X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=ipc%2Fmsg.c;h=9547cb7ac3135b9ba8964d13018f5ab6340552c9;hp=d035bd2aba9671cc56fdd6f10b81182ac628b011;hb=4434ade8c9334a3ab975d8993de456f06841899e;hpb=19b4946ca9d1e35d4c641dcebe27378de34f3ddd diff --git a/ipc/msg.c b/ipc/msg.c index d035bd2..9547cb7 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -1,6 +1,6 @@ /* * linux/ipc/msg.c - * Copyright (C) 1992 Krishna Balasubramanian + * Copyright (C) 1992 Krishna Balasubramanian * * Removed all the remaining kerneld mess * Catch the -EFAULT stuff properly @@ -12,14 +12,21 @@ * * mostly rewritten, threaded and wake-one semantics added * MSGMAX limit removed, sysctl's added - * (c) 1999 Manfred Spraul + * (c) 1999 Manfred Spraul + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov */ -#include -#include +#include #include #include #include +#include #include #include #include @@ -27,31 +34,32 @@ #include #include #include +#include +#include +#include + #include #include #include "util.h" -/* sysctl: */ -int msg_ctlmax = MSGMAX; -int msg_ctlmnb = MSGMNB; -int msg_ctlmni = MSGMNI; - -/* one msg_receiver structure for each sleeping receiver */ +/* + * one msg_receiver structure for each sleeping receiver: + */ struct msg_receiver { - struct list_head r_list; - struct task_struct* r_tsk; + struct list_head r_list; + struct task_struct *r_tsk; - int r_mode; - long r_msgtype; - long r_maxsize; + int r_mode; + long r_msgtype; + long r_maxsize; - struct msg_msg* volatile r_msg; + struct msg_msg *volatile r_msg; }; /* one msg_sender for each sleeping sender */ struct msg_sender { - struct list_head list; - struct task_struct* tsk; + struct list_head list; + struct task_struct *tsk; }; #define SEARCH_ANY 1 @@ -59,45 +67,128 @@ struct msg_sender { #define SEARCH_NOTEQUAL 3 #define SEARCH_LESSEQUAL 4 -static atomic_t msg_bytes = ATOMIC_INIT(0); -static atomic_t msg_hdrs = ATOMIC_INIT(0); - -static struct ipc_ids msg_ids; +#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS]) -#define msg_lock(id) ((struct msg_queue*)ipc_lock(&msg_ids,id)) -#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) -#define msg_rmid(id) ((struct msg_queue*)ipc_rmid(&msg_ids,id)) -#define msg_checkid(msq, msgid) \ - ipc_checkid(&msg_ids,&msq->q_perm,msgid) -#define msg_buildid(id, seq) \ - ipc_buildid(&msg_ids, id, seq) +#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) -static void freeque (struct msg_queue *msq, int id); -static int newque (key_t key, int msgflg); +static void freeque(struct ipc_namespace *, struct kern_ipc_perm *); +static int newque(struct ipc_namespace *, struct ipc_params *); #ifdef CONFIG_PROC_FS static int sysvipc_msg_proc_show(struct seq_file *s, void *it); #endif -void __init msg_init (void) +/* + * Scale msgmni with the available lowmem size: the memory dedicated to msg + * queues should occupy at most 1/MSG_MEM_SCALE of lowmem. + * Also take into account the number of nsproxies created so far. + * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range. + */ +void recompute_msgmni(struct ipc_namespace *ns) +{ + struct sysinfo i; + unsigned long allowed; + int nb_ns; + + si_meminfo(&i); + allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit) + / MSGMNB; + nb_ns = atomic_read(&nr_ipc_ns); + allowed /= nb_ns; + + if (allowed < MSGMNI) { + ns->msg_ctlmni = MSGMNI; + return; + } + + if (allowed > IPCMNI / nb_ns) { + ns->msg_ctlmni = IPCMNI / nb_ns; + return; + } + + ns->msg_ctlmni = allowed; +} + +void msg_init_ns(struct ipc_namespace *ns) +{ + ns->msg_ctlmax = MSGMAX; + ns->msg_ctlmnb = MSGMNB; + + recompute_msgmni(ns); + + atomic_set(&ns->msg_bytes, 0); + atomic_set(&ns->msg_hdrs, 0); + ipc_init_ids(&ns->ids[IPC_MSG_IDS]); +} + +#ifdef CONFIG_IPC_NS +void msg_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &msg_ids(ns), freeque); + idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr); +} +#endif + +void __init msg_init(void) { - ipc_init_ids(&msg_ids,msg_ctlmni); + msg_init_ns(&init_ipc_ns); + + printk(KERN_INFO "msgmni has been set to %d\n", + init_ipc_ns.msg_ctlmni); + ipc_init_proc_interface("sysvipc/msg", " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n", - &msg_ids, - sysvipc_msg_proc_show); + IPC_MSG_IDS, sysvipc_msg_proc_show); +} + +/* + * msg_lock_(check_) routines are called in the paths where the rw_mutex + * is not held. + */ +static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct msg_queue *)ipcp; + + return container_of(ipcp, struct msg_queue, q_perm); +} + +static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns, + int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct msg_queue *)ipcp; + + return container_of(ipcp, struct msg_queue, q_perm); } -static int newque (key_t key, int msgflg) +static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) +{ + ipc_rmid(&msg_ids(ns), &s->q_perm); +} + +/** + * newque - Create a new msg queue + * @ns: namespace + * @params: ptr to the structure that contains the key and msgflg + * + * Called with msg_ids.rw_mutex held (writer) + */ +static int newque(struct ipc_namespace *ns, struct ipc_params *params) { - int id; - int retval; struct msg_queue *msq; + int id, retval; + key_t key = params->key; + int msgflg = params->flg; - msq = ipc_rcu_alloc(sizeof(*msq)); - if (!msq) + msq = ipc_rcu_alloc(sizeof(*msq)); + if (!msq) return -ENOMEM; - msq->q_perm.mode = (msgflg & S_IRWXUGO); + msq->q_perm.mode = msgflg & S_IRWXUGO; msq->q_perm.key = key; msq->q_perm.security = NULL; @@ -107,65 +198,68 @@ static int newque (key_t key, int msgflg) return retval; } - id = ipc_addid(&msg_ids, &msq->q_perm, msg_ctlmni); - if(id == -1) { + /* + * ipc_addid() locks msq + */ + id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); + if (id < 0) { security_msg_queue_free(msq); ipc_rcu_putref(msq); - return -ENOSPC; + return id; } - msq->q_id = msg_buildid(id,msq->q_perm.seq); msq->q_stime = msq->q_rtime = 0; msq->q_ctime = get_seconds(); msq->q_cbytes = msq->q_qnum = 0; - msq->q_qbytes = msg_ctlmnb; + 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); + msg_unlock(msq); - return msq->q_id; + return msq->q_perm.id; } -static inline void ss_add(struct msg_queue* msq, struct msg_sender* mss) +static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss) { - mss->tsk=current; - current->state=TASK_INTERRUPTIBLE; - list_add_tail(&mss->list,&msq->q_senders); + mss->tsk = current; + current->state = TASK_INTERRUPTIBLE; + list_add_tail(&mss->list, &msq->q_senders); } -static inline void ss_del(struct msg_sender* mss) +static inline void ss_del(struct msg_sender *mss) { - if(mss->list.next != NULL) + if (mss->list.next != NULL) list_del(&mss->list); } -static void ss_wakeup(struct list_head* h, int kill) +static void ss_wakeup(struct list_head *h, int kill) { struct list_head *tmp; tmp = h->next; while (tmp != h) { - struct msg_sender* mss; - - mss = list_entry(tmp,struct msg_sender,list); + struct msg_sender *mss; + + mss = list_entry(tmp, struct msg_sender, list); tmp = tmp->next; - if(kill) - mss->list.next=NULL; + if (kill) + mss->list.next = NULL; wake_up_process(mss->tsk); } } -static void expunge_all(struct msg_queue* msq, int res) +static void expunge_all(struct msg_queue *msq, int res) { struct list_head *tmp; tmp = msq->q_receivers.next; while (tmp != &msq->q_receivers) { - struct msg_receiver* msr; - - msr = list_entry(tmp,struct msg_receiver,r_list); + struct msg_receiver *msr; + + msr = list_entry(tmp, struct msg_receiver, r_list); tmp = tmp->next; msr->r_msg = NULL; wake_up_process(msr->r_tsk); @@ -173,78 +267,77 @@ static void expunge_all(struct msg_queue* msq, int res) msr->r_msg = ERR_PTR(res); } } -/* - * freeque() wakes up waiters on the sender and receiver waiting queue, - * removes the message queue from message queue ID - * array, and cleans up all the messages associated with this queue. + +/* + * 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.sem and the spinlock for this message queue is hold - * before freeque() is called. msg_ids.sem remains locked on exit. + * msg_ids.rw_mutex (writer) and the spinlock for this message queue are held + * before freeque() is called. msg_ids.rw_mutex remains locked on exit. */ -static void freeque (struct msg_queue *msq, int id) +static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct list_head *tmp; + struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); - expunge_all(msq,-EIDRM); - ss_wakeup(&msq->q_senders,1); - msq = msg_rmid(id); + expunge_all(msq, -EIDRM); + ss_wakeup(&msq->q_senders, 1); + msg_rmid(ns, msq); msg_unlock(msq); - + tmp = msq->q_messages.next; - while(tmp != &msq->q_messages) { - struct msg_msg* msg = list_entry(tmp,struct msg_msg,m_list); + while (tmp != &msq->q_messages) { + struct msg_msg *msg = list_entry(tmp, struct msg_msg, m_list); + tmp = tmp->next; - atomic_dec(&msg_hdrs); + atomic_dec(&ns->msg_hdrs); free_msg(msg); } - atomic_sub(msq->q_cbytes, &msg_bytes); + atomic_sub(msq->q_cbytes, &ns->msg_bytes); security_msg_queue_free(msq); ipc_rcu_putref(msq); } -asmlinkage long sys_msgget (key_t key, int msgflg) +/* + * Called with msg_ids.rw_mutex and ipcp locked. + */ +static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg) { - int id, ret = -EPERM; - struct msg_queue *msq; - - down(&msg_ids.sem); - if (key == IPC_PRIVATE) - ret = newque(key, msgflg); - else if ((id = ipc_findkey(&msg_ids, key)) == -1) { /* key not used */ - if (!(msgflg & IPC_CREAT)) - ret = -ENOENT; - else - ret = newque(key, msgflg); - } else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) { - ret = -EEXIST; - } else { - msq = msg_lock(id); - if(msq==NULL) - BUG(); - if (ipcperms(&msq->q_perm, msgflg)) - ret = -EACCES; - else { - int qid = msg_buildid(id, msq->q_perm.seq); - ret = security_msg_queue_associate(msq, msgflg); - if (!ret) - ret = qid; - } - msg_unlock(msq); - } - up(&msg_ids.sem); - return ret; + struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); + + return security_msg_queue_associate(msq, msgflg); } -static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) +SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) +{ + struct ipc_namespace *ns; + struct ipc_ops msg_ops; + struct ipc_params msg_params; + + ns = current->nsproxy->ipc_ns; + + msg_ops.getnew = newque; + msg_ops.associate = msg_security; + msg_ops.more_checks = NULL; + + 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)); + return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: - { + { struct msqid_ds out; - memset(&out,0,sizeof(out)); + memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); @@ -252,19 +345,19 @@ static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ out.msg_rtime = in->msg_rtime; out.msg_ctime = in->msg_ctime; - if(in->msg_cbytes > USHRT_MAX) - out.msg_cbytes = USHRT_MAX; + if (in->msg_cbytes > USHORT_MAX) + out.msg_cbytes = USHORT_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; + if (in->msg_qnum > USHORT_MAX) + out.msg_qnum = USHORT_MAX; else out.msg_qnum = in->msg_qnum; - if(in->msg_qbytes > USHRT_MAX) - out.msg_qbytes = USHRT_MAX; + if (in->msg_qbytes > USHORT_MAX) + out.msg_qbytes = USHORT_MAX; else out.msg_qbytes = in->msg_qbytes; out.msg_lqbytes = in->msg_qbytes; @@ -272,143 +365,189 @@ static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ out.msg_lspid = in->msg_lspid; out.msg_lrpid = in->msg_lrpid; - return copy_to_user (buf, &out, sizeof(out)); - } + return copy_to_user(buf, &out, sizeof(out)); + } default: return -EINVAL; } } -struct msq_setbuf { - unsigned long qbytes; - uid_t uid; - gid_t gid; - mode_t mode; -}; - -static inline unsigned long copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version) +static inline unsigned long +copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { switch(version) { case IPC_64: - { - struct msqid64_ds tbuf; - - if (copy_from_user (&tbuf, buf, sizeof (tbuf))) + if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; - - out->qbytes = tbuf.msg_qbytes; - out->uid = tbuf.msg_perm.uid; - out->gid = tbuf.msg_perm.gid; - out->mode = tbuf.msg_perm.mode; - return 0; - } case IPC_OLD: - { + { struct msqid_ds tbuf_old; - if (copy_from_user (&tbuf_old, buf, sizeof (tbuf_old))) + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; - out->uid = tbuf_old.msg_perm.uid; - out->gid = tbuf_old.msg_perm.gid; - out->mode = tbuf_old.msg_perm.mode; + 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->qbytes = tbuf_old.msg_lqbytes; + if (tbuf_old.msg_qbytes == 0) + out->msg_qbytes = tbuf_old.msg_lqbytes; else - out->qbytes = tbuf_old.msg_qbytes; + out->msg_qbytes = tbuf_old.msg_qbytes; return 0; - } + } default: return -EINVAL; } } -asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf) +/* + * This function handles some msgctl commands which require the rw_mutex + * to be held in write mode. + * NOTE: no locks must be held, the rw_mutex is taken inside this function. + */ +static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, + struct msqid_ds __user *buf, int version) { - int err, version; - struct msg_queue *msq; - struct msq_setbuf setbuf; 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; + } + + ipcp = ipcctl_pre_down(&msg_ids(ns), msqid, cmd, + &msqid64.msg_perm, msqid64.msg_qbytes); + if (IS_ERR(ipcp)) + return PTR_ERR(ipcp); + + msq = container_of(ipcp, struct msg_queue, q_perm); + + err = security_msg_queue_msgctl(msq, cmd); + if (err) + goto out_unlock; + + switch (cmd) { + case IPC_RMID: + freeque(ns, ipcp); + goto out_up; + case IPC_SET: + if (msqid64.msg_qbytes > ns->msg_ctlmnb && + !capable(CAP_SYS_RESOURCE)) { + err = -EPERM; + goto out_unlock; + } + + msq->q_qbytes = msqid64.msg_qbytes; + + ipc_update_perm(&msqid64.msg_perm, ipcp); + msq->q_ctime = get_seconds(); + /* sleeping receivers might be excluded by + * stricter permissions. + */ + expunge_all(msq, -EAGAIN); + /* sleeping senders might be able to send + * due to a larger queue size. + */ + ss_wakeup(&msq->q_senders, 0); + break; + default: + err = -EINVAL; + } +out_unlock: + msg_unlock(msq); +out_up: + up_write(&msg_ids(ns).rw_mutex); + return err; +} + +SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) +{ + struct msg_queue *msq; + int err, 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 IPC_INFO: + case MSG_INFO: + { struct msginfo msginfo; int max_id; + if (!buf) return -EFAULT; - /* We must not return kernel stack data. + /* + * 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 = msg_ctlmni; - msginfo.msgmax = msg_ctlmax; - msginfo.msgmnb = msg_ctlmnb; + 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(&msg_ids.sem); + down_read(&msg_ids(ns).rw_mutex); if (cmd == MSG_INFO) { - msginfo.msgpool = msg_ids.in_use; - msginfo.msgmap = atomic_read(&msg_hdrs); - msginfo.msgtql = atomic_read(&msg_bytes); + 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 = msg_ids.max_id; - up(&msg_ids.sem); - if (copy_to_user (buf, &msginfo, sizeof(struct msginfo))) + max_id = ipc_get_maxid(&msg_ids(ns)); + up_read(&msg_ids(ns).rw_mutex); + if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) return -EFAULT; - return (max_id < 0) ? 0: max_id; + return (max_id < 0) ? 0 : max_id; } - case MSG_STAT: + case MSG_STAT: /* msqid is an index rather than a msg queue id */ case IPC_STAT: { struct msqid64_ds tbuf; int success_return; + if (!buf) return -EFAULT; - if(cmd == MSG_STAT && msqid >= msg_ids.entries->size) - return -EINVAL; - - memset(&tbuf,0,sizeof(tbuf)); - - msq = msg_lock(msqid); - if (msq == NULL) - return -EINVAL; - if(cmd == MSG_STAT) { - success_return = msg_buildid(msqid, msq->q_perm.seq); + if (cmd == MSG_STAT) { + msq = msg_lock(ns, msqid); + if (IS_ERR(msq)) + return PTR_ERR(msq); + success_return = msq->q_perm.id; } else { - err = -EIDRM; - if (msg_checkid(msq,msqid)) - goto out_unlock; + msq = msg_lock_check(ns, msqid); + if (IS_ERR(msq)) + return PTR_ERR(msq); success_return = 0; } err = -EACCES; - if (ipcperms (&msq->q_perm, S_IRUGO)) + if (ipcperms(&msq->q_perm, S_IRUGO)) goto out_unlock; err = security_msg_queue_msgctl(msq, cmd); if (err) goto out_unlock; + memset(&tbuf, 0, sizeof(tbuf)); + kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm); tbuf.msg_stime = msq->q_stime; tbuf.msg_rtime = msq->q_rtime; @@ -424,126 +563,68 @@ asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf) return success_return; } case IPC_SET: - if (!buf) - return -EFAULT; - if (copy_msqid_from_user (&setbuf, buf, version)) - return -EFAULT; - if ((err = audit_ipc_perms(setbuf.qbytes, setbuf.uid, setbuf.gid, setbuf.mode))) - return err; - break; case IPC_RMID: - break; + err = msgctl_down(ns, msqid, cmd, buf, version); + return err; default: return -EINVAL; } - down(&msg_ids.sem); - msq = msg_lock(msqid); - err=-EINVAL; - if (msq == NULL) - goto out_up; - - err = -EIDRM; - if (msg_checkid(msq,msqid)) - goto out_unlock_up; - ipcp = &msq->q_perm; - err = -EPERM; - if (current->euid != ipcp->cuid && - current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) - /* We _could_ check for CAP_CHOWN above, but we don't */ - goto out_unlock_up; - - err = security_msg_queue_msgctl(msq, cmd); - if (err) - goto out_unlock_up; - - switch (cmd) { - case IPC_SET: - { - err = -EPERM; - if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) - goto out_unlock_up; - - msq->q_qbytes = setbuf.qbytes; - - ipcp->uid = setbuf.uid; - ipcp->gid = setbuf.gid; - ipcp->mode = (ipcp->mode & ~S_IRWXUGO) | - (S_IRWXUGO & setbuf.mode); - msq->q_ctime = get_seconds(); - /* sleeping receivers might be excluded by - * stricter permissions. - */ - expunge_all(msq,-EAGAIN); - /* sleeping senders might be able to send - * due to a larger queue size. - */ - ss_wakeup(&msq->q_senders,0); - msg_unlock(msq); - break; - } - case IPC_RMID: - freeque (msq, msqid); - break; - } - err = 0; -out_up: - up(&msg_ids.sem); - return err; -out_unlock_up: - msg_unlock(msq); - goto out_up; out_unlock: msg_unlock(msq); return err; } -static int testmsg(struct msg_msg* msg,long type,int mode) +static int testmsg(struct msg_msg *msg, long type, int mode) { switch(mode) { case SEARCH_ANY: return 1; case SEARCH_LESSEQUAL: - if(msg->m_type <=type) + if (msg->m_type <=type) return 1; break; case SEARCH_EQUAL: - if(msg->m_type == type) + if (msg->m_type == type) return 1; break; case SEARCH_NOTEQUAL: - if(msg->m_type != type) + if (msg->m_type != type) return 1; break; } return 0; } -static inline int pipelined_send(struct msg_queue* msq, struct msg_msg* msg) +static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) { - struct list_head* tmp; + struct list_head *tmp; tmp = msq->q_receivers.next; while (tmp != &msq->q_receivers) { - struct msg_receiver* msr; - msr = list_entry(tmp,struct msg_receiver,r_list); + struct msg_receiver *msr; + + msr = list_entry(tmp, struct msg_receiver, r_list); tmp = tmp->next; - if(testmsg(msg,msr->r_msgtype,msr->r_mode) && - !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) { + 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) { + if (msr->r_maxsize < msg->m_ts) { msr->r_msg = NULL; wake_up_process(msr->r_tsk); smp_mb(); msr->r_msg = ERR_PTR(-E2BIG); } else { msr->r_msg = NULL; - msq->q_lrpid = msr->r_tsk->pid; + msq->q_lrpid = task_pid_vnr(msr->r_tsk); msq->q_rtime = get_seconds(); wake_up_process(msr->r_tsk); smp_mb(); msr->r_msg = msg; + return 1; } } @@ -551,40 +632,38 @@ static inline int pipelined_send(struct msg_queue* msq, struct msg_msg* msg) return 0; } -asmlinkage long sys_msgsnd (int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) +long do_msgsnd(int msqid, long mtype, void __user *mtext, + size_t msgsz, int msgflg) { struct msg_queue *msq; struct msg_msg *msg; - long mtype; int err; - - if (msgsz > msg_ctlmax || (long) msgsz < 0 || msqid < 0) + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; + + if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) return -EINVAL; - if (get_user(mtype, &msgp->mtype)) - return -EFAULT; if (mtype < 1) return -EINVAL; - msg = load_msg(msgp->mtext, msgsz); - if(IS_ERR(msg)) + msg = load_msg(mtext, msgsz); + if (IS_ERR(msg)) return PTR_ERR(msg); msg->m_type = mtype; msg->m_ts = msgsz; - msq = msg_lock(msqid); - err=-EINVAL; - if(msq==NULL) + msq = msg_lock_check(ns, msqid); + if (IS_ERR(msq)) { + err = PTR_ERR(msq); goto out_free; - - err= -EIDRM; - if (msg_checkid(msq,msqid)) - goto out_unlock_free; + } for (;;) { struct msg_sender s; - err=-EACCES; + err = -EACCES; if (ipcperms(&msq->q_perm, S_IWUGO)) goto out_unlock_free; @@ -592,14 +671,14 @@ asmlinkage long sys_msgsnd (int msqid, struct msgbuf __user *msgp, size_t msgsz, if (err) goto out_unlock_free; - if(msgsz + msq->q_cbytes <= msq->q_qbytes && + if (msgsz + msq->q_cbytes <= msq->q_qbytes && 1 + msq->q_qnum <= msq->q_qbytes) { break; } /* queue full, wait: */ - if(msgflg&IPC_NOWAIT) { - err=-EAGAIN; + if (msgflg & IPC_NOWAIT) { + err = -EAGAIN; goto out_unlock_free; } ss_add(msq, &s); @@ -614,102 +693,117 @@ asmlinkage long sys_msgsnd (int msqid, struct msgbuf __user *msgp, size_t msgsz, goto out_unlock_free; } ss_del(&s); - + if (signal_pending(current)) { - err=-ERESTARTNOHAND; + err = -ERESTARTNOHAND; goto out_unlock_free; } } - msq->q_lspid = current->tgid; + msq->q_lspid = task_tgid_vnr(current); msq->q_stime = get_seconds(); - if(!pipelined_send(msq,msg)) { + if (!pipelined_send(msq, msg)) { /* noone is waiting for this message, enqueue it */ - list_add_tail(&msg->m_list,&msq->q_messages); + list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; - atomic_add(msgsz,&msg_bytes); - atomic_inc(&msg_hdrs); + atomic_add(msgsz, &ns->msg_bytes); + atomic_inc(&ns->msg_hdrs); } - + err = 0; msg = NULL; out_unlock_free: msg_unlock(msq); out_free: - if(msg!=NULL) + if (msg != NULL) free_msg(msg); return err; } -static inline int convert_mode(long* msgtyp, int msgflg) +SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + int, msgflg) { - /* + long mtype; + + if (get_user(mtype, &msgp->mtype)) + return -EFAULT; + return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg); +} + +static inline int convert_mode(long *msgtyp, int msgflg) +{ + /* * find message of correct type. * msgtyp = 0 => get first. * msgtyp > 0 => get first message of matching type. - * msgtyp < 0 => get message with least type must be < abs(msgtype). + * msgtyp < 0 => get message with least type must be < abs(msgtype). */ - if(*msgtyp==0) + if (*msgtyp == 0) return SEARCH_ANY; - if(*msgtyp<0) { - *msgtyp=-(*msgtyp); + if (*msgtyp < 0) { + *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } - if(msgflg & MSG_EXCEPT) + if (msgflg & MSG_EXCEPT) return SEARCH_NOTEQUAL; return SEARCH_EQUAL; } -asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, - long msgtyp, int msgflg) +long do_msgrcv(int msqid, long *pmtype, void __user *mtext, + size_t msgsz, long msgtyp, int msgflg) { struct msg_queue *msq; struct msg_msg *msg; int mode; + struct ipc_namespace *ns; if (msqid < 0 || (long) msgsz < 0) return -EINVAL; - mode = convert_mode(&msgtyp,msgflg); - - msq = msg_lock(msqid); - if(msq==NULL) - return -EINVAL; + mode = convert_mode(&msgtyp, msgflg); + ns = current->nsproxy->ipc_ns; - msg = ERR_PTR(-EIDRM); - if (msg_checkid(msq,msqid)) - goto out_unlock; + msq = msg_lock_check(ns, msqid); + if (IS_ERR(msq)) + return PTR_ERR(msq); for (;;) { struct msg_receiver msr_d; - struct list_head* tmp; + struct list_head *tmp; msg = ERR_PTR(-EACCES); - if (ipcperms (&msq->q_perm, S_IRUGO)) + if (ipcperms(&msq->q_perm, S_IRUGO)) goto out_unlock; msg = ERR_PTR(-EAGAIN); tmp = msq->q_messages.next; while (tmp != &msq->q_messages) { struct msg_msg *walk_msg; - walk_msg = list_entry(tmp,struct msg_msg,m_list); - if(testmsg(walk_msg,msgtyp,mode) && - !security_msg_queue_msgrcv(msq, walk_msg, current, msgtyp, mode)) { + + walk_msg = list_entry(tmp, struct msg_msg, m_list); + if (testmsg(walk_msg, msgtyp, mode) && + !security_msg_queue_msgrcv(msq, walk_msg, current, + msgtyp, mode)) { + msg = walk_msg; - if(mode == SEARCH_LESSEQUAL && walk_msg->m_type != 1) { - msg=walk_msg; - msgtyp=walk_msg->m_type-1; + if (mode == SEARCH_LESSEQUAL && + walk_msg->m_type != 1) { + msg = walk_msg; + msgtyp = walk_msg->m_type - 1; } else { - msg=walk_msg; + msg = walk_msg; break; } } tmp = tmp->next; } - if(!IS_ERR(msg)) { - /* Found a suitable message. Unlink it from the queue. */ + if (!IS_ERR(msg)) { + /* + * Found a suitable message. + * Unlink it from the queue. + */ if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) { msg = ERR_PTR(-E2BIG); goto out_unlock; @@ -717,11 +811,11 @@ asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, list_del(&msg->m_list); msq->q_qnum--; msq->q_rtime = get_seconds(); - msq->q_lrpid = current->tgid; + msq->q_lrpid = task_tgid_vnr(current); msq->q_cbytes -= msg->m_ts; - atomic_sub(msg->m_ts,&msg_bytes); - atomic_dec(&msg_hdrs); - ss_wakeup(&msq->q_senders,0); + atomic_sub(msg->m_ts, &ns->msg_bytes); + atomic_dec(&ns->msg_hdrs); + ss_wakeup(&msq->q_senders, 0); msg_unlock(msq); break; } @@ -730,13 +824,13 @@ asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, msg = ERR_PTR(-ENOMSG); goto out_unlock; } - list_add_tail(&msr_d.r_list,&msq->q_receivers); + list_add_tail(&msr_d.r_list, &msq->q_receivers); msr_d.r_tsk = current; msr_d.r_msgtype = msgtyp; msr_d.r_mode = mode; - if(msgflg & MSG_NOERROR) + if (msgflg & MSG_NOERROR) msr_d.r_maxsize = INT_MAX; - else + else msr_d.r_maxsize = msgsz; msr_d.r_msg = ERR_PTR(-EAGAIN); current->state = TASK_INTERRUPTIBLE; @@ -761,17 +855,17 @@ asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, * wake_up_process(). There is a race with exit(), see * ipc/mqueue.c for the details. */ - msg = (struct msg_msg*) msr_d.r_msg; + msg = (struct msg_msg*)msr_d.r_msg; while (msg == NULL) { cpu_relax(); - msg = (struct msg_msg*) msr_d.r_msg; + msg = (struct msg_msg *)msr_d.r_msg; } /* Lockless receive, part 3: * If there is a message or an error then accept it without * locking. */ - if(msg != ERR_PTR(-EAGAIN)) { + if (msg != ERR_PTR(-EAGAIN)) { rcu_read_unlock(); break; } @@ -786,7 +880,7 @@ asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, * Repeat test after acquiring the spinlock. */ msg = (struct msg_msg*)msr_d.r_msg; - if(msg != ERR_PTR(-EAGAIN)) + if (msg != ERR_PTR(-EAGAIN)) goto out_unlock; list_del(&msr_d.r_list); @@ -798,37 +892,53 @@ out_unlock: } } if (IS_ERR(msg)) - return PTR_ERR(msg); + return PTR_ERR(msg); msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz; - if (put_user (msg->m_type, &msgp->mtype) || - store_msg(msgp->mtext, msg, msgsz)) { - msgsz = -EFAULT; - } + *pmtype = msg->m_type; + if (store_msg(mtext, msg, msgsz)) + msgsz = -EFAULT; + free_msg(msg); + return msgsz; } +SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + long, msgtyp, int, msgflg) +{ + long err, mtype; + + err = do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg); + if (err < 0) + goto out; + + if (put_user(mtype, &msgp->mtype)) + err = -EFAULT; +out: + return err; +} + #ifdef CONFIG_PROC_FS static int sysvipc_msg_proc_show(struct seq_file *s, void *it) { struct msg_queue *msq = it; return seq_printf(s, - "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n", - msq->q_perm.key, - msq->q_id, - msq->q_perm.mode, - msq->q_cbytes, - msq->q_qnum, - msq->q_lspid, - msq->q_lrpid, - msq->q_perm.uid, - msq->q_perm.gid, - msq->q_perm.cuid, - msq->q_perm.cgid, - msq->q_stime, - msq->q_rtime, - msq->q_ctime); + "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n", + msq->q_perm.key, + msq->q_perm.id, + msq->q_perm.mode, + msq->q_cbytes, + msq->q_qnum, + msq->q_lspid, + msq->q_lrpid, + msq->q_perm.uid, + msq->q_perm.gid, + msq->q_perm.cuid, + msq->q_perm.cgid, + msq->q_stime, + msq->q_rtime, + msq->q_ctime); } #endif