linux/ipc/util.c

891 lines
22 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* linux/ipc/util.c
* Copyright (C) 1992 Krishna Balasubramanian
*
* Sep 1997 - Call suser() last after "normal" permission checks so we
* get BSD style process accounting right.
* Occurs in several places in the IPC code.
* Chris Evans, <chris@ferret.lmh.ox.ac.uk>
* Nov 1999 - ipc helper functions, unified SMP locking
* Manfred Spraul <manfred@colorfullife.com>
* Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary().
* Mingming Cao <cmm@us.ibm.com>
[PATCH] Rework of IPC auditing 1) The audit_ipc_perms() function has been split into two different functions: - audit_ipc_obj() - audit_ipc_set_perm() There's a key shift here... The audit_ipc_obj() collects the uid, gid, mode, and SElinux context label of the current ipc object. This audit_ipc_obj() hook is now found in several places. Most notably, it is hooked in ipcperms(), which is called in various places around the ipc code permforming a MAC check. Additionally there are several places where *checkid() is used to validate that an operation is being performed on a valid object while not necessarily having a nearby ipcperms() call. In these locations, audit_ipc_obj() is called to ensure that the information is captured by the audit system. The audit_set_new_perm() function is called any time the permissions on the ipc object changes. In this case, the NEW permissions are recorded (and note that an audit_ipc_obj() call exists just a few lines before each instance). 2) Support for an AUDIT_IPC_SET_PERM audit message type. This allows for separate auxiliary audit records for normal operations on an IPC object and permissions changes. Note that the same struct audit_aux_data_ipcctl is used and populated, however there are separate audit_log_format statements based on the type of the message. Finally, the AUDIT_IPC block of code in audit_free_aux() was extended to handle aux messages of this new type. No more mem leaks I hope ;-) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2006-04-03 05:07:33 +08:00
* Mar 2006 - support for audit of ipc object properties
* Dustin Kirkland <dustin.kirkland@us.ibm.com>
* Jun 2006 - namespaces ssupport
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*
* General sysv ipc locking scheme:
* rcu_read_lock()
* obtain the ipc object (kern_ipc_perm) by looking up the id in an idr
* tree.
* - perform initial checks (capabilities, auditing and permission,
* etc).
* - perform read-only operations, such as STAT, INFO commands.
* acquire the ipc lock (kern_ipc_perm.lock) through
* ipc_lock_object()
* - perform data updates, such as SET, RMID commands and
* mechanism-specific operations (semop/semtimedop,
* msgsnd/msgrcv, shmat/shmdt).
* drop the ipc lock, through ipc_unlock_object().
* rcu_read_unlock()
*
* The ids->rwsem must be taken when:
* - creating, removing and iterating the existing entries in ipc
* identifier sets.
* - iterating through files under /proc/sysvipc/
*
* Note that sems have a special fast path that avoids kern_ipc_perm.lock -
* see sem_lock().
*/
#include <linux/mm.h>
#include <linux/shm.h>
#include <linux/init.h>
#include <linux/msg.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/capability.h>
#include <linux/highuid.h>
#include <linux/security.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
[PATCH] Rework of IPC auditing 1) The audit_ipc_perms() function has been split into two different functions: - audit_ipc_obj() - audit_ipc_set_perm() There's a key shift here... The audit_ipc_obj() collects the uid, gid, mode, and SElinux context label of the current ipc object. This audit_ipc_obj() hook is now found in several places. Most notably, it is hooked in ipcperms(), which is called in various places around the ipc code permforming a MAC check. Additionally there are several places where *checkid() is used to validate that an operation is being performed on a valid object while not necessarily having a nearby ipcperms() call. In these locations, audit_ipc_obj() is called to ensure that the information is captured by the audit system. The audit_set_new_perm() function is called any time the permissions on the ipc object changes. In this case, the NEW permissions are recorded (and note that an audit_ipc_obj() call exists just a few lines before each instance). 2) Support for an AUDIT_IPC_SET_PERM audit message type. This allows for separate auxiliary audit records for normal operations on an IPC object and permissions changes. Note that the same struct audit_aux_data_ipcctl is used and populated, however there are separate audit_log_format statements based on the type of the message. Finally, the AUDIT_IPC block of code in audit_free_aux() was extended to handle aux messages of this new type. No more mem leaks I hope ;-) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2006-04-03 05:07:33 +08:00
#include <linux/audit.h>
#include <linux/nsproxy.h>
#include <linux/rwsem.h>
#include <linux/memory.h>
namespaces: move the IPC namespace under IPC_NS option Currently the IPC namespace management code is spread over the ipc/*.c files. I moved this code into ipc/namespace.c file which is compiled out when needed. The linux/ipc_namespace.h file is used to store the prototypes of the functions in namespace.c and the stubs for NAMESPACES=n case. This is done so, because the stub for copy_ipc_namespace requires the knowledge of the CLONE_NEWIPC flag, which is in sched.h. But the linux/ipc.h file itself in included into many many .c files via the sys.h->sem.h sequence so adding the sched.h into it will make all these .c depend on sched.h which is not that good. On the other hand the knowledge about the namespaces stuff is required in 4 .c files only. Besides, this patch compiles out some auxiliary functions from ipc/sem.c, msg.c and shm.c files. It turned out that moving these functions into namespaces.c is not that easy because they use many other calls and macros from the original file. Moving them would make this patch complicated. On the other hand all these functions can be consolidated, so I will send a separate patch doing this a bit later. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:18:22 +08:00
#include <linux/ipc_namespace.h>
#include <asm/unistd.h>
#include "util.h"
struct ipc_proc_iface {
const char *path;
const char *header;
int ids;
int (*show)(struct seq_file *, void *);
};
/**
* ipc_init - initialise ipc subsystem
*
* The various sysv ipc resources (semaphores, messages and shared
* memory) are initialised.
*
* A callback routine is registered into the memory hotplug notifier
* chain: since msgmni scales to lowmem this callback routine will be
* called upon successful memory add / remove to recompute msmgni.
*/
static int __init ipc_init(void)
{
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
int err_sem, err_msg;
err_sem = sem_init();
WARN(err_sem, "ipc: sysv sem_init failed: %d\n", err_sem);
err_msg = msg_init();
WARN(err_msg, "ipc: sysv msg_init failed: %d\n", err_msg);
shm_init();
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
return err_msg ? err_msg : err_sem;
}
device_initcall(ipc_init);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
static const struct rhashtable_params ipc_kht_params = {
.head_offset = offsetof(struct kern_ipc_perm, khtnode),
.key_offset = offsetof(struct kern_ipc_perm, key),
.key_len = FIELD_SIZEOF(struct kern_ipc_perm, key),
.locks_mul = 1,
.automatic_shrinking = true,
};
/**
* ipc_init_ids - initialise ipc identifiers
* @ids: ipc identifier set
*
* Set up the sequence range to use for the ipc identifier range (limited
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
* below IPCMNI) then initialise the keys hashtable and ids idr.
*/
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
int ipc_init_ids(struct ipc_ids *ids)
{
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
int err;
ids->in_use = 0;
ids->seq = 0;
init_rwsem(&ids->rwsem);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
err = rhashtable_init(&ids->key_ht, &ipc_kht_params);
if (err)
return err;
idr_init(&ids->ipcs_idr);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
ids->tables_initialized = true;
ids->max_id = -1;
#ifdef CONFIG_CHECKPOINT_RESTORE
ids->next_id = -1;
#endif
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
return 0;
}
#ifdef CONFIG_PROC_FS
static const struct file_operations sysvipc_proc_fops;
/**
* ipc_init_proc_interface - create a proc interface for sysipc types using a seq_file interface.
* @path: Path in procfs
* @header: Banner to be printed at the beginning of the file.
* @ids: ipc id table to iterate.
* @show: show routine.
*/
void __init ipc_init_proc_interface(const char *path, const char *header,
int ids, int (*show)(struct seq_file *, void *))
{
struct proc_dir_entry *pde;
struct ipc_proc_iface *iface;
iface = kmalloc(sizeof(*iface), GFP_KERNEL);
if (!iface)
return;
iface->path = path;
iface->header = header;
iface->ids = ids;
iface->show = show;
pde = proc_create_data(path,
S_IRUGO, /* world readable */
NULL, /* parent dir */
&sysvipc_proc_fops,
iface);
if (!pde)
kfree(iface);
}
#endif
/**
* ipc_findkey - find a key in an ipc identifier set
* @ids: ipc identifier set
* @key: key to find
*
* Returns the locked pointer to the ipc structure if found or NULL
* otherwise. If key is found ipc points to the owning ipc structure
*
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
* Called with writer ipc_ids.rwsem held.
*/
static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
{
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
struct kern_ipc_perm *ipcp = NULL;
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
if (likely(ids->tables_initialized))
ipcp = rhashtable_lookup_fast(&ids->key_ht, &key,
ipc_kht_params);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
if (ipcp) {
rcu_read_lock();
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
ipc_lock_object(ipcp);
return ipcp;
}
return NULL;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
/*
* Specify desired id for next allocated IPC object.
*/
#define ipc_idr_alloc(ids, new) \
idr_alloc(&(ids)->ipcs_idr, (new), \
(ids)->next_id < 0 ? 0 : ipcid_to_idx((ids)->next_id),\
0, GFP_NOWAIT)
static inline int ipc_buildid(int id, struct ipc_ids *ids,
struct kern_ipc_perm *new)
{
if (ids->next_id < 0) { /* default, behave as !CHECKPOINT_RESTORE */
new->seq = ids->seq++;
if (ids->seq > IPCID_SEQ_MAX)
ids->seq = 0;
} else {
new->seq = ipcid_to_seqx(ids->next_id);
ids->next_id = -1;
}
return SEQ_MULTIPLIER * new->seq + id;
}
#else
#define ipc_idr_alloc(ids, new) \
idr_alloc(&(ids)->ipcs_idr, (new), 0, 0, GFP_NOWAIT)
static inline int ipc_buildid(int id, struct ipc_ids *ids,
struct kern_ipc_perm *new)
{
new->seq = ids->seq++;
if (ids->seq > IPCID_SEQ_MAX)
ids->seq = 0;
return SEQ_MULTIPLIER * new->seq + id;
}
#endif /* CONFIG_CHECKPOINT_RESTORE */
/**
* ipc_addid - add an ipc identifier
* @ids: ipc identifier set
* @new: new ipc permission set
* @limit: limit for the number of used ids
*
* Add an entry 'new' to the ipc ids idr. The permissions object is
* initialised and the first free entry is set up and the id assigned
* is returned. The 'new' entry is returned in a locked state on success.
* On failure the entry is not locked and a negative err-code is returned.
*
* Called with writer ipc_ids.rwsem held.
*/
int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
{
kuid_t euid;
kgid_t egid;
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
int id, err;
if (limit > IPCMNI)
limit = IPCMNI;
if (!ids->tables_initialized || ids->in_use >= limit)
return -ENOSPC;
idr_preload(GFP_KERNEL);
refcount_set(&new->refcount, 1);
spin_lock_init(&new->lock);
new->deleted = false;
rcu_read_lock();
spin_lock(&new->lock);
current_euid_egid(&euid, &egid);
new->cuid = new->uid = euid;
new->gid = new->cgid = egid;
id = ipc_idr_alloc(ids, new);
idr_preload_end();
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
if (id >= 0 && new->key != IPC_PRIVATE) {
err = rhashtable_insert_fast(&ids->key_ht, &new->khtnode,
ipc_kht_params);
if (err < 0) {
idr_remove(&ids->ipcs_idr, id);
id = err;
}
}
if (id < 0) {
spin_unlock(&new->lock);
rcu_read_unlock();
return id;
}
ids->in_use++;
if (id > ids->max_id)
ids->max_id = id;
new->id = ipc_buildid(id, ids, new);
return id;
}
/**
* ipcget_new - create a new ipc object
* @ns: ipc namespace
* @ids: ipc identifier set
* @ops: the actual creation routine to call
* @params: its parameters
*
* This routine is called by sys_msgget, sys_semget() and sys_shmget()
* when the key is IPC_PRIVATE.
*/
static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
const struct ipc_ops *ops, struct ipc_params *params)
{
int err;
down_write(&ids->rwsem);
err = ops->getnew(ns, params);
up_write(&ids->rwsem);
return err;
}
/**
* ipc_check_perms - check security and permissions for an ipc object
* @ns: ipc namespace
* @ipcp: ipc permission set
* @ops: the actual security routine to call
* @params: its parameters
*
* This routine is called by sys_msgget(), sys_semget() and sys_shmget()
* when the key is not IPC_PRIVATE and that key already exists in the
* ds IDR.
*
* On success, the ipc id is returned.
*
* It is called with ipc_ids.rwsem and ipcp->lock held.
*/
static int ipc_check_perms(struct ipc_namespace *ns,
struct kern_ipc_perm *ipcp,
const struct ipc_ops *ops,
struct ipc_params *params)
{
int err;
if (ipcperms(ns, ipcp, params->flg))
err = -EACCES;
else {
err = ops->associate(ipcp, params->flg);
if (!err)
err = ipcp->id;
}
return err;
}
/**
* ipcget_public - get an ipc object or create a new one
* @ns: ipc namespace
* @ids: ipc identifier set
* @ops: the actual creation routine to call
* @params: its parameters
*
* This routine is called by sys_msgget, sys_semget() and sys_shmget()
* when the key is not IPC_PRIVATE.
* It adds a new entry if the key is not found and does some permission
* / security checkings if the key is found.
*
* On success, the ipc id is returned.
*/
static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
const struct ipc_ops *ops, struct ipc_params *params)
{
struct kern_ipc_perm *ipcp;
int flg = params->flg;
int err;
/*
* Take the lock as a writer since we are potentially going to add
* a new entry + read locks are not "upgradable"
*/
down_write(&ids->rwsem);
ipcp = ipc_findkey(ids, params->key);
if (ipcp == NULL) {
/* key not used */
if (!(flg & IPC_CREAT))
err = -ENOENT;
else
err = ops->getnew(ns, params);
} else {
/* ipc object has been locked by ipc_findkey() */
if (flg & IPC_CREAT && flg & IPC_EXCL)
err = -EEXIST;
else {
err = 0;
if (ops->more_checks)
err = ops->more_checks(ipcp, params);
if (!err)
/*
* ipc_check_perms returns the IPC id on
* success
*/
err = ipc_check_perms(ns, ipcp, ops, params);
}
ipc_unlock(ipcp);
}
up_write(&ids->rwsem);
return err;
}
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
/**
* ipc_kht_remove - remove an ipc from the key hashtable
* @ids: ipc identifier set
* @ipcp: ipc perm structure containing the key to remove
*
* ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
if (ipcp->key != IPC_PRIVATE)
rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
ipc_kht_params);
}
/**
* ipc_rmid - remove an ipc identifier
* @ids: ipc identifier set
* @ipcp: ipc perm structure containing the identifier to remove
*
* ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
int lid = ipcid_to_idx(ipcp->id);
idr_remove(&ids->ipcs_idr, lid);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
ipc_kht_remove(ids, ipcp);
ids->in_use--;
ipcp->deleted = true;
if (unlikely(lid == ids->max_id)) {
do {
lid--;
if (lid == -1)
break;
} while (!idr_find(&ids->ipcs_idr, lid));
ids->max_id = lid;
}
}
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
/**
* ipc_set_key_private - switch the key of an existing ipc to IPC_PRIVATE
* @ids: ipc identifier set
* @ipcp: ipc perm structure containing the key to modify
*
* ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
void ipc_set_key_private(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
ipc_kht_remove(ids, ipcp);
ipcp->key = IPC_PRIVATE;
}
int ipc_rcu_getref(struct kern_ipc_perm *ptr)
{
return refcount_inc_not_zero(&ptr->refcount);
2006-11-22 22:55:48 +08:00
}
void ipc_rcu_putref(struct kern_ipc_perm *ptr,
void (*func)(struct rcu_head *head))
{
if (!refcount_dec_and_test(&ptr->refcount))
return;
call_rcu(&ptr->rcu, func);
ipc: fix race with LSMs Currently, IPC mechanisms do security and auditing related checks under RCU. However, since security modules can free the security structure, for example, through selinux_[sem,msg_queue,shm]_free_security(), we can race if the structure is freed before other tasks are done with it, creating a use-after-free condition. Manfred illustrates this nicely, for instance with shared mem and selinux: -> do_shmat calls rcu_read_lock() -> do_shmat calls shm_object_check(). Checks that the object is still valid - but doesn't acquire any locks. Then it returns. -> do_shmat calls security_shm_shmat (e.g. selinux_shm_shmat) -> selinux_shm_shmat calls ipc_has_perm() -> ipc_has_perm accesses ipc_perms->security shm_close() -> shm_close acquires rw_mutex & shm_lock -> shm_close calls shm_destroy -> shm_destroy calls security_shm_free (e.g. selinux_shm_free_security) -> selinux_shm_free_security calls ipc_free_security(&shp->shm_perm) -> ipc_free_security calls kfree(ipc_perms->security) This patch delays the freeing of the security structures after all RCU readers are done. Furthermore it aligns the security life cycle with that of the rest of IPC - freeing them based on the reference counter. For situations where we need not free security, the current behavior is kept. Linus states: "... the old behavior was suspect for another reason too: having the security blob go away from under a user sounds like it could cause various other problems anyway, so I think the old code was at least _prone_ to bugs even if it didn't have catastrophic behavior." I have tested this patch with IPC testcases from LTP on both my quad-core laptop and on a 64 core NUMA server. In both cases selinux is enabled, and tests pass for both voluntary and forced preemption models. While the mentioned races are theoretical (at least no one as reported them), I wanted to make sure that this new logic doesn't break anything we weren't aware of. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Acked-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-24 08:04:45 +08:00
}
/**
* ipcperms - check ipc permissions
* @ns: ipc namespace
* @ipcp: ipc permission set
* @flag: desired permission set
*
* Check user, group, other permissions for access
* to ipc resources. return 0 if allowed
*
* @flag will most probably be 0 or ``S_...UGO`` from <linux/stat.h>
*/
int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag)
{
kuid_t euid = current_euid();
int requested_mode, granted_mode;
audit_ipc_obj(ipcp);
requested_mode = (flag >> 6) | (flag >> 3) | flag;
granted_mode = ipcp->mode;
if (uid_eq(euid, ipcp->cuid) ||
uid_eq(euid, ipcp->uid))
granted_mode >>= 6;
else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid))
granted_mode >>= 3;
/* is there some bit set in requested_mode but not in granted_mode? */
if ((requested_mode & ~granted_mode & 0007) &&
!ns_capable(ns->user_ns, CAP_IPC_OWNER))
return -1;
return security_ipc_permission(ipcp, flag);
}
/*
* Functions to convert between the kern_ipc_perm structure and the
* old/new ipc_perm structures
*/
/**
* kernel_to_ipc64_perm - convert kernel ipc permissions to user
* @in: kernel permissions
* @out: new style ipc permissions
*
* Turn the kernel object @in into a set of permissions descriptions
* for returning to userspace (@out).
*/
void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out)
{
out->key = in->key;
out->uid = from_kuid_munged(current_user_ns(), in->uid);
out->gid = from_kgid_munged(current_user_ns(), in->gid);
out->cuid = from_kuid_munged(current_user_ns(), in->cuid);
out->cgid = from_kgid_munged(current_user_ns(), in->cgid);
out->mode = in->mode;
out->seq = in->seq;
}
/**
* ipc64_perm_to_ipc_perm - convert new ipc permissions to old
* @in: new style ipc permissions
* @out: old style ipc permissions
*
* Turn the new style permissions object @in into a compatibility
* object and store it into the @out pointer.
*/
void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out)
{
out->key = in->key;
SET_UID(out->uid, in->uid);
SET_GID(out->gid, in->gid);
SET_UID(out->cuid, in->cuid);
SET_GID(out->cgid, in->cgid);
out->mode = in->mode;
out->seq = in->seq;
}
/**
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
* ipc_obtain_object_idr
* @ids: ipc identifier set
* @id: ipc id to look for
*
* Look for an id in the ipc ids idr and return associated ipc object.
*
* Call inside the RCU critical section.
* The ipc object is *not* locked on exit.
*/
struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id)
{
struct kern_ipc_perm *out;
int lid = ipcid_to_idx(id);
ipc: optimize semget/shmget/msgget for lots of keys ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Kees Cook <keescook@chromium.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Serge Hallyn <serge@hallyn.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com> Cc: Marc Pardo <marc.pardo@supersonicimagine.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 07:17:55 +08:00
if (unlikely(!ids->tables_initialized))
return ERR_PTR(-EINVAL);
out = idr_find(&ids->ipcs_idr, lid);
if (!out)
return ERR_PTR(-EINVAL);
return out;
}
/**
* ipc_lock - lock an ipc structure without rwsem held
* @ids: ipc identifier set
* @id: ipc id to look for
*
* Look for an id in the ipc ids idr and lock the associated ipc object.
*
* The ipc object is locked on successful exit.
*/
struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
{
struct kern_ipc_perm *out;
rcu_read_lock();
out = ipc_obtain_object_idr(ids, id);
if (IS_ERR(out))
ipc,sysv: make return -EIDRM when racing with RMID consistent The ipc_lock helper is used by all forms of sysv ipc to acquire the ipc object's spinlock. Upon error (bogus identifier), we always return -EINVAL, whether the problem be in the idr path or because we raced with a task performing RMID. For the later, however, all ipc related manpages, state the that for: EIDRM <ID> points to a removed identifier. And return: EINVAL Invalid <ID> value, or unaligned, etc. Which (EINVAL) should only return once the ipc resource is deleted. For all types of ipc this is done immediately upon a RMID command. However, shared memory behaves slightly different as it can merely mark a segment for deletion, and delay the actual freeing until there are no more active consumers. Per shmctl(IPC_RMID) manpage: "" Mark the segment to be destroyed. The segment will only actually be destroyed after the last process detaches it (i.e., when the shm_nattch member of the associated structure shmid_ds is zero). "" Unlike ipc_lock, paths that behave "correctly", at least per the manpage, involve controlling the ipc resource via *ctl(), doing the exact same validity check as ipc_lock after right acquiring the spinlock: if (!ipc_valid_object()) { err = -EIDRM; goto out_unlock; } Thus make ipc_lock consistent with the rest of ipc code and return -EIDRM in ipc_lock when !ipc_valid_object(). Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-07-01 05:58:45 +08:00
goto err;
spin_lock(&out->lock);
ipc,sysv: make return -EIDRM when racing with RMID consistent The ipc_lock helper is used by all forms of sysv ipc to acquire the ipc object's spinlock. Upon error (bogus identifier), we always return -EINVAL, whether the problem be in the idr path or because we raced with a task performing RMID. For the later, however, all ipc related manpages, state the that for: EIDRM <ID> points to a removed identifier. And return: EINVAL Invalid <ID> value, or unaligned, etc. Which (EINVAL) should only return once the ipc resource is deleted. For all types of ipc this is done immediately upon a RMID command. However, shared memory behaves slightly different as it can merely mark a segment for deletion, and delay the actual freeing until there are no more active consumers. Per shmctl(IPC_RMID) manpage: "" Mark the segment to be destroyed. The segment will only actually be destroyed after the last process detaches it (i.e., when the shm_nattch member of the associated structure shmid_ds is zero). "" Unlike ipc_lock, paths that behave "correctly", at least per the manpage, involve controlling the ipc resource via *ctl(), doing the exact same validity check as ipc_lock after right acquiring the spinlock: if (!ipc_valid_object()) { err = -EIDRM; goto out_unlock; } Thus make ipc_lock consistent with the rest of ipc code and return -EIDRM in ipc_lock when !ipc_valid_object(). Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-07-01 05:58:45 +08:00
/*
* ipc_rmid() may have already freed the ID while ipc_lock()
* was spinning: here verify that the structure is still valid.
* Upon races with RMID, return -EIDRM, thus indicating that
* the ID points to a removed identifier.
*/
if (ipc_valid_object(out))
return out;
spin_unlock(&out->lock);
ipc,sysv: make return -EIDRM when racing with RMID consistent The ipc_lock helper is used by all forms of sysv ipc to acquire the ipc object's spinlock. Upon error (bogus identifier), we always return -EINVAL, whether the problem be in the idr path or because we raced with a task performing RMID. For the later, however, all ipc related manpages, state the that for: EIDRM <ID> points to a removed identifier. And return: EINVAL Invalid <ID> value, or unaligned, etc. Which (EINVAL) should only return once the ipc resource is deleted. For all types of ipc this is done immediately upon a RMID command. However, shared memory behaves slightly different as it can merely mark a segment for deletion, and delay the actual freeing until there are no more active consumers. Per shmctl(IPC_RMID) manpage: "" Mark the segment to be destroyed. The segment will only actually be destroyed after the last process detaches it (i.e., when the shm_nattch member of the associated structure shmid_ds is zero). "" Unlike ipc_lock, paths that behave "correctly", at least per the manpage, involve controlling the ipc resource via *ctl(), doing the exact same validity check as ipc_lock after right acquiring the spinlock: if (!ipc_valid_object()) { err = -EIDRM; goto out_unlock; } Thus make ipc_lock consistent with the rest of ipc code and return -EIDRM in ipc_lock when !ipc_valid_object(). Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-07-01 05:58:45 +08:00
out = ERR_PTR(-EIDRM);
err:
rcu_read_unlock();
return out;
}
/**
* ipc_obtain_object_check
* @ids: ipc identifier set
* @id: ipc id to look for
*
* Similar to ipc_obtain_object_idr() but also checks
* the ipc object reference counter.
*
* Call inside the RCU critical section.
* The ipc object is *not* locked on exit.
*/
struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id)
{
struct kern_ipc_perm *out = ipc_obtain_object_idr(ids, id);
if (IS_ERR(out))
goto out;
if (ipc_checkid(out, id))
return ERR_PTR(-EINVAL);
out:
return out;
}
/**
* ipcget - Common sys_*get() code
* @ns: namespace
* @ids: ipc identifier set
* @ops: operations to be called on ipc object creation, permission checks
* and further checks
* @params: the parameters needed by the previous operations.
*
* Common routine called by sys_msgget(), sys_semget() and sys_shmget().
*/
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
const struct ipc_ops *ops, struct ipc_params *params)
{
if (params->key == IPC_PRIVATE)
return ipcget_new(ns, ids, ops, params);
else
return ipcget_public(ns, ids, ops, params);
}
/**
* ipc_update_perm - update the permissions of an ipc object
* @in: the permission given as input.
* @out: the permission of the ipc to set.
*/
int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
{
kuid_t uid = make_kuid(current_user_ns(), in->uid);
kgid_t gid = make_kgid(current_user_ns(), in->gid);
if (!uid_valid(uid) || !gid_valid(gid))
return -EINVAL;
out->uid = uid;
out->gid = gid;
out->mode = (out->mode & ~S_IRWXUGO)
| (in->mode & S_IRWXUGO);
return 0;
}
/**
* ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
* @ns: ipc namespace
* @ids: the table of ids where to look for the ipc
* @id: the id of the ipc to retrieve
* @cmd: the cmd to check
* @perm: the permission to set
* @extra_perm: one extra permission parameter used by msq
*
* This function does some common audit and permissions check for some IPC_XXX
* cmd and is called from semctl_down, shmctl_down and msgctl_down.
* It must be called without any lock held and:
*
* - retrieves the ipc with the given id in the given table.
* - performs some audit and permission check, depending on the given cmd
* - returns a pointer to the ipc object or otherwise, the corresponding
* error.
*
* Call holding the both the rwsem and the rcu read lock.
*/
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
struct ipc64_perm *perm, int extra_perm)
{
kuid_t euid;
int err = -EPERM;
struct kern_ipc_perm *ipcp;
ipcp = ipc_obtain_object_check(ids, id);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
goto err;
}
audit_ipc_obj(ipcp);
if (cmd == IPC_SET)
audit_ipc_set_perm(extra_perm, perm->uid,
perm->gid, perm->mode);
euid = current_euid();
if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) ||
ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ipcp; /* successful lookup */
err:
return ERR_PTR(err);
}
#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
/**
* ipc_parse_version - ipc call version
* @cmd: pointer to command
*
* Return IPC_64 for new style IPC and IPC_OLD for old style IPC.
* The @cmd value is turned from an encoding command and version into
* just the command code.
*/
int ipc_parse_version(int *cmd)
{
if (*cmd & IPC_64) {
*cmd ^= IPC_64;
return IPC_64;
} else {
return IPC_OLD;
}
}
#endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */
#ifdef CONFIG_PROC_FS
struct ipc_proc_iter {
struct ipc_namespace *ns;
struct ipc_proc_iface *iface;
};
/*
* This routine locks the ipc structure found at least at position pos.
*/
static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
loff_t *new_pos)
{
struct kern_ipc_perm *ipc;
int total, id;
total = 0;
for (id = 0; id < pos && total < ids->in_use; id++) {
ipc = idr_find(&ids->ipcs_idr, id);
if (ipc != NULL)
total++;
}
if (total >= ids->in_use)
return NULL;
for (; pos < IPCMNI; pos++) {
ipc = idr_find(&ids->ipcs_idr, pos);
if (ipc != NULL) {
*new_pos = pos + 1;
rcu_read_lock();
ipc_lock_object(ipc);
return ipc;
}
}
/* Out of range - return NULL to terminate iteration */
return NULL;
}
static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos)
{
struct ipc_proc_iter *iter = s->private;
struct ipc_proc_iface *iface = iter->iface;
struct kern_ipc_perm *ipc = it;
/* If we had an ipc id locked before, unlock it */
if (ipc && ipc != SEQ_START_TOKEN)
ipc_unlock(ipc);
return sysvipc_find_ipc(&iter->ns->ids[iface->ids], *pos, pos);
}
/*
* File positions: pos 0 -> header, pos n -> ipc id = n - 1.
* SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START.
*/
static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
{
struct ipc_proc_iter *iter = s->private;
struct ipc_proc_iface *iface = iter->iface;
struct ipc_ids *ids;
ids = &iter->ns->ids[iface->ids];
/*
* Take the lock - this will be released by the corresponding
* call to stop().
*/
down_read(&ids->rwsem);
/* pos < 0 is invalid */
if (*pos < 0)
return NULL;
/* pos == 0 means header */
if (*pos == 0)
return SEQ_START_TOKEN;
/* Find the (pos-1)th ipc */
return sysvipc_find_ipc(ids, *pos - 1, pos);
}
static void sysvipc_proc_stop(struct seq_file *s, void *it)
{
struct kern_ipc_perm *ipc = it;
struct ipc_proc_iter *iter = s->private;
struct ipc_proc_iface *iface = iter->iface;
struct ipc_ids *ids;
/* If we had a locked structure, release it */
if (ipc && ipc != SEQ_START_TOKEN)
ipc_unlock(ipc);
ids = &iter->ns->ids[iface->ids];
/* Release the lock we took in start() */
up_read(&ids->rwsem);
}
static int sysvipc_proc_show(struct seq_file *s, void *it)
{
struct ipc_proc_iter *iter = s->private;
struct ipc_proc_iface *iface = iter->iface;
if (it == SEQ_START_TOKEN) {
seq_puts(s, iface->header);
return 0;
}
return iface->show(s, it);
}
static const struct seq_operations sysvipc_proc_seqops = {
.start = sysvipc_proc_start,
.stop = sysvipc_proc_stop,
.next = sysvipc_proc_next,
.show = sysvipc_proc_show,
};
static int sysvipc_proc_open(struct inode *inode, struct file *file)
{
struct ipc_proc_iter *iter;
iter = __seq_open_private(file, &sysvipc_proc_seqops, sizeof(*iter));
if (!iter)
return -ENOMEM;
iter->iface = PDE_DATA(inode);
iter->ns = get_ipc_ns(current->nsproxy->ipc_ns);
return 0;
}
static int sysvipc_proc_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
struct ipc_proc_iter *iter = seq->private;
put_ipc_ns(iter->ns);
return seq_release_private(inode, file);
}
static const struct file_operations sysvipc_proc_fops = {
.open = sysvipc_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = sysvipc_proc_release,
};
#endif /* CONFIG_PROC_FS */