msgget, msgsnd, msgrcv 분석

int msgget (key_t key, int msgflg) { #ifdef __ASSUME_DIRECT_SYSVIPC_SYSCALLS return INLINE_SYSCALL_CALL (msgget, key, msgflg); #else return INLINE_SYSCALL_CALL (ipc, IPCOP_msgget, key, msgflg, 0, NULL); #endif }

SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { return ksys_msgget(key, msgflg); }

long ksys_msgget(key_t key, int msgflg) { struct ipc_namespace *ns; static const struct ipc_ops msg_ops = { .getnew = newque, .associate = security_msg_queue_associate, }; 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); } SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { return ksys_msgget(key, msgflg); }

/** * 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); }

/** * 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; }

long ksys_msgget(key_t key, int msgflg) { ... static const struct ipc_ops msg_ops = { .getnew = newque, .associate = security_msg_queue_associate, }; ... return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params); } int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params) { ... return ipcget_new(ns, ids, ops, params); ... } static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params) { ... err = ops->getnew(ns, params); ... }

/** * 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 = kmalloc(sizeof(*msq), GFP_KERNEL_ACCOUNT); if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; msq->q_perm.key = key; msq->q_perm.security = NULL; retval = security_msg_queue_alloc(&msq->q_perm); if (retval) { kfree(msq); return retval; } msq->q_stime = msq->q_rtime = 0; msq->q_ctime = ktime_get_real_seconds(); msq->q_cbytes = msq->q_qnum = 0; msq->q_qbytes = ns->msg_ctlmnb; msq->q_lspid = msq->q_lrpid = NULL; 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) { ipc_rcu_putref(&msq->q_perm, msg_rcu_free); return retval; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); return msq->q_perm.id; }

1. ksys_msgget() 2. ipcget() 3. ipcget_new() 4. newque()

int __libc_msgsnd (int msqid, const void *msgp, size_t msgsz, int msgflg) { #ifdef __ASSUME_DIRECT_SYSVIPC_SYSCALLS return SYSCALL_CANCEL (msgsnd, msqid, msgp, msgsz, msgflg); #else return SYSCALL_CANCEL (ipc, IPCOP_msgsnd, msqid, msgsz, msgflg, msgp); #endif } weak_alias (__libc_msgsnd, msgsnd)

SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, int, msgflg) { return ksys_msgsnd(msqid, msgp, msgsz, msgflg); }

long ksys_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); }

struct msgbuf { __kernel_long_t mtype; /* type of message */ char mtext[1]; /* message text */ };

static 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 = msgsz; rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock1; } ipc_lock_object(&msq->q_perm); for (;;) { struct msg_sender s; err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } err = security_msg_queue_msgsnd(&msq->q_perm, msg, msgflg); if (err) goto out_unlock0; if (msg_fits_inqueue(msq, msgsz)) break; /* queue full, wait: */ if (msgflg & IPC_NOWAIT) { err = -EAGAIN; goto out_unlock0; } /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); rcu_read_lock(); ipc_lock_object(&msq->q_perm); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ss_del(&s); if (signal_pending(current)) { err = -ERESTARTNOHAND; goto out_unlock0; } } ipc_update_pid(&msq->q_lspid, task_tgid(current)); msq->q_stime = ktime_get_real_seconds(); if (!pipelined_send(msq, msg, &wake_q)) { /* no one is waiting for this message, enqueue it */ list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); } err = 0; msg = NULL; out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (msg != NULL) free_msg(msg); return err; }

static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { ... struct msg_msg *msg; msg = load_msg(mtext, msgsz); ... }

struct msg_msg { struct list_head m_list; long m_type; size_t m_ts; /* message text size */ struct msg_msgseg *next; void *security; /* the actual message follows immediately */ }; struct list_head { struct list_head *next, *prev; }; struct msg_msgseg { struct msg_msgseg *next; /* the next part of the message follows immediately */ };

struct msg_msg *load_msg(const void __user *src, size_t len) { struct msg_msg *msg; struct msg_msgseg *seg; int err = -EFAULT; size_t alen; msg = alloc_msg(len); }

#define DATALEN_MSG ((size_t)PAGE_SIZE-sizeof(struct msg_msg)) #define DATALEN_SEG ((size_t)PAGE_SIZE-sizeof(struct msg_msgseg)) static struct msg_msg *alloc_msg(size_t len) { struct msg_msg *msg; struct msg_msgseg **pseg; size_t alen; alen = min(len, DATALEN_MSG); msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT); if (msg == NULL) return NULL; msg->next = NULL; msg->security = NULL; len -= alen; pseg = &msg->next; while (len > 0) { struct msg_msgseg *seg; cond_resched(); alen = min(len, DATALEN_SEG); seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT); if (seg == NULL) goto out_err; *pseg = seg; seg->next = NULL; pseg = &seg->next; len -= alen; } return msg; out_err: free_msg(msg); return NULL; }

struct msg_msg *load_msg(const void __user *src, size_t len) { struct msg_msg *msg; struct msg_msgseg *seg; int err = -EFAULT; size_t alen; msg = alloc_msg(len); if (msg == NULL) return ERR_PTR(-ENOMEM); alen = min(len, DATALEN_MSG); if (copy_from_user(msg + 1, src, alen)) goto out_err; for (seg = msg->next; seg != NULL; seg = seg->next) { len -= alen; src = (char __user *)src + alen; alen = min(len, DATALEN_SEG); if (copy_from_user(seg + 1, src, alen)) goto out_err; } err = security_msg_msg_alloc(msg); if (err) goto out_err; return msg; out_err: free_msg(msg); return ERR_PTR(err); }저

struct msg_msg { struct list_head m_list; long m_type; size_t m_ts; /* message text size */ struct msg_msgseg *next; void *security; /* the actual message follows immediately */ };

struct msg_msg { struct list_head m_list; long m_type; size_t m_ts; /* message text size */ struct msg_msgseg *next; void *security; char data[] };

static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { ... msg = load_msg(mtext, msgsz); if (IS_ERR(msg)) return PTR_ERR(msg); msg->m_type = mtype; msg->m_ts = msgsz; ... }

static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { ... rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock1; } ipc_lock_object(&msq->q_perm); ... }

struct msg_sender { struct list_head list; struct task_struct *tsk; size_t msgsz; }; static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { ... for (;;) { struct msg_sender s; err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ... }

static 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 = msgsz; rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock1; } ipc_lock_object(&msq->q_perm); for (;;) { struct msg_sender s; err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } err = security_msg_queue_msgsnd(&msq->q_perm, msg, msgflg); if (err) goto out_unlock0; if (msg_fits_inqueue(msq, msgsz)) break; /* queue full, wait: */ if (msgflg & IPC_NOWAIT) { err = -EAGAIN; goto out_unlock0; } /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); rcu_read_lock(); ipc_lock_object(&msq->q_perm); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ss_del(&s); if (signal_pending(current)) { err = -ERESTARTNOHAND; goto out_unlock0; } } ipc_update_pid(&msq->q_lspid, task_tgid(current)); msq->q_stime = ktime_get_real_seconds(); if (!pipelined_send(msq, msg, &wake_q)) { /* no one is waiting for this message, enqueue it */ list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); } err = 0; msg = NULL; out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (msg != NULL) free_msg(msg); return err; }

1. ksys_msgsnd() 2. do_msgsnd() 3. load_msg() 4. alloc_msg()

ssize_t __libc_msgrcv (int msqid, void *msgp, size_t msgsz, long int msgtyp, int msgflg) { #ifdef __ASSUME_DIRECT_SYSVIPC_SYSCALLS return SYSCALL_CANCEL (msgrcv, msqid, msgp, msgsz, msgtyp, msgflg); #else return SYSCALL_CANCEL (ipc, IPCOP_msgrcv, msqid, msgsz, msgflg, MSGRCV_ARGS (msgp, msgtyp)); #endif } weak_alias (__libc_msgrcv, msgrcv)

SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, long, msgtyp, int, msgflg) { return ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); }

long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg) { return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill); }

static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { int mode; struct msg_queue *msq; struct ipc_namespace *ns; struct msg_msg *msg, *copy = NULL; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msqid < 0 || (long) bufsz < 0) return -EINVAL; ... }

if (msgflg & MSG_COPY) { if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT)) return -EINVAL; copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax)); if (IS_ERR(copy)) return PTR_ERR(copy); }

static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) { struct msg_msg *copy; /* * Create dummy message to copy real message to. */ copy = load_msg(buf, bufsz); if (!IS_ERR(copy)) copy->m_ts = bufsz; return copy; }

static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { ... mode = convert_mode(&msgtyp, msgflg); ... }

static inline int convert_mode(long *msgtyp, int msgflg) { if (msgflg & MSG_COPY) return SEARCH_NUMBER; /* * 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). */ if (*msgtyp == 0) return SEARCH_ANY; if (*msgtyp < 0) { if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ *msgtyp = LONG_MAX; else *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } if (msgflg & MSG_EXCEPT) return SEARCH_NOTEQUAL; return SEARCH_EQUAL; }

static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { ... msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { rcu_read_unlock(); free_copy(copy); return PTR_ERR(msq); ... }

for (;;) { struct msg_receiver msr_d; ... msg = find_msg(msq, &msgtyp, mode); } ...

static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode) { struct msg_msg *msg, *found = NULL; long count = 0; list_for_each_entry(msg, &msq->q_messages, m_list) { if (testmsg(msg, *msgtyp, mode) && !security_msg_queue_msgrcv(&msq->q_perm, msg, current, *msgtyp, mode)) { if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) { *msgtyp = msg->m_type - 1; found = msg; } else if (mode == SEARCH_NUMBER) { if (*msgtyp == count) return msg; } else return msg; count++; } } return found ?: ERR_PTR(-EAGAIN); }

for (;;) { struct msg_receiver msr_d; ... msg = find_msg(msq, &msgtyp, mode); } ... bufsz = msg_handler(buf, msg, bufsz); free_msg(msg); return bufsz;

long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg) { return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill); } static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { ... }

int store_msg(void __user *dest, struct msg_msg *msg, size_t len) { size_t alen; struct msg_msgseg *seg; alen = min(len, DATALEN_MSG); if (copy_to_user(dest, msg + 1, alen)) return -1; for (seg = msg->next; seg != NULL; seg = seg->next) { len -= alen; dest = (char __user *)dest + alen; alen = min(len, DATALEN_SEG); if (copy_to_user(dest, seg + 1, alen)) return -1; } return 0; }

static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) { struct msgbuf __user *msgp = dest; size_t msgsz; if (put_user(msg->m_type, &msgp->mtype)) return -EFAULT; msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; if (store_msg(msgp->mtext, msg, msgsz)) return -EFAULT; return msgsz; }

for (;;) { struct msg_receiver msr_d; ... msg = find_msg(msq, &msgtyp, mode); } ... bufsz = msg_handler(buf, msg, bufsz); free_msg(msg); return bufsz;

void free_msg(struct msg_msg *msg) { struct msg_msgseg *seg; security_msg_msg_free(msg); seg = msg->next; kfree(msg); while (seg != NULL) { struct msg_msgseg *tmp = seg->next; cond_resched(); kfree(seg); seg = tmp; } } void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; }

1. ksys_msgrcv() 2. do_msgrcv() 3. find_msg() 4. do_msg_fill() 5. free_msg()