5 times, averages are shown.

1 & 2: Base (6.22 seconds for 10.000.000 semops)
1 & 40: -0.2%
1 & 3348: - 0.8%
1 & 27348: - 1.6%
1 & 15777204: - 3.2%

Or: ~12.6 cpu cycles per additional radix tree level.
The cpu is an Intel I3-5010U. ~1300 cpu cycles/syscall is slower
than what I remember (spectre impact?).

V2 of the patch:
- use "min" and "max"
- use RADIX_TREE_MAP_SIZE * RADIX_TREE_MAP_SIZE instead of
	(2<<12).

[akpm@linux-foundation.org: fix max() warning]
Link: http://lkml.kernel.org/r/20190329204930.21620-3-longman@redhat.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Acked-by: Waiman Long <longman@redhat.com>
Cc: "Luis R. Rodriguez" <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 19:52:52 -07:00

261 lines
6.3 KiB
C

/*
* Copyright (C) 2007
*
* Author: Eric Biederman <ebiederm@xmision.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation, version 2 of the
* License.
*/
#include <linux/module.h>
#include <linux/ipc.h>
#include <linux/nsproxy.h>
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <linux/ipc_namespace.h>
#include <linux/msg.h>
#include "util.h"
static void *get_ipc(struct ctl_table *table)
{
char *which = table->data;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
return which;
}
#ifdef CONFIG_PROC_SYSCTL
static int proc_ipc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
}
static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
}
static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ipc_namespace *ns = current->nsproxy->ipc_ns;
int err = proc_ipc_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_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_doulongvec_minmax(&ipc_table, write, buffer,
lenp, ppos);
}
static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
void __user *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 __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret, semmni;
struct ipc_namespace *ns = current->nsproxy->ipc_ns;
semmni = ns->sem_ctls[3];
ret = proc_ipc_dointvec(table, write, buffer, lenp, ppos);
if (!ret)
ret = sem_check_semmni(current->nsproxy->ipc_ns);
/*
* Reset the semmni value if an error happens.
*/
if (ret)
ns->sem_ctls[3] = semmni;
return ret;
}
#else
#define proc_ipc_doulongvec_minmax NULL
#define proc_ipc_dointvec NULL
#define proc_ipc_dointvec_minmax NULL
#define proc_ipc_dointvec_minmax_orphans NULL
#define proc_ipc_auto_msgmni NULL
#define proc_ipc_sem_dointvec NULL
#endif
static int zero;
static int one = 1;
static int int_max = INT_MAX;
int ipc_mni = IPCMNI;
int ipc_mni_shift = IPCMNI_SHIFT;
int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
static struct ctl_table ipc_kern_table[] = {
{
.procname = "shmmax",
.data = &init_ipc_ns.shm_ctlmax,
.maxlen = sizeof(init_ipc_ns.shm_ctlmax),
.mode = 0644,
.proc_handler = proc_ipc_doulongvec_minmax,
},
{
.procname = "shmall",
.data = &init_ipc_ns.shm_ctlall,
.maxlen = sizeof(init_ipc_ns.shm_ctlall),
.mode = 0644,
.proc_handler = proc_ipc_doulongvec_minmax,
},
{
.procname = "shmmni",
.data = &init_ipc_ns.shm_ctlmni,
.maxlen = sizeof(init_ipc_ns.shm_ctlmni),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &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 = &zero,
.extra2 = &one,
},
{
.procname = "msgmax",
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof(init_ipc_ns.msg_ctlmax),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "msgmni",
.data = &init_ipc_ns.msg_ctlmni,
.maxlen = sizeof(init_ipc_ns.msg_ctlmni),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &ipc_mni,
},
{
.procname = "auto_msgmni",
.data = NULL,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_ipc_auto_msgmni,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "msgmnb",
.data = &init_ipc_ns.msg_ctlmnb,
.maxlen = sizeof(init_ipc_ns.msg_ctlmnb),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &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 = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &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 = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &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 = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
#endif
{}
};
static struct ctl_table ipc_root_table[] = {
{
.procname = "kernel",
.mode = 0555,
.child = ipc_kern_table,
},
{}
};
static int __init ipc_sysctl_init(void)
{
register_sysctl_table(ipc_root_table);
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);