cregit-Linux how code gets into the kernel

Release 4.13 ipc/msg.c

Directory: ipc
 * linux/ipc/msg.c
 * Copyright (C) 1992 Krishna Balasubramanian
 * Removed all the remaining kerneld mess
 * Catch the -EFAULT stuff properly
 * Use GFP_KERNEL for messages as in 1.2
 * Fixed up the unchecked user space derefs
 * Copyright (C) 1998 Alan Cox & Andi Kleen
 * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <>
 * mostly rewritten, threaded and wake-one semantics added
 * MSGMAX limit removed, sysctl's added
 * (c) 1999 Manfred Spraul <>
 * support for audit of ipc object properties and permission changes
 * Dustin Kirkland <>
 * namespaces support
 * OpenVZ, SWsoft Inc.
 * Pavel Emelianov <>

#include <linux/capability.h>
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/list.h>
#include <linux/security.h>
#include <linux/sched/wake_q.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>

#include <asm/current.h>
#include <linux/uaccess.h>
#include "util.h"

/* one msg_receiver structure for each sleeping receiver */

struct msg_receiver {
struct list_head	r_list;
struct task_struct	*r_tsk;

int			r_mode;
long			r_msgtype;
long			r_maxsize;

struct msg_msg		*r_msg;

/* one msg_sender for each sleeping sender */

struct msg_sender {
struct list_head	list;
struct task_struct	*tsk;
size_t                  msgsz;

#define SEARCH_ANY		1

#define SEARCH_EQUAL		2



#define SEARCH_NUMBER		5

#define msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])

static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); }


Davidlohr Bueso A57100.00%2100.00%

static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); }


Davidlohr Bueso A57100.00%1100.00%

static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) { ipc_rmid(&msg_ids(ns), &s->q_perm); }


Nadia Derbey31100.00%1100.00%

static void msg_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(msq); kvfree(msq); }


Davidlohr Bueso A3772.55%125.00%
Manfred Spraul815.69%125.00%
Kees Cook611.76%250.00%

/** * newque - Create a new msg queue * @ns: namespace * @params: ptr to the structure that contains the key and msgflg * * Called with msg_ids.rwsem held (writer) */
static int newque(struct ipc_namespace *ns, struct ipc_params *params) { struct msg_queue *msq; int retval; key_t key = params->key; int msgflg = params->flg; msq = kvmalloc(sizeof(*msq), GFP_KERNEL); if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; msq->q_perm.key = key; msq-> = NULL; retval = security_msg_queue_alloc(msq); if (retval) { kvfree(msq); return retval; } msq->q_stime = msq->q_rtime = 0; msq->q_ctime = get_seconds(); msq->q_cbytes = msq->q_qnum = 0; msq->q_qbytes = ns->msg_ctlmnb; msq->q_lspid = msq->q_lrpid = 0; INIT_LIST_HEAD(&msq->q_messages); INIT_LIST_HEAD(&msq->q_receivers); INIT_LIST_HEAD(&msq->q_senders); /* ipc_addid() locks msq upon success. */ retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (retval < 0) { call_rcu(&msq->q_perm.rcu, msg_rcu_free); return retval; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); return msq->; }


Linus Torvalds (pre-git)9639.83%420.00%
Linus Torvalds3514.52%15.00%
Greg Kroah-Hartman239.54%315.00%
Stephen D. Smalley239.54%15.00%
Nadia Derbey218.71%210.00%
Kees Cook145.81%15.00%
Manfred Spraul93.73%210.00%
Kirill Korotaev72.90%15.00%
Davidlohr Bueso A72.90%210.00%
Ingo Molnar31.24%15.00%
Andi Kleen20.83%15.00%
Andrew Morton10.41%15.00%

static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz) { return msgsz + msq->q_cbytes <= msq->q_qbytes && 1 + msq->q_qnum <= msq->q_qbytes; }


Davidlohr Bueso A36100.00%1100.00%

static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss, size_t msgsz) { mss->tsk = current; mss->msgsz = msgsz; __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); }


Linus Torvalds (pre-git)3876.00%133.33%
Davidlohr Bueso A1224.00%266.67%

static inline void ss_del(struct msg_sender *mss) { if (mss-> list_del(&mss->list); }


Linus Torvalds (pre-git)28100.00%1100.00%

static void ss_wakeup(struct msg_queue *msq, struct wake_q_head *wake_q, bool kill) { struct msg_sender *mss, *t; struct task_struct *stop_tsk = NULL; struct list_head *h = &msq->q_senders; list_for_each_entry_safe(mss, t, h, list) { if (kill) mss-> = NULL; /* * Stop at the first task we don't wakeup, * we've already iterated the original * sender queue. */ else if (stop_tsk == mss->tsk) break; /* * We are not in an EIDRM scenario here, therefore * verify that we really need to wakeup the task. * To maintain current semantics and wakeup order, * move the sender to the tail on behalf of the * blocked task. */ else if (!msg_fits_inqueue(msq, mss->msgsz)) { if (!stop_tsk) stop_tsk = mss->tsk; list_move_tail(&mss->list, &msq->q_senders); continue; } wake_q_add(wake_q, mss->tsk); } }


Davidlohr Bueso A8062.02%342.86%
Linus Torvalds (pre-git)3930.23%342.86%
Nikola Pajkovsky107.75%114.29%

static void expunge_all(struct msg_queue *msq, int res, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { wake_q_add(wake_q, msr->r_tsk); WRITE_ONCE(msr->r_msg, ERR_PTR(res)); } }


Linus Torvalds (pre-git)3050.00%350.00%
Sebastian Andrzej Siewior1220.00%116.67%
Nikola Pajkovsky1016.67%116.67%
Manfred Spraul813.33%116.67%

/* * freeque() wakes up waiters on the sender and receiver waiting queue, * removes the message queue from message queue ID IDR, and cleans up all the * messages associated with this queue. * * msg_ids.rwsem (writer) and the spinlock for this message queue are held * before freeque() is called. msg_ids.rwsem remains locked on exit. */
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct msg_msg *msg, *t; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); DEFINE_WAKE_Q(wake_q); expunge_all(msq, -EIDRM, &wake_q); ss_wakeup(msq, &wake_q, true); msg_rmid(ns, msq); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); rcu_read_unlock(); list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { atomic_dec(&ns->msg_hdrs); free_msg(msg); } atomic_sub(msq->q_cbytes, &ns->msg_bytes); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); }


Linus Torvalds (pre-git)5741.91%421.05%
Pierre Peiffer1712.50%15.26%
Davidlohr Bueso A139.56%421.05%
Sebastian Andrzej Siewior139.56%15.26%
Nikola Pajkovsky128.82%15.26%
Kirill Korotaev118.09%210.53%
Andrew Morton75.15%210.53%
Manfred Spraul42.94%210.53%
Waiman Long10.74%15.26%
Nadia Derbey10.74%15.26%

/* * Called with msg_ids.rwsem and ipcp locked. */
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg) { struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); return security_msg_queue_associate(msq, msgflg); }


Nadia Derbey38100.00%2100.00%

SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { struct ipc_namespace *ns; static const struct ipc_ops msg_ops = { .getnew = newque, .associate = msg_security, }; struct ipc_params msg_params; ns = current->nsproxy->ipc_ns; msg_params.key = key; msg_params.flg = msgflg; return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params); }
static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct msqid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); out.msg_stime = in->msg_stime; out.msg_rtime = in->msg_rtime; out.msg_ctime = in->msg_ctime; if (in->msg_cbytes > USHRT_MAX) out.msg_cbytes = USHRT_MAX; else out.msg_cbytes = in->msg_cbytes; out.msg_lcbytes = in->msg_cbytes; if (in->msg_qnum > USHRT_MAX) out.msg_qnum = USHRT_MAX; else out.msg_qnum = in->msg_qnum; if (in->msg_qbytes > USHRT_MAX) out.msg_qbytes = USHRT_MAX; else out.msg_qbytes = in->msg_qbytes; out.msg_lqbytes = in->msg_qbytes; out.msg_lspid = in->msg_lspid; out.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } }


Linus Torvalds (pre-git)21696.86%133.33%
Alexey Dobriyan62.69%133.33%
Al Viro10.45%133.33%

static inline unsigned long copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct msqid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->msg_perm.uid = tbuf_old.msg_perm.uid; out->msg_perm.gid = tbuf_old.msg_perm.gid; out->msg_perm.mode = tbuf_old.msg_perm.mode; if (tbuf_old.msg_qbytes == 0) out->msg_qbytes = tbuf_old.msg_lqbytes; else out->msg_qbytes = tbuf_old.msg_qbytes; return 0; } default: return -EINVAL; } }


Linus Torvalds (pre-git)13691.28%133.33%
Pierre Peiffer128.05%133.33%
Al Viro10.67%133.33%

/* * This function handles some msgctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, struct msqid_ds __user *buf, int version) { struct kern_ipc_perm *ipcp; struct msqid64_ds uninitialized_var(msqid64); struct msg_queue *msq; int err; if (cmd == IPC_SET) { if (copy_msqid_from_user(&msqid64, buf, version)) return -EFAULT; } down_write(&msg_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } msq = container_of(ipcp, struct msg_queue, q_perm); err = security_msg_queue_msgctl(msq, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&msq->q_perm); /* freeque unlocks the ipc object and rcu */ freeque(ns, ipcp); goto out_up; case IPC_SET: { DEFINE_WAKE_Q(wake_q); if (msqid64.msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; goto out_unlock1; } ipc_lock_object(&msq->q_perm); err = ipc_update_perm(&msqid64.msg_perm, ipcp); if (err) goto out_unlock0; msq->q_qbytes = msqid64.msg_qbytes; msq->q_ctime = get_seconds(); /* * Sleeping receivers might be excluded by * stricter permissions. */ expunge_all(msq, -EAGAIN, &wake_q); /* * Sleeping senders might be able to send * due to a larger queue size. */ ss_wakeup(msq, &wake_q, false); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); goto out_unlock1; } default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&msq->q_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&msg_ids(ns).rwsem); return err; }


Pierre Peiffer14843.15%417.39%
Davidlohr Bueso A8625.07%521.74%
Linus Torvalds (pre-git)5215.16%417.39%
Eric W. Biedermann154.37%14.35%
Nadia Derbey144.08%14.35%
Ingo Molnar72.04%14.35%
Stephen D. Smalley61.75%14.35%
Kirill Korotaev51.46%14.35%
Felipe Contreras30.87%14.35%
Sebastian Andrzej Siewior30.87%14.35%
Serge E. Hallyn20.58%14.35%
Waiman Long10.29%14.35%
Al Viro10.29%14.35%

static int msgctl_nolock(struct ipc_namespace *ns, int msqid, int cmd, int version, void __user *buf) { int err; struct msg_queue *msq; switch (cmd) { case IPC_INFO: case MSG_INFO: { struct msginfo msginfo; int max_id; if (!buf) return -EFAULT; /* * We must not return kernel stack data. * due to padding, it's not enough * to set all member fields. */ err = security_msg_queue_msgctl(NULL, cmd); if (err) return err; memset(&msginfo, 0, sizeof(msginfo)); msginfo.msgmni = ns->msg_ctlmni; msginfo.msgmax = ns->msg_ctlmax; msginfo.msgmnb = ns->msg_ctlmnb; msginfo.msgssz = MSGSSZ; msginfo.msgseg = MSGSEG; down_read(&msg_ids(ns).rwsem); if (cmd == MSG_INFO) { msginfo.msgpool = msg_ids(ns).in_use; msginfo.msgmap = atomic_read(&ns->msg_hdrs); msginfo.msgtql = atomic_read(&ns->msg_bytes); } else { msginfo.msgmap = MSGMAP; msginfo.msgpool = MSGPOOL; msginfo.msgtql = MSGTQL; } max_id = ipc_get_maxid(&msg_ids(ns)); up_read(&msg_ids(ns).rwsem); if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) return -EFAULT; return (max_id < 0) ? 0 : max_id; } case MSG_STAT: case IPC_STAT: { struct msqid64_ds tbuf; int success_return; if (!buf) return -EFAULT; memset(&tbuf, 0, sizeof(tbuf)); rcu_read_lock(); if (cmd == MSG_STAT) { msq = msq_obtain_object(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } success_return = msq->; } else { msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } success_return = 0; } err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IRUGO)) goto out_unlock; err = security_msg_queue_msgctl(msq, cmd); if (err) goto out_unlock; kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm); tbuf.msg_stime = msq->q_stime; tbuf.msg_rtime = msq->q_rtime; tbuf.msg_ctime = msq->q_ctime; tbuf.msg_cbytes = msq->q_cbytes; tbuf.msg_qnum = msq->q_qnum; tbuf.msg_qbytes = msq->q_qbytes; tbuf.msg_lspid = msq->q_lspid; tbuf.msg_lrpid = msq->q_lrpid; rcu_read_unlock(); if (copy_msqid_to_user(buf, &tbuf, version)) return -EFAULT; return success_return; } default: return -EINVAL; } return err; out_unlock: rcu_read_unlock(); return err; }


Pierre Peiffer27551.98%213.33%
Linus Torvalds (pre-git)11521.74%426.67%
Davidlohr Bueso A8015.12%320.00%
Stephen D. Smalley275.10%16.67%
Nadia Derbey152.84%16.67%
Steve Grubb71.32%16.67%
Linda Knippers50.95%16.67%
Kirill Korotaev30.57%16.67%
Serge E. Hallyn20.38%16.67%

SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { int version; struct ipc_namespace *ns; if (msqid < 0 || cmd < 0) return -EINVAL; version = ipc_parse_version(&cmd); ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: case MSG_INFO: case MSG_STAT: /* msqid is an index rather than a msg queue id */ case IPC_STAT: return msgctl_nolock(ns, msqid, cmd, version, buf); case IPC_SET: case IPC_RMID: return msgctl_down(ns, msqid, cmd, buf, version); default: return -EINVAL; } }
static int testmsg(struct msg_msg *msg, long type, int mode) { switch (mode) { case SEARCH_ANY: case SEARCH_NUMBER: return 1; case SEARCH_LESSEQUAL: if (msg->m_type <= type) return 1; break; case SEARCH_EQUAL: if (msg->m_type == type) return 1; break; case SEARCH_NOTEQUAL: if (msg->m_type != type) return 1; break; } return 0; }


Linus Torvalds (pre-git)7796.25%375.00%
Peter Hurley33.75%125.00%

static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { if (testmsg(msg, msr->r_msgtype, msr->r_mode) && !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) { list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { wake_q_add(wake_q, msr->r_tsk); WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG)); } else { msq->q_lrpid = task_pid_vnr(msr->r_tsk); msq->q_rtime = get_seconds(); wake_q_add(wake_q, msr->r_tsk); WRITE_ONCE(msr->r_msg, msg); return 1; } } } return 0; }


Linus Torvalds (pre-git)9557.23%325.00%
Stephen D. Smalley2012.05%18.33%
Sebastian Andrzej Siewior1911.45%18.33%
Manfred Spraul148.43%18.33%
Nikola Pajkovsky106.02%18.33%
Pavel Emelyanov31.81%18.33%
Andi Kleen21.20%18.33%
Stephen Rothwell10.60%18.33%
Dave Jones10.60%18.33%
Linus Torvalds10.60%18.33%

long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { struct msg_queue *msq; struct msg_msg *msg; int err; struct ipc_namespace *ns; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) return -EINVAL; if (mtype < 1) return -EINVAL; msg = load_msg(mtext, msgsz); if (IS_ERR(msg)) return PTR_ERR(msg); msg->m_type = mtype; msg->m_ts =