diff options
Diffstat (limited to 'ipc')
| -rw-r--r-- | ipc/Makefile | 11 | ||||
| -rw-r--r-- | ipc/compat.c | 682 | ||||
| -rw-r--r-- | ipc/compat_mq.c | 146 | ||||
| -rw-r--r-- | ipc/ipc_sysctl.c | 289 | ||||
| -rw-r--r-- | ipc/ipcns_notifier.c | 92 | ||||
| -rw-r--r-- | ipc/mqueue.c | 1294 | ||||
| -rw-r--r-- | ipc/msg.c | 944 | ||||
| -rw-r--r-- | ipc/msgutil.c | 127 | ||||
| -rw-r--r-- | ipc/namespace.c | 112 | ||||
| -rw-r--r-- | ipc/sem.c | 1381 | ||||
| -rw-r--r-- | ipc/shm.c | 1080 | ||||
| -rw-r--r-- | ipc/util.c | 1002 | ||||
| -rw-r--r-- | ipc/util.h | 157 |
13 files changed, 7317 insertions, 0 deletions
diff --git a/ipc/Makefile b/ipc/Makefile new file mode 100644 index 0000000..65c3843 --- /dev/null +++ b/ipc/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for the linux ipc. +# + +obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o +obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o +obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o +obj_mq-$(CONFIG_COMPAT) += compat_mq.o +obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y) +obj-$(CONFIG_IPC_NS) += namespace.o + diff --git a/ipc/compat.c b/ipc/compat.c new file mode 100644 index 0000000..ab76fb0 --- /dev/null +++ b/ipc/compat.c @@ -0,0 +1,682 @@ +/* + * 32 bit compatibility code for System V IPC + * + * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) + * Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com> + * Copyright (C) 2000 VA Linux Co + * Copyright (C) 2000 Don Dugger <n0ano@valinux.com> + * Copyright (C) 2000 Hewlett-Packard Co. + * Copyright (C) 2000 David Mosberger-Tang <davidm@hpl.hp.com> + * Copyright (C) 2000 Gerhard Tonn (ton@de.ibm.com) + * Copyright (C) 2000-2002 Andi Kleen, SuSE Labs (x86-64 port) + * Copyright (C) 2000 Silicon Graphics, Inc. + * Copyright (C) 2001 IBM + * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) 2004 Arnd Bergmann (arnd@arndb.de) + * + * This code is collected from the versions for sparc64, mips64, s390x, ia64, + * ppc64 and x86_64, all of which are based on the original sparc64 version + * by Jakub Jelinek. + * + */ +#include <linux/compat.h> +#include <linux/errno.h> +#include <linux/highuid.h> +#include <linux/init.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/slab.h> +#include <linux/syscalls.h> + +#include <linux/mutex.h> +#include <asm/uaccess.h> + +#include "util.h" + +struct compat_msgbuf { + compat_long_t mtype; + char mtext[1]; +}; + +struct compat_ipc_perm { + key_t key; + __compat_uid_t uid; + __compat_gid_t gid; + __compat_uid_t cuid; + __compat_gid_t cgid; + compat_mode_t mode; + unsigned short seq; +}; + +struct compat_semid_ds { + struct compat_ipc_perm sem_perm; + compat_time_t sem_otime; + compat_time_t sem_ctime; + compat_uptr_t sem_base; + compat_uptr_t sem_pending; + compat_uptr_t sem_pending_last; + compat_uptr_t undo; + unsigned short sem_nsems; +}; + +struct compat_msqid_ds { + struct compat_ipc_perm msg_perm; + compat_uptr_t msg_first; + compat_uptr_t msg_last; + compat_time_t msg_stime; + compat_time_t msg_rtime; + compat_time_t msg_ctime; + compat_ulong_t msg_lcbytes; + compat_ulong_t msg_lqbytes; + unsigned short msg_cbytes; + unsigned short msg_qnum; + unsigned short msg_qbytes; + compat_ipc_pid_t msg_lspid; + compat_ipc_pid_t msg_lrpid; +}; + +struct compat_shmid_ds { + struct compat_ipc_perm shm_perm; + int shm_segsz; + compat_time_t shm_atime; + compat_time_t shm_dtime; + compat_time_t shm_ctime; + compat_ipc_pid_t shm_cpid; + compat_ipc_pid_t shm_lpid; + unsigned short shm_nattch; + unsigned short shm_unused; + compat_uptr_t shm_unused2; + compat_uptr_t shm_unused3; +}; + +struct compat_ipc_kludge { + compat_uptr_t msgp; + compat_long_t msgtyp; +}; + +struct compat_shminfo64 { + compat_ulong_t shmmax; + compat_ulong_t shmmin; + compat_ulong_t shmmni; + compat_ulong_t shmseg; + compat_ulong_t shmall; + compat_ulong_t __unused1; + compat_ulong_t __unused2; + compat_ulong_t __unused3; + compat_ulong_t __unused4; +}; + +struct compat_shm_info { + compat_int_t used_ids; + compat_ulong_t shm_tot, shm_rss, shm_swp; + compat_ulong_t swap_attempts, swap_successes; +}; + +extern int sem_ctls[]; +#define sc_semopm (sem_ctls[2]) + +static inline int compat_ipc_parse_version(int *cmd) +{ + int version = *cmd & IPC_64; + + /* this is tricky: architectures that have support for the old + * ipc structures in 64 bit binaries need to have IPC_64 set + * in cmd, the others need to have it cleared */ +#ifndef ipc_parse_version + *cmd |= IPC_64; +#else + *cmd &= ~IPC_64; +#endif + return version; +} + +static inline int __get_compat_ipc64_perm(struct ipc64_perm *p64, + struct compat_ipc64_perm __user *up64) +{ + int err; + + err = __get_user(p64->uid, &up64->uid); + err |= __get_user(p64->gid, &up64->gid); + err |= __get_user(p64->mode, &up64->mode); + return err; +} + +static inline int __get_compat_ipc_perm(struct ipc64_perm *p, + struct compat_ipc_perm __user *up) +{ + int err; + + err = __get_user(p->uid, &up->uid); + err |= __get_user(p->gid, &up->gid); + err |= __get_user(p->mode, &up->mode); + return err; +} + +static inline int __put_compat_ipc64_perm(struct ipc64_perm *p64, + struct compat_ipc64_perm __user *up64) +{ + int err; + + err = __put_user(p64->key, &up64->key); + err |= __put_user(p64->uid, &up64->uid); + err |= __put_user(p64->gid, &up64->gid); + err |= __put_user(p64->cuid, &up64->cuid); + err |= __put_user(p64->cgid, &up64->cgid); + err |= __put_user(p64->mode, &up64->mode); + err |= __put_user(p64->seq, &up64->seq); + return err; +} + +static inline int __put_compat_ipc_perm(struct ipc64_perm *p, + struct compat_ipc_perm __user *up) +{ + int err; + __compat_uid_t u; + __compat_gid_t g; + + err = __put_user(p->key, &up->key); + SET_UID(u, p->uid); + err |= __put_user(u, &up->uid); + SET_GID(g, p->gid); + err |= __put_user(g, &up->gid); + SET_UID(u, p->cuid); + err |= __put_user(u, &up->cuid); + SET_GID(g, p->cgid); + err |= __put_user(g, &up->cgid); + err |= __put_user(p->mode, &up->mode); + err |= __put_user(p->seq, &up->seq); + return err; +} + +static inline int get_compat_semid64_ds(struct semid64_ds *s64, + struct compat_semid64_ds __user *up64) +{ + if (!access_ok (VERIFY_READ, up64, sizeof(*up64))) + return -EFAULT; + return __get_compat_ipc64_perm(&s64->sem_perm, &up64->sem_perm); +} + +static inline int get_compat_semid_ds(struct semid64_ds *s, + struct compat_semid_ds __user *up) +{ + if (!access_ok (VERIFY_READ, up, sizeof(*up))) + return -EFAULT; + return __get_compat_ipc_perm(&s->sem_perm, &up->sem_perm); +} + +static inline int put_compat_semid64_ds(struct semid64_ds *s64, + struct compat_semid64_ds __user *up64) +{ + int err; + + if (!access_ok (VERIFY_WRITE, up64, sizeof(*up64))) + return -EFAULT; + err = __put_compat_ipc64_perm(&s64->sem_perm, &up64->sem_perm); + err |= __put_user(s64->sem_otime, &up64->sem_otime); + err |= __put_user(s64->sem_ctime, &up64->sem_ctime); + err |= __put_user(s64->sem_nsems, &up64->sem_nsems); + return err; +} + +static inline int put_compat_semid_ds(struct semid64_ds *s, + struct compat_semid_ds __user *up) +{ + int err; + + if (!access_ok (VERIFY_WRITE, up, sizeof(*up))) + return -EFAULT; + err = __put_compat_ipc_perm(&s->sem_perm, &up->sem_perm); + err |= __put_user(s->sem_otime, &up->sem_otime); + err |= __put_user(s->sem_ctime, &up->sem_ctime); + err |= __put_user(s->sem_nsems, &up->sem_nsems); + return err; +} + +long compat_sys_semctl(int first, int second, int third, void __user *uptr) +{ + union semun fourth; + u32 pad; + int err, err2; + struct semid64_ds s64; + struct semid64_ds __user *up64; + int version = compat_ipc_parse_version(&third); + + if (!uptr) + return -EINVAL; + if (get_user(pad, (u32 __user *) uptr)) + return -EFAULT; + if ((third & (~IPC_64)) == SETVAL) + fourth.val = (int) pad; + else + fourth.__pad = compat_ptr(pad); + switch (third & (~IPC_64)) { + case IPC_INFO: + case IPC_RMID: + case SEM_INFO: + case GETVAL: + case GETPID: + case GETNCNT: + case GETZCNT: + case GETALL: + case SETVAL: + case SETALL: + err = sys_semctl(first, second, third, fourth); + break; + + case IPC_STAT: + case SEM_STAT: + up64 = compat_alloc_user_space(sizeof(s64)); + fourth.__pad = up64; + err = sys_semctl(first, second, third, fourth); + if (err < 0) + break; + if (copy_from_user(&s64, up64, sizeof(s64))) + err2 = -EFAULT; + else if (version == IPC_64) + err2 = put_compat_semid64_ds(&s64, compat_ptr(pad)); + else + err2 = put_compat_semid_ds(&s64, compat_ptr(pad)); + if (err2) + err = -EFAULT; + break; + + case IPC_SET: + if (version == IPC_64) { + err = get_compat_semid64_ds(&s64, compat_ptr(pad)); + } else { + err = get_compat_semid_ds(&s64, compat_ptr(pad)); + } + up64 = compat_alloc_user_space(sizeof(s64)); + if (copy_to_user(up64, &s64, sizeof(s64))) + err = -EFAULT; + if (err) + break; + + fourth.__pad = up64; + err = sys_semctl(first, second, third, fourth); + break; + + default: + err = -EINVAL; + break; + } + return err; +} + +long compat_sys_msgsnd(int first, int second, int third, void __user *uptr) +{ + struct compat_msgbuf __user *up = uptr; + long type; + + if (first < 0) + return -EINVAL; + if (second < 0) + return -EINVAL; + + if (get_user(type, &up->mtype)) + return -EFAULT; + + return do_msgsnd(first, type, up->mtext, second, third); +} + +long compat_sys_msgrcv(int first, int second, int msgtyp, int third, + int version, void __user *uptr) +{ + struct compat_msgbuf __user *up; + long type; + int err; + + if (first < 0) + return -EINVAL; + if (second < 0) + return -EINVAL; + + if (!version) { + struct compat_ipc_kludge ipck; + err = -EINVAL; + if (!uptr) + goto out; + err = -EFAULT; + if (copy_from_user (&ipck, uptr, sizeof(ipck))) + goto out; + uptr = compat_ptr(ipck.msgp); + msgtyp = ipck.msgtyp; + } + up = uptr; + err = do_msgrcv(first, &type, up->mtext, second, msgtyp, third); + if (err < 0) + goto out; + if (put_user(type, &up->mtype)) + err = -EFAULT; +out: + return err; +} + +static inline int get_compat_msqid64(struct msqid64_ds *m64, + struct compat_msqid64_ds __user *up64) +{ + int err; + + if (!access_ok(VERIFY_READ, up64, sizeof(*up64))) + return -EFAULT; + err = __get_compat_ipc64_perm(&m64->msg_perm, &up64->msg_perm); + err |= __get_user(m64->msg_qbytes, &up64->msg_qbytes); + return err; +} + +static inline int get_compat_msqid(struct msqid64_ds *m, + struct compat_msqid_ds __user *up) +{ + int err; + + if (!access_ok(VERIFY_READ, up, sizeof(*up))) + return -EFAULT; + err = __get_compat_ipc_perm(&m->msg_perm, &up->msg_perm); + err |= __get_user(m->msg_qbytes, &up->msg_qbytes); + return err; +} + +static inline int put_compat_msqid64_ds(struct msqid64_ds *m64, + struct compat_msqid64_ds __user *up64) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64))) + return -EFAULT; + err = __put_compat_ipc64_perm(&m64->msg_perm, &up64->msg_perm); + err |= __put_user(m64->msg_stime, &up64->msg_stime); + err |= __put_user(m64->msg_rtime, &up64->msg_rtime); + err |= __put_user(m64->msg_ctime, &up64->msg_ctime); + err |= __put_user(m64->msg_cbytes, &up64->msg_cbytes); + err |= __put_user(m64->msg_qnum, &up64->msg_qnum); + err |= __put_user(m64->msg_qbytes, &up64->msg_qbytes); + err |= __put_user(m64->msg_lspid, &up64->msg_lspid); + err |= __put_user(m64->msg_lrpid, &up64->msg_lrpid); + return err; +} + +static inline int put_compat_msqid_ds(struct msqid64_ds *m, + struct compat_msqid_ds __user *up) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up, sizeof(*up))) + return -EFAULT; + err = __put_compat_ipc_perm(&m->msg_perm, &up->msg_perm); + err |= __put_user(m->msg_stime, &up->msg_stime); + err |= __put_user(m->msg_rtime, &up->msg_rtime); + err |= __put_user(m->msg_ctime, &up->msg_ctime); + err |= __put_user(m->msg_cbytes, &up->msg_cbytes); + err |= __put_user(m->msg_qnum, &up->msg_qnum); + err |= __put_user(m->msg_qbytes, &up->msg_qbytes); + err |= __put_user(m->msg_lspid, &up->msg_lspid); + err |= __put_user(m->msg_lrpid, &up->msg_lrpid); + return err; +} + +long compat_sys_msgctl(int first, int second, void __user *uptr) +{ + int err, err2; + struct msqid64_ds m64; + int version = compat_ipc_parse_version(&second); + void __user *p; + + switch (second & (~IPC_64)) { + case IPC_INFO: + case IPC_RMID: + case MSG_INFO: + err = sys_msgctl(first, second, uptr); + break; + + case IPC_SET: + if (version == IPC_64) { + err = get_compat_msqid64(&m64, uptr); + } else { + err = get_compat_msqid(&m64, uptr); + } + if (err) + break; + p = compat_alloc_user_space(sizeof(m64)); + if (copy_to_user(p, &m64, sizeof(m64))) + err = -EFAULT; + else + err = sys_msgctl(first, second, p); + break; + + case IPC_STAT: + case MSG_STAT: + p = compat_alloc_user_space(sizeof(m64)); + err = sys_msgctl(first, second, p); + if (err < 0) + break; + if (copy_from_user(&m64, p, sizeof(m64))) + err2 = -EFAULT; + else if (version == IPC_64) + err2 = put_compat_msqid64_ds(&m64, uptr); + else + err2 = put_compat_msqid_ds(&m64, uptr); + if (err2) + err = -EFAULT; + break; + + default: + err = -EINVAL; + break; + } + return err; +} + +long compat_sys_shmat(int first, int second, compat_uptr_t third, int version, + void __user *uptr) +{ + int err; + unsigned long raddr; + compat_ulong_t __user *uaddr; + + if (version == 1) + return -EINVAL; + err = do_shmat(first, uptr, second, &raddr); + if (err < 0) + return err; + uaddr = compat_ptr(third); + return put_user(raddr, uaddr); +} + +static inline int get_compat_shmid64_ds(struct shmid64_ds *s64, + struct compat_shmid64_ds __user *up64) +{ + if (!access_ok(VERIFY_READ, up64, sizeof(*up64))) + return -EFAULT; + return __get_compat_ipc64_perm(&s64->shm_perm, &up64->shm_perm); +} + +static inline int get_compat_shmid_ds(struct shmid64_ds *s, + struct compat_shmid_ds __user *up) +{ + if (!access_ok(VERIFY_READ, up, sizeof(*up))) + return -EFAULT; + return __get_compat_ipc_perm(&s->shm_perm, &up->shm_perm); +} + +static inline int put_compat_shmid64_ds(struct shmid64_ds *s64, + struct compat_shmid64_ds __user *up64) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64))) + return -EFAULT; + err = __put_compat_ipc64_perm(&s64->shm_perm, &up64->shm_perm); + err |= __put_user(s64->shm_atime, &up64->shm_atime); + err |= __put_user(s64->shm_dtime, &up64->shm_dtime); + err |= __put_user(s64->shm_ctime, &up64->shm_ctime); + err |= __put_user(s64->shm_segsz, &up64->shm_segsz); + err |= __put_user(s64->shm_nattch, &up64->shm_nattch); + err |= __put_user(s64->shm_cpid, &up64->shm_cpid); + err |= __put_user(s64->shm_lpid, &up64->shm_lpid); + return err; +} + +static inline int put_compat_shmid_ds(struct shmid64_ds *s, + struct compat_shmid_ds __user *up) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up, sizeof(*up))) + return -EFAULT; + err = __put_compat_ipc_perm(&s->shm_perm, &up->shm_perm); + err |= __put_user(s->shm_atime, &up->shm_atime); + err |= __put_user(s->shm_dtime, &up->shm_dtime); + err |= __put_user(s->shm_ctime, &up->shm_ctime); + err |= __put_user(s->shm_segsz, &up->shm_segsz); + err |= __put_user(s->shm_nattch, &up->shm_nattch); + err |= __put_user(s->shm_cpid, &up->shm_cpid); + err |= __put_user(s->shm_lpid, &up->shm_lpid); + return err; +} + +static inline int put_compat_shminfo64(struct shminfo64 *smi, + struct compat_shminfo64 __user *up64) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64))) + return -EFAULT; + if (smi->shmmax > INT_MAX) + smi->shmmax = INT_MAX; + err = __put_user(smi->shmmax, &up64->shmmax); + err |= __put_user(smi->shmmin, &up64->shmmin); + err |= __put_user(smi->shmmni, &up64->shmmni); + err |= __put_user(smi->shmseg, &up64->shmseg); + err |= __put_user(smi->shmall, &up64->shmall); + return err; +} + +static inline int put_compat_shminfo(struct shminfo64 *smi, + struct shminfo __user *up) +{ + int err; + + if (!access_ok(VERIFY_WRITE, up, sizeof(*up))) + return -EFAULT; + if (smi->shmmax > INT_MAX) + smi->shmmax = INT_MAX; + err = __put_user(smi->shmmax, &up->shmmax); + err |= __put_user(smi->shmmin, &up->shmmin); + err |= __put_user(smi->shmmni, &up->shmmni); + err |= __put_user(smi->shmseg, &up->shmseg); + err |= __put_user(smi->shmall, &up->shmall); + return err; +} + +static inline int put_compat_shm_info(struct shm_info __user *ip, + struct compat_shm_info __user *uip) +{ + int err; + struct shm_info si; + + if (!access_ok(VERIFY_WRITE, uip, sizeof(*uip)) || + copy_from_user(&si, ip, sizeof(si))) + return -EFAULT; + err = __put_user(si.used_ids, &uip->used_ids); + err |= __put_user(si.shm_tot, &uip->shm_tot); + err |= __put_user(si.shm_rss, &uip->shm_rss); + err |= __put_user(si.shm_swp, &uip->shm_swp); + err |= __put_user(si.swap_attempts, &uip->swap_attempts); + err |= __put_user(si.swap_successes, &uip->swap_successes); + return err; +} + +long compat_sys_shmctl(int first, int second, void __user *uptr) +{ + void __user *p; + struct shmid64_ds s64; + struct shminfo64 smi; + int err, err2; + int version = compat_ipc_parse_version(&second); + + switch (second & (~IPC_64)) { + case IPC_RMID: + case SHM_LOCK: + case SHM_UNLOCK: + err = sys_shmctl(first, second, uptr); + break; + + case IPC_INFO: + p = compat_alloc_user_space(sizeof(smi)); + err = sys_shmctl(first, second, p); + if (err < 0) + break; + if (copy_from_user(&smi, p, sizeof(smi))) + err2 = -EFAULT; + else if (version == IPC_64) + err2 = put_compat_shminfo64(&smi, uptr); + else + err2 = put_compat_shminfo(&smi, uptr); + if (err2) + err = -EFAULT; + break; + + + case IPC_SET: + if (version == IPC_64) { + err = get_compat_shmid64_ds(&s64, uptr); + } else { + err = get_compat_shmid_ds(&s64, uptr); + } + if (err) + break; + p = compat_alloc_user_space(sizeof(s64)); + if (copy_to_user(p, &s64, sizeof(s64))) + err = -EFAULT; + else + err = sys_shmctl(first, second, p); + break; + + case IPC_STAT: + case SHM_STAT: + p = compat_alloc_user_space(sizeof(s64)); + err = sys_shmctl(first, second, p); + if (err < 0) + break; + if (copy_from_user(&s64, p, sizeof(s64))) + err2 = -EFAULT; + else if (version == IPC_64) + err2 = put_compat_shmid64_ds(&s64, uptr); + else + err2 = put_compat_shmid_ds(&s64, uptr); + if (err2) + err = -EFAULT; + break; + + case SHM_INFO: + p = compat_alloc_user_space(sizeof(struct shm_info)); + err = sys_shmctl(first, second, p); + if (err < 0) + break; + err2 = put_compat_shm_info(p, uptr); + if (err2) + err = -EFAULT; + break; + + default: + err = -EINVAL; + break; + } + return err; +} + +long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, + unsigned nsops, const struct compat_timespec __user *timeout) +{ + struct timespec __user *ts64 = NULL; + if (timeout) { + struct timespec ts; + ts64 = compat_alloc_user_space(sizeof(*ts64)); + if (get_compat_timespec(&ts, timeout)) + return -EFAULT; + if (copy_to_user(ts64, &ts, sizeof(ts))) + return -EFAULT; + } + return sys_semtimedop(semid, tsems, nsops, ts64); +} diff --git a/ipc/compat_mq.c b/ipc/compat_mq.c new file mode 100644 index 0000000..d8d1e9f --- /dev/null +++ b/ipc/compat_mq.c @@ -0,0 +1,146 @@ +/* + * ipc/compat_mq.c + * 32 bit emulation for POSIX message queue system calls + * + * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Author: Arnd Bergmann <arnd@arndb.de> + */ + +#include <linux/compat.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/mqueue.h> +#include <linux/syscalls.h> + +#include <asm/uaccess.h> + +struct compat_mq_attr { + compat_long_t mq_flags; /* message queue flags */ + compat_long_t mq_maxmsg; /* maximum number of messages */ + compat_long_t mq_msgsize; /* maximum message size */ + compat_long_t mq_curmsgs; /* number of messages currently queued */ + compat_long_t __reserved[4]; /* ignored for input, zeroed for output */ +}; + +static inline int get_compat_mq_attr(struct mq_attr *attr, + const struct compat_mq_attr __user *uattr) +{ + if (!access_ok(VERIFY_READ, uattr, sizeof *uattr)) + return -EFAULT; + + return __get_user(attr->mq_flags, &uattr->mq_flags) + | __get_user(attr->mq_maxmsg, &uattr->mq_maxmsg) + | __get_user(attr->mq_msgsize, &uattr->mq_msgsize) + | __get_user(attr->mq_curmsgs, &uattr->mq_curmsgs); +} + +static inline int put_compat_mq_attr(const struct mq_attr *attr, + struct compat_mq_attr __user *uattr) +{ + if (clear_user(uattr, sizeof *uattr)) + return -EFAULT; + + return __put_user(attr->mq_flags, &uattr->mq_flags) + | __put_user(attr->mq_maxmsg, &uattr->mq_maxmsg) + | __put_user(attr->mq_msgsize, &uattr->mq_msgsize) + | __put_user(attr->mq_curmsgs, &uattr->mq_curmsgs); +} + +asmlinkage long compat_sys_mq_open(const char __user *u_name, + int oflag, compat_mode_t mode, + struct compat_mq_attr __user *u_attr) +{ + void __user *p = NULL; + if (u_attr && oflag & O_CREAT) { + struct mq_attr attr; + p = compat_alloc_user_space(sizeof(attr)); + if (get_compat_mq_attr(&attr, u_attr) || + copy_to_user(p, &attr, sizeof(attr))) + return -EFAULT; + } + return sys_mq_open(u_name, oflag, mode, p); +} + +static int compat_prepare_timeout(struct timespec __user * *p, + const struct compat_timespec __user *u) +{ + struct timespec ts; + if (!u) { + *p = NULL; + return 0; + } + *p = compat_alloc_user_space(sizeof(ts)); + if (get_compat_timespec(&ts, u) || copy_to_user(*p, &ts, sizeof(ts))) + return -EFAULT; + return 0; +} + +asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes, + const char __user *u_msg_ptr, + size_t msg_len, unsigned int msg_prio, + const struct compat_timespec __user *u_abs_timeout) +{ + struct timespec __user *u_ts; + + if (compat_prepare_timeout(&u_ts, u_abs_timeout)) + return -EFAULT; + + return sys_mq_timedsend(mqdes, u_msg_ptr, msg_len, + msg_prio, u_ts); +} + +asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, + char __user *u_msg_ptr, + size_t msg_len, unsigned int __user *u_msg_prio, + const struct compat_timespec __user *u_abs_timeout) +{ + struct timespec __user *u_ts; + if (compat_prepare_timeout(&u_ts, u_abs_timeout)) + return -EFAULT; + + return sys_mq_timedreceive(mqdes, u_msg_ptr, msg_len, + u_msg_prio, u_ts); +} + +asmlinkage long compat_sys_mq_notify(mqd_t mqdes, + const struct compat_sigevent __user *u_notification) +{ + struct sigevent __user *p = NULL; + if (u_notification) { + struct sigevent n; + p = compat_alloc_user_space(sizeof(*p)); + if (get_compat_sigevent(&n, u_notification)) + return -EFAULT; + if (n.sigev_notify == SIGEV_THREAD) + n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int); + if (copy_to_user(p, &n, sizeof(*p))) + return -EFAULT; + } + return sys_mq_notify(mqdes, p); +} + +asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, + const struct compat_mq_attr __user *u_mqstat, + struct compat_mq_attr __user *u_omqstat) +{ + struct mq_attr mqstat; + struct mq_attr __user *p = compat_alloc_user_space(2 * sizeof(*p)); + long ret; + + if (u_mqstat) { + if (get_compat_mq_attr(&mqstat, u_mqstat) || + copy_to_user(p, &mqstat, sizeof(mqstat))) + return -EFAULT; + } + ret = sys_mq_getsetattr(mqdes, + u_mqstat ? p : NULL, + u_omqstat ? p + 1 : NULL); + if (ret) + return ret; + if (u_omqstat) { + if (copy_from_user(&mqstat, p + 1, sizeof(mqstat)) || + put_compat_mq_attr(&mqstat, u_omqstat)) + return -EFAULT; + } + return 0; +} diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c new file mode 100644 index 0000000..0dfebc5 --- /dev/null +++ b/ipc/ipc_sysctl.c @@ -0,0 +1,289 @@ +/* + * Copyright (C) 2007 + * + * Author: Eric Biederman <ebiederm@xmision.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include <linux/module.h> +#include <linux/ipc.h> +#include <linux/nsproxy.h> +#include <linux/sysctl.h> +#include <linux/uaccess.h> +#include <linux/ipc_namespace.h> +#include <linux/msg.h> +#include "util.h" + +static void *get_ipc(ctl_table *table) +{ + char *which = table->data; + struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; + which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns; + return which; +} + +/* + * Routine that is called when the file "auto_msgmni" has successfully been + * written. + * Two values are allowed: + * 0: unregister msgmni's callback routine from the ipc namespace notifier + * chain. This means that msgmni won't be recomputed anymore upon memory + * add/remove or ipc namespace creation/removal. + * 1: register back the callback routine. + */ +static void ipc_auto_callback(int val) +{ + if (!val) + unregister_ipcns_notifier(current->nsproxy->ipc_ns); + else { + /* + * Re-enable automatic recomputing only if not already + * enabled. + */ + recompute_msgmni(current->nsproxy->ipc_ns); + cond_register_ipcns_notifier(current->nsproxy->ipc_ns); + } +} + +#ifdef CONFIG_PROC_FS +static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table ipc_table; + memcpy(&ipc_table, table, sizeof(ipc_table)); + ipc_table.data = get_ipc(table); + + return proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); +} + +static int proc_ipc_callback_dointvec(ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table ipc_table; + size_t lenp_bef = *lenp; + int rc; + + memcpy(&ipc_table, table, sizeof(ipc_table)); + ipc_table.data = get_ipc(table); + + rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); + + if (write && !rc && lenp_bef == *lenp) + /* + * Tunable has successfully been changed by hand. Disable its + * automatic adjustment. This simply requires unregistering + * the notifiers that trigger recalculation. + */ + unregister_ipcns_notifier(current->nsproxy->ipc_ns); + + return rc; +} + +static int proc_ipc_doulongvec_minmax(ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table ipc_table; + memcpy(&ipc_table, table, sizeof(ipc_table)); + ipc_table.data = get_ipc(table); + + return proc_doulongvec_minmax(&ipc_table, write, filp, buffer, + lenp, ppos); +} + +static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table ipc_table; + size_t lenp_bef = *lenp; + int oldval; + int rc; + + memcpy(&ipc_table, table, sizeof(ipc_table)); + ipc_table.data = get_ipc(table); + oldval = *((int *)(ipc_table.data)); + + rc = proc_dointvec_minmax(&ipc_table, write, filp, buffer, lenp, ppos); + + if (write && !rc && lenp_bef == *lenp) { + int newval = *((int *)(ipc_table.data)); + /* + * The file "auto_msgmni" has correctly been set. + * React by (un)registering the corresponding tunable, if the + * value has changed. + */ + if (newval != oldval) + ipc_auto_callback(newval); + } + + return rc; +} + +#else +#define proc_ipc_doulongvec_minmax NULL +#define proc_ipc_dointvec NULL +#define proc_ipc_callback_dointvec NULL +#define proc_ipcauto_dointvec_minmax NULL +#endif + +#ifdef CONFIG_SYSCTL_SYSCALL +/* The generic sysctl ipc data routine. */ +static int sysctl_ipc_data(ctl_table *table, + void __user *oldval, size_t __user *oldlenp, + void __user *newval, size_t newlen) +{ + size_t len; + void *data; + + /* Get out of I don't have a variable */ + if (!table->data || !table->maxlen) + return -ENOTDIR; + + data = get_ipc(table); + if (!data) + return -ENOTDIR; + + if (oldval && oldlenp) { + if (get_user(len, oldlenp)) + return -EFAULT; + if (len) { + if (len > table->maxlen) + len = table->maxlen; + if (copy_to_user(oldval, data, len)) + return -EFAULT; + if (put_user(len, oldlenp)) + return -EFAULT; + } + } + + if (newval && newlen) { + if (newlen > table->maxlen) + newlen = table->maxlen; + + if (copy_from_user(data, newval, newlen)) + return -EFAULT; + } + return 1; +} + +static int sysctl_ipc_registered_data(ctl_table *table, + void __user *oldval, size_t __user *oldlenp, + void __user *newval, size_t newlen) +{ + int rc; + + rc = sysctl_ipc_data(table, oldval, oldlenp, newval, newlen); + + if (newval && newlen && rc > 0) + /* + * Tunable has successfully been changed from userland + */ + unregister_ipcns_notifier(current->nsproxy->ipc_ns); + + return rc; +} +#else +#define sysctl_ipc_data NULL +#define sysctl_ipc_registered_data NULL +#endif + +static int zero; +static int one = 1; + +static struct ctl_table ipc_kern_table[] = { + { + .ctl_name = KERN_SHMMAX, + .procname = "shmmax", + .data = &init_ipc_ns.shm_ctlmax, + .maxlen = sizeof (init_ipc_ns.shm_ctlmax), + .mode = 0644, + .proc_handler = proc_ipc_doulongvec_minmax, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = KERN_SHMALL, + .procname = "shmall", + .data = &init_ipc_ns.shm_ctlall, + .maxlen = sizeof (init_ipc_ns.shm_ctlall), + .mode = 0644, + .proc_handler = proc_ipc_doulongvec_minmax, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = KERN_SHMMNI, + .procname = "shmmni", + .data = &init_ipc_ns.shm_ctlmni, + .maxlen = sizeof (init_ipc_ns.shm_ctlmni), + .mode = 0644, + .proc_handler = proc_ipc_dointvec, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = KERN_MSGMAX, + .procname = "msgmax", + .data = &init_ipc_ns.msg_ctlmax, + .maxlen = sizeof (init_ipc_ns.msg_ctlmax), + .mode = 0644, + .proc_handler = proc_ipc_dointvec, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = KERN_MSGMNI, + .procname = "msgmni", + .data = &init_ipc_ns.msg_ctlmni, + .maxlen = sizeof (init_ipc_ns.msg_ctlmni), + .mode = 0644, + .proc_handler = proc_ipc_callback_dointvec, + .strategy = sysctl_ipc_registered_data, + }, + { + .ctl_name = KERN_MSGMNB, + .procname = "msgmnb", + .data = &init_ipc_ns.msg_ctlmnb, + .maxlen = sizeof (init_ipc_ns.msg_ctlmnb), + .mode = 0644, + .proc_handler = proc_ipc_dointvec, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = KERN_SEM, + .procname = "sem", + .data = &init_ipc_ns.sem_ctls, + .maxlen = 4*sizeof (int), + .mode = 0644, + .proc_handler = proc_ipc_dointvec, + .strategy = sysctl_ipc_data, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "auto_msgmni", + .data = &init_ipc_ns.auto_msgmni, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_ipcauto_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + {} +}; + +static struct ctl_table ipc_root_table[] = { + { + .ctl_name = CTL_KERN, + .procname = "kernel", + .mode = 0555, + .child = ipc_kern_table, + }, + {} +}; + +static int __init ipc_sysctl_init(void) +{ + register_sysctl_table(ipc_root_table); + return 0; +} + +__initcall(ipc_sysctl_init); diff --git a/ipc/ipcns_notifier.c b/ipc/ipcns_notifier.c new file mode 100644 index 0000000..b9b31a4 --- /dev/null +++ b/ipc/ipcns_notifier.c @@ -0,0 +1,92 @@ +/* + * linux/ipc/ipcns_notifier.c + * Copyright (C) 2007 BULL SA. Nadia Derbey + * + * Notification mechanism for ipc namespaces: + * The callback routine registered in the memory chain invokes the ipcns + * notifier chain with the IPCNS_MEMCHANGED event. + * Each callback routine registered in the ipcns namespace recomputes msgmni + * for the owning namespace. + */ + +#include <linux/msg.h> +#include <linux/rcupdate.h> +#include <linux/notifier.h> +#include <linux/nsproxy.h> +#include <linux/ipc_namespace.h> + +#include "util.h" + + + +static BLOCKING_NOTIFIER_HEAD(ipcns_chain); + + +static int ipcns_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + struct ipc_namespace *ns; + + switch (action) { + case IPCNS_MEMCHANGED: /* amount of lowmem has changed */ + case IPCNS_CREATED: + case IPCNS_REMOVED: + /* + * It's time to recompute msgmni + */ + ns = container_of(self, struct ipc_namespace, ipcns_nb); + /* + * No need to get a reference on the ns: the 1st job of + * free_ipc_ns() is to unregister the callback routine. + * blocking_notifier_chain_unregister takes the wr lock to do + * it. + * When this callback routine is called the rd lock is held by + * blocking_notifier_call_chain. + * So the ipc ns cannot be freed while we are here. + */ + recompute_msgmni(ns); + break; + default: + break; + } + + return NOTIFY_OK; +} + +int register_ipcns_notifier(struct ipc_namespace *ns) +{ + int rc; + + memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb)); + ns->ipcns_nb.notifier_call = ipcns_callback; + ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI; + rc = blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb); + if (!rc) + ns->auto_msgmni = 1; + return rc; +} + +int cond_register_ipcns_notifier(struct ipc_namespace *ns) +{ + int rc; + + memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb)); + ns->ipcns_nb.notifier_call = ipcns_callback; + ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI; + rc = blocking_notifier_chain_cond_register(&ipcns_chain, + &ns->ipcns_nb); + if (!rc) + ns->auto_msgmni = 1; + return rc; +} + +void unregister_ipcns_notifier(struct ipc_namespace *ns) +{ + blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb); + ns->auto_msgmni = 0; +} + +int ipcns_notify(unsigned long val) +{ + return blocking_notifier_call_chain(&ipcns_chain, val, NULL); +} diff --git a/ipc/mqueue.c b/ipc/mqueue.c new file mode 100644 index 0000000..0cefc8e --- /dev/null +++ b/ipc/mqueue.c @@ -0,0 +1,1294 @@ +/* + * POSIX message queues filesystem for Linux. + * + * Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl) + * Michal Wronski (michal.wronski@gmail.com) + * + * Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com) + * Lockless receive & send, fd based notify: + * Manfred Spraul (manfred@colorfullife.com) + * + * Audit: George Wilson (ltcgcw@us.ibm.com) + * + * This file is released under the GPL. + */ + +#include <linux/capability.h> +#include <linux/init.h> +#include <linux/pagemap.h> +#include <linux/file.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/sysctl.h> +#include <linux/poll.h> +#include <linux/mqueue.h> +#include <linux/msg.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/signal.h> +#include <linux/mutex.h> +#include <linux/nsproxy.h> +#include <linux/pid.h> + +#include <net/sock.h> +#include "util.h" + +#define MQUEUE_MAGIC 0x19800202 +#define DIRENT_SIZE 20 +#define FILENT_SIZE 80 + +#define SEND 0 +#define RECV 1 + +#define STATE_NONE 0 +#define STATE_PENDING 1 +#define STATE_READY 2 + +/* default values */ +#define DFLT_QUEUESMAX 256 /* max number of message queues */ +#define DFLT_MSGMAX 10 /* max number of messages in each queue */ +#define HARD_MSGMAX (131072/sizeof(void*)) +#define DFLT_MSGSIZEMAX 8192 /* max message size */ + +/* + * Define the ranges various user-specified maximum values can + * be set to. + */ +#define MIN_MSGMAX 1 /* min value for msg_max */ +#define MAX_MSGMAX HARD_MSGMAX /* max value for msg_max */ +#define MIN_MSGSIZEMAX 128 /* min value for msgsize_max */ +#define MAX_MSGSIZEMAX (8192*128) /* max value for msgsize_max */ + +struct ext_wait_queue { /* queue of sleeping tasks */ + struct task_struct *task; + struct list_head list; + struct msg_msg *msg; /* ptr of loaded message */ + int state; /* one of STATE_* values */ +}; + +struct mqueue_inode_info { + spinlock_t lock; + struct inode vfs_inode; + wait_queue_head_t wait_q; + + struct msg_msg **messages; + struct mq_attr attr; + + struct sigevent notify; + struct pid* notify_owner; + struct user_struct *user; /* user who created, for accounting */ + struct sock *notify_sock; + struct sk_buff *notify_cookie; + + /* for tasks waiting for free space and messages, respectively */ + struct ext_wait_queue e_wait_q[2]; + + unsigned long qsize; /* size of queue in memory (sum of all msgs) */ +}; + +static const struct inode_operations mqueue_dir_inode_operations; +static const struct file_operations mqueue_file_operations; +static struct super_operations mqueue_super_ops; +static void remove_notification(struct mqueue_inode_info *info); + +static spinlock_t mq_lock; +static struct kmem_cache *mqueue_inode_cachep; +static struct vfsmount *mqueue_mnt; + +static unsigned int queues_count; +static unsigned int queues_max = DFLT_QUEUESMAX; +static unsigned int msg_max = DFLT_MSGMAX; +static unsigned int msgsize_max = DFLT_MSGSIZEMAX; + +static struct ctl_table_header * mq_sysctl_table; + +static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode) +{ + return container_of(inode, struct mqueue_inode_info, vfs_inode); +} + +static struct inode *mqueue_get_inode(struct super_block *sb, int mode, + struct mq_attr *attr) +{ + struct inode *inode; + + inode = new_inode(sb); + if (inode) { + inode->i_mode = mode; + inode->i_uid = current->fsuid; + inode->i_gid = current->fsgid; + inode->i_blocks = 0; + inode->i_mtime = inode->i_ctime = inode->i_atime = + CURRENT_TIME; + + if (S_ISREG(mode)) { + struct mqueue_inode_info *info; + struct task_struct *p = current; + struct user_struct *u = p->user; + unsigned long mq_bytes, mq_msg_tblsz; + + inode->i_fop = &mqueue_file_operations; + inode->i_size = FILENT_SIZE; + /* mqueue specific info */ + info = MQUEUE_I(inode); + spin_lock_init(&info->lock); + init_waitqueue_head(&info->wait_q); + INIT_LIST_HEAD(&info->e_wait_q[0].list); + INIT_LIST_HEAD(&info->e_wait_q[1].list); + info->messages = NULL; + info->notify_owner = NULL; + info->qsize = 0; + info->user = NULL; /* set when all is ok */ + memset(&info->attr, 0, sizeof(info->attr)); + info->attr.mq_maxmsg = msg_max; + info->attr.mq_msgsize = msgsize_max; + if (attr) { + info->attr.mq_maxmsg = attr->mq_maxmsg; + info->attr.mq_msgsize = attr->mq_msgsize; + } + mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *); + mq_bytes = (mq_msg_tblsz + + (info->attr.mq_maxmsg * info->attr.mq_msgsize)); + + spin_lock(&mq_lock); + if (u->mq_bytes + mq_bytes < u->mq_bytes || + u->mq_bytes + mq_bytes > + p->signal->rlim[RLIMIT_MSGQUEUE].rlim_cur) { + spin_unlock(&mq_lock); + goto out_inode; + } + u->mq_bytes += mq_bytes; + spin_unlock(&mq_lock); + + info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL); + if (!info->messages) { + spin_lock(&mq_lock); + u->mq_bytes -= mq_bytes; + spin_unlock(&mq_lock); + goto out_inode; + } + /* all is ok */ + info->user = get_uid(u); + } else if (S_ISDIR(mode)) { + inc_nlink(inode); + /* Some things misbehave if size == 0 on a directory */ + inode->i_size = 2 * DIRENT_SIZE; + inode->i_op = &mqueue_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + } + } + return inode; +out_inode: + make_bad_inode(inode); + iput(inode); + return NULL; +} + +static int mqueue_fill_super(struct super_block *sb, void *data, int silent) +{ + struct inode *inode; + + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = MQUEUE_MAGIC; + sb->s_op = &mqueue_super_ops; + + inode = mqueue_get_inode(sb, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL); + if (!inode) + return -ENOMEM; + + sb->s_root = d_alloc_root(inode); + if (!sb->s_root) { + iput(inode); + return -ENOMEM; + } + + return 0; +} + +static int mqueue_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data, struct vfsmount *mnt) +{ + return get_sb_single(fs_type, flags, data, mqueue_fill_super, mnt); +} + +static void init_once(void *foo) +{ + struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo; + + inode_init_once(&p->vfs_inode); +} + +static struct inode *mqueue_alloc_inode(struct super_block *sb) +{ + struct mqueue_inode_info *ei; + + ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL); + if (!ei) + return NULL; + return &ei->vfs_inode; +} + +static void mqueue_destroy_inode(struct inode *inode) +{ + kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode)); +} + +static void mqueue_delete_inode(struct inode *inode) +{ + struct mqueue_inode_info *info; + struct user_struct *user; + unsigned long mq_bytes; + int i; + + if (S_ISDIR(inode->i_mode)) { + clear_inode(inode); + return; + } + info = MQUEUE_I(inode); + spin_lock(&info->lock); + for (i = 0; i < info->attr.mq_curmsgs; i++) + free_msg(info->messages[i]); + kfree(info->messages); + spin_unlock(&info->lock); + + clear_inode(inode); + + mq_bytes = (info->attr.mq_maxmsg * sizeof(struct msg_msg *) + + (info->attr.mq_maxmsg * info->attr.mq_msgsize)); + user = info->user; + if (user) { + spin_lock(&mq_lock); + user->mq_bytes -= mq_bytes; + queues_count--; + spin_unlock(&mq_lock); + free_uid(user); + } +} + +static int mqueue_create(struct inode *dir, struct dentry *dentry, + int mode, struct nameidata *nd) +{ + struct inode *inode; + struct mq_attr *attr = dentry->d_fsdata; + int error; + + spin_lock(&mq_lock); + if (queues_count >= queues_max && !capable(CAP_SYS_RESOURCE)) { + error = -ENOSPC; + goto out_lock; + } + queues_count++; + spin_unlock(&mq_lock); + + inode = mqueue_get_inode(dir->i_sb, mode, attr); + if (!inode) { + error = -ENOMEM; + spin_lock(&mq_lock); + queues_count--; + goto out_lock; + } + + dir->i_size += DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME; + + d_instantiate(dentry, inode); + dget(dentry); + return 0; +out_lock: + spin_unlock(&mq_lock); + return error; +} + +static int mqueue_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + + dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME; + dir->i_size -= DIRENT_SIZE; + drop_nlink(inode); + dput(dentry); + return 0; +} + +/* +* This is routine for system read from queue file. +* To avoid mess with doing here some sort of mq_receive we allow +* to read only queue size & notification info (the only values +* that are interesting from user point of view and aren't accessible +* through std routines) +*/ +static ssize_t mqueue_read_file(struct file *filp, char __user *u_data, + size_t count, loff_t *off) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode); + char buffer[FILENT_SIZE]; + ssize_t ret; + + spin_lock(&info->lock); + snprintf(buffer, sizeof(buffer), + "QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n", + info->qsize, + info->notify_owner ? info->notify.sigev_notify : 0, + (info->notify_owner && + info->notify.sigev_notify == SIGEV_SIGNAL) ? + info->notify.sigev_signo : 0, + pid_vnr(info->notify_owner)); + spin_unlock(&info->lock); + buffer[sizeof(buffer)-1] = '\0'; + + ret = simple_read_from_buffer(u_data, count, off, buffer, + strlen(buffer)); + if (ret <= 0) + return ret; + + filp->f_path.dentry->d_inode->i_atime = filp->f_path.dentry->d_inode->i_ctime = CURRENT_TIME; + return ret; +} + +static int mqueue_flush_file(struct file *filp, fl_owner_t id) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode); + + spin_lock(&info->lock); + if (task_tgid(current) == info->notify_owner) + remove_notification(info); + + spin_unlock(&info->lock); + return 0; +} + +static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode); + int retval = 0; + + poll_wait(filp, &info->wait_q, poll_tab); + + spin_lock(&info->lock); + if (info->attr.mq_curmsgs) + retval = POLLIN | POLLRDNORM; + + if (info->attr.mq_curmsgs < info->attr.mq_maxmsg) + retval |= POLLOUT | POLLWRNORM; + spin_unlock(&info->lock); + + return retval; +} + +/* Adds current to info->e_wait_q[sr] before element with smaller prio */ +static void wq_add(struct mqueue_inode_info *info, int sr, + struct ext_wait_queue *ewp) +{ + struct ext_wait_queue *walk; + + ewp->task = current; + + list_for_each_entry(walk, &info->e_wait_q[sr].list, list) { + if (walk->task->static_prio <= current->static_prio) { + list_add_tail(&ewp->list, &walk->list); + return; + } + } + list_add_tail(&ewp->list, &info->e_wait_q[sr].list); +} + +/* + * Puts current task to sleep. Caller must hold queue lock. After return + * lock isn't held. + * sr: SEND or RECV + */ +static int wq_sleep(struct mqueue_inode_info *info, int sr, + long timeout, struct ext_wait_queue *ewp) +{ + int retval; + signed long time; + + wq_add(info, sr, ewp); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + spin_unlock(&info->lock); + time = schedule_timeout(timeout); + + while (ewp->state == STATE_PENDING) + cpu_relax(); + + if (ewp->state == STATE_READY) { + retval = 0; + goto out; + } + spin_lock(&info->lock); + if (ewp->state == STATE_READY) { + retval = 0; + goto out_unlock; + } + if (signal_pending(current)) { + retval = -ERESTARTSYS; + break; + } + if (time == 0) { + retval = -ETIMEDOUT; + break; + } + } + list_del(&ewp->list); +out_unlock: + spin_unlock(&info->lock); +out: + return retval; +} + +/* + * Returns waiting task that should be serviced first or NULL if none exists + */ +static struct ext_wait_queue *wq_get_first_waiter( + struct mqueue_inode_info *info, int sr) +{ + struct list_head *ptr; + + ptr = info->e_wait_q[sr].list.prev; + if (ptr == &info->e_wait_q[sr].list) + return NULL; + return list_entry(ptr, struct ext_wait_queue, list); +} + +/* Auxiliary functions to manipulate messages' list */ +static void msg_insert(struct msg_msg *ptr, struct mqueue_inode_info *info) +{ + int k; + + k = info->attr.mq_curmsgs - 1; + while (k >= 0 && info->messages[k]->m_type >= ptr->m_type) { + info->messages[k + 1] = info->messages[k]; + k--; + } + info->attr.mq_curmsgs++; + info->qsize += ptr->m_ts; + info->messages[k + 1] = ptr; +} + +static inline struct msg_msg *msg_get(struct mqueue_inode_info *info) +{ + info->qsize -= info->messages[--info->attr.mq_curmsgs]->m_ts; + return info->messages[info->attr.mq_curmsgs]; +} + +static inline void set_cookie(struct sk_buff *skb, char code) +{ + ((char*)skb->data)[NOTIFY_COOKIE_LEN-1] = code; +} + +/* + * The next function is only to split too long sys_mq_timedsend + */ +static void __do_notify(struct mqueue_inode_info *info) +{ + /* notification + * invoked when there is registered process and there isn't process + * waiting synchronously for message AND state of queue changed from + * empty to not empty. Here we are sure that no one is waiting + * synchronously. */ + if (info->notify_owner && + info->attr.mq_curmsgs == 1) { + struct siginfo sig_i; + switch (info->notify.sigev_notify) { + case SIGEV_NONE: + break; + case SIGEV_SIGNAL: + /* sends signal */ + + sig_i.si_signo = info->notify.sigev_signo; + sig_i.si_errno = 0; + sig_i.si_code = SI_MESGQ; + sig_i.si_value = info->notify.sigev_value; + sig_i.si_pid = task_tgid_nr_ns(current, + ns_of_pid(info->notify_owner)); + sig_i.si_uid = current->uid; + + kill_pid_info(info->notify.sigev_signo, + &sig_i, info->notify_owner); + break; + case SIGEV_THREAD: + set_cookie(info->notify_cookie, NOTIFY_WOKENUP); + netlink_sendskb(info->notify_sock, info->notify_cookie); + break; + } + /* after notification unregisters process */ + put_pid(info->notify_owner); + info->notify_owner = NULL; + } + wake_up(&info->wait_q); +} + +static long prepare_timeout(const struct timespec __user *u_arg) +{ + struct timespec ts, nowts; + long timeout; + + if (u_arg) { + if (unlikely(copy_from_user(&ts, u_arg, + sizeof(struct timespec)))) + return -EFAULT; + + if (unlikely(ts.tv_nsec < 0 || ts.tv_sec < 0 + || ts.tv_nsec >= NSEC_PER_SEC)) + return -EINVAL; + nowts = CURRENT_TIME; + /* first subtract as jiffies can't be too big */ + ts.tv_sec -= nowts.tv_sec; + if (ts.tv_nsec < nowts.tv_nsec) { + ts.tv_nsec += NSEC_PER_SEC; + ts.tv_sec--; + } + ts.tv_nsec -= nowts.tv_nsec; + if (ts.tv_sec < 0) + return 0; + + timeout = timespec_to_jiffies(&ts) + 1; + } else + return MAX_SCHEDULE_TIMEOUT; + + return timeout; +} + +static void remove_notification(struct mqueue_inode_info *info) +{ + if (info->notify_owner != NULL && + info->notify.sigev_notify == SIGEV_THREAD) { + set_cookie(info->notify_cookie, NOTIFY_REMOVED); + netlink_sendskb(info->notify_sock, info->notify_cookie); + } + put_pid(info->notify_owner); + info->notify_owner = NULL; +} + +static int mq_attr_ok(struct mq_attr *attr) +{ + if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0) + return 0; + if (capable(CAP_SYS_RESOURCE)) { + if (attr->mq_maxmsg > HARD_MSGMAX) + return 0; + } else { + if (attr->mq_maxmsg > msg_max || + attr->mq_msgsize > msgsize_max) + return 0; + } + /* check for overflow */ + if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg) + return 0; + if ((unsigned long)(attr->mq_maxmsg * attr->mq_msgsize) + + (attr->mq_maxmsg * sizeof (struct msg_msg *)) < + (unsigned long)(attr->mq_maxmsg * attr->mq_msgsize)) + return 0; + return 1; +} + +/* + * Invoked when creating a new queue via sys_mq_open + */ +static struct file *do_create(struct dentry *dir, struct dentry *dentry, + int oflag, mode_t mode, struct mq_attr __user *u_attr) +{ + struct mq_attr attr; + struct file *result; + int ret; + + if (u_attr) { + ret = -EFAULT; + if (copy_from_user(&attr, u_attr, sizeof(attr))) + goto out; + ret = -EINVAL; + if (!mq_attr_ok(&attr)) + goto out; + /* store for use during create */ + dentry->d_fsdata = &attr; + } + + mode &= ~current->fs->umask; + ret = mnt_want_write(mqueue_mnt); + if (ret) + goto out; + ret = vfs_create(dir->d_inode, dentry, mode, NULL); + dentry->d_fsdata = NULL; + if (ret) + goto out_drop_write; + + result = dentry_open(dentry, mqueue_mnt, oflag); + /* + * dentry_open() took a persistent mnt_want_write(), + * so we can now drop this one. + */ + mnt_drop_write(mqueue_mnt); + return result; + +out_drop_write: + mnt_drop_write(mqueue_mnt); +out: + dput(dentry); + mntput(mqueue_mnt); + return ERR_PTR(ret); +} + +/* Opens existing queue */ +static struct file *do_open(struct dentry *dentry, int oflag) +{ +static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, + MAY_READ | MAY_WRITE }; + + if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) { + dput(dentry); + mntput(mqueue_mnt); + return ERR_PTR(-EINVAL); + } + + if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) { + dput(dentry); + mntput(mqueue_mnt); + return ERR_PTR(-EACCES); + } + + return dentry_open(dentry, mqueue_mnt, oflag); +} + +SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, mode_t, mode, + struct mq_attr __user *, u_attr) +{ + struct dentry *dentry; + struct file *filp; + char *name; + int fd, error; + + error = audit_mq_open(oflag, mode, u_attr); + if (error != 0) + return error; + + if (IS_ERR(name = getname(u_name))) + return PTR_ERR(name); + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + goto out_putname; + + mutex_lock(&mqueue_mnt->mnt_root->d_inode->i_mutex); + dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name)); + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); + goto out_err; + } + mntget(mqueue_mnt); + + if (oflag & O_CREAT) { + if (dentry->d_inode) { /* entry already exists */ + audit_inode(name, dentry); + error = -EEXIST; + if (oflag & O_EXCL) + goto out; + filp = do_open(dentry, oflag); + } else { + filp = do_create(mqueue_mnt->mnt_root, dentry, + oflag, mode, u_attr); + } + } else { + error = -ENOENT; + if (!dentry->d_inode) + goto out; + audit_inode(name, dentry); + filp = do_open(dentry, oflag); + } + + if (IS_ERR(filp)) { + error = PTR_ERR(filp); + goto out_putfd; + } + + fd_install(fd, filp); + goto out_upsem; + +out: + dput(dentry); + mntput(mqueue_mnt); +out_putfd: + put_unused_fd(fd); +out_err: + fd = error; +out_upsem: + mutex_unlock(&mqueue_mnt->mnt_root->d_inode->i_mutex); +out_putname: + putname(name); + return fd; +} + +SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) +{ + int err; + char *name; + struct dentry *dentry; + struct inode *inode = NULL; + + name = getname(u_name); + if (IS_ERR(name)) + return PTR_ERR(name); + + mutex_lock_nested(&mqueue_mnt->mnt_root->d_inode->i_mutex, + I_MUTEX_PARENT); + dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name)); + if (IS_ERR(dentry)) { + err = PTR_ERR(dentry); + goto out_unlock; + } + + if (!dentry->d_inode) { + err = -ENOENT; + goto out_err; + } + + inode = dentry->d_inode; + if (inode) + atomic_inc(&inode->i_count); + err = mnt_want_write(mqueue_mnt); + if (err) + goto out_err; + err = vfs_unlink(dentry->d_parent->d_inode, dentry); + mnt_drop_write(mqueue_mnt); +out_err: + dput(dentry); + +out_unlock: + mutex_unlock(&mqueue_mnt->mnt_root->d_inode->i_mutex); + putname(name); + if (inode) + iput(inode); + + return err; +} + +/* Pipelined send and receive functions. + * + * If a receiver finds no waiting message, then it registers itself in the + * list of waiting receivers. A sender checks that list before adding the new + * message into the message array. If there is a waiting receiver, then it + * bypasses the message array and directly hands the message over to the + * receiver. + * The receiver accepts the message and returns without grabbing the queue + * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers + * are necessary. The same algorithm is used for sysv semaphores, see + * ipc/sem.c for more details. + * + * The same algorithm is used for senders. + */ + +/* pipelined_send() - send a message directly to the task waiting in + * sys_mq_timedreceive() (without inserting message into a queue). + */ +static inline void pipelined_send(struct mqueue_inode_info *info, + struct msg_msg *message, + struct ext_wait_queue *receiver) +{ + receiver->msg = message; + list_del(&receiver->list); + receiver->state = STATE_PENDING; + wake_up_process(receiver->task); + smp_wmb(); + receiver->state = STATE_READY; +} + +/* pipelined_receive() - if there is task waiting in sys_mq_timedsend() + * gets its message and put to the queue (we have one free place for sure). */ +static inline void pipelined_receive(struct mqueue_inode_info *info) +{ + struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND); + + if (!sender) { + /* for poll */ + wake_up_interruptible(&info->wait_q); + return; + } + msg_insert(sender->msg, info); + list_del(&sender->list); + sender->state = STATE_PENDING; + wake_up_process(sender->task); + smp_wmb(); + sender->state = STATE_READY; +} + +SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, + size_t, msg_len, unsigned int, msg_prio, + const struct timespec __user *, u_abs_timeout) +{ + struct file *filp; + struct inode *inode; + struct ext_wait_queue wait; + struct ext_wait_queue *receiver; + struct msg_msg *msg_ptr; + struct mqueue_inode_info *info; + long timeout; + int ret; + + ret = audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout); + if (ret != 0) + return ret; + + if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX)) + return -EINVAL; + + timeout = prepare_timeout(u_abs_timeout); + + ret = -EBADF; + filp = fget(mqdes); + if (unlikely(!filp)) + goto out; + + inode = filp->f_path.dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + audit_inode(NULL, filp->f_path.dentry); + + if (unlikely(!(filp->f_mode & FMODE_WRITE))) + goto out_fput; + + if (unlikely(msg_len > info->attr.mq_msgsize)) { + ret = -EMSGSIZE; + goto out_fput; + } + + /* First try to allocate memory, before doing anything with + * existing queues. */ + msg_ptr = load_msg(u_msg_ptr, msg_len); + if (IS_ERR(msg_ptr)) { + ret = PTR_ERR(msg_ptr); + goto out_fput; + } + msg_ptr->m_ts = msg_len; + msg_ptr->m_type = msg_prio; + + spin_lock(&info->lock); + + if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) { + if (filp->f_flags & O_NONBLOCK) { + spin_unlock(&info->lock); + ret = -EAGAIN; + } else if (unlikely(timeout < 0)) { + spin_unlock(&info->lock); + ret = timeout; + } else { + wait.task = current; + wait.msg = (void *) msg_ptr; + wait.state = STATE_NONE; + ret = wq_sleep(info, SEND, timeout, &wait); + } + if (ret < 0) + free_msg(msg_ptr); + } else { + receiver = wq_get_first_waiter(info, RECV); + if (receiver) { + pipelined_send(info, msg_ptr, receiver); + } else { + /* adds message to the queue */ + msg_insert(msg_ptr, info); + __do_notify(info); + } + inode->i_atime = inode->i_mtime = inode->i_ctime = + CURRENT_TIME; + spin_unlock(&info->lock); + ret = 0; + } +out_fput: + fput(filp); +out: + return ret; +} + +SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, + size_t, msg_len, unsigned int __user *, u_msg_prio, + const struct timespec __user *, u_abs_timeout) +{ + long timeout; + ssize_t ret; + struct msg_msg *msg_ptr; + struct file *filp; + struct inode *inode; + struct mqueue_inode_info *info; + struct ext_wait_queue wait; + + ret = audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout); + if (ret != 0) + return ret; + + timeout = prepare_timeout(u_abs_timeout); + + ret = -EBADF; + filp = fget(mqdes); + if (unlikely(!filp)) + goto out; + + inode = filp->f_path.dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + audit_inode(NULL, filp->f_path.dentry); + + if (unlikely(!(filp->f_mode & FMODE_READ))) + goto out_fput; + + /* checks if buffer is big enough */ + if (unlikely(msg_len < info->attr.mq_msgsize)) { + ret = -EMSGSIZE; + goto out_fput; + } + + spin_lock(&info->lock); + if (info->attr.mq_curmsgs == 0) { + if (filp->f_flags & O_NONBLOCK) { + spin_unlock(&info->lock); + ret = -EAGAIN; + msg_ptr = NULL; + } else if (unlikely(timeout < 0)) { + spin_unlock(&info->lock); + ret = timeout; + msg_ptr = NULL; + } else { + wait.task = current; + wait.state = STATE_NONE; + ret = wq_sleep(info, RECV, timeout, &wait); + msg_ptr = wait.msg; + } + } else { + msg_ptr = msg_get(info); + + inode->i_atime = inode->i_mtime = inode->i_ctime = + CURRENT_TIME; + + /* There is now free space in queue. */ + pipelined_receive(info); + spin_unlock(&info->lock); + ret = 0; + } + if (ret == 0) { + ret = msg_ptr->m_ts; + + if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) || + store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) { + ret = -EFAULT; + } + free_msg(msg_ptr); + } +out_fput: + fput(filp); +out: + return ret; +} + +/* + * Notes: the case when user wants us to deregister (with NULL as pointer) + * and he isn't currently owner of notification, will be silently discarded. + * It isn't explicitly defined in the POSIX. + */ +SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes, + const struct sigevent __user *, u_notification) +{ + int ret; + struct file *filp; + struct sock *sock; + struct inode *inode; + struct sigevent notification; + struct mqueue_inode_info *info; + struct sk_buff *nc; + + ret = audit_mq_notify(mqdes, u_notification); + if (ret != 0) + return ret; + + nc = NULL; + sock = NULL; + if (u_notification != NULL) { + if (copy_from_user(¬ification, u_notification, + sizeof(struct sigevent))) + return -EFAULT; + + if (unlikely(notification.sigev_notify != SIGEV_NONE && + notification.sigev_notify != SIGEV_SIGNAL && + notification.sigev_notify != SIGEV_THREAD)) + return -EINVAL; + if (notification.sigev_notify == SIGEV_SIGNAL && + !valid_signal(notification.sigev_signo)) { + return -EINVAL; + } + if (notification.sigev_notify == SIGEV_THREAD) { + long timeo; + + /* create the notify skb */ + nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL); + ret = -ENOMEM; + if (!nc) + goto out; + ret = -EFAULT; + if (copy_from_user(nc->data, + notification.sigev_value.sival_ptr, + NOTIFY_COOKIE_LEN)) { + goto out; + } + + /* TODO: add a header? */ + skb_put(nc, NOTIFY_COOKIE_LEN); + /* and attach it to the socket */ +retry: + filp = fget(notification.sigev_signo); + ret = -EBADF; + if (!filp) + goto out; + sock = netlink_getsockbyfilp(filp); + fput(filp); + if (IS_ERR(sock)) { + ret = PTR_ERR(sock); + sock = NULL; + goto out; + } + + timeo = MAX_SCHEDULE_TIMEOUT; + ret = netlink_attachskb(sock, nc, &timeo, NULL); + if (ret == 1) + goto retry; + if (ret) { + sock = NULL; + nc = NULL; + goto out; + } + } + } + + ret = -EBADF; + filp = fget(mqdes); + if (!filp) + goto out; + + inode = filp->f_path.dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + + ret = 0; + spin_lock(&info->lock); + if (u_notification == NULL) { + if (info->notify_owner == task_tgid(current)) { + remove_notification(info); + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + } else if (info->notify_owner != NULL) { + ret = -EBUSY; + } else { + switch (notification.sigev_notify) { + case SIGEV_NONE: + info->notify.sigev_notify = SIGEV_NONE; + break; + case SIGEV_THREAD: + info->notify_sock = sock; + info->notify_cookie = nc; + sock = NULL; + nc = NULL; + info->notify.sigev_notify = SIGEV_THREAD; + break; + case SIGEV_SIGNAL: + info->notify.sigev_signo = notification.sigev_signo; + info->notify.sigev_value = notification.sigev_value; + info->notify.sigev_notify = SIGEV_SIGNAL; + break; + } + + info->notify_owner = get_pid(task_tgid(current)); + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + spin_unlock(&info->lock); +out_fput: + fput(filp); +out: + if (sock) { + netlink_detachskb(sock, nc); + } else if (nc) { + dev_kfree_skb(nc); + } + return ret; +} + +SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes, + const struct mq_attr __user *, u_mqstat, + struct mq_attr __user *, u_omqstat) +{ + int ret; + struct mq_attr mqstat, omqstat; + struct file *filp; + struct inode *inode; + struct mqueue_inode_info *info; + + if (u_mqstat != NULL) { + if (copy_from_user(&mqstat, u_mqstat, sizeof(struct mq_attr))) + return -EFAULT; + if (mqstat.mq_flags & (~O_NONBLOCK)) + return -EINVAL; + } + + ret = -EBADF; + filp = fget(mqdes); + if (!filp) + goto out; + + inode = filp->f_path.dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + + spin_lock(&info->lock); + + omqstat = info->attr; + omqstat.mq_flags = filp->f_flags & O_NONBLOCK; + if (u_mqstat) { + ret = audit_mq_getsetattr(mqdes, &mqstat); + if (ret != 0) { + spin_unlock(&info->lock); + goto out_fput; + } + if (mqstat.mq_flags & O_NONBLOCK) + filp->f_flags |= O_NONBLOCK; + else + filp->f_flags &= ~O_NONBLOCK; + + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + + spin_unlock(&info->lock); + + ret = 0; + if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat, + sizeof(struct mq_attr))) + ret = -EFAULT; + +out_fput: + fput(filp); +out: + return ret; +} + +static const struct inode_operations mqueue_dir_inode_operations = { + .lookup = simple_lookup, + .create = mqueue_create, + .unlink = mqueue_unlink, +}; + +static const struct file_operations mqueue_file_operations = { + .flush = mqueue_flush_file, + .poll = mqueue_poll_file, + .read = mqueue_read_file, +}; + +static struct super_operations mqueue_super_ops = { + .alloc_inode = mqueue_alloc_inode, + .destroy_inode = mqueue_destroy_inode, + .statfs = simple_statfs, + .delete_inode = mqueue_delete_inode, + .drop_inode = generic_delete_inode, +}; + +static struct file_system_type mqueue_fs_type = { + .name = "mqueue", + .get_sb = mqueue_get_sb, + .kill_sb = kill_litter_super, +}; + +static int msg_max_limit_min = MIN_MSGMAX; +static int msg_max_limit_max = MAX_MSGMAX; + +static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; +static int msg_maxsize_limit_max = MAX_MSGSIZEMAX; + +static ctl_table mq_sysctls[] = { + { + .procname = "queues_max", + .data = &queues_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .procname = "msg_max", + .data = &msg_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &msg_max_limit_min, + .extra2 = &msg_max_limit_max, + }, + { + .procname = "msgsize_max", + .data = &msgsize_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &msg_maxsize_limit_min, + .extra2 = &msg_maxsize_limit_max, + }, + { .ctl_name = 0 } +}; + +static ctl_table mq_sysctl_dir[] = { + { + .procname = "mqueue", + .mode = 0555, + .child = mq_sysctls, + }, + { .ctl_name = 0 } +}; + +static ctl_table mq_sysctl_root[] = { + { + .ctl_name = CTL_FS, + .procname = "fs", + .mode = 0555, + .child = mq_sysctl_dir, + }, + { .ctl_name = 0 } +}; + +static int __init init_mqueue_fs(void) +{ + int error; + + mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache", + sizeof(struct mqueue_inode_info), 0, + SLAB_HWCACHE_ALIGN, init_once); + if (mqueue_inode_cachep == NULL) + return -ENOMEM; + + /* ignore failues - they are not fatal */ + mq_sysctl_table = register_sysctl_table(mq_sysctl_root); + + error = register_filesystem(&mqueue_fs_type); + if (error) + goto out_sysctl; + + if (IS_ERR(mqueue_mnt = kern_mount(&mqueue_fs_type))) { + error = PTR_ERR(mqueue_mnt); + goto out_filesystem; + } + + /* internal initialization - not common for vfs */ + queues_count = 0; + spin_lock_init(&mq_lock); + + return 0; + +out_filesystem: + unregister_filesystem(&mqueue_fs_type); +out_sysctl: + if (mq_sysctl_table) + unregister_sysctl_table(mq_sysctl_table); + kmem_cache_destroy(mqueue_inode_cachep); + return error; +} + +__initcall(init_mqueue_fs); diff --git a/ipc/msg.c b/ipc/msg.c new file mode 100644 index 0000000..2ceab7f --- /dev/null +++ b/ipc/msg.c @@ -0,0 +1,944 @@ +/* + * 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 <dragos@iname.com> + * + * mostly rewritten, threaded and wake-one semantics added + * MSGMAX limit removed, sysctl's added + * (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#include <linux/capability.h> +#include <linux/slab.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.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 <asm/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 *volatile r_msg; +}; + +/* one msg_sender for each sleeping sender */ +struct msg_sender { + struct list_head list; + struct task_struct *tsk; +}; + +#define SEARCH_ANY 1 +#define SEARCH_EQUAL 2 +#define SEARCH_NOTEQUAL 3 +#define SEARCH_LESSEQUAL 4 + +#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS]) + +#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) + +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 + +/* + * 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); +} +#endif + +void __init msg_init(void) +{ + 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", + 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 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) +{ + struct msg_queue *msq; + int id, retval; + key_t key = params->key; + int msgflg = params->flg; + + msq = ipc_rcu_alloc(sizeof(*msq)); + if (!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); + if (retval) { + ipc_rcu_putref(msq); + return retval; + } + + /* + * 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 id; + } + + 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); + + msg_unlock(msq); + + return msq->q_perm.id; +} + +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); +} + +static inline void ss_del(struct msg_sender *mss) +{ + if (mss->list.next != NULL) + list_del(&mss->list); +} + +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); + tmp = tmp->next; + if (kill) + mss->list.next = NULL; + wake_up_process(mss->tsk); + } +} + +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); + tmp = tmp->next; + msr->r_msg = NULL; + wake_up_process(msr->r_tsk); + smp_mb(); + 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 IDR, and cleans up all the + * messages associated with this queue. + * + * 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 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); + 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); + + tmp = tmp->next; + atomic_dec(&ns->msg_hdrs); + free_msg(msg); + } + atomic_sub(msq->q_cbytes, &ns->msg_bytes); + security_msg_queue_free(msq); + ipc_rcu_putref(msq); +} + +/* + * Called with msg_ids.rw_mutex 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); +} + +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)); + 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 > USHORT_MAX) + out.msg_cbytes = USHORT_MAX; + else + out.msg_cbytes = in->msg_cbytes; + out.msg_lcbytes = in->msg_cbytes; + + if (in->msg_qnum > USHORT_MAX) + out.msg_qnum = USHORT_MAX; + else + out.msg_qnum = in->msg_qnum; + + if (in->msg_qbytes > USHORT_MAX) + out.msg_qbytes = USHORT_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; + } +} + +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; + } +} + +/* + * 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) +{ + struct kern_ipc_perm *ipcp; + struct msqid64_ds 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: + { + 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).rw_mutex); + 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).rw_mutex); + if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) + return -EFAULT; + return (max_id < 0) ? 0 : max_id; + } + 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) { + msq = msg_lock(ns, msqid); + if (IS_ERR(msq)) + return PTR_ERR(msq); + success_return = msq->q_perm.id; + } else { + 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)) + 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; + 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; + msg_unlock(msq); + if (copy_msqid_to_user(buf, &tbuf, version)) + return -EFAULT; + return success_return; + } + case IPC_SET: + case IPC_RMID: + err = msgctl_down(ns, msqid, cmd, buf, version); + return err; + default: + return -EINVAL; + } + +out_unlock: + msg_unlock(msq); + return err; +} + +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) + 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; +} + +static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) +{ + 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); + 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)) { + + list_del(&msr->r_list); + 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 = 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; + } + } + } + return 0; +} + +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; + + 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; + + msq = msg_lock_check(ns, msqid); + if (IS_ERR(msq)) { + err = PTR_ERR(msq); + goto out_free; + } + + for (;;) { + struct msg_sender s; + + err = -EACCES; + if (ipcperms(&msq->q_perm, S_IWUGO)) + goto out_unlock_free; + + err = security_msg_queue_msgsnd(msq, msg, msgflg); + if (err) + goto out_unlock_free; + + 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; + goto out_unlock_free; + } + ss_add(msq, &s); + ipc_rcu_getref(msq); + msg_unlock(msq); + schedule(); + + ipc_lock_by_ptr(&msq->q_perm); + ipc_rcu_putref(msq); + if (msq->q_perm.deleted) { + err = -EIDRM; + goto out_unlock_free; + } + ss_del(&s); + + if (signal_pending(current)) { + err = -ERESTARTNOHAND; + goto out_unlock_free; + } + } + + msq->q_lspid = task_tgid_vnr(current); + msq->q_stime = get_seconds(); + + if (!pipelined_send(msq, msg)) { + /* noone is waiting for this message, enqueue it */ + list_add_tail(&msg->m_list, &msq->q_messages); + msq->q_cbytes += msgsz; + msq->q_qnum++; + 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) + free_msg(msg); + return err; +} + +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). + */ + if (*msgtyp == 0) + return SEARCH_ANY; + if (*msgtyp < 0) { + *msgtyp = -*msgtyp; + return SEARCH_LESSEQUAL; + } + if (msgflg & MSG_EXCEPT) + return SEARCH_NOTEQUAL; + return SEARCH_EQUAL; +} + +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); + ns = current->nsproxy->ipc_ns; + + msq = msg_lock_check(ns, msqid); + if (IS_ERR(msq)) + return PTR_ERR(msq); + + for (;;) { + struct msg_receiver msr_d; + struct list_head *tmp; + + msg = ERR_PTR(-EACCES); + 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)) { + + msg = walk_msg; + if (mode == SEARCH_LESSEQUAL && + walk_msg->m_type != 1) { + msg = walk_msg; + msgtyp = walk_msg->m_type - 1; + } else { + msg = walk_msg; + break; + } + } + tmp = tmp->next; + } + 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; + } + list_del(&msg->m_list); + msq->q_qnum--; + msq->q_rtime = get_seconds(); + msq->q_lrpid = task_tgid_vnr(current); + msq->q_cbytes -= msg->m_ts; + atomic_sub(msg->m_ts, &ns->msg_bytes); + atomic_dec(&ns->msg_hdrs); + ss_wakeup(&msq->q_senders, 0); + msg_unlock(msq); + break; + } + /* No message waiting. Wait for a message */ + if (msgflg & IPC_NOWAIT) { + msg = ERR_PTR(-ENOMSG); + goto out_unlock; + } + 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) + msr_d.r_maxsize = INT_MAX; + else + msr_d.r_maxsize = msgsz; + msr_d.r_msg = ERR_PTR(-EAGAIN); + current->state = TASK_INTERRUPTIBLE; + msg_unlock(msq); + + schedule(); + + /* Lockless receive, part 1: + * Disable preemption. We don't hold a reference to the queue + * and getting a reference would defeat the idea of a lockless + * operation, thus the code relies on rcu to guarantee the + * existance of msq: + * Prior to destruction, expunge_all(-EIRDM) changes r_msg. + * Thus if r_msg is -EAGAIN, then the queue not yet destroyed. + * rcu_read_lock() prevents preemption between reading r_msg + * and the spin_lock() inside ipc_lock_by_ptr(). + */ + rcu_read_lock(); + + /* Lockless receive, part 2: + * Wait until pipelined_send or expunge_all are outside of + * wake_up_process(). There is a race with exit(), see + * ipc/mqueue.c for the details. + */ + msg = (struct msg_msg*)msr_d.r_msg; + while (msg == NULL) { + cpu_relax(); + 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)) { + rcu_read_unlock(); + break; + } + + /* Lockless receive, part 3: + * Acquire the queue spinlock. + */ + ipc_lock_by_ptr(&msq->q_perm); + rcu_read_unlock(); + + /* Lockless receive, part 4: + * Repeat test after acquiring the spinlock. + */ + msg = (struct msg_msg*)msr_d.r_msg; + if (msg != ERR_PTR(-EAGAIN)) + goto out_unlock; + + list_del(&msr_d.r_list); + if (signal_pending(current)) { + msg = ERR_PTR(-ERESTARTNOHAND); +out_unlock: + msg_unlock(msq); + break; + } + } + if (IS_ERR(msg)) + return PTR_ERR(msg); + + msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz; + *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_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 diff --git a/ipc/msgutil.c b/ipc/msgutil.c new file mode 100644 index 0000000..c82c215 --- /dev/null +++ b/ipc/msgutil.c @@ -0,0 +1,127 @@ +/* + * linux/ipc/msgutil.c + * Copyright (C) 1999, 2004 Manfred Spraul + * + * This file is released under GNU General Public Licence version 2 or + * (at your option) any later version. + * + * See the file COPYING for more details. + */ + +#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/security.h> +#include <linux/slab.h> +#include <linux/ipc.h> +#include <asm/uaccess.h> + +#include "util.h" + +struct msg_msgseg { + struct msg_msgseg* next; + /* the next part of the message follows immediately */ +}; + +#define DATALEN_MSG (PAGE_SIZE-sizeof(struct msg_msg)) +#define DATALEN_SEG (PAGE_SIZE-sizeof(struct msg_msgseg)) + +struct msg_msg *load_msg(const void __user *src, int len) +{ + struct msg_msg *msg; + struct msg_msgseg **pseg; + int err; + int alen; + + alen = len; + if (alen > DATALEN_MSG) + alen = DATALEN_MSG; + + msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL); + if (msg == NULL) + return ERR_PTR(-ENOMEM); + + msg->next = NULL; + msg->security = NULL; + + if (copy_from_user(msg + 1, src, alen)) { + err = -EFAULT; + goto out_err; + } + + len -= alen; + src = ((char __user *)src) + alen; + pseg = &msg->next; + while (len > 0) { + struct msg_msgseg *seg; + alen = len; + if (alen > DATALEN_SEG) + alen = DATALEN_SEG; + seg = kmalloc(sizeof(*seg) + alen, + GFP_KERNEL); + if (seg == NULL) { + err = -ENOMEM; + goto out_err; + } + *pseg = seg; + seg->next = NULL; + if (copy_from_user(seg + 1, src, alen)) { + err = -EFAULT; + goto out_err; + } + pseg = &seg->next; + len -= alen; + src = ((char __user *)src) + alen; + } + + err = security_msg_msg_alloc(msg); + if (err) + goto out_err; + + return msg; + +out_err: + free_msg(msg); + return ERR_PTR(err); +} + +int store_msg(void __user *dest, struct msg_msg *msg, int len) +{ + int alen; + struct msg_msgseg *seg; + + alen = len; + if (alen > DATALEN_MSG) + alen = DATALEN_MSG; + if (copy_to_user(dest, msg + 1, alen)) + return -1; + + len -= alen; + dest = ((char __user *)dest) + alen; + seg = msg->next; + while (len > 0) { + alen = len; + if (alen > DATALEN_SEG) + alen = DATALEN_SEG; + if (copy_to_user(dest, seg + 1, alen)) + return -1; + len -= alen; + dest = ((char __user *)dest) + alen; + seg = seg->next; + } + return 0; +} + +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; + kfree(seg); + seg = tmp; + } +} diff --git a/ipc/namespace.c b/ipc/namespace.c new file mode 100644 index 0000000..9171d94 --- /dev/null +++ b/ipc/namespace.c @@ -0,0 +1,112 @@ +/* + * linux/ipc/namespace.c + * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc. + */ + +#include <linux/ipc.h> +#include <linux/msg.h> +#include <linux/ipc_namespace.h> +#include <linux/rcupdate.h> +#include <linux/nsproxy.h> +#include <linux/slab.h> + +#include "util.h" + +static struct ipc_namespace *clone_ipc_ns(struct ipc_namespace *old_ns) +{ + struct ipc_namespace *ns; + + ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL); + if (ns == NULL) + return ERR_PTR(-ENOMEM); + + atomic_inc(&nr_ipc_ns); + + sem_init_ns(ns); + msg_init_ns(ns); + shm_init_ns(ns); + + /* + * msgmni has already been computed for the new ipc ns. + * Thus, do the ipcns creation notification before registering that + * new ipcns in the chain. + */ + ipcns_notify(IPCNS_CREATED); + register_ipcns_notifier(ns); + + kref_init(&ns->kref); + return ns; +} + +struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns) +{ + struct ipc_namespace *new_ns; + + BUG_ON(!ns); + get_ipc_ns(ns); + + if (!(flags & CLONE_NEWIPC)) + return ns; + + new_ns = clone_ipc_ns(ns); + + put_ipc_ns(ns); + return new_ns; +} + +/* + * free_ipcs - free all ipcs of one type + * @ns: the namespace to remove the ipcs from + * @ids: the table of ipcs to free + * @free: the function called to free each individual ipc + * + * Called for each kind of ipc when an ipc_namespace exits. + */ +void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, + void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)) +{ + struct kern_ipc_perm *perm; + int next_id; + int total, in_use; + + down_write(&ids->rw_mutex); + + in_use = ids->in_use; + + for (total = 0, next_id = 0; total < in_use; next_id++) { + perm = idr_find(&ids->ipcs_idr, next_id); + if (perm == NULL) + continue; + ipc_lock_by_ptr(perm); + free(ns, perm); + total++; + } + up_write(&ids->rw_mutex); +} + +void free_ipc_ns(struct kref *kref) +{ + struct ipc_namespace *ns; + + ns = container_of(kref, struct ipc_namespace, kref); + /* + * Unregistering the hotplug notifier at the beginning guarantees + * that the ipc namespace won't be freed while we are inside the + * callback routine. Since the blocking_notifier_chain_XXX routines + * hold a rw lock on the notifier list, unregister_ipcns_notifier() + * won't take the rw lock before blocking_notifier_call_chain() has + * released the rd lock. + */ + unregister_ipcns_notifier(ns); + sem_exit_ns(ns); + msg_exit_ns(ns); + shm_exit_ns(ns); + kfree(ns); + atomic_dec(&nr_ipc_ns); + + /* + * Do the ipcns removal notification after decrementing nr_ipc_ns in + * order to have a correct value when recomputing msgmni. + */ + ipcns_notify(IPCNS_REMOVED); +} diff --git a/ipc/sem.c b/ipc/sem.c new file mode 100644 index 0000000..4d842a5 --- /dev/null +++ b/ipc/sem.c @@ -0,0 +1,1381 @@ +/* + * linux/ipc/sem.c + * Copyright (C) 1992 Krishna Balasubramanian + * Copyright (C) 1995 Eric Schenk, Bruno Haible + * + * IMPLEMENTATION NOTES ON CODE REWRITE (Eric Schenk, January 1995): + * This code underwent a massive rewrite in order to solve some problems + * with the original code. In particular the original code failed to + * wake up processes that were waiting for semval to go to 0 if the + * value went to 0 and was then incremented rapidly enough. In solving + * this problem I have also modified the implementation so that it + * processes pending operations in a FIFO manner, thus give a guarantee + * that processes waiting for a lock on the semaphore won't starve + * unless another locking process fails to unlock. + * In addition the following two changes in behavior have been introduced: + * - The original implementation of semop returned the value + * last semaphore element examined on success. This does not + * match the manual page specifications, and effectively + * allows the user to read the semaphore even if they do not + * have read permissions. The implementation now returns 0 + * on success as stated in the manual page. + * - There is some confusion over whether the set of undo adjustments + * to be performed at exit should be done in an atomic manner. + * That is, if we are attempting to decrement the semval should we queue + * up and wait until we can do so legally? + * The original implementation attempted to do this. + * The current implementation does not do so. This is because I don't + * think it is the right thing (TM) to do, and because I couldn't + * see a clean way to get the old behavior with the new design. + * The POSIX standard and SVID should be consulted to determine + * what behavior is mandated. + * + * Further notes on refinement (Christoph Rohland, December 1998): + * - The POSIX standard says, that the undo adjustments simply should + * redo. So the current implementation is o.K. + * - The previous code had two flaws: + * 1) It actively gave the semaphore to the next waiting process + * sleeping on the semaphore. Since this process did not have the + * cpu this led to many unnecessary context switches and bad + * performance. Now we only check which process should be able to + * get the semaphore and if this process wants to reduce some + * semaphore value we simply wake it up without doing the + * operation. So it has to try to get it later. Thus e.g. the + * running process may reacquire the semaphore during the current + * time slice. If it only waits for zero or increases the semaphore, + * we do the operation in advance and wake it up. + * 2) It did not wake up all zero waiting processes. We try to do + * better but only get the semops right which only wait for zero or + * increase. If there are decrement operations in the operations + * array we do the same as before. + * + * With the incarnation of O(1) scheduler, it becomes unnecessary to perform + * check/retry algorithm for waking up blocked processes as the new scheduler + * is better at handling thread switch than the old one. + * + * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com> + * + * SMP-threaded, sysctl's added + * (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * Enforced range limit on SEM_UNDO + * (c) 2001 Red Hat Inc <alan@redhat.com> + * Lockless wakeup + * (c) 2003 Manfred Spraul <manfred@colorfullife.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/time.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/capability.h> +#include <linux/seq_file.h> +#include <linux/rwsem.h> +#include <linux/nsproxy.h> +#include <linux/ipc_namespace.h> + +#include <asm/uaccess.h> +#include "util.h" + +#define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS]) + +#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm) +#define sem_checkid(sma, semid) ipc_checkid(&sma->sem_perm, semid) + +static int newary(struct ipc_namespace *, struct ipc_params *); +static void freeary(struct ipc_namespace *, struct kern_ipc_perm *); +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_proc_show(struct seq_file *s, void *it); +#endif + +#define SEMMSL_FAST 256 /* 512 bytes on stack */ +#define SEMOPM_FAST 64 /* ~ 372 bytes on stack */ + +/* + * linked list protection: + * sem_undo.id_next, + * sem_array.sem_pending{,last}, + * sem_array.sem_undo: sem_lock() for read/write + * sem_undo.proc_next: only "current" is allowed to read/write that field. + * + */ + +#define sc_semmsl sem_ctls[0] +#define sc_semmns sem_ctls[1] +#define sc_semopm sem_ctls[2] +#define sc_semmni sem_ctls[3] + +void sem_init_ns(struct ipc_namespace *ns) +{ + ns->sc_semmsl = SEMMSL; + ns->sc_semmns = SEMMNS; + ns->sc_semopm = SEMOPM; + ns->sc_semmni = SEMMNI; + ns->used_sems = 0; + ipc_init_ids(&ns->ids[IPC_SEM_IDS]); +} + +#ifdef CONFIG_IPC_NS +void sem_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &sem_ids(ns), freeary); +} +#endif + +void __init sem_init (void) +{ + sem_init_ns(&init_ipc_ns); + ipc_init_proc_interface("sysvipc/sem", + " key semid perms nsems uid gid cuid cgid otime ctime\n", + IPC_SEM_IDS, sysvipc_sem_proc_show); +} + +/* + * sem_lock_(check_) routines are called in the paths where the rw_mutex + * is not held. + */ +static inline struct sem_array *sem_lock(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock(&sem_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct sem_array *)ipcp; + + return container_of(ipcp, struct sem_array, sem_perm); +} + +static inline struct sem_array *sem_lock_check(struct ipc_namespace *ns, + int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock_check(&sem_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct sem_array *)ipcp; + + return container_of(ipcp, struct sem_array, sem_perm); +} + +static inline void sem_lock_and_putref(struct sem_array *sma) +{ + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); +} + +static inline void sem_getref_and_unlock(struct sem_array *sma) +{ + ipc_rcu_getref(sma); + ipc_unlock(&(sma)->sem_perm); +} + +static inline void sem_putref(struct sem_array *sma) +{ + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + ipc_unlock(&(sma)->sem_perm); +} + +static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) +{ + ipc_rmid(&sem_ids(ns), &s->sem_perm); +} + +/* + * Lockless wakeup algorithm: + * Without the check/retry algorithm a lockless wakeup is possible: + * - queue.status is initialized to -EINTR before blocking. + * - wakeup is performed by + * * unlinking the queue entry from sma->sem_pending + * * setting queue.status to IN_WAKEUP + * This is the notification for the blocked thread that a + * result value is imminent. + * * call wake_up_process + * * set queue.status to the final value. + * - the previously blocked thread checks queue.status: + * * if it's IN_WAKEUP, then it must wait until the value changes + * * if it's not -EINTR, then the operation was completed by + * update_queue. semtimedop can return queue.status without + * performing any operation on the sem array. + * * otherwise it must acquire the spinlock and check what's up. + * + * The two-stage algorithm is necessary to protect against the following + * races: + * - if queue.status is set after wake_up_process, then the woken up idle + * thread could race forward and try (and fail) to acquire sma->lock + * before update_queue had a chance to set queue.status + * - if queue.status is written before wake_up_process and if the + * blocked process is woken up by a signal between writing + * queue.status and the wake_up_process, then the woken up + * process could return from semtimedop and die by calling + * sys_exit before wake_up_process is called. Then wake_up_process + * will oops, because the task structure is already invalid. + * (yes, this happened on s390 with sysv msg). + * + */ +#define IN_WAKEUP 1 + +/** + * newary - Create a new semaphore set + * @ns: namespace + * @params: ptr to the structure that contains key, semflg and nsems + * + * Called with sem_ids.rw_mutex held (as a writer) + */ + +static int newary(struct ipc_namespace *ns, struct ipc_params *params) +{ + int id; + int retval; + struct sem_array *sma; + int size; + key_t key = params->key; + int nsems = params->u.nsems; + int semflg = params->flg; + + if (!nsems) + return -EINVAL; + if (ns->used_sems + nsems > ns->sc_semmns) + return -ENOSPC; + + size = sizeof (*sma) + nsems * sizeof (struct sem); + sma = ipc_rcu_alloc(size); + if (!sma) { + return -ENOMEM; + } + memset (sma, 0, size); + + sma->sem_perm.mode = (semflg & S_IRWXUGO); + sma->sem_perm.key = key; + + sma->sem_perm.security = NULL; + retval = security_sem_alloc(sma); + if (retval) { + ipc_rcu_putref(sma); + return retval; + } + + id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); + if (id < 0) { + security_sem_free(sma); + ipc_rcu_putref(sma); + return id; + } + ns->used_sems += nsems; + + sma->sem_base = (struct sem *) &sma[1]; + INIT_LIST_HEAD(&sma->sem_pending); + INIT_LIST_HEAD(&sma->list_id); + sma->sem_nsems = nsems; + sma->sem_ctime = get_seconds(); + sem_unlock(sma); + + return sma->sem_perm.id; +} + + +/* + * Called with sem_ids.rw_mutex and ipcp locked. + */ +static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg) +{ + struct sem_array *sma; + + sma = container_of(ipcp, struct sem_array, sem_perm); + return security_sem_associate(sma, semflg); +} + +/* + * Called with sem_ids.rw_mutex and ipcp locked. + */ +static inline int sem_more_checks(struct kern_ipc_perm *ipcp, + struct ipc_params *params) +{ + struct sem_array *sma; + + sma = container_of(ipcp, struct sem_array, sem_perm); + if (params->u.nsems > sma->sem_nsems) + return -EINVAL; + + return 0; +} + +SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) +{ + struct ipc_namespace *ns; + struct ipc_ops sem_ops; + struct ipc_params sem_params; + + ns = current->nsproxy->ipc_ns; + + if (nsems < 0 || nsems > ns->sc_semmsl) + return -EINVAL; + + sem_ops.getnew = newary; + sem_ops.associate = sem_security; + sem_ops.more_checks = sem_more_checks; + + sem_params.key = key; + sem_params.flg = semflg; + sem_params.u.nsems = nsems; + + return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); +} + +/* + * Determine whether a sequence of semaphore operations would succeed + * all at once. Return 0 if yes, 1 if need to sleep, else return error code. + */ + +static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops, + int nsops, struct sem_undo *un, int pid) +{ + int result, sem_op; + struct sembuf *sop; + struct sem * curr; + + for (sop = sops; sop < sops + nsops; sop++) { + curr = sma->sem_base + sop->sem_num; + sem_op = sop->sem_op; + result = curr->semval; + + if (!sem_op && result) + goto would_block; + + result += sem_op; + if (result < 0) + goto would_block; + if (result > SEMVMX) + goto out_of_range; + if (sop->sem_flg & SEM_UNDO) { + int undo = un->semadj[sop->sem_num] - sem_op; + /* + * Exceeding the undo range is an error. + */ + if (undo < (-SEMAEM - 1) || undo > SEMAEM) + goto out_of_range; + } + curr->semval = result; + } + + sop--; + while (sop >= sops) { + sma->sem_base[sop->sem_num].sempid = pid; + if (sop->sem_flg & SEM_UNDO) + un->semadj[sop->sem_num] -= sop->sem_op; + sop--; + } + + sma->sem_otime = get_seconds(); + return 0; + +out_of_range: + result = -ERANGE; + goto undo; + +would_block: + if (sop->sem_flg & IPC_NOWAIT) + result = -EAGAIN; + else + result = 1; + +undo: + sop--; + while (sop >= sops) { + sma->sem_base[sop->sem_num].semval -= sop->sem_op; + sop--; + } + + return result; +} + +/* Go through the pending queue for the indicated semaphore + * looking for tasks that can be completed. + */ +static void update_queue (struct sem_array * sma) +{ + int error; + struct sem_queue * q; + + q = list_entry(sma->sem_pending.next, struct sem_queue, list); + while (&q->list != &sma->sem_pending) { + error = try_atomic_semop(sma, q->sops, q->nsops, + q->undo, q->pid); + + /* Does q->sleeper still need to sleep? */ + if (error <= 0) { + struct sem_queue *n; + + /* + * Continue scanning. The next operation + * that must be checked depends on the type of the + * completed operation: + * - if the operation modified the array, then + * restart from the head of the queue and + * check for threads that might be waiting + * for semaphore values to become 0. + * - if the operation didn't modify the array, + * then just continue. + * The order of list_del() and reading ->next + * is crucial: In the former case, the list_del() + * must be done first [because we might be the + * first entry in ->sem_pending], in the latter + * case the list_del() must be done last + * [because the list is invalid after the list_del()] + */ + if (q->alter) { + list_del(&q->list); + n = list_entry(sma->sem_pending.next, + struct sem_queue, list); + } else { + n = list_entry(q->list.next, struct sem_queue, + list); + list_del(&q->list); + } + + /* wake up the waiting thread */ + q->status = IN_WAKEUP; + + wake_up_process(q->sleeper); + /* hands-off: q will disappear immediately after + * writing q->status. + */ + smp_wmb(); + q->status = error; + q = n; + } else { + q = list_entry(q->list.next, struct sem_queue, list); + } + } +} + +/* The following counts are associated to each semaphore: + * semncnt number of tasks waiting on semval being nonzero + * semzcnt number of tasks waiting on semval being zero + * This model assumes that a task waits on exactly one semaphore. + * Since semaphore operations are to be performed atomically, tasks actually + * wait on a whole sequence of semaphores simultaneously. + * The counts we return here are a rough approximation, but still + * warrant that semncnt+semzcnt>0 if the task is on the pending queue. + */ +static int count_semncnt (struct sem_array * sma, ushort semnum) +{ + int semncnt; + struct sem_queue * q; + + semncnt = 0; + list_for_each_entry(q, &sma->sem_pending, list) { + struct sembuf * sops = q->sops; + int nsops = q->nsops; + int i; + for (i = 0; i < nsops; i++) + if (sops[i].sem_num == semnum + && (sops[i].sem_op < 0) + && !(sops[i].sem_flg & IPC_NOWAIT)) + semncnt++; + } + return semncnt; +} + +static int count_semzcnt (struct sem_array * sma, ushort semnum) +{ + int semzcnt; + struct sem_queue * q; + + semzcnt = 0; + list_for_each_entry(q, &sma->sem_pending, list) { + struct sembuf * sops = q->sops; + int nsops = q->nsops; + int i; + for (i = 0; i < nsops; i++) + if (sops[i].sem_num == semnum + && (sops[i].sem_op == 0) + && !(sops[i].sem_flg & IPC_NOWAIT)) + semzcnt++; + } + return semzcnt; +} + +static void free_un(struct rcu_head *head) +{ + struct sem_undo *un = container_of(head, struct sem_undo, rcu); + kfree(un); +} + +/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked + * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex + * remains locked on exit. + */ +static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) +{ + struct sem_undo *un, *tu; + struct sem_queue *q, *tq; + struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); + + /* Free the existing undo structures for this semaphore set. */ + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { + list_del(&un->list_id); + spin_lock(&un->ulp->lock); + un->semid = -1; + list_del_rcu(&un->list_proc); + spin_unlock(&un->ulp->lock); + call_rcu(&un->rcu, free_un); + } + + /* Wake up all pending processes and let them fail with EIDRM. */ + list_for_each_entry_safe(q, tq, &sma->sem_pending, list) { + list_del(&q->list); + + q->status = IN_WAKEUP; + wake_up_process(q->sleeper); /* doesn't sleep */ + smp_wmb(); + q->status = -EIDRM; /* hands-off q */ + } + + /* Remove the semaphore set from the IDR */ + sem_rmid(ns, sma); + sem_unlock(sma); + + ns->used_sems -= sma->sem_nsems; + security_sem_free(sma); + ipc_rcu_putref(sma); +} + +static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) +{ + switch(version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct semid_ds out; + + ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm); + + out.sem_otime = in->sem_otime; + out.sem_ctime = in->sem_ctime; + out.sem_nsems = in->sem_nsems; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +static int semctl_nolock(struct ipc_namespace *ns, int semid, + int cmd, int version, union semun arg) +{ + int err = -EINVAL; + struct sem_array *sma; + + switch(cmd) { + case IPC_INFO: + case SEM_INFO: + { + struct seminfo seminfo; + int max_id; + + err = security_sem_semctl(NULL, cmd); + if (err) + return err; + + memset(&seminfo,0,sizeof(seminfo)); + seminfo.semmni = ns->sc_semmni; + seminfo.semmns = ns->sc_semmns; + seminfo.semmsl = ns->sc_semmsl; + seminfo.semopm = ns->sc_semopm; + seminfo.semvmx = SEMVMX; + seminfo.semmnu = SEMMNU; + seminfo.semmap = SEMMAP; + seminfo.semume = SEMUME; + down_read(&sem_ids(ns).rw_mutex); + if (cmd == SEM_INFO) { + seminfo.semusz = sem_ids(ns).in_use; + seminfo.semaem = ns->used_sems; + } else { + seminfo.semusz = SEMUSZ; + seminfo.semaem = SEMAEM; + } + max_id = ipc_get_maxid(&sem_ids(ns)); + up_read(&sem_ids(ns).rw_mutex); + if (copy_to_user (arg.__buf, &seminfo, sizeof(struct seminfo))) + return -EFAULT; + return (max_id < 0) ? 0: max_id; + } + case IPC_STAT: + case SEM_STAT: + { + struct semid64_ds tbuf; + int id; + + if (cmd == SEM_STAT) { + sma = sem_lock(ns, semid); + if (IS_ERR(sma)) + return PTR_ERR(sma); + id = sma->sem_perm.id; + } else { + sma = sem_lock_check(ns, semid); + if (IS_ERR(sma)) + return PTR_ERR(sma); + id = 0; + } + + err = -EACCES; + if (ipcperms (&sma->sem_perm, S_IRUGO)) + goto out_unlock; + + err = security_sem_semctl(sma, cmd); + if (err) + goto out_unlock; + + memset(&tbuf, 0, sizeof(tbuf)); + + kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm); + tbuf.sem_otime = sma->sem_otime; + tbuf.sem_ctime = sma->sem_ctime; + tbuf.sem_nsems = sma->sem_nsems; + sem_unlock(sma); + if (copy_semid_to_user (arg.buf, &tbuf, version)) + return -EFAULT; + return id; + } + default: + return -EINVAL; + } + return err; +out_unlock: + sem_unlock(sma); + return err; +} + +static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, + int cmd, int version, union semun arg) +{ + struct sem_array *sma; + struct sem* curr; + int err; + ushort fast_sem_io[SEMMSL_FAST]; + ushort* sem_io = fast_sem_io; + int nsems; + + sma = sem_lock_check(ns, semid); + if (IS_ERR(sma)) + return PTR_ERR(sma); + + nsems = sma->sem_nsems; + + err = -EACCES; + if (ipcperms (&sma->sem_perm, (cmd==SETVAL||cmd==SETALL)?S_IWUGO:S_IRUGO)) + goto out_unlock; + + err = security_sem_semctl(sma, cmd); + if (err) + goto out_unlock; + + err = -EACCES; + switch (cmd) { + case GETALL: + { + ushort __user *array = arg.array; + int i; + + if(nsems > SEMMSL_FAST) { + sem_getref_and_unlock(sma); + + sem_io = ipc_alloc(sizeof(ushort)*nsems); + if(sem_io == NULL) { + sem_putref(sma); + return -ENOMEM; + } + + sem_lock_and_putref(sma); + if (sma->sem_perm.deleted) { + sem_unlock(sma); + err = -EIDRM; + goto out_free; + } + } + + for (i = 0; i < sma->sem_nsems; i++) + sem_io[i] = sma->sem_base[i].semval; + sem_unlock(sma); + err = 0; + if(copy_to_user(array, sem_io, nsems*sizeof(ushort))) + err = -EFAULT; + goto out_free; + } + case SETALL: + { + int i; + struct sem_undo *un; + + sem_getref_and_unlock(sma); + + if(nsems > SEMMSL_FAST) { + sem_io = ipc_alloc(sizeof(ushort)*nsems); + if(sem_io == NULL) { + sem_putref(sma); + return -ENOMEM; + } + } + + if (copy_from_user (sem_io, arg.array, nsems*sizeof(ushort))) { + sem_putref(sma); + err = -EFAULT; + goto out_free; + } + + for (i = 0; i < nsems; i++) { + if (sem_io[i] > SEMVMX) { + sem_putref(sma); + err = -ERANGE; + goto out_free; + } + } + sem_lock_and_putref(sma); + if (sma->sem_perm.deleted) { + sem_unlock(sma); + err = -EIDRM; + goto out_free; + } + + for (i = 0; i < nsems; i++) + sma->sem_base[i].semval = sem_io[i]; + + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry(un, &sma->list_id, list_id) { + for (i = 0; i < nsems; i++) + un->semadj[i] = 0; + } + sma->sem_ctime = get_seconds(); + /* maybe some queued-up processes were waiting for this */ + update_queue(sma); + err = 0; + goto out_unlock; + } + /* GETVAL, GETPID, GETNCTN, GETZCNT, SETVAL: fall-through */ + } + err = -EINVAL; + if(semnum < 0 || semnum >= nsems) + goto out_unlock; + + curr = &sma->sem_base[semnum]; + + switch (cmd) { + case GETVAL: + err = curr->semval; + goto out_unlock; + case GETPID: + err = curr->sempid; + goto out_unlock; + case GETNCNT: + err = count_semncnt(sma,semnum); + goto out_unlock; + case GETZCNT: + err = count_semzcnt(sma,semnum); + goto out_unlock; + case SETVAL: + { + int val = arg.val; + struct sem_undo *un; + + err = -ERANGE; + if (val > SEMVMX || val < 0) + goto out_unlock; + + assert_spin_locked(&sma->sem_perm.lock); + list_for_each_entry(un, &sma->list_id, list_id) + un->semadj[semnum] = 0; + + curr->semval = val; + curr->sempid = task_tgid_vnr(current); + sma->sem_ctime = get_seconds(); + /* maybe some queued-up processes were waiting for this */ + update_queue(sma); + err = 0; + goto out_unlock; + } + } +out_unlock: + sem_unlock(sma); +out_free: + if(sem_io != fast_sem_io) + ipc_free(sem_io, sizeof(ushort)*nsems); + return err; +} + +static inline unsigned long +copy_semid_from_user(struct semid64_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 semid_ds tbuf_old; + + if(copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->sem_perm.uid = tbuf_old.sem_perm.uid; + out->sem_perm.gid = tbuf_old.sem_perm.gid; + out->sem_perm.mode = tbuf_old.sem_perm.mode; + + return 0; + } + default: + return -EINVAL; + } +} + +/* + * This function handles some semctl 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 semctl_down(struct ipc_namespace *ns, int semid, + int cmd, int version, union semun arg) +{ + struct sem_array *sma; + int err; + struct semid64_ds semid64; + struct kern_ipc_perm *ipcp; + + if(cmd == IPC_SET) { + if (copy_semid_from_user(&semid64, arg.buf, version)) + return -EFAULT; + } + + ipcp = ipcctl_pre_down(&sem_ids(ns), semid, cmd, &semid64.sem_perm, 0); + if (IS_ERR(ipcp)) + return PTR_ERR(ipcp); + + sma = container_of(ipcp, struct sem_array, sem_perm); + + err = security_sem_semctl(sma, cmd); + if (err) + goto out_unlock; + + switch(cmd){ + case IPC_RMID: + freeary(ns, ipcp); + goto out_up; + case IPC_SET: + ipc_update_perm(&semid64.sem_perm, ipcp); + sma->sem_ctime = get_seconds(); + break; + default: + err = -EINVAL; + } + +out_unlock: + sem_unlock(sma); +out_up: + up_write(&sem_ids(ns).rw_mutex); + return err; +} + +SYSCALL_DEFINE(semctl)(int semid, int semnum, int cmd, union semun arg) +{ + int err = -EINVAL; + int version; + struct ipc_namespace *ns; + + if (semid < 0) + return -EINVAL; + + version = ipc_parse_version(&cmd); + ns = current->nsproxy->ipc_ns; + + switch(cmd) { + case IPC_INFO: + case SEM_INFO: + case IPC_STAT: + case SEM_STAT: + err = semctl_nolock(ns, semid, cmd, version, arg); + return err; + case GETALL: + case GETVAL: + case GETPID: + case GETNCNT: + case GETZCNT: + case SETVAL: + case SETALL: + err = semctl_main(ns,semid,semnum,cmd,version,arg); + return err; + case IPC_RMID: + case IPC_SET: + err = semctl_down(ns, semid, cmd, version, arg); + return err; + default: + return -EINVAL; + } +} +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_semctl(int semid, int semnum, int cmd, union semun arg) +{ + return SYSC_semctl((int) semid, (int) semnum, (int) cmd, arg); +} +SYSCALL_ALIAS(sys_semctl, SyS_semctl); +#endif + +/* If the task doesn't already have a undo_list, then allocate one + * here. We guarantee there is only one thread using this undo list, + * and current is THE ONE + * + * If this allocation and assignment succeeds, but later + * portions of this code fail, there is no need to free the sem_undo_list. + * Just let it stay associated with the task, and it'll be freed later + * at exit time. + * + * This can block, so callers must hold no locks. + */ +static inline int get_undo_list(struct sem_undo_list **undo_listp) +{ + struct sem_undo_list *undo_list; + + undo_list = current->sysvsem.undo_list; + if (!undo_list) { + undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL); + if (undo_list == NULL) + return -ENOMEM; + spin_lock_init(&undo_list->lock); + atomic_set(&undo_list->refcnt, 1); + INIT_LIST_HEAD(&undo_list->list_proc); + + current->sysvsem.undo_list = undo_list; + } + *undo_listp = undo_list; + return 0; +} + +static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) +{ + struct sem_undo *walk; + + list_for_each_entry_rcu(walk, &ulp->list_proc, list_proc) { + if (walk->semid == semid) + return walk; + } + return NULL; +} + +/** + * find_alloc_undo - Lookup (and if not present create) undo array + * @ns: namespace + * @semid: semaphore array id + * + * The function looks up (and if not present creates) the undo structure. + * The size of the undo structure depends on the size of the semaphore + * array, thus the alloc path is not that straightforward. + * Lifetime-rules: sem_undo is rcu-protected, on success, the function + * performs a rcu_read_lock(). + */ +static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) +{ + struct sem_array *sma; + struct sem_undo_list *ulp; + struct sem_undo *un, *new; + int nsems; + int error; + + error = get_undo_list(&ulp); + if (error) + return ERR_PTR(error); + + rcu_read_lock(); + spin_lock(&ulp->lock); + un = lookup_undo(ulp, semid); + spin_unlock(&ulp->lock); + if (likely(un!=NULL)) + goto out; + rcu_read_unlock(); + + /* no undo structure around - allocate one. */ + /* step 1: figure out the size of the semaphore array */ + sma = sem_lock_check(ns, semid); + if (IS_ERR(sma)) + return ERR_PTR(PTR_ERR(sma)); + + nsems = sma->sem_nsems; + sem_getref_and_unlock(sma); + + /* step 2: allocate new undo structure */ + new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); + if (!new) { + sem_putref(sma); + return ERR_PTR(-ENOMEM); + } + + /* step 3: Acquire the lock on semaphore array */ + sem_lock_and_putref(sma); + if (sma->sem_perm.deleted) { + sem_unlock(sma); + kfree(new); + un = ERR_PTR(-EIDRM); + goto out; + } + spin_lock(&ulp->lock); + + /* + * step 4: check for races: did someone else allocate the undo struct? + */ + un = lookup_undo(ulp, semid); + if (un) { + kfree(new); + goto success; + } + /* step 5: initialize & link new undo structure */ + new->semadj = (short *) &new[1]; + new->ulp = ulp; + new->semid = semid; + assert_spin_locked(&ulp->lock); + list_add_rcu(&new->list_proc, &ulp->list_proc); + assert_spin_locked(&sma->sem_perm.lock); + list_add(&new->list_id, &sma->list_id); + un = new; + +success: + spin_unlock(&ulp->lock); + rcu_read_lock(); + sem_unlock(sma); +out: + return un; +} + +SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops, const struct timespec __user *, timeout) +{ + int error = -EINVAL; + struct sem_array *sma; + struct sembuf fast_sops[SEMOPM_FAST]; + struct sembuf* sops = fast_sops, *sop; + struct sem_undo *un; + int undos = 0, alter = 0, max; + struct sem_queue queue; + unsigned long jiffies_left = 0; + struct ipc_namespace *ns; + + ns = current->nsproxy->ipc_ns; + + if (nsops < 1 || semid < 0) + return -EINVAL; + if (nsops > ns->sc_semopm) + return -E2BIG; + if(nsops > SEMOPM_FAST) { + sops = kmalloc(sizeof(*sops)*nsops,GFP_KERNEL); + if(sops==NULL) + return -ENOMEM; + } + if (copy_from_user (sops, tsops, nsops * sizeof(*tsops))) { + error=-EFAULT; + goto out_free; + } + if (timeout) { + struct timespec _timeout; + if (copy_from_user(&_timeout, timeout, sizeof(*timeout))) { + error = -EFAULT; + goto out_free; + } + if (_timeout.tv_sec < 0 || _timeout.tv_nsec < 0 || + _timeout.tv_nsec >= 1000000000L) { + error = -EINVAL; + goto out_free; + } + jiffies_left = timespec_to_jiffies(&_timeout); + } + max = 0; + for (sop = sops; sop < sops + nsops; sop++) { + if (sop->sem_num >= max) + max = sop->sem_num; + if (sop->sem_flg & SEM_UNDO) + undos = 1; + if (sop->sem_op != 0) + alter = 1; + } + + if (undos) { + un = find_alloc_undo(ns, semid); + if (IS_ERR(un)) { + error = PTR_ERR(un); + goto out_free; + } + } else + un = NULL; + + sma = sem_lock_check(ns, semid); + if (IS_ERR(sma)) { + if (un) + rcu_read_unlock(); + error = PTR_ERR(sma); + goto out_free; + } + + /* + * semid identifiers are not unique - find_alloc_undo may have + * allocated an undo structure, it was invalidated by an RMID + * and now a new array with received the same id. Check and fail. + * This case can be detected checking un->semid. The existance of + * "un" itself is guaranteed by rcu. + */ + error = -EIDRM; + if (un) { + if (un->semid == -1) { + rcu_read_unlock(); + goto out_unlock_free; + } else { + /* + * rcu lock can be released, "un" cannot disappear: + * - sem_lock is acquired, thus IPC_RMID is + * impossible. + * - exit_sem is impossible, it always operates on + * current (or a dead task). + */ + + rcu_read_unlock(); + } + } + + error = -EFBIG; + if (max >= sma->sem_nsems) + goto out_unlock_free; + + error = -EACCES; + if (ipcperms(&sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) + goto out_unlock_free; + + error = security_sem_semop(sma, sops, nsops, alter); + if (error) + goto out_unlock_free; + + error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current)); + if (error <= 0) { + if (alter && error == 0) + update_queue (sma); + goto out_unlock_free; + } + + /* We need to sleep on this operation, so we put the current + * task into the pending queue and go to sleep. + */ + + queue.sops = sops; + queue.nsops = nsops; + queue.undo = un; + queue.pid = task_tgid_vnr(current); + queue.alter = alter; + if (alter) + list_add_tail(&queue.list, &sma->sem_pending); + else + list_add(&queue.list, &sma->sem_pending); + + queue.status = -EINTR; + queue.sleeper = current; + current->state = TASK_INTERRUPTIBLE; + sem_unlock(sma); + + if (timeout) + jiffies_left = schedule_timeout(jiffies_left); + else + schedule(); + + error = queue.status; + while(unlikely(error == IN_WAKEUP)) { + cpu_relax(); + error = queue.status; + } + + if (error != -EINTR) { + /* fast path: update_queue already obtained all requested + * resources */ + goto out_free; + } + + sma = sem_lock(ns, semid); + if (IS_ERR(sma)) { + error = -EIDRM; + goto out_free; + } + + /* + * If queue.status != -EINTR we are woken up by another process + */ + error = queue.status; + if (error != -EINTR) { + goto out_unlock_free; + } + + /* + * If an interrupt occurred we have to clean up the queue + */ + if (timeout && jiffies_left == 0) + error = -EAGAIN; + list_del(&queue.list); + goto out_unlock_free; + +out_unlock_free: + sem_unlock(sma); +out_free: + if(sops != fast_sops) + kfree(sops); + return error; +} + +SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops) +{ + return sys_semtimedop(semid, tsops, nsops, NULL); +} + +/* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between + * parent and child tasks. + */ + +int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) +{ + struct sem_undo_list *undo_list; + int error; + + if (clone_flags & CLONE_SYSVSEM) { + error = get_undo_list(&undo_list); + if (error) + return error; + atomic_inc(&undo_list->refcnt); + tsk->sysvsem.undo_list = undo_list; + } else + tsk->sysvsem.undo_list = NULL; + + return 0; +} + +/* + * add semadj values to semaphores, free undo structures. + * undo structures are not freed when semaphore arrays are destroyed + * so some of them may be out of date. + * IMPLEMENTATION NOTE: There is some confusion over whether the + * set of adjustments that needs to be done should be done in an atomic + * manner or not. That is, if we are attempting to decrement the semval + * should we queue up and wait until we can do so legally? + * The original implementation attempted to do this (queue and wait). + * The current implementation does not do so. The POSIX standard + * and SVID should be consulted to determine what behavior is mandated. + */ +void exit_sem(struct task_struct *tsk) +{ + struct sem_undo_list *ulp; + + ulp = tsk->sysvsem.undo_list; + if (!ulp) + return; + tsk->sysvsem.undo_list = NULL; + + if (!atomic_dec_and_test(&ulp->refcnt)) + return; + + for (;;) { + struct sem_array *sma; + struct sem_undo *un; + int semid; + int i; + + rcu_read_lock(); + un = list_entry(rcu_dereference(ulp->list_proc.next), + struct sem_undo, list_proc); + if (&un->list_proc == &ulp->list_proc) + semid = -1; + else + semid = un->semid; + rcu_read_unlock(); + + if (semid == -1) + break; + + sma = sem_lock_check(tsk->nsproxy->ipc_ns, un->semid); + + /* exit_sem raced with IPC_RMID, nothing to do */ + if (IS_ERR(sma)) + continue; + + un = lookup_undo(ulp, semid); + if (un == NULL) { + /* exit_sem raced with IPC_RMID+semget() that created + * exactly the same semid. Nothing to do. + */ + sem_unlock(sma); + continue; + } + + /* remove un from the linked lists */ + assert_spin_locked(&sma->sem_perm.lock); + list_del(&un->list_id); + + spin_lock(&ulp->lock); + list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); + + /* perform adjustments registered in un */ + for (i = 0; i < sma->sem_nsems; i++) { + struct sem * semaphore = &sma->sem_base[i]; + if (un->semadj[i]) { + semaphore->semval += un->semadj[i]; + /* + * Range checks of the new semaphore value, + * not defined by sus: + * - Some unices ignore the undo entirely + * (e.g. HP UX 11i 11.22, Tru64 V5.1) + * - some cap the value (e.g. FreeBSD caps + * at 0, but doesn't enforce SEMVMX) + * + * Linux caps the semaphore value, both at 0 + * and at SEMVMX. + * + * Manfred <manfred@colorfullife.com> + */ + if (semaphore->semval < 0) + semaphore->semval = 0; + if (semaphore->semval > SEMVMX) + semaphore->semval = SEMVMX; + semaphore->sempid = task_tgid_vnr(current); + } + } + sma->sem_otime = get_seconds(); + /* maybe some queued-up processes were waiting for this */ + update_queue(sma); + sem_unlock(sma); + + call_rcu(&un->rcu, free_un); + } + kfree(ulp); +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_proc_show(struct seq_file *s, void *it) +{ + struct sem_array *sma = it; + + return seq_printf(s, + "%10d %10d %4o %10lu %5u %5u %5u %5u %10lu %10lu\n", + sma->sem_perm.key, + sma->sem_perm.id, + sma->sem_perm.mode, + sma->sem_nsems, + sma->sem_perm.uid, + sma->sem_perm.gid, + sma->sem_perm.cuid, + sma->sem_perm.cgid, + sma->sem_otime, + sma->sem_ctime); +} +#endif diff --git a/ipc/shm.c b/ipc/shm.c new file mode 100644 index 0000000..29c2eb5 --- /dev/null +++ b/ipc/shm.c @@ -0,0 +1,1080 @@ +/* + * linux/ipc/shm.c + * Copyright (C) 1992, 1993 Krishna Balasubramanian + * Many improvements/fixes by Bruno Haible. + * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. + * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. + * + * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> + * BIGMEM support, Andrea Arcangeli <andrea@suse.de> + * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> + * HIGHMEM support, Ingo Molnar <mingo@redhat.com> + * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> + * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> + * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/shm.h> +#include <linux/init.h> +#include <linux/file.h> +#include <linux/mman.h> +#include <linux/shmem_fs.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/capability.h> +#include <linux/ptrace.h> +#include <linux/seq_file.h> +#include <linux/rwsem.h> +#include <linux/nsproxy.h> +#include <linux/mount.h> +#include <linux/ipc_namespace.h> + +#include <asm/uaccess.h> + +#include "util.h" + +struct shm_file_data { + int id; + struct ipc_namespace *ns; + struct file *file; + const struct vm_operations_struct *vm_ops; +}; + +#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) + +static const struct file_operations shm_file_operations; +static struct vm_operations_struct shm_vm_ops; + +#define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) + +#define shm_unlock(shp) \ + ipc_unlock(&(shp)->shm_perm) + +static int newseg(struct ipc_namespace *, struct ipc_params *); +static void shm_open(struct vm_area_struct *vma); +static void shm_close(struct vm_area_struct *vma); +static void shm_destroy (struct ipc_namespace *ns, struct shmid_kernel *shp); +#ifdef CONFIG_PROC_FS +static int sysvipc_shm_proc_show(struct seq_file *s, void *it); +#endif + +void shm_init_ns(struct ipc_namespace *ns) +{ + ns->shm_ctlmax = SHMMAX; + ns->shm_ctlall = SHMALL; + ns->shm_ctlmni = SHMMNI; + ns->shm_tot = 0; + ipc_init_ids(&ns->ids[IPC_SHM_IDS]); +} + +/* + * Called with shm_ids.rw_mutex (writer) and the shp structure locked. + * Only shm_ids.rw_mutex remains locked on exit. + */ +static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) +{ + struct shmid_kernel *shp; + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + + if (shp->shm_nattch){ + shp->shm_perm.mode |= SHM_DEST; + /* Do not find it any more */ + shp->shm_perm.key = IPC_PRIVATE; + shm_unlock(shp); + } else + shm_destroy(ns, shp); +} + +#ifdef CONFIG_IPC_NS +void shm_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &shm_ids(ns), do_shm_rmid); +} +#endif + +void __init shm_init (void) +{ + shm_init_ns(&init_ipc_ns); + ipc_init_proc_interface("sysvipc/shm", + " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime\n", + IPC_SHM_IDS, sysvipc_shm_proc_show); +} + +/* + * shm_lock_(check_) routines are called in the paths where the rw_mutex + * is not necessarily held. + */ +static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct shmid_kernel *)ipcp; + + return container_of(ipcp, struct shmid_kernel, shm_perm); +} + +static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns, + int id) +{ + struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id); + + if (IS_ERR(ipcp)) + return (struct shmid_kernel *)ipcp; + + return container_of(ipcp, struct shmid_kernel, shm_perm); +} + +static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) +{ + ipc_rmid(&shm_ids(ns), &s->shm_perm); +} + + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + struct shmid_kernel *shp; + + shp = shm_lock(sfd->ns, sfd->id); + BUG_ON(IS_ERR(shp)); + shp->shm_atim = get_seconds(); + shp->shm_lprid = task_tgid_vnr(current); + shp->shm_nattch++; + shm_unlock(shp); +} + +/* + * shm_destroy - free the struct shmid_kernel + * + * @ns: namespace + * @shp: struct to free + * + * It has to be called with shp and shm_ids.rw_mutex (writer) locked, + * but returns with shp unlocked and freed. + */ +static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) +{ + ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; + shm_rmid(ns, shp); + shm_unlock(shp); + if (!is_file_hugepages(shp->shm_file)) + shmem_lock(shp->shm_file, 0, shp->mlock_user); + else + user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size, + shp->mlock_user); + fput (shp->shm_file); + security_shm_free(shp); + ipc_rcu_putref(shp); +} + +/* + * remove the attach descriptor vma. + * free memory for segment if it is marked destroyed. + * The descriptor has already been removed from the current->mm->mmap list + * and will later be kfree()d. + */ +static void shm_close(struct vm_area_struct *vma) +{ + struct file * file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + struct shmid_kernel *shp; + struct ipc_namespace *ns = sfd->ns; + + down_write(&shm_ids(ns).rw_mutex); + /* remove from the list of attaches of the shm segment */ + shp = shm_lock(ns, sfd->id); + BUG_ON(IS_ERR(shp)); + shp->shm_lprid = task_tgid_vnr(current); + shp->shm_dtim = get_seconds(); + shp->shm_nattch--; + if(shp->shm_nattch == 0 && + shp->shm_perm.mode & SHM_DEST) + shm_destroy(ns, shp); + else + shm_unlock(shp); + up_write(&shm_ids(ns).rw_mutex); +} + +static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + return sfd->vm_ops->fault(vma, vmf); +} + +#ifdef CONFIG_NUMA +static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + int err = 0; + if (sfd->vm_ops->set_policy) + err = sfd->vm_ops->set_policy(vma, new); + return err; +} + +static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + struct mempolicy *pol = NULL; + + if (sfd->vm_ops->get_policy) + pol = sfd->vm_ops->get_policy(vma, addr); + else if (vma->vm_policy) + pol = vma->vm_policy; + + return pol; +} +#endif + +static int shm_mmap(struct file * file, struct vm_area_struct * vma) +{ + struct shm_file_data *sfd = shm_file_data(file); + int ret; + + ret = sfd->file->f_op->mmap(sfd->file, vma); + if (ret != 0) + return ret; + sfd->vm_ops = vma->vm_ops; +#ifdef CONFIG_MMU + BUG_ON(!sfd->vm_ops->fault); +#endif + vma->vm_ops = &shm_vm_ops; + shm_open(vma); + + return ret; +} + +static int shm_release(struct inode *ino, struct file *file) +{ + struct shm_file_data *sfd = shm_file_data(file); + + put_ipc_ns(sfd->ns); + shm_file_data(file) = NULL; + kfree(sfd); + return 0; +} + +static int shm_fsync(struct file *file, struct dentry *dentry, int datasync) +{ + int (*fsync) (struct file *, struct dentry *, int datasync); + struct shm_file_data *sfd = shm_file_data(file); + int ret = -EINVAL; + + fsync = sfd->file->f_op->fsync; + if (fsync) + ret = fsync(sfd->file, sfd->file->f_path.dentry, datasync); + return ret; +} + +static unsigned long shm_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct shm_file_data *sfd = shm_file_data(file); + return get_unmapped_area(sfd->file, addr, len, pgoff, flags); +} + +int is_file_shm_hugepages(struct file *file) +{ + int ret = 0; + + if (file->f_op == &shm_file_operations) { + struct shm_file_data *sfd; + sfd = shm_file_data(file); + ret = is_file_hugepages(sfd->file); + } + return ret; +} + +static const struct file_operations shm_file_operations = { + .mmap = shm_mmap, + .fsync = shm_fsync, + .release = shm_release, + .get_unmapped_area = shm_get_unmapped_area, +}; + +static struct vm_operations_struct shm_vm_ops = { + .open = shm_open, /* callback for a new vm-area open */ + .close = shm_close, /* callback for when the vm-area is released */ + .fault = shm_fault, +#if defined(CONFIG_NUMA) + .set_policy = shm_set_policy, + .get_policy = shm_get_policy, +#endif +}; + +/** + * newseg - Create a new shared memory segment + * @ns: namespace + * @params: ptr to the structure that contains key, size and shmflg + * + * Called with shm_ids.rw_mutex held as a writer. + */ + +static int newseg(struct ipc_namespace *ns, struct ipc_params *params) +{ + key_t key = params->key; + int shmflg = params->flg; + size_t size = params->u.size; + int error; + struct shmid_kernel *shp; + int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT; + struct file * file; + char name[13]; + int id; + + if (size < SHMMIN || size > ns->shm_ctlmax) + return -EINVAL; + + if (ns->shm_tot + numpages > ns->shm_ctlall) + return -ENOSPC; + + shp = ipc_rcu_alloc(sizeof(*shp)); + if (!shp) + return -ENOMEM; + + shp->shm_perm.key = key; + shp->shm_perm.mode = (shmflg & S_IRWXUGO); + shp->mlock_user = NULL; + + shp->shm_perm.security = NULL; + error = security_shm_alloc(shp); + if (error) { + ipc_rcu_putref(shp); + return error; + } + + sprintf (name, "SYSV%08x", key); + if (shmflg & SHM_HUGETLB) { + /* hugetlb_file_setup takes care of mlock user accounting */ + file = hugetlb_file_setup(name, size); + shp->mlock_user = current->user; + } else { + int acctflag = VM_ACCOUNT; + /* + * Do not allow no accounting for OVERCOMMIT_NEVER, even + * if it's asked for. + */ + if ((shmflg & SHM_NORESERVE) && + sysctl_overcommit_memory != OVERCOMMIT_NEVER) + acctflag = 0; + file = shmem_file_setup(name, size, acctflag); + } + error = PTR_ERR(file); + if (IS_ERR(file)) + goto no_file; + + id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); + if (id < 0) { + error = id; + goto no_id; + } + + shp->shm_cprid = task_tgid_vnr(current); + shp->shm_lprid = 0; + shp->shm_atim = shp->shm_dtim = 0; + shp->shm_ctim = get_seconds(); + shp->shm_segsz = size; + shp->shm_nattch = 0; + shp->shm_file = file; + /* + * shmid gets reported as "inode#" in /proc/pid/maps. + * proc-ps tools use this. Changing this will break them. + */ + file->f_dentry->d_inode->i_ino = shp->shm_perm.id; + + ns->shm_tot += numpages; + error = shp->shm_perm.id; + shm_unlock(shp); + return error; + +no_id: + fput(file); +no_file: + security_shm_free(shp); + ipc_rcu_putref(shp); + return error; +} + +/* + * Called with shm_ids.rw_mutex and ipcp locked. + */ +static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg) +{ + struct shmid_kernel *shp; + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + return security_shm_associate(shp, shmflg); +} + +/* + * Called with shm_ids.rw_mutex and ipcp locked. + */ +static inline int shm_more_checks(struct kern_ipc_perm *ipcp, + struct ipc_params *params) +{ + struct shmid_kernel *shp; + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + if (shp->shm_segsz < params->u.size) + return -EINVAL; + + return 0; +} + +SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) +{ + struct ipc_namespace *ns; + struct ipc_ops shm_ops; + struct ipc_params shm_params; + + ns = current->nsproxy->ipc_ns; + + shm_ops.getnew = newseg; + shm_ops.associate = shm_security; + shm_ops.more_checks = shm_more_checks; + + shm_params.key = key; + shm_params.flg = shmflg; + shm_params.u.size = size; + + return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); +} + +static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) +{ + switch(version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct shmid_ds out; + + ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); + out.shm_segsz = in->shm_segsz; + out.shm_atime = in->shm_atime; + out.shm_dtime = in->shm_dtime; + out.shm_ctime = in->shm_ctime; + out.shm_cpid = in->shm_cpid; + out.shm_lpid = in->shm_lpid; + out.shm_nattch = in->shm_nattch; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +static inline unsigned long +copy_shmid_from_user(struct shmid64_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 shmid_ds tbuf_old; + + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->shm_perm.uid = tbuf_old.shm_perm.uid; + out->shm_perm.gid = tbuf_old.shm_perm.gid; + out->shm_perm.mode = tbuf_old.shm_perm.mode; + + return 0; + } + default: + return -EINVAL; + } +} + +static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) +{ + switch(version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct shminfo out; + + if(in->shmmax > INT_MAX) + out.shmmax = INT_MAX; + else + out.shmmax = (int)in->shmmax; + + out.shmmin = in->shmmin; + out.shmmni = in->shmmni; + out.shmseg = in->shmseg; + out.shmall = in->shmall; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +/* + * Called with shm_ids.rw_mutex held as a reader + */ +static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, + unsigned long *swp) +{ + int next_id; + int total, in_use; + + *rss = 0; + *swp = 0; + + in_use = shm_ids(ns).in_use; + + for (total = 0, next_id = 0; total < in_use; next_id++) { + struct shmid_kernel *shp; + struct inode *inode; + + shp = idr_find(&shm_ids(ns).ipcs_idr, next_id); + if (shp == NULL) + continue; + + inode = shp->shm_file->f_path.dentry->d_inode; + + if (is_file_hugepages(shp->shm_file)) { + struct address_space *mapping = inode->i_mapping; + struct hstate *h = hstate_file(shp->shm_file); + *rss += pages_per_huge_page(h) * mapping->nrpages; + } else { +#ifdef CONFIG_SHMEM + struct shmem_inode_info *info = SHMEM_I(inode); + spin_lock(&info->lock); + *rss += inode->i_mapping->nrpages; + *swp += info->swapped; + spin_unlock(&info->lock); +#else + *rss += inode->i_mapping->nrpages; +#endif + } + + total++; + } +} + +/* + * This function handles some shmctl 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 shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, + struct shmid_ds __user *buf, int version) +{ + struct kern_ipc_perm *ipcp; + struct shmid64_ds shmid64; + struct shmid_kernel *shp; + int err; + + if (cmd == IPC_SET) { + if (copy_shmid_from_user(&shmid64, buf, version)) + return -EFAULT; + } + + ipcp = ipcctl_pre_down(&shm_ids(ns), shmid, cmd, &shmid64.shm_perm, 0); + if (IS_ERR(ipcp)) + return PTR_ERR(ipcp); + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + + err = security_shm_shmctl(shp, cmd); + if (err) + goto out_unlock; + switch (cmd) { + case IPC_RMID: + do_shm_rmid(ns, ipcp); + goto out_up; + case IPC_SET: + ipc_update_perm(&shmid64.shm_perm, ipcp); + shp->shm_ctim = get_seconds(); + break; + default: + err = -EINVAL; + } +out_unlock: + shm_unlock(shp); +out_up: + up_write(&shm_ids(ns).rw_mutex); + return err; +} + +SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) +{ + struct shmid_kernel *shp; + int err, version; + struct ipc_namespace *ns; + + if (cmd < 0 || shmid < 0) { + err = -EINVAL; + goto out; + } + + version = ipc_parse_version(&cmd); + ns = current->nsproxy->ipc_ns; + + switch (cmd) { /* replace with proc interface ? */ + case IPC_INFO: + { + struct shminfo64 shminfo; + + err = security_shm_shmctl(NULL, cmd); + if (err) + return err; + + memset(&shminfo,0,sizeof(shminfo)); + shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni; + shminfo.shmmax = ns->shm_ctlmax; + shminfo.shmall = ns->shm_ctlall; + + shminfo.shmmin = SHMMIN; + if(copy_shminfo_to_user (buf, &shminfo, version)) + return -EFAULT; + + down_read(&shm_ids(ns).rw_mutex); + err = ipc_get_maxid(&shm_ids(ns)); + up_read(&shm_ids(ns).rw_mutex); + + if(err<0) + err = 0; + goto out; + } + case SHM_INFO: + { + struct shm_info shm_info; + + err = security_shm_shmctl(NULL, cmd); + if (err) + return err; + + memset(&shm_info,0,sizeof(shm_info)); + down_read(&shm_ids(ns).rw_mutex); + shm_info.used_ids = shm_ids(ns).in_use; + shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp); + shm_info.shm_tot = ns->shm_tot; + shm_info.swap_attempts = 0; + shm_info.swap_successes = 0; + err = ipc_get_maxid(&shm_ids(ns)); + up_read(&shm_ids(ns).rw_mutex); + if(copy_to_user (buf, &shm_info, sizeof(shm_info))) { + err = -EFAULT; + goto out; + } + + err = err < 0 ? 0 : err; + goto out; + } + case SHM_STAT: + case IPC_STAT: + { + struct shmid64_ds tbuf; + int result; + + if (!buf) { + err = -EFAULT; + goto out; + } + + if (cmd == SHM_STAT) { + shp = shm_lock(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out; + } + result = shp->shm_perm.id; + } else { + shp = shm_lock_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out; + } + result = 0; + } + err=-EACCES; + if (ipcperms (&shp->shm_perm, S_IRUGO)) + goto out_unlock; + err = security_shm_shmctl(shp, cmd); + if (err) + goto out_unlock; + memset(&tbuf, 0, sizeof(tbuf)); + kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm); + tbuf.shm_segsz = shp->shm_segsz; + tbuf.shm_atime = shp->shm_atim; + tbuf.shm_dtime = shp->shm_dtim; + tbuf.shm_ctime = shp->shm_ctim; + tbuf.shm_cpid = shp->shm_cprid; + tbuf.shm_lpid = shp->shm_lprid; + tbuf.shm_nattch = shp->shm_nattch; + shm_unlock(shp); + if(copy_shmid_to_user (buf, &tbuf, version)) + err = -EFAULT; + else + err = result; + goto out; + } + case SHM_LOCK: + case SHM_UNLOCK: + { + struct file *uninitialized_var(shm_file); + + lru_add_drain_all(); /* drain pagevecs to lru lists */ + + shp = shm_lock_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out; + } + + err = audit_ipc_obj(&(shp->shm_perm)); + if (err) + goto out_unlock; + + if (!capable(CAP_IPC_LOCK)) { + err = -EPERM; + if (current->euid != shp->shm_perm.uid && + current->euid != shp->shm_perm.cuid) + goto out_unlock; + if (cmd == SHM_LOCK && + !current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur) + goto out_unlock; + } + + err = security_shm_shmctl(shp, cmd); + if (err) + goto out_unlock; + + if(cmd==SHM_LOCK) { + struct user_struct * user = current->user; + if (!is_file_hugepages(shp->shm_file)) { + err = shmem_lock(shp->shm_file, 1, user); + if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){ + shp->shm_perm.mode |= SHM_LOCKED; + shp->mlock_user = user; + } + } + } else if (!is_file_hugepages(shp->shm_file)) { + shmem_lock(shp->shm_file, 0, shp->mlock_user); + shp->shm_perm.mode &= ~SHM_LOCKED; + shp->mlock_user = NULL; + } + shm_unlock(shp); + goto out; + } + case IPC_RMID: + case IPC_SET: + err = shmctl_down(ns, shmid, cmd, buf, version); + return err; + default: + return -EINVAL; + } + +out_unlock: + shm_unlock(shp); +out: + return err; +} + +/* + * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. + * + * NOTE! Despite the name, this is NOT a direct system call entrypoint. The + * "raddr" thing points to kernel space, and there has to be a wrapper around + * this. + */ +long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) +{ + struct shmid_kernel *shp; + unsigned long addr; + unsigned long size; + struct file * file; + int err; + unsigned long flags; + unsigned long prot; + int acc_mode; + unsigned long user_addr; + struct ipc_namespace *ns; + struct shm_file_data *sfd; + struct path path; + fmode_t f_mode; + + err = -EINVAL; + if (shmid < 0) + goto out; + else if ((addr = (ulong)shmaddr)) { + if (addr & (SHMLBA-1)) { + if (shmflg & SHM_RND) + addr &= ~(SHMLBA-1); /* round down */ + else +#ifndef __ARCH_FORCE_SHMLBA + if (addr & ~PAGE_MASK) +#endif + goto out; + } + flags = MAP_SHARED | MAP_FIXED; + } else { + if ((shmflg & SHM_REMAP)) + goto out; + + flags = MAP_SHARED; + } + + if (shmflg & SHM_RDONLY) { + prot = PROT_READ; + acc_mode = S_IRUGO; + f_mode = FMODE_READ; + } else { + prot = PROT_READ | PROT_WRITE; + acc_mode = S_IRUGO | S_IWUGO; + f_mode = FMODE_READ | FMODE_WRITE; + } + if (shmflg & SHM_EXEC) { + prot |= PROT_EXEC; + acc_mode |= S_IXUGO; + } + + /* + * We cannot rely on the fs check since SYSV IPC does have an + * additional creator id... + */ + ns = current->nsproxy->ipc_ns; + shp = shm_lock_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out; + } + + err = -EACCES; + if (ipcperms(&shp->shm_perm, acc_mode)) + goto out_unlock; + + err = security_shm_shmat(shp, shmaddr, shmflg); + if (err) + goto out_unlock; + + path.dentry = dget(shp->shm_file->f_path.dentry); + path.mnt = shp->shm_file->f_path.mnt; + shp->shm_nattch++; + size = i_size_read(path.dentry->d_inode); + shm_unlock(shp); + + err = -ENOMEM; + sfd = kzalloc(sizeof(*sfd), GFP_KERNEL); + if (!sfd) + goto out_put_dentry; + + file = alloc_file(path.mnt, path.dentry, f_mode, &shm_file_operations); + if (!file) + goto out_free; + + file->private_data = sfd; + file->f_mapping = shp->shm_file->f_mapping; + sfd->id = shp->shm_perm.id; + sfd->ns = get_ipc_ns(ns); + sfd->file = shp->shm_file; + sfd->vm_ops = NULL; + + down_write(¤t->mm->mmap_sem); + if (addr && !(shmflg & SHM_REMAP)) { + err = -EINVAL; + if (find_vma_intersection(current->mm, addr, addr + size)) + goto invalid; + /* + * If shm segment goes below stack, make sure there is some + * space left for the stack to grow (at least 4 pages). + */ + if (addr < current->mm->start_stack && + addr > current->mm->start_stack - size - PAGE_SIZE * 5) + goto invalid; + } + + user_addr = do_mmap (file, addr, size, prot, flags, 0); + *raddr = user_addr; + err = 0; + if (IS_ERR_VALUE(user_addr)) + err = (long)user_addr; +invalid: + up_write(¤t->mm->mmap_sem); + + fput(file); + +out_nattch: + down_write(&shm_ids(ns).rw_mutex); + shp = shm_lock(ns, shmid); + BUG_ON(IS_ERR(shp)); + shp->shm_nattch--; + if(shp->shm_nattch == 0 && + shp->shm_perm.mode & SHM_DEST) + shm_destroy(ns, shp); + else + shm_unlock(shp); + up_write(&shm_ids(ns).rw_mutex); + +out: + return err; + +out_unlock: + shm_unlock(shp); + goto out; + +out_free: + kfree(sfd); +out_put_dentry: + dput(path.dentry); + goto out_nattch; +} + +SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) +{ + unsigned long ret; + long err; + + err = do_shmat(shmid, shmaddr, shmflg, &ret); + if (err) + return err; + force_successful_syscall_return(); + return (long)ret; +} + +/* + * detach and kill segment if marked destroyed. + * The work is done in shm_close. + */ +SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *next; + unsigned long addr = (unsigned long)shmaddr; + loff_t size = 0; + int retval = -EINVAL; + + if (addr & ~PAGE_MASK) + return retval; + + down_write(&mm->mmap_sem); + + /* + * This function tries to be smart and unmap shm segments that + * were modified by partial mlock or munmap calls: + * - It first determines the size of the shm segment that should be + * unmapped: It searches for a vma that is backed by shm and that + * started at address shmaddr. It records it's size and then unmaps + * it. + * - Then it unmaps all shm vmas that started at shmaddr and that + * are within the initially determined size. + * Errors from do_munmap are ignored: the function only fails if + * it's called with invalid parameters or if it's called to unmap + * a part of a vma. Both calls in this function are for full vmas, + * the parameters are directly copied from the vma itself and always + * valid - therefore do_munmap cannot fail. (famous last words?) + */ + /* + * If it had been mremap()'d, the starting address would not + * match the usual checks anyway. So assume all vma's are + * above the starting address given. + */ + vma = find_vma(mm, addr); + + while (vma) { + next = vma->vm_next; + + /* + * Check if the starting address would match, i.e. it's + * a fragment created by mprotect() and/or munmap(), or it + * otherwise it starts at this address with no hassles. + */ + if ((vma->vm_ops == &shm_vm_ops) && + (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { + + + size = vma->vm_file->f_path.dentry->d_inode->i_size; + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + /* + * We discovered the size of the shm segment, so + * break out of here and fall through to the next + * loop that uses the size information to stop + * searching for matching vma's. + */ + retval = 0; + vma = next; + break; + } + vma = next; + } + + /* + * We need look no further than the maximum address a fragment + * could possibly have landed at. Also cast things to loff_t to + * prevent overflows and make comparisions vs. equal-width types. + */ + size = PAGE_ALIGN(size); + while (vma && (loff_t)(vma->vm_end - addr) <= size) { + next = vma->vm_next; + + /* finding a matching vma now does not alter retval */ + if ((vma->vm_ops == &shm_vm_ops) && + (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) + + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + vma = next; + } + + up_write(&mm->mmap_sem); + return retval; +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_shm_proc_show(struct seq_file *s, void *it) +{ + struct shmid_kernel *shp = it; + +#if BITS_PER_LONG <= 32 +#define SIZE_SPEC "%10lu" +#else +#define SIZE_SPEC "%21lu" +#endif + + return seq_printf(s, + "%10d %10d %4o " SIZE_SPEC " %5u %5u " + "%5lu %5u %5u %5u %5u %10lu %10lu %10lu\n", + shp->shm_perm.key, + shp->shm_perm.id, + shp->shm_perm.mode, + shp->shm_segsz, + shp->shm_cprid, + shp->shm_lprid, + shp->shm_nattch, + shp->shm_perm.uid, + shp->shm_perm.gid, + shp->shm_perm.cuid, + shp->shm_perm.cgid, + shp->shm_atim, + shp->shm_dtim, + shp->shm_ctim); +} +#endif diff --git a/ipc/util.c b/ipc/util.c new file mode 100644 index 0000000..361fd1c --- /dev/null +++ b/ipc/util.c @@ -0,0 +1,1002 @@ +/* + * 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> + * 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> + */ + +#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/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> +#include <linux/audit.h> +#include <linux/nsproxy.h> +#include <linux/rwsem.h> +#include <linux/memory.h> +#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 *); +}; + +struct ipc_namespace init_ipc_ns = { + .kref = { + .refcount = ATOMIC_INIT(2), + }, +}; + +atomic_t nr_ipc_ns = ATOMIC_INIT(1); + + +#ifdef CONFIG_MEMORY_HOTPLUG + +static void ipc_memory_notifier(struct work_struct *work) +{ + ipcns_notify(IPCNS_MEMCHANGED); +} + +static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier); + + +static int ipc_memory_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + switch (action) { + case MEM_ONLINE: /* memory successfully brought online */ + case MEM_OFFLINE: /* or offline: it's time to recompute msgmni */ + /* + * This is done by invoking the ipcns notifier chain with the + * IPC_MEMCHANGED event. + * In order not to keep the lock on the hotplug memory chain + * for too long, queue a work item that will, when waken up, + * activate the ipcns notification chain. + * No need to keep several ipc work items on the queue. + */ + if (!work_pending(&ipc_memory_wq)) + schedule_work(&ipc_memory_wq); + break; + case MEM_GOING_ONLINE: + case MEM_GOING_OFFLINE: + case MEM_CANCEL_ONLINE: + case MEM_CANCEL_OFFLINE: + default: + break; + } + + return NOTIFY_OK; +} + +#endif /* CONFIG_MEMORY_HOTPLUG */ + +/** + * ipc_init - initialise IPC subsystem + * + * The various system5 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) +{ + sem_init(); + msg_init(); + shm_init(); + hotplug_memory_notifier(ipc_memory_callback, IPC_CALLBACK_PRI); + register_ipcns_notifier(&init_ipc_ns); + return 0; +} +__initcall(ipc_init); + +/** + * ipc_init_ids - initialise IPC identifiers + * @ids: Identifier set + * + * Set up the sequence range to use for the ipc identifier range (limited + * below IPCMNI) then initialise the ids idr. + */ + +void ipc_init_ids(struct ipc_ids *ids) +{ + init_rwsem(&ids->rw_mutex); + + ids->in_use = 0; + ids->seq = 0; + { + int seq_limit = INT_MAX/SEQ_MULTIPLIER; + if (seq_limit > USHORT_MAX) + ids->seq_max = USHORT_MAX; + else + ids->seq_max = seq_limit; + } + + idr_init(&ids->ipcs_idr); +} + +#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: Identifier set + * @key: The key to find + * + * Requires ipc_ids.rw_mutex locked. + * Returns the LOCKED pointer to the ipc structure if found or NULL + * if not. + * If key is found ipc points to the owning ipc structure + */ + +static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) +{ + struct kern_ipc_perm *ipc; + int next_id; + int total; + + for (total = 0, next_id = 0; total < ids->in_use; next_id++) { + ipc = idr_find(&ids->ipcs_idr, next_id); + + if (ipc == NULL) + continue; + + if (ipc->key != key) { + total++; + continue; + } + + ipc_lock_by_ptr(ipc); + return ipc; + } + + return NULL; +} + +/** + * ipc_get_maxid - get the last assigned id + * @ids: IPC identifier set + * + * Called with ipc_ids.rw_mutex held. + */ + +int ipc_get_maxid(struct ipc_ids *ids) +{ + struct kern_ipc_perm *ipc; + int max_id = -1; + int total, id; + + if (ids->in_use == 0) + return -1; + + if (ids->in_use == IPCMNI) + return IPCMNI - 1; + + /* Look for the last assigned id */ + total = 0; + for (id = 0; id < IPCMNI && total < ids->in_use; id++) { + ipc = idr_find(&ids->ipcs_idr, id); + if (ipc != NULL) { + max_id = id; + total++; + } + } + return max_id; +} + +/** + * ipc_addid - add an IPC identifier + * @ids: IPC identifier set + * @new: new IPC permission set + * @size: 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 ipc_ids.rw_mutex held as a writer. + */ + +int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) +{ + int id, err; + + if (size > IPCMNI) + size = IPCMNI; + + if (ids->in_use >= size) + return -ENOSPC; + + spin_lock_init(&new->lock); + new->deleted = 0; + rcu_read_lock(); + spin_lock(&new->lock); + + err = idr_get_new(&ids->ipcs_idr, new, &id); + if (err) { + spin_unlock(&new->lock); + rcu_read_unlock(); + return err; + } + + ids->in_use++; + + new->cuid = new->uid = current->euid; + new->gid = new->cgid = current->egid; + + new->seq = ids->seq++; + if(ids->seq > ids->seq_max) + ids->seq = 0; + + new->id = ipc_buildid(id, new->seq); + return id; +} + +/** + * ipcget_new - create a new ipc object + * @ns: namespace + * @ids: IPC identifer 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, + struct ipc_ops *ops, struct ipc_params *params) +{ + int err; +retry: + err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); + + if (!err) + return -ENOMEM; + + down_write(&ids->rw_mutex); + err = ops->getnew(ns, params); + up_write(&ids->rw_mutex); + + if (err == -EAGAIN) + goto retry; + + return err; +} + +/** + * ipc_check_perms - check security and permissions for an IPC + * @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 + * ids IDR. + * + * On success, the IPC id is returned. + * + * It is called with ipc_ids.rw_mutex and ipcp->lock held. + */ +static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops, + struct ipc_params *params) +{ + int err; + + if (ipcperms(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: namespace + * @ids: IPC identifer 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, + struct ipc_ops *ops, struct ipc_params *params) +{ + struct kern_ipc_perm *ipcp; + int flg = params->flg; + int err; +retry: + err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); + + /* + * Take the lock as a writer since we are potentially going to add + * a new entry + read locks are not "upgradable" + */ + down_write(&ids->rw_mutex); + ipcp = ipc_findkey(ids, params->key); + if (ipcp == NULL) { + /* key not used */ + if (!(flg & IPC_CREAT)) + err = -ENOENT; + else if (!err) + err = -ENOMEM; + 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(ipcp, ops, params); + } + ipc_unlock(ipcp); + } + up_write(&ids->rw_mutex); + + if (err == -EAGAIN) + goto retry; + + return err; +} + + +/** + * ipc_rmid - remove an IPC identifier + * @ids: IPC identifier set + * @ipcp: ipc perm structure containing the identifier to remove + * + * ipc_ids.rw_mutex (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); + + ids->in_use--; + + ipcp->deleted = 1; + + return; +} + +/** + * ipc_alloc - allocate ipc space + * @size: size desired + * + * Allocate memory from the appropriate pools and return a pointer to it. + * NULL is returned if the allocation fails + */ + +void* ipc_alloc(int size) +{ + void* out; + if(size > PAGE_SIZE) + out = vmalloc(size); + else + out = kmalloc(size, GFP_KERNEL); + return out; +} + +/** + * ipc_free - free ipc space + * @ptr: pointer returned by ipc_alloc + * @size: size of block + * + * Free a block created with ipc_alloc(). The caller must know the size + * used in the allocation call. + */ + +void ipc_free(void* ptr, int size) +{ + if(size > PAGE_SIZE) + vfree(ptr); + else + kfree(ptr); +} + +/* + * rcu allocations: + * There are three headers that are prepended to the actual allocation: + * - during use: ipc_rcu_hdr. + * - during the rcu grace period: ipc_rcu_grace. + * - [only if vmalloc]: ipc_rcu_sched. + * Their lifetime doesn't overlap, thus the headers share the same memory. + * Unlike a normal union, they are right-aligned, thus some container_of + * forward/backward casting is necessary: + */ +struct ipc_rcu_hdr +{ + int refcount; + int is_vmalloc; + void *data[0]; +}; + + +struct ipc_rcu_grace +{ + struct rcu_head rcu; + /* "void *" makes sure alignment of following data is sane. */ + void *data[0]; +}; + +struct ipc_rcu_sched +{ + struct work_struct work; + /* "void *" makes sure alignment of following data is sane. */ + void *data[0]; +}; + +#define HDRLEN_KMALLOC (sizeof(struct ipc_rcu_grace) > sizeof(struct ipc_rcu_hdr) ? \ + sizeof(struct ipc_rcu_grace) : sizeof(struct ipc_rcu_hdr)) +#define HDRLEN_VMALLOC (sizeof(struct ipc_rcu_sched) > HDRLEN_KMALLOC ? \ + sizeof(struct ipc_rcu_sched) : HDRLEN_KMALLOC) + +static inline int rcu_use_vmalloc(int size) +{ + /* Too big for a single page? */ + if (HDRLEN_KMALLOC + size > PAGE_SIZE) + return 1; + return 0; +} + +/** + * ipc_rcu_alloc - allocate ipc and rcu space + * @size: size desired + * + * Allocate memory for the rcu header structure + the object. + * Returns the pointer to the object. + * NULL is returned if the allocation fails. + */ + +void* ipc_rcu_alloc(int size) +{ + void* out; + /* + * We prepend the allocation with the rcu struct, and + * workqueue if necessary (for vmalloc). + */ + if (rcu_use_vmalloc(size)) { + out = vmalloc(HDRLEN_VMALLOC + size); + if (out) { + out += HDRLEN_VMALLOC; + container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 1; + container_of(out, struct ipc_rcu_hdr, data)->refcount = 1; + } + } else { + out = kmalloc(HDRLEN_KMALLOC + size, GFP_KERNEL); + if (out) { + out += HDRLEN_KMALLOC; + container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 0; + container_of(out, struct ipc_rcu_hdr, data)->refcount = 1; + } + } + + return out; +} + +void ipc_rcu_getref(void *ptr) +{ + container_of(ptr, struct ipc_rcu_hdr, data)->refcount++; +} + +static void ipc_do_vfree(struct work_struct *work) +{ + vfree(container_of(work, struct ipc_rcu_sched, work)); +} + +/** + * ipc_schedule_free - free ipc + rcu space + * @head: RCU callback structure for queued work + * + * Since RCU callback function is called in bh, + * we need to defer the vfree to schedule_work(). + */ +static void ipc_schedule_free(struct rcu_head *head) +{ + struct ipc_rcu_grace *grace; + struct ipc_rcu_sched *sched; + + grace = container_of(head, struct ipc_rcu_grace, rcu); + sched = container_of(&(grace->data[0]), struct ipc_rcu_sched, + data[0]); + + INIT_WORK(&sched->work, ipc_do_vfree); + schedule_work(&sched->work); +} + +/** + * ipc_immediate_free - free ipc + rcu space + * @head: RCU callback structure that contains pointer to be freed + * + * Free from the RCU callback context. + */ +static void ipc_immediate_free(struct rcu_head *head) +{ + struct ipc_rcu_grace *free = + container_of(head, struct ipc_rcu_grace, rcu); + kfree(free); +} + +void ipc_rcu_putref(void *ptr) +{ + if (--container_of(ptr, struct ipc_rcu_hdr, data)->refcount > 0) + return; + + if (container_of(ptr, struct ipc_rcu_hdr, data)->is_vmalloc) { + call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu, + ipc_schedule_free); + } else { + call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu, + ipc_immediate_free); + } +} + +/** + * ipcperms - check IPC permissions + * @ipcp: IPC permission set + * @flag: desired permission set. + * + * Check user, group, other permissions for access + * to ipc resources. return 0 if allowed + */ + +int ipcperms (struct kern_ipc_perm *ipcp, short flag) +{ /* flag will most probably be 0 or S_...UGO from <linux/stat.h> */ + int requested_mode, granted_mode, err; + + if (unlikely((err = audit_ipc_obj(ipcp)))) + return err; + requested_mode = (flag >> 6) | (flag >> 3) | flag; + granted_mode = ipcp->mode; + if (current->euid == ipcp->cuid || current->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) && + !capable(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 = in->uid; + out->gid = in->gid; + out->cuid = in->cuid; + out->cgid = 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_lock - Lock an ipc structure without rw_mutex 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 exit. + */ + +struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id) +{ + struct kern_ipc_perm *out; + int lid = ipcid_to_idx(id); + + rcu_read_lock(); + out = idr_find(&ids->ipcs_idr, lid); + if (out == NULL) { + rcu_read_unlock(); + return ERR_PTR(-EINVAL); + } + + spin_lock(&out->lock); + + /* ipc_rmid() may have already freed the ID while ipc_lock + * was spinning: here verify that the structure is still valid + */ + if (out->deleted) { + spin_unlock(&out->lock); + rcu_read_unlock(); + return ERR_PTR(-EINVAL); + } + + return out; +} + +struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id) +{ + struct kern_ipc_perm *out; + + out = ipc_lock(ids, id); + if (IS_ERR(out)) + return out; + + if (ipc_checkid(out, id)) { + ipc_unlock(out); + return ERR_PTR(-EIDRM); + } + + return out; +} + +/** + * ipcget - Common sys_*get() code + * @ns : namsepace + * @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, + 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. + * @in: the permission given as input. + * @out: the permission of the ipc to set. + */ +void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out) +{ + out->uid = in->uid; + out->gid = in->gid; + out->mode = (out->mode & ~S_IRWXUGO) + | (in->mode & S_IRWXUGO); +} + +/** + * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd + * @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 the ipc with both ipc and rw_mutex locks held in case of success + * or an err-code without any lock held otherwise. + */ +struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, + struct ipc64_perm *perm, int extra_perm) +{ + struct kern_ipc_perm *ipcp; + int err; + + down_write(&ids->rw_mutex); + ipcp = ipc_lock_check(ids, id); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto out_up; + } + + err = audit_ipc_obj(ipcp); + if (err) + goto out_unlock; + + if (cmd == IPC_SET) { + err = audit_ipc_set_perm(extra_perm, perm->uid, + perm->gid, perm->mode); + if (err) + goto out_unlock; + } + if (current->euid == ipcp->cuid || + current->euid == ipcp->uid || capable(CAP_SYS_ADMIN)) + return ipcp; + + err = -EPERM; +out_unlock: + ipc_unlock(ipcp); +out_up: + up_write(&ids->rw_mutex); + return ERR_PTR(err); +} + +#ifdef __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 /* __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; + ipc_lock_by_ptr(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->rw_mutex); + + /* 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->rw_mutex); +} + +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) + return seq_puts(s, iface->header); + + return iface->show(s, it); +} + +static 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) +{ + int ret; + struct seq_file *seq; + struct ipc_proc_iter *iter; + + ret = -ENOMEM; + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + goto out; + + ret = seq_open(file, &sysvipc_proc_seqops); + if (ret) + goto out_kfree; + + seq = file->private_data; + seq->private = iter; + + iter->iface = PDE(inode)->data; + iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); +out: + return ret; +out_kfree: + kfree(iter); + goto out; +} + +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 */ diff --git a/ipc/util.h b/ipc/util.h new file mode 100644 index 0000000..3646b45 --- /dev/null +++ b/ipc/util.h @@ -0,0 +1,157 @@ +/* + * linux/ipc/util.h + * Copyright (C) 1999 Christoph Rohland + * + * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * namespaces support. 2006 OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#ifndef _IPC_UTIL_H +#define _IPC_UTIL_H + +#include <linux/err.h> + +#define SEQ_MULTIPLIER (IPCMNI) + +void sem_init (void); +void msg_init (void); +void shm_init (void); + +struct ipc_namespace; + +void sem_init_ns(struct ipc_namespace *ns); +void msg_init_ns(struct ipc_namespace *ns); +void shm_init_ns(struct ipc_namespace *ns); + +void sem_exit_ns(struct ipc_namespace *ns); +void msg_exit_ns(struct ipc_namespace *ns); +void shm_exit_ns(struct ipc_namespace *ns); + +/* + * Structure that holds the parameters needed by the ipc operations + * (see after) + */ +struct ipc_params { + key_t key; + int flg; + union { + size_t size; /* for shared memories */ + int nsems; /* for semaphores */ + } u; /* holds the getnew() specific param */ +}; + +/* + * Structure that holds some ipc operations. This structure is used to unify + * the calls to sys_msgget(), sys_semget(), sys_shmget() + * . routine to call to create a new ipc object. Can be one of newque, + * newary, newseg + * . routine to call to check permissions for a new ipc object. + * Can be one of security_msg_associate, security_sem_associate, + * security_shm_associate + * . routine to call for an extra check if needed + */ +struct ipc_ops { + int (*getnew) (struct ipc_namespace *, struct ipc_params *); + int (*associate) (struct kern_ipc_perm *, int); + int (*more_checks) (struct kern_ipc_perm *, struct ipc_params *); +}; + +struct seq_file; +struct ipc_ids; + +void ipc_init_ids(struct ipc_ids *); +#ifdef CONFIG_PROC_FS +void __init ipc_init_proc_interface(const char *path, const char *header, + int ids, int (*show)(struct seq_file *, void *)); +#else +#define ipc_init_proc_interface(path, header, ids, show) do {} while (0) +#endif + +#define IPC_SEM_IDS 0 +#define IPC_MSG_IDS 1 +#define IPC_SHM_IDS 2 + +#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER) + +/* must be called with ids->rw_mutex acquired for writing */ +int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int); + +/* must be called with ids->rw_mutex acquired for reading */ +int ipc_get_maxid(struct ipc_ids *); + +/* must be called with both locks acquired. */ +void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); + +/* must be called with ipcp locked */ +int ipcperms(struct kern_ipc_perm *ipcp, short flg); + +/* for rare, potentially huge allocations. + * both function can sleep + */ +void* ipc_alloc(int size); +void ipc_free(void* ptr, int size); + +/* + * For allocation that need to be freed by RCU. + * Objects are reference counted, they start with reference count 1. + * getref increases the refcount, the putref call that reduces the recount + * to 0 schedules the rcu destruction. Caller must guarantee locking. + */ +void* ipc_rcu_alloc(int size); +void ipc_rcu_getref(void *ptr); +void ipc_rcu_putref(void *ptr); + +struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); + +void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out); +void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out); +void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out); +struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, + struct ipc64_perm *perm, int extra_perm); + +#if defined(__ia64__) || defined(__x86_64__) || defined(__hppa__) || defined(__XTENSA__) + /* On IA-64, we always use the "64-bit version" of the IPC structures. */ +# define ipc_parse_version(cmd) IPC_64 +#else +int ipc_parse_version (int *cmd); +#endif + +extern void free_msg(struct msg_msg *msg); +extern struct msg_msg *load_msg(const void __user *src, int len); +extern int store_msg(void __user *dest, struct msg_msg *msg, int len); + +extern void recompute_msgmni(struct ipc_namespace *); + +static inline int ipc_buildid(int id, int seq) +{ + return SEQ_MULTIPLIER * seq + id; +} + +/* + * Must be called with ipcp locked + */ +static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid) +{ + if (uid / SEQ_MULTIPLIER != ipcp->seq) + return 1; + return 0; +} + +static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm) +{ + rcu_read_lock(); + spin_lock(&perm->lock); +} + +static inline void ipc_unlock(struct kern_ipc_perm *perm) +{ + spin_unlock(&perm->lock); + rcu_read_unlock(); +} + +struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id); +int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, + struct ipc_ops *ops, struct ipc_params *params); + +#endif |
