From 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 16 Apr 2005 15:20:36 -0700 Subject: Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip! --- ipc/Makefile | 9 + ipc/compat.c | 687 +++++++++++++++++++++++++++ ipc/compat_mq.c | 146 ++++++ ipc/mqueue.c | 1252 +++++++++++++++++++++++++++++++++++++++++++++++++ ipc/msg.c | 862 ++++++++++++++++++++++++++++++++++ ipc/msgutil.c | 127 +++++ ipc/sem.c | 1384 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ ipc/shm.c | 917 ++++++++++++++++++++++++++++++++++++ ipc/util.c | 580 +++++++++++++++++++++++ ipc/util.h | 81 ++++ 10 files changed, 6045 insertions(+) create mode 100644 ipc/Makefile create mode 100644 ipc/compat.c create mode 100644 ipc/compat_mq.c create mode 100644 ipc/mqueue.c create mode 100644 ipc/msg.c create mode 100644 ipc/msgutil.c create mode 100644 ipc/sem.c create mode 100644 ipc/shm.c create mode 100644 ipc/util.c create mode 100644 ipc/util.h (limited to 'ipc') diff --git a/ipc/Makefile b/ipc/Makefile new file mode 100644 index 000000000000..0a6d626cd794 --- /dev/null +++ b/ipc/Makefile @@ -0,0 +1,9 @@ +# +# Makefile for the linux ipc. +# + +obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o +obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o +obj_mq-$(CONFIG_COMPAT) += compat_mq.o +obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y) + diff --git a/ipc/compat.c b/ipc/compat.c new file mode 100644 index 000000000000..70e4e4e10fd1 --- /dev/null +++ b/ipc/compat.c @@ -0,0 +1,687 @@ +/* + * 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 + * Copyright (C) 2000 VA Linux Co + * Copyright (C) 2000 Don Dugger + * Copyright (C) 2000 Hewlett-Packard Co. + * Copyright (C) 2000 David Mosberger-Tang + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#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]) +#define MAXBUF (64*1024) + +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))) + err = -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 msgbuf __user *p; + struct compat_msgbuf __user *up = uptr; + long type; + + if (first < 0) + return -EINVAL; + if (second < 0 || (second >= MAXBUF - sizeof(struct msgbuf))) + return -EINVAL; + + p = compat_alloc_user_space(second + sizeof(struct msgbuf)); + if (get_user(type, &up->mtype) || + put_user(type, &p->mtype) || + copy_in_user(p->mtext, up->mtext, second)) + return -EFAULT; + + return sys_msgsnd(first, p, second, third); +} + +long compat_sys_msgrcv(int first, int second, int msgtyp, int third, + int version, void __user *uptr) +{ + struct msgbuf __user *p; + struct compat_msgbuf __user *up; + long type; + int err; + + if (first < 0) + return -EINVAL; + if (second < 0 || (second >= MAXBUF - sizeof(struct msgbuf))) + 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; + } + p = compat_alloc_user_space(second + sizeof(struct msgbuf)); + err = sys_msgrcv(first, p, second, msgtyp, third); + if (err < 0) + goto out; + up = uptr; + if (get_user(type, &p->mtype) || + put_user(type, &up->mtype) || + copy_in_user(up->mtext, p->mtext, err)) + 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; + 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; + 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); +} + +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 000000000000..d8d1e9ff4e88 --- /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 + */ + +#include +#include +#include +#include +#include + +#include + +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/mqueue.c b/ipc/mqueue.c new file mode 100644 index 000000000000..cb0cd3cf3b5a --- /dev/null +++ b/ipc/mqueue.c @@ -0,0 +1,1252 @@ +/* + * POSIX message queues filesystem for Linux. + * + * Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl) + * Michal Wronski (wrona@mat.uni.torun.pl) + * + * Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com) + * Lockless receive & send, fd based notify: + * Manfred Spraul (manfred@colorfullife.com) + * + * This file is released under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#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 + +/* used by sysctl */ +#define FS_MQUEUE 1 +#define CTL_QUEUESMAX 2 +#define CTL_MSGMAX 3 +#define CTL_MSGSIZEMAX 4 + +/* 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 NOTIFY_COOKIE_LEN 32 + +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; + pid_t notify_owner; + struct user_struct *user; /* user who created, for accouting */ + 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 struct inode_operations mqueue_dir_inode_operations; +static 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 kmem_cache_t *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_blksize = PAGE_CACHE_SIZE; + 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 = 0; + info->qsize = 0; + info->user = NULL; /* set when all is ok */ + memset(&info->attr, 0, sizeof(info->attr)); + info->attr.mq_maxmsg = DFLT_MSGMAX; + info->attr.mq_msgsize = DFLT_MSGSIZEMAX; + 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)) { + inode->i_nlink++; + /* 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 struct super_block *mqueue_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return get_sb_single(fs_type, flags, data, mqueue_fill_super); +} + +static void init_once(void *foo, kmem_cache_t * cachep, unsigned long flags) +{ + struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo; + + if ((flags & (SLAB_CTOR_VERIFY | SLAB_CTOR_CONSTRUCTOR)) == + SLAB_CTOR_CONSTRUCTOR) + 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, SLAB_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; + inode->i_nlink--; + 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_dentry->d_inode); + char buffer[FILENT_SIZE]; + size_t slen; + loff_t o; + + if (!count) + return 0; + + 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, + info->notify_owner); + spin_unlock(&info->lock); + buffer[sizeof(buffer)-1] = '\0'; + slen = strlen(buffer)+1; + + o = *off; + if (o > slen) + return 0; + + if (o + count > slen) + count = slen - o; + + if (copy_to_user(u_data, buffer + o, count)) + return -EFAULT; + + *off = o + count; + filp->f_dentry->d_inode->i_atime = filp->f_dentry->d_inode->i_ctime = CURRENT_TIME; + return count; +} + +static int mqueue_flush_file(struct file *filp) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode); + + spin_lock(&info->lock); + if (current->tgid == 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_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 = current->tgid; + sig_i.si_uid = current->uid; + + kill_proc_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, 0); + break; + } + /* after notification unregisters process */ + info->notify_owner = 0; + } + 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 != 0 && + info->notify.sigev_notify == SIGEV_THREAD) { + set_cookie(info->notify_cookie, NOTIFY_REMOVED); + netlink_sendskb(info->notify_sock, info->notify_cookie, 0); + } + info->notify_owner = 0; +} + +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 file *filp; + struct mq_attr attr; + int ret; + + if (u_attr != NULL) { + if (copy_from_user(&attr, u_attr, sizeof(attr))) + return ERR_PTR(-EFAULT); + if (!mq_attr_ok(&attr)) + return ERR_PTR(-EINVAL); + /* store for use during create */ + dentry->d_fsdata = &attr; + } + + ret = vfs_create(dir->d_inode, dentry, mode, NULL); + dentry->d_fsdata = NULL; + if (ret) + return ERR_PTR(ret); + + filp = dentry_open(dentry, mqueue_mnt, oflag); + if (!IS_ERR(filp)) + dget(dentry); + + return filp; +} + +/* 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 }; + struct file *filp; + + if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) + return ERR_PTR(-EINVAL); + + if (permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE], NULL)) + return ERR_PTR(-EACCES); + + filp = dentry_open(dentry, mqueue_mnt, oflag); + + if (!IS_ERR(filp)) + dget(dentry); + + return filp; +} + +asmlinkage long sys_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; + + if (IS_ERR(name = getname(u_name))) + return PTR_ERR(name); + + fd = get_unused_fd(); + if (fd < 0) + goto out_putname; + + down(&mqueue_mnt->mnt_root->d_inode->i_sem); + 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 */ + filp = (oflag & O_EXCL) ? ERR_PTR(-EEXIST) : + do_open(dentry, oflag); + } else { + filp = do_create(mqueue_mnt->mnt_root, dentry, + oflag, mode, u_attr); + } + } else + filp = (dentry->d_inode) ? do_open(dentry, oflag) : + ERR_PTR(-ENOENT); + + dput(dentry); + + if (IS_ERR(filp)) { + error = PTR_ERR(filp); + goto out_putfd; + } + + set_close_on_exec(fd, 1); + fd_install(fd, filp); + goto out_upsem; + +out_putfd: + mntput(mqueue_mnt); + put_unused_fd(fd); +out_err: + fd = error; +out_upsem: + up(&mqueue_mnt->mnt_root->d_inode->i_sem); +out_putname: + putname(name); + return fd; +} + +asmlinkage long sys_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); + + down(&mqueue_mnt->mnt_root->d_inode->i_sem); + 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 = vfs_unlink(dentry->d_parent->d_inode, dentry); +out_err: + dput(dentry); + +out_unlock: + up(&mqueue_mnt->mnt_root->d_inode->i_sem); + 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 fore 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); + 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); + wmb(); + sender->state = STATE_READY; +} + +asmlinkage long sys_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; + + 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_dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + + 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; +} + +asmlinkage ssize_t sys_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; + + timeout = prepare_timeout(u_abs_timeout); + + ret = -EBADF; + filp = fget(mqdes); + if (unlikely(!filp)) + goto out; + + inode = filp->f_dentry->d_inode; + if (unlikely(filp->f_op != &mqueue_file_operations)) + goto out_fput; + info = MQUEUE_I(inode); + + 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. + */ +asmlinkage long sys_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; + + 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 && + (notification.sigev_signo < 0 || + notification.sigev_signo > _NSIG)) { + return -EINVAL; + } + if (notification.sigev_notify == SIGEV_THREAD) { + /* 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; + } + + ret = netlink_attachskb(sock, nc, 0, MAX_SCHEDULE_TIMEOUT); + 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_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 == current->tgid) { + remove_notification(info); + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + } else if (info->notify_owner != 0) { + 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 = current->tgid; + 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; +} + +asmlinkage long sys_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_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) { + 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 struct inode_operations mqueue_dir_inode_operations = { + .lookup = simple_lookup, + .create = mqueue_create, + .unlink = mqueue_unlink, +}; + +static 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 = DFLT_MSGMAX; +static int msg_max_limit_max = HARD_MSGMAX; + +static int msg_maxsize_limit_min = DFLT_MSGSIZEMAX; +static int msg_maxsize_limit_max = INT_MAX; + +static ctl_table mq_sysctls[] = { + { + .ctl_name = CTL_QUEUESMAX, + .procname = "queues_max", + .data = &queues_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = CTL_MSGMAX, + .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, + }, + { + .ctl_name = CTL_MSGSIZEMAX, + .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[] = { + { + .ctl_name = FS_MQUEUE, + .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, NULL); + if (mqueue_inode_cachep == NULL) + return -ENOMEM; + + /* ignore failues - they are not fatal */ + mq_sysctl_table = register_sysctl_table(mq_sysctl_root, 0); + + 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); + if (kmem_cache_destroy(mqueue_inode_cachep)) { + printk(KERN_INFO + "mqueue_inode_cache: not all structures were freed\n"); + } + return error; +} + +__initcall(init_mqueue_fs); diff --git a/ipc/msg.c b/ipc/msg.c new file mode 100644 index 000000000000..27e516f96cdc --- /dev/null +++ b/ipc/msg.c @@ -0,0 +1,862 @@ +/* + * linux/ipc/msg.c + * Copyright (C) 1992 Krishna Balasubramanian + * + * Removed all the remaining kerneld mess + * Catch the -EFAULT stuff properly + * Use GFP_KERNEL for messages as in 1.2 + * Fixed up the unchecked user space derefs + * Copyright (C) 1998 Alan Cox & Andi Kleen + * + * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie + * + * mostly rewritten, threaded and wake-one semantics added + * MSGMAX limit removed, sysctl's added + * (c) 1999 Manfred Spraul + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "util.h" + +/* sysctl: */ +int msg_ctlmax = MSGMAX; +int msg_ctlmnb = MSGMNB; +int msg_ctlmni = MSGMNI; + +/* one msg_receiver structure for each sleeping receiver */ +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 + +static atomic_t msg_bytes = ATOMIC_INIT(0); +static atomic_t msg_hdrs = ATOMIC_INIT(0); + +static struct ipc_ids msg_ids; + +#define msg_lock(id) ((struct msg_queue*)ipc_lock(&msg_ids,id)) +#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm) +#define msg_rmid(id) ((struct msg_queue*)ipc_rmid(&msg_ids,id)) +#define msg_checkid(msq, msgid) \ + ipc_checkid(&msg_ids,&msq->q_perm,msgid) +#define msg_buildid(id, seq) \ + ipc_buildid(&msg_ids, id, seq) + +static void freeque (struct msg_queue *msq, int id); +static int newque (key_t key, int msgflg); +#ifdef CONFIG_PROC_FS +static int sysvipc_msg_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data); +#endif + +void __init msg_init (void) +{ + ipc_init_ids(&msg_ids,msg_ctlmni); + +#ifdef CONFIG_PROC_FS + create_proc_read_entry("sysvipc/msg", 0, NULL, sysvipc_msg_read_proc, NULL); +#endif +} + +static int newque (key_t key, int msgflg) +{ + int id; + int retval; + struct msg_queue *msq; + + 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; + } + + id = ipc_addid(&msg_ids, &msq->q_perm, msg_ctlmni); + if(id == -1) { + security_msg_queue_free(msq); + ipc_rcu_putref(msq); + return -ENOSPC; + } + + msq->q_stime = msq->q_rtime = 0; + msq->q_ctime = get_seconds(); + msq->q_cbytes = msq->q_qnum = 0; + msq->q_qbytes = msg_ctlmnb; + msq->q_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 msg_buildid(id,msq->q_perm.seq); +} + +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 + * array, and cleans up all the messages associated with this queue. + * + * msg_ids.sem and the spinlock for this message queue is hold + * before freeque() is called. msg_ids.sem remains locked on exit. + */ +static void freeque (struct msg_queue *msq, int id) +{ + struct list_head *tmp; + + expunge_all(msq,-EIDRM); + ss_wakeup(&msq->q_senders,1); + msq = msg_rmid(id); + 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(&msg_hdrs); + free_msg(msg); + } + atomic_sub(msq->q_cbytes, &msg_bytes); + security_msg_queue_free(msq); + ipc_rcu_putref(msq); +} + +asmlinkage long sys_msgget (key_t key, int msgflg) +{ + int id, ret = -EPERM; + struct msg_queue *msq; + + down(&msg_ids.sem); + if (key == IPC_PRIVATE) + ret = newque(key, msgflg); + else if ((id = ipc_findkey(&msg_ids, key)) == -1) { /* key not used */ + if (!(msgflg & IPC_CREAT)) + ret = -ENOENT; + else + ret = newque(key, msgflg); + } else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) { + ret = -EEXIST; + } else { + msq = msg_lock(id); + if(msq==NULL) + BUG(); + if (ipcperms(&msq->q_perm, msgflg)) + ret = -EACCES; + else { + int qid = msg_buildid(id, msq->q_perm.seq); + ret = security_msg_queue_associate(msq, msgflg); + if (!ret) + ret = qid; + } + msg_unlock(msq); + } + up(&msg_ids.sem); + return ret; +} + +static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) +{ + switch(version) { + case IPC_64: + return copy_to_user (buf, in, sizeof(*in)); + case IPC_OLD: + { + struct msqid_ds out; + + memset(&out,0,sizeof(out)); + + ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); + + out.msg_stime = in->msg_stime; + out.msg_rtime = in->msg_rtime; + out.msg_ctime = in->msg_ctime; + + if(in->msg_cbytes > USHRT_MAX) + out.msg_cbytes = USHRT_MAX; + else + out.msg_cbytes = in->msg_cbytes; + out.msg_lcbytes = in->msg_cbytes; + + if(in->msg_qnum > USHRT_MAX) + out.msg_qnum = USHRT_MAX; + else + out.msg_qnum = in->msg_qnum; + + if(in->msg_qbytes > USHRT_MAX) + out.msg_qbytes = USHRT_MAX; + else + out.msg_qbytes = in->msg_qbytes; + out.msg_lqbytes = in->msg_qbytes; + + out.msg_lspid = in->msg_lspid; + out.msg_lrpid = in->msg_lrpid; + + return copy_to_user (buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +struct msq_setbuf { + unsigned long qbytes; + uid_t uid; + gid_t gid; + mode_t mode; +}; + +static inline unsigned long copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version) +{ + switch(version) { + case IPC_64: + { + struct msqid64_ds tbuf; + + if (copy_from_user (&tbuf, buf, sizeof (tbuf))) + return -EFAULT; + + out->qbytes = tbuf.msg_qbytes; + out->uid = tbuf.msg_perm.uid; + out->gid = tbuf.msg_perm.gid; + out->mode = tbuf.msg_perm.mode; + + return 0; + } + case IPC_OLD: + { + struct msqid_ds tbuf_old; + + if (copy_from_user (&tbuf_old, buf, sizeof (tbuf_old))) + return -EFAULT; + + out->uid = tbuf_old.msg_perm.uid; + out->gid = tbuf_old.msg_perm.gid; + out->mode = tbuf_old.msg_perm.mode; + + if(tbuf_old.msg_qbytes == 0) + out->qbytes = tbuf_old.msg_lqbytes; + else + out->qbytes = tbuf_old.msg_qbytes; + + return 0; + } + default: + return -EINVAL; + } +} + +asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds __user *buf) +{ + int err, version; + struct msg_queue *msq; + struct msq_setbuf setbuf; + struct kern_ipc_perm *ipcp; + + if (msqid < 0 || cmd < 0) + return -EINVAL; + + version = ipc_parse_version(&cmd); + + 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 = msg_ctlmni; + msginfo.msgmax = msg_ctlmax; + msginfo.msgmnb = msg_ctlmnb; + msginfo.msgssz = MSGSSZ; + msginfo.msgseg = MSGSEG; + down(&msg_ids.sem); + if (cmd == MSG_INFO) { + msginfo.msgpool = msg_ids.in_use; + msginfo.msgmap = atomic_read(&msg_hdrs); + msginfo.msgtql = atomic_read(&msg_bytes); + } else { + msginfo.msgmap = MSGMAP; + msginfo.msgpool = MSGPOOL; + msginfo.msgtql = MSGTQL; + } + max_id = msg_ids.max_id; + up(&msg_ids.sem); + if (copy_to_user (buf, &msginfo, sizeof(struct msginfo))) + return -EFAULT; + return (max_id < 0) ? 0: max_id; + } + case MSG_STAT: + case IPC_STAT: + { + struct msqid64_ds tbuf; + int success_return; + if (!buf) + return -EFAULT; + if(cmd == MSG_STAT && msqid >= msg_ids.entries->size) + return -EINVAL; + + memset(&tbuf,0,sizeof(tbuf)); + + msq = msg_lock(msqid); + if (msq == NULL) + return -EINVAL; + + if(cmd == MSG_STAT) { + success_return = msg_buildid(msqid, msq->q_perm.seq); + } else { + err = -EIDRM; + if (msg_checkid(msq,msqid)) + goto out_unlock; + 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; + + 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: + if (!buf) + return -EFAULT; + if (copy_msqid_from_user (&setbuf, buf, version)) + return -EFAULT; + if ((err = audit_ipc_perms(setbuf.qbytes, setbuf.uid, setbuf.gid, setbuf.mode))) + return err; + break; + case IPC_RMID: + break; + default: + return -EINVAL; + } + + down(&msg_ids.sem); + msq = msg_lock(msqid); + err=-EINVAL; + if (msq == NULL) + goto out_up; + + err = -EIDRM; + if (msg_checkid(msq,msqid)) + goto out_unlock_up; + ipcp = &msq->q_perm; + err = -EPERM; + if (current->euid != ipcp->cuid && + current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) + /* We _could_ check for CAP_CHOWN above, but we don't */ + goto out_unlock_up; + + err = security_msg_queue_msgctl(msq, cmd); + if (err) + goto out_unlock_up; + + switch (cmd) { + case IPC_SET: + { + err = -EPERM; + if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) + goto out_unlock_up; + + msq->q_qbytes = setbuf.qbytes; + + ipcp->uid = setbuf.uid; + ipcp->gid = setbuf.gid; + ipcp->mode = (ipcp->mode & ~S_IRWXUGO) | + (S_IRWXUGO & setbuf.mode); + msq->q_ctime = get_seconds(); + /* sleeping receivers might be excluded by + * stricter permissions. + */ + expunge_all(msq,-EAGAIN); + /* sleeping senders might be able to send + * due to a larger queue size. + */ + ss_wakeup(&msq->q_senders,0); + msg_unlock(msq); + break; + } + case IPC_RMID: + freeque (msq, msqid); + break; + } + err = 0; +out_up: + up(&msg_ids.sem); + return err; +out_unlock_up: + msg_unlock(msq); + goto out_up; +out_unlock: + msg_unlock(msq); + return err; +} + +static int testmsg(struct msg_msg* msg,long type,int mode) +{ + 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 = msr->r_tsk->pid; + msq->q_rtime = get_seconds(); + wake_up_process(msr->r_tsk); + smp_mb(); + msr->r_msg = msg; + return 1; + } + } + } + return 0; +} + +asmlinkage long sys_msgsnd (int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) +{ + struct msg_queue *msq; + struct msg_msg *msg; + long mtype; + int err; + + if (msgsz > msg_ctlmax || (long) msgsz < 0 || msqid < 0) + return -EINVAL; + if (get_user(mtype, &msgp->mtype)) + return -EFAULT; + if (mtype < 1) + return -EINVAL; + + msg = load_msg(msgp->mtext, msgsz); + if(IS_ERR(msg)) + return PTR_ERR(msg); + + msg->m_type = mtype; + msg->m_ts = msgsz; + + msq = msg_lock(msqid); + err=-EINVAL; + if(msq==NULL) + goto out_free; + + err= -EIDRM; + if (msg_checkid(msq,msqid)) + goto out_unlock_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 = current->tgid; + 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,&msg_bytes); + atomic_inc(&msg_hdrs); + } + + err = 0; + msg = NULL; + +out_unlock_free: + msg_unlock(msq); +out_free: + if(msg!=NULL) + free_msg(msg); + return err; +} + +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; +} + +asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz, + long msgtyp, int msgflg) +{ + struct msg_queue *msq; + struct msg_msg *msg; + int mode; + + if (msqid < 0 || (long) msgsz < 0) + return -EINVAL; + mode = convert_mode(&msgtyp,msgflg); + + msq = msg_lock(msqid); + if(msq==NULL) + return -EINVAL; + + msg = ERR_PTR(-EIDRM); + if (msg_checkid(msq,msqid)) + goto out_unlock; + + 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 = current->tgid; + msq->q_cbytes -= msg->m_ts; + atomic_sub(msg->m_ts,&msg_bytes); + atomic_dec(&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; + if (put_user (msg->m_type, &msgp->mtype) || + store_msg(msgp->mtext, msg, msgsz)) { + msgsz = -EFAULT; + } + free_msg(msg); + return msgsz; +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_msg_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data) +{ + off_t pos = 0; + off_t begin = 0; + int i, len = 0; + + down(&msg_ids.sem); + len += sprintf(buffer, " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n"); + + for(i = 0; i <= msg_ids.max_id; i++) { + struct msg_queue * msq; + msq = msg_lock(i); + if(msq != NULL) { + len += sprintf(buffer + len, "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n", + msq->q_perm.key, + msg_buildid(i,msq->q_perm.seq), + 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); + msg_unlock(msq); + + pos += len; + if(pos < offset) { + len = 0; + begin = pos; + } + if(pos > offset + length) + goto done; + } + + } + *eof = 1; +done: + up(&msg_ids.sem); + *start = buffer + (offset - begin); + len -= (offset - begin); + if(len > length) + len = length; + if(len < 0) + len = 0; + return len; +} +#endif diff --git a/ipc/msgutil.c b/ipc/msgutil.c new file mode 100644 index 000000000000..66cfb87646eb --- /dev/null +++ b/ipc/msgutil.c @@ -0,0 +1,127 @@ +/* + * linux/ipc/util.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 +#include +#include +#include +#include +#include + +#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 = (struct 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 = (struct msg_msgseg *)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/sem.c b/ipc/sem.c new file mode 100644 index 000000000000..5ad7ac0ed60d --- /dev/null +++ b/ipc/sem.c @@ -0,0 +1,1384 @@ +/* + * 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 + * + * SMP-threaded, sysctl's added + * (c) 1999 Manfred Spraul + * Enforced range limit on SEM_UNDO + * (c) 2001 Red Hat Inc + * Lockless wakeup + * (c) 2003 Manfred Spraul + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "util.h" + + +#define sem_lock(id) ((struct sem_array*)ipc_lock(&sem_ids,id)) +#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm) +#define sem_rmid(id) ((struct sem_array*)ipc_rmid(&sem_ids,id)) +#define sem_checkid(sma, semid) \ + ipc_checkid(&sem_ids,&sma->sem_perm,semid) +#define sem_buildid(id, seq) \ + ipc_buildid(&sem_ids, id, seq) +static struct ipc_ids sem_ids; + +static int newary (key_t, int, int); +static void freeary (struct sem_array *sma, int id); +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data); +#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. + * + */ + +int sem_ctls[4] = {SEMMSL, SEMMNS, SEMOPM, SEMMNI}; +#define sc_semmsl (sem_ctls[0]) +#define sc_semmns (sem_ctls[1]) +#define sc_semopm (sem_ctls[2]) +#define sc_semmni (sem_ctls[3]) + +static int used_sems; + +void __init sem_init (void) +{ + used_sems = 0; + ipc_init_ids(&sem_ids,sc_semmni); + +#ifdef CONFIG_PROC_FS + create_proc_read_entry("sysvipc/sem", 0, NULL, sysvipc_sem_read_proc, NULL); +#endif +} + +/* + * 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 semaphore 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 + +static int newary (key_t key, int nsems, int semflg) +{ + int id; + int retval; + struct sem_array *sma; + int size; + + if (!nsems) + return -EINVAL; + if (used_sems + nsems > 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, &sma->sem_perm, sc_semmni); + if(id == -1) { + security_sem_free(sma); + ipc_rcu_putref(sma); + return -ENOSPC; + } + used_sems += nsems; + + sma->sem_base = (struct sem *) &sma[1]; + /* sma->sem_pending = NULL; */ + sma->sem_pending_last = &sma->sem_pending; + /* sma->undo = NULL; */ + sma->sem_nsems = nsems; + sma->sem_ctime = get_seconds(); + sem_unlock(sma); + + return sem_buildid(id, sma->sem_perm.seq); +} + +asmlinkage long sys_semget (key_t key, int nsems, int semflg) +{ + int id, err = -EINVAL; + struct sem_array *sma; + + if (nsems < 0 || nsems > sc_semmsl) + return -EINVAL; + down(&sem_ids.sem); + + if (key == IPC_PRIVATE) { + err = newary(key, nsems, semflg); + } else if ((id = ipc_findkey(&sem_ids, key)) == -1) { /* key not used */ + if (!(semflg & IPC_CREAT)) + err = -ENOENT; + else + err = newary(key, nsems, semflg); + } else if (semflg & IPC_CREAT && semflg & IPC_EXCL) { + err = -EEXIST; + } else { + sma = sem_lock(id); + if(sma==NULL) + BUG(); + if (nsems > sma->sem_nsems) + err = -EINVAL; + else if (ipcperms(&sma->sem_perm, semflg)) + err = -EACCES; + else { + int semid = sem_buildid(id, sma->sem_perm.seq); + err = security_sem_associate(sma, semflg); + if (!err) + err = semid; + } + sem_unlock(sma); + } + + up(&sem_ids.sem); + return err; +} + +/* Manage the doubly linked list sma->sem_pending as a FIFO: + * insert new queue elements at the tail sma->sem_pending_last. + */ +static inline void append_to_queue (struct sem_array * sma, + struct sem_queue * q) +{ + *(q->prev = sma->sem_pending_last) = q; + *(sma->sem_pending_last = &q->next) = NULL; +} + +static inline void prepend_to_queue (struct sem_array * sma, + struct sem_queue * q) +{ + q->next = sma->sem_pending; + *(q->prev = &sma->sem_pending) = q; + if (q->next) + q->next->prev = &q->next; + else /* sma->sem_pending_last == &sma->sem_pending */ + sma->sem_pending_last = &q->next; +} + +static inline void remove_from_queue (struct sem_array * sma, + struct sem_queue * q) +{ + *(q->prev) = q->next; + if (q->next) + q->next->prev = q->prev; + else /* sma->sem_pending_last == &q->next */ + sma->sem_pending_last = q->prev; + q->prev = NULL; /* mark as removed */ +} + +/* + * 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 = sma->sem_pending; + while(q) { + 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; + remove_from_queue(sma,q); + q->status = IN_WAKEUP; + /* + * 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. + */ + if (q->alter) + n = sma->sem_pending; + else + n = q->next; + wake_up_process(q->sleeper); + /* hands-off: q will disappear immediately after + * writing q->status. + */ + q->status = error; + q = n; + } else { + q = q->next; + } + } +} + +/* 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; + for (q = sma->sem_pending; q; q = q->next) { + 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; + for (q = sma->sem_pending; q; q = q->next) { + 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; +} + +/* Free a semaphore set. freeary() is called with sem_ids.sem down and + * the spinlock for this semaphore set hold. sem_ids.sem remains locked + * on exit. + */ +static void freeary (struct sem_array *sma, int id) +{ + struct sem_undo *un; + struct sem_queue *q; + int size; + + /* Invalidate the existing undo structures for this semaphore set. + * (They will be freed without any further action in exit_sem() + * or during the next semop.) + */ + for (un = sma->undo; un; un = un->id_next) + un->semid = -1; + + /* Wake up all pending processes and let them fail with EIDRM. */ + q = sma->sem_pending; + while(q) { + struct sem_queue *n; + /* lazy remove_from_queue: we are killing the whole queue */ + q->prev = NULL; + n = q->next; + q->status = IN_WAKEUP; + wake_up_process(q->sleeper); /* doesn't sleep */ + q->status = -EIDRM; /* hands-off q */ + q = n; + } + + /* Remove the semaphore set from the ID array*/ + sma = sem_rmid(id); + sem_unlock(sma); + + used_sems -= sma->sem_nsems; + size = sizeof (*sma) + sma->sem_nsems * sizeof (struct sem); + 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(int semid, int semnum, 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 = sc_semmni; + seminfo.semmns = sc_semmns; + seminfo.semmsl = sc_semmsl; + seminfo.semopm = sc_semopm; + seminfo.semvmx = SEMVMX; + seminfo.semmnu = SEMMNU; + seminfo.semmap = SEMMAP; + seminfo.semume = SEMUME; + down(&sem_ids.sem); + if (cmd == SEM_INFO) { + seminfo.semusz = sem_ids.in_use; + seminfo.semaem = used_sems; + } else { + seminfo.semusz = SEMUSZ; + seminfo.semaem = SEMAEM; + } + max_id = sem_ids.max_id; + up(&sem_ids.sem); + if (copy_to_user (arg.__buf, &seminfo, sizeof(struct seminfo))) + return -EFAULT; + return (max_id < 0) ? 0: max_id; + } + case SEM_STAT: + { + struct semid64_ds tbuf; + int id; + + if(semid >= sem_ids.entries->size) + return -EINVAL; + + memset(&tbuf,0,sizeof(tbuf)); + + sma = sem_lock(semid); + if(sma == NULL) + return -EINVAL; + + err = -EACCES; + if (ipcperms (&sma->sem_perm, S_IRUGO)) + goto out_unlock; + + err = security_sem_semctl(sma, cmd); + if (err) + goto out_unlock; + + id = sem_buildid(semid, sma->sem_perm.seq); + + 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(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(semid); + if(sma==NULL) + return -EINVAL; + + nsems = sma->sem_nsems; + + err=-EIDRM; + if (sem_checkid(sma,semid)) + goto out_unlock; + + 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) { + ipc_rcu_getref(sma); + sem_unlock(sma); + + sem_io = ipc_alloc(sizeof(ushort)*nsems); + if(sem_io == NULL) { + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + return -ENOMEM; + } + + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_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; + + ipc_rcu_getref(sma); + sem_unlock(sma); + + if(nsems > SEMMSL_FAST) { + sem_io = ipc_alloc(sizeof(ushort)*nsems); + if(sem_io == NULL) { + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + return -ENOMEM; + } + } + + if (copy_from_user (sem_io, arg.array, nsems*sizeof(ushort))) { + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + err = -EFAULT; + goto out_free; + } + + for (i = 0; i < nsems; i++) { + if (sem_io[i] > SEMVMX) { + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + err = -ERANGE; + goto out_free; + } + } + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_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]; + for (un = sma->undo; un; un = un->id_next) + 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; + } + case IPC_STAT: + { + struct semid64_ds tbuf; + 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 0; + } + /* 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; + + for (un = sma->undo; un; un = un->id_next) + un->semadj[semnum] = 0; + curr->semval = val; + curr->sempid = current->tgid; + 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; +} + +struct sem_setbuf { + uid_t uid; + gid_t gid; + mode_t mode; +}; + +static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __user *buf, int version) +{ + switch(version) { + case IPC_64: + { + struct semid64_ds tbuf; + + if(copy_from_user(&tbuf, buf, sizeof(tbuf))) + return -EFAULT; + + out->uid = tbuf.sem_perm.uid; + out->gid = tbuf.sem_perm.gid; + out->mode = tbuf.sem_perm.mode; + + return 0; + } + case IPC_OLD: + { + struct semid_ds tbuf_old; + + if(copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->uid = tbuf_old.sem_perm.uid; + out->gid = tbuf_old.sem_perm.gid; + out->mode = tbuf_old.sem_perm.mode; + + return 0; + } + default: + return -EINVAL; + } +} + +static int semctl_down(int semid, int semnum, int cmd, int version, union semun arg) +{ + struct sem_array *sma; + int err; + struct sem_setbuf setbuf; + struct kern_ipc_perm *ipcp; + + if(cmd == IPC_SET) { + if(copy_semid_from_user (&setbuf, arg.buf, version)) + return -EFAULT; + if ((err = audit_ipc_perms(0, setbuf.uid, setbuf.gid, setbuf.mode))) + return err; + } + sma = sem_lock(semid); + if(sma==NULL) + return -EINVAL; + + if (sem_checkid(sma,semid)) { + err=-EIDRM; + goto out_unlock; + } + ipcp = &sma->sem_perm; + + if (current->euid != ipcp->cuid && + current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) { + err=-EPERM; + goto out_unlock; + } + + err = security_sem_semctl(sma, cmd); + if (err) + goto out_unlock; + + switch(cmd){ + case IPC_RMID: + freeary(sma, semid); + err = 0; + break; + case IPC_SET: + ipcp->uid = setbuf.uid; + ipcp->gid = setbuf.gid; + ipcp->mode = (ipcp->mode & ~S_IRWXUGO) + | (setbuf.mode & S_IRWXUGO); + sma->sem_ctime = get_seconds(); + sem_unlock(sma); + err = 0; + break; + default: + sem_unlock(sma); + err = -EINVAL; + break; + } + return err; + +out_unlock: + sem_unlock(sma); + return err; +} + +asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) +{ + int err = -EINVAL; + int version; + + if (semid < 0) + return -EINVAL; + + version = ipc_parse_version(&cmd); + + switch(cmd) { + case IPC_INFO: + case SEM_INFO: + case SEM_STAT: + err = semctl_nolock(semid,semnum,cmd,version,arg); + return err; + case GETALL: + case GETVAL: + case GETPID: + case GETNCNT: + case GETZCNT: + case IPC_STAT: + case SETVAL: + case SETALL: + err = semctl_main(semid,semnum,cmd,version,arg); + return err; + case IPC_RMID: + case IPC_SET: + down(&sem_ids.sem); + err = semctl_down(semid,semnum,cmd,version,arg); + up(&sem_ids.sem); + return err; + default: + return -EINVAL; + } +} + +static inline void lock_semundo(void) +{ + struct sem_undo_list *undo_list; + + undo_list = current->sysvsem.undo_list; + if ((undo_list != NULL) && (atomic_read(&undo_list->refcnt) != 1)) + spin_lock(&undo_list->lock); +} + +/* This code has an interaction with copy_semundo(). + * Consider; two tasks are sharing the undo_list. task1 + * acquires the undo_list lock in lock_semundo(). If task2 now + * exits before task1 releases the lock (by calling + * unlock_semundo()), then task1 will never call spin_unlock(). + * This leave the sem_undo_list in a locked state. If task1 now creats task3 + * and once again shares the sem_undo_list, the sem_undo_list will still be + * locked, and future SEM_UNDO operations will deadlock. This case is + * dealt with in copy_semundo() by having it reinitialize the spin lock when + * the refcnt goes from 1 to 2. + */ +static inline void unlock_semundo(void) +{ + struct sem_undo_list *undo_list; + + undo_list = current->sysvsem.undo_list; + if ((undo_list != NULL) && (atomic_read(&undo_list->refcnt) != 1)) + spin_unlock(&undo_list->lock); +} + + +/* 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; + int size; + + undo_list = current->sysvsem.undo_list; + if (!undo_list) { + size = sizeof(struct sem_undo_list); + undo_list = (struct sem_undo_list *) kmalloc(size, GFP_KERNEL); + if (undo_list == NULL) + return -ENOMEM; + memset(undo_list, 0, size); + /* don't initialize unodhd->lock here. It's done + * in copy_semundo() instead. + */ + atomic_set(&undo_list->refcnt, 1); + 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 **last, *un; + + last = &ulp->proc_list; + un = *last; + while(un != NULL) { + if(un->semid==semid) + break; + if(un->semid==-1) { + *last=un->proc_next; + kfree(un); + } else { + last=&un->proc_next; + } + un=*last; + } + return un; +} + +static struct sem_undo *find_undo(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); + + lock_semundo(); + un = lookup_undo(ulp, semid); + unlock_semundo(); + if (likely(un!=NULL)) + goto out; + + /* no undo structure around - allocate one. */ + sma = sem_lock(semid); + un = ERR_PTR(-EINVAL); + if(sma==NULL) + goto out; + un = ERR_PTR(-EIDRM); + if (sem_checkid(sma,semid)) { + sem_unlock(sma); + goto out; + } + nsems = sma->sem_nsems; + ipc_rcu_getref(sma); + sem_unlock(sma); + + new = (struct sem_undo *) kmalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); + if (!new) { + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + return ERR_PTR(-ENOMEM); + } + memset(new, 0, sizeof(struct sem_undo) + sizeof(short)*nsems); + new->semadj = (short *) &new[1]; + new->semid = semid; + + lock_semundo(); + un = lookup_undo(ulp, semid); + if (un) { + unlock_semundo(); + kfree(new); + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + sem_unlock(sma); + goto out; + } + ipc_lock_by_ptr(&sma->sem_perm); + ipc_rcu_putref(sma); + if (sma->sem_perm.deleted) { + sem_unlock(sma); + unlock_semundo(); + kfree(new); + un = ERR_PTR(-EIDRM); + goto out; + } + new->proc_next = ulp->proc_list; + ulp->proc_list = new; + new->id_next = sma->undo; + sma->undo = new; + sem_unlock(sma); + un = new; + unlock_semundo(); +out: + return un; +} + +asmlinkage long sys_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, decrease = 0, alter = 0, max; + struct sem_queue queue; + unsigned long jiffies_left = 0; + + if (nsops < 1 || semid < 0) + return -EINVAL; + if (nsops > 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++; + if (sop->sem_op < 0) + decrease = 1; + if (sop->sem_op > 0) + alter = 1; + } + alter |= decrease; + +retry_undos: + if (undos) { + un = find_undo(semid); + if (IS_ERR(un)) { + error = PTR_ERR(un); + goto out_free; + } + } else + un = NULL; + + sma = sem_lock(semid); + error=-EINVAL; + if(sma==NULL) + goto out_free; + error = -EIDRM; + if (sem_checkid(sma,semid)) + goto out_unlock_free; + /* + * semid identifies are not unique - find_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 retry. + */ + if (un && un->semid == -1) { + sem_unlock(sma); + goto retry_undos; + } + 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, current->tgid); + 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.sma = sma; + queue.sops = sops; + queue.nsops = nsops; + queue.undo = un; + queue.pid = current->tgid; + queue.id = semid; + queue.alter = alter; + if (alter) + append_to_queue(sma ,&queue); + else + prepend_to_queue(sma ,&queue); + + 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(semid); + if(sma==NULL) { + if(queue.prev != NULL) + BUG(); + 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; + remove_from_queue(sma,&queue); + goto out_unlock_free; + +out_unlock_free: + sem_unlock(sma); +out_free: + if(sops != fast_sops) + kfree(sops); + return error; +} + +asmlinkage long sys_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. + * + * See the notes above unlock_semundo() regarding the spin_lock_init() + * in this code. Initialize the undo_list->lock here instead of get_undo_list() + * because of the reasoning in the comment above unlock_semundo. + */ + +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; + if (atomic_read(&undo_list->refcnt) == 1) + spin_lock_init(&undo_list->lock); + 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 *undo_list; + struct sem_undo *u, **up; + + undo_list = tsk->sysvsem.undo_list; + if (!undo_list) + return; + + if (!atomic_dec_and_test(&undo_list->refcnt)) + return; + + /* There's no need to hold the semundo list lock, as current + * is the last task exiting for this undo list. + */ + for (up = &undo_list->proc_list; (u = *up); *up = u->proc_next, kfree(u)) { + struct sem_array *sma; + int nsems, i; + struct sem_undo *un, **unp; + int semid; + + semid = u->semid; + + if(semid == -1) + continue; + sma = sem_lock(semid); + if (sma == NULL) + continue; + + if (u->semid == -1) + goto next_entry; + + BUG_ON(sem_checkid(sma,u->semid)); + + /* remove u from the sma->undo list */ + for (unp = &sma->undo; (un = *unp); unp = &un->id_next) { + if (u == un) + goto found; + } + printk ("exit_sem undo list error id=%d\n", u->semid); + goto next_entry; +found: + *unp = un->id_next; + /* perform adjustments registered in u */ + nsems = sma->sem_nsems; + for (i = 0; i < nsems; i++) { + struct sem * sem = &sma->sem_base[i]; + if (u->semadj[i]) { + sem->semval += u->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 + */ + if (sem->semval < 0) + sem->semval = 0; + if (sem->semval > SEMVMX) + sem->semval = SEMVMX; + sem->sempid = current->tgid; + } + } + sma->sem_otime = get_seconds(); + /* maybe some queued-up processes were waiting for this */ + update_queue(sma); +next_entry: + sem_unlock(sma); + } + kfree(undo_list); +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data) +{ + off_t pos = 0; + off_t begin = 0; + int i, len = 0; + + len += sprintf(buffer, " key semid perms nsems uid gid cuid cgid otime ctime\n"); + down(&sem_ids.sem); + + for(i = 0; i <= sem_ids.max_id; i++) { + struct sem_array *sma; + sma = sem_lock(i); + if(sma) { + len += sprintf(buffer + len, "%10d %10d %4o %10lu %5u %5u %5u %5u %10lu %10lu\n", + sma->sem_perm.key, + sem_buildid(i,sma->sem_perm.seq), + 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); + sem_unlock(sma); + + pos += len; + if(pos < offset) { + len = 0; + begin = pos; + } + if(pos > offset + length) + goto done; + } + } + *eof = 1; +done: + up(&sem_ids.sem); + *start = buffer + (offset - begin); + len -= (offset - begin); + if(len > length) + len = length; + if(len < 0) + len = 0; + return len; +} +#endif diff --git a/ipc/shm.c b/ipc/shm.c new file mode 100644 index 000000000000..06cd5c91056f --- /dev/null +++ b/ipc/shm.c @@ -0,0 +1,917 @@ +/* + * 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 + * BIGMEM support, Andrea Arcangeli + * SMP thread shm, Jean-Luc Boyard + * HIGHMEM support, Ingo Molnar + * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland + * Shared /dev/zero support, Kanoj Sarcar + * Move the mm functionality over to mm/shmem.c, Christoph Rohland + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "util.h" + +#define shm_flags shm_perm.mode + +static struct file_operations shm_file_operations; +static struct vm_operations_struct shm_vm_ops; + +static struct ipc_ids shm_ids; + +#define shm_lock(id) ((struct shmid_kernel*)ipc_lock(&shm_ids,id)) +#define shm_unlock(shp) ipc_unlock(&(shp)->shm_perm) +#define shm_get(id) ((struct shmid_kernel*)ipc_get(&shm_ids,id)) +#define shm_buildid(id, seq) \ + ipc_buildid(&shm_ids, id, seq) + +static int newseg (key_t key, int shmflg, size_t size); +static void shm_open (struct vm_area_struct *shmd); +static void shm_close (struct vm_area_struct *shmd); +#ifdef CONFIG_PROC_FS +static int sysvipc_shm_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data); +#endif + +size_t shm_ctlmax = SHMMAX; +size_t shm_ctlall = SHMALL; +int shm_ctlmni = SHMMNI; + +static int shm_tot; /* total number of shared memory pages */ + +void __init shm_init (void) +{ + ipc_init_ids(&shm_ids, 1); +#ifdef CONFIG_PROC_FS + create_proc_read_entry("sysvipc/shm", 0, NULL, sysvipc_shm_read_proc, NULL); +#endif +} + +static inline int shm_checkid(struct shmid_kernel *s, int id) +{ + if (ipc_checkid(&shm_ids,&s->shm_perm,id)) + return -EIDRM; + return 0; +} + +static inline struct shmid_kernel *shm_rmid(int id) +{ + return (struct shmid_kernel *)ipc_rmid(&shm_ids,id); +} + +static inline int shm_addid(struct shmid_kernel *shp) +{ + return ipc_addid(&shm_ids, &shp->shm_perm, shm_ctlmni); +} + + + +static inline void shm_inc (int id) { + struct shmid_kernel *shp; + + if(!(shp = shm_lock(id))) + BUG(); + shp->shm_atim = get_seconds(); + shp->shm_lprid = current->tgid; + shp->shm_nattch++; + shm_unlock(shp); +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open (struct vm_area_struct *shmd) +{ + shm_inc (shmd->vm_file->f_dentry->d_inode->i_ino); +} + +/* + * shm_destroy - free the struct shmid_kernel + * + * @shp: struct to free + * + * It has to be called with shp and shm_ids.sem locked, + * but returns with shp unlocked and freed. + */ +static void shm_destroy (struct shmid_kernel *shp) +{ + shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; + shm_rmid (shp->id); + 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_dentry->d_inode->i_size, + shp->mlock_user); + fput (shp->shm_file); + security_shm_free(shp); + ipc_rcu_putref(shp); +} + +/* + * remove the attach descriptor shmd. + * 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 *shmd) +{ + struct file * file = shmd->vm_file; + int id = file->f_dentry->d_inode->i_ino; + struct shmid_kernel *shp; + + down (&shm_ids.sem); + /* remove from the list of attaches of the shm segment */ + if(!(shp = shm_lock(id))) + BUG(); + shp->shm_lprid = current->tgid; + shp->shm_dtim = get_seconds(); + shp->shm_nattch--; + if(shp->shm_nattch == 0 && + shp->shm_flags & SHM_DEST) + shm_destroy (shp); + else + shm_unlock(shp); + up (&shm_ids.sem); +} + +static int shm_mmap(struct file * file, struct vm_area_struct * vma) +{ + file_accessed(file); + vma->vm_ops = &shm_vm_ops; + shm_inc(file->f_dentry->d_inode->i_ino); + return 0; +} + +static struct file_operations shm_file_operations = { + .mmap = shm_mmap +}; + +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 */ + .nopage = shmem_nopage, +#ifdef CONFIG_NUMA + .set_policy = shmem_set_policy, + .get_policy = shmem_get_policy, +#endif +}; + +static int newseg (key_t key, int shmflg, size_t 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 > shm_ctlmax) + return -EINVAL; + + if (shm_tot + numpages >= shm_ctlall) + return -ENOSPC; + + shp = ipc_rcu_alloc(sizeof(*shp)); + if (!shp) + return -ENOMEM; + + shp->shm_perm.key = key; + shp->shm_flags = (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; + } + + if (shmflg & SHM_HUGETLB) { + /* hugetlb_zero_setup takes care of mlock user accounting */ + file = hugetlb_zero_setup(size); + shp->mlock_user = current->user; + } else { + sprintf (name, "SYSV%08x", key); + file = shmem_file_setup(name, size, VM_ACCOUNT); + } + error = PTR_ERR(file); + if (IS_ERR(file)) + goto no_file; + + error = -ENOSPC; + id = shm_addid(shp); + if(id == -1) + goto no_id; + + shp->shm_cprid = current->tgid; + 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->id = shm_buildid(id,shp->shm_perm.seq); + shp->shm_file = file; + file->f_dentry->d_inode->i_ino = shp->id; + if (shmflg & SHM_HUGETLB) + set_file_hugepages(file); + else + file->f_op = &shm_file_operations; + shm_tot += numpages; + shm_unlock(shp); + return shp->id; + +no_id: + fput(file); +no_file: + security_shm_free(shp); + ipc_rcu_putref(shp); + return error; +} + +asmlinkage long sys_shmget (key_t key, size_t size, int shmflg) +{ + struct shmid_kernel *shp; + int err, id = 0; + + down(&shm_ids.sem); + if (key == IPC_PRIVATE) { + err = newseg(key, shmflg, size); + } else if ((id = ipc_findkey(&shm_ids, key)) == -1) { + if (!(shmflg & IPC_CREAT)) + err = -ENOENT; + else + err = newseg(key, shmflg, size); + } else if ((shmflg & IPC_CREAT) && (shmflg & IPC_EXCL)) { + err = -EEXIST; + } else { + shp = shm_lock(id); + if(shp==NULL) + BUG(); + if (shp->shm_segsz < size) + err = -EINVAL; + else if (ipcperms(&shp->shm_perm, shmflg)) + err = -EACCES; + else { + int shmid = shm_buildid(id, shp->shm_perm.seq); + err = security_shm_associate(shp, shmflg); + if (!err) + err = shmid; + } + shm_unlock(shp); + } + up(&shm_ids.sem); + + return err; +} + +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; + } +} + +struct shm_setbuf { + uid_t uid; + gid_t gid; + mode_t mode; +}; + +static inline unsigned long copy_shmid_from_user(struct shm_setbuf *out, void __user *buf, int version) +{ + switch(version) { + case IPC_64: + { + struct shmid64_ds tbuf; + + if (copy_from_user(&tbuf, buf, sizeof(tbuf))) + return -EFAULT; + + out->uid = tbuf.shm_perm.uid; + out->gid = tbuf.shm_perm.gid; + out->mode = tbuf.shm_flags; + + return 0; + } + case IPC_OLD: + { + struct shmid_ds tbuf_old; + + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->uid = tbuf_old.shm_perm.uid; + out->gid = tbuf_old.shm_perm.gid; + out->mode = tbuf_old.shm_flags; + + 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; + } +} + +static void shm_get_stat(unsigned long *rss, unsigned long *swp) +{ + int i; + + *rss = 0; + *swp = 0; + + for (i = 0; i <= shm_ids.max_id; i++) { + struct shmid_kernel *shp; + struct inode *inode; + + shp = shm_get(i); + if(!shp) + continue; + + inode = shp->shm_file->f_dentry->d_inode; + + if (is_file_hugepages(shp->shm_file)) { + struct address_space *mapping = inode->i_mapping; + *rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages; + } else { + struct shmem_inode_info *info = SHMEM_I(inode); + spin_lock(&info->lock); + *rss += inode->i_mapping->nrpages; + *swp += info->swapped; + spin_unlock(&info->lock); + } + } +} + +asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) +{ + struct shm_setbuf setbuf; + struct shmid_kernel *shp; + int err, version; + + if (cmd < 0 || shmid < 0) { + err = -EINVAL; + goto out; + } + + version = ipc_parse_version(&cmd); + + 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 = shm_ctlmni; + shminfo.shmmax = shm_ctlmax; + shminfo.shmall = shm_ctlall; + + shminfo.shmmin = SHMMIN; + if(copy_shminfo_to_user (buf, &shminfo, version)) + return -EFAULT; + /* reading a integer is always atomic */ + err= shm_ids.max_id; + 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(&shm_ids.sem); + shm_info.used_ids = shm_ids.in_use; + shm_get_stat (&shm_info.shm_rss, &shm_info.shm_swp); + shm_info.shm_tot = shm_tot; + shm_info.swap_attempts = 0; + shm_info.swap_successes = 0; + err = shm_ids.max_id; + up(&shm_ids.sem); + 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; + memset(&tbuf, 0, sizeof(tbuf)); + shp = shm_lock(shmid); + if(shp==NULL) { + err = -EINVAL; + goto out; + } else if(cmd==SHM_STAT) { + err = -EINVAL; + if (shmid > shm_ids.max_id) + goto out_unlock; + result = shm_buildid(shmid, shp->shm_perm.seq); + } else { + err = shm_checkid(shp,shmid); + if(err) + goto out_unlock; + 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; + 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; + if (!is_file_hugepages(shp->shm_file)) + tbuf.shm_nattch = shp->shm_nattch; + else + tbuf.shm_nattch = file_count(shp->shm_file) - 1; + shm_unlock(shp); + if(copy_shmid_to_user (buf, &tbuf, version)) + err = -EFAULT; + else + err = result; + goto out; + } + case SHM_LOCK: + case SHM_UNLOCK: + { + shp = shm_lock(shmid); + if(shp==NULL) { + err = -EINVAL; + goto out; + } + err = shm_checkid(shp,shmid); + 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_flags |= 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_flags &= ~SHM_LOCKED; + shp->mlock_user = NULL; + } + shm_unlock(shp); + goto out; + } + case IPC_RMID: + { + /* + * We cannot simply remove the file. The SVID states + * that the block remains until the last person + * detaches from it, then is deleted. A shmat() on + * an RMID segment is legal in older Linux and if + * we change it apps break... + * + * Instead we set a destroyed flag, and then blow + * the name away when the usage hits zero. + */ + down(&shm_ids.sem); + shp = shm_lock(shmid); + err = -EINVAL; + if (shp == NULL) + goto out_up; + err = shm_checkid(shp, shmid); + if(err) + goto out_unlock_up; + + if (current->euid != shp->shm_perm.uid && + current->euid != shp->shm_perm.cuid && + !capable(CAP_SYS_ADMIN)) { + err=-EPERM; + goto out_unlock_up; + } + + err = security_shm_shmctl(shp, cmd); + if (err) + goto out_unlock_up; + + if (shp->shm_nattch){ + shp->shm_flags |= SHM_DEST; + /* Do not find it any more */ + shp->shm_perm.key = IPC_PRIVATE; + shm_unlock(shp); + } else + shm_destroy (shp); + up(&shm_ids.sem); + goto out; + } + + case IPC_SET: + { + if (copy_shmid_from_user (&setbuf, buf, version)) { + err = -EFAULT; + goto out; + } + if ((err = audit_ipc_perms(0, setbuf.uid, setbuf.gid, setbuf.mode))) + return err; + down(&shm_ids.sem); + shp = shm_lock(shmid); + err=-EINVAL; + if(shp==NULL) + goto out_up; + err = shm_checkid(shp,shmid); + if(err) + goto out_unlock_up; + err=-EPERM; + if (current->euid != shp->shm_perm.uid && + current->euid != shp->shm_perm.cuid && + !capable(CAP_SYS_ADMIN)) { + goto out_unlock_up; + } + + err = security_shm_shmctl(shp, cmd); + if (err) + goto out_unlock_up; + + shp->shm_perm.uid = setbuf.uid; + shp->shm_perm.gid = setbuf.gid; + shp->shm_flags = (shp->shm_flags & ~S_IRWXUGO) + | (setbuf.mode & S_IRWXUGO); + shp->shm_ctim = get_seconds(); + break; + } + + default: + err = -EINVAL; + goto out; + } + + err = 0; +out_unlock_up: + shm_unlock(shp); +out_up: + up(&shm_ids.sem); + goto out; +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; + unsigned long o_flags; + int acc_mode; + void *user_addr; + + if (shmid < 0) { + err = -EINVAL; + 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 + return -EINVAL; + } + flags = MAP_SHARED | MAP_FIXED; + } else { + if ((shmflg & SHM_REMAP)) + return -EINVAL; + + flags = MAP_SHARED; + } + + if (shmflg & SHM_RDONLY) { + prot = PROT_READ; + o_flags = O_RDONLY; + acc_mode = S_IRUGO; + } else { + prot = PROT_READ | PROT_WRITE; + o_flags = O_RDWR; + acc_mode = S_IRUGO | S_IWUGO; + } + 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... + */ + shp = shm_lock(shmid); + if(shp == NULL) { + err = -EINVAL; + goto out; + } + err = shm_checkid(shp,shmid); + if (err) { + shm_unlock(shp); + goto out; + } + if (ipcperms(&shp->shm_perm, acc_mode)) { + shm_unlock(shp); + err = -EACCES; + goto out; + } + + err = security_shm_shmat(shp, shmaddr, shmflg); + if (err) { + shm_unlock(shp); + return err; + } + + file = shp->shm_file; + size = i_size_read(file->f_dentry->d_inode); + shp->shm_nattch++; + shm_unlock(shp); + + down_write(¤t->mm->mmap_sem); + if (addr && !(shmflg & SHM_REMAP)) { + user_addr = ERR_PTR(-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 = (void*) do_mmap (file, addr, size, prot, flags, 0); + +invalid: + up_write(¤t->mm->mmap_sem); + + down (&shm_ids.sem); + if(!(shp = shm_lock(shmid))) + BUG(); + shp->shm_nattch--; + if(shp->shm_nattch == 0 && + shp->shm_flags & SHM_DEST) + shm_destroy (shp); + else + shm_unlock(shp); + up (&shm_ids.sem); + + *raddr = (unsigned long) user_addr; + err = 0; + if (IS_ERR(user_addr)) + err = PTR_ERR(user_addr); +out: + return err; +} + +/* + * detach and kill segment if marked destroyed. + * The work is done in shm_close. + */ +asmlinkage long sys_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; + + 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 || is_vm_hugetlb_page(vma)) && + (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { + + + size = vma->vm_file->f_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. + */ + 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 || is_vm_hugetlb_page(vma)) && + (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_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data) +{ + off_t pos = 0; + off_t begin = 0; + int i, len = 0; + + down(&shm_ids.sem); + len += sprintf(buffer, " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime\n"); + + for(i = 0; i <= shm_ids.max_id; i++) { + struct shmid_kernel* shp; + + shp = shm_lock(i); + if(shp!=NULL) { +#define SMALL_STRING "%10d %10d %4o %10u %5u %5u %5d %5u %5u %5u %5u %10lu %10lu %10lu\n" +#define BIG_STRING "%10d %10d %4o %21u %5u %5u %5d %5u %5u %5u %5u %10lu %10lu %10lu\n" + char *format; + + if (sizeof(size_t) <= sizeof(int)) + format = SMALL_STRING; + else + format = BIG_STRING; + len += sprintf(buffer + len, format, + shp->shm_perm.key, + shm_buildid(i, shp->shm_perm.seq), + shp->shm_flags, + shp->shm_segsz, + shp->shm_cprid, + shp->shm_lprid, + is_file_hugepages(shp->shm_file) ? (file_count(shp->shm_file) - 1) : 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); + shm_unlock(shp); + + pos += len; + if(pos < offset) { + len = 0; + begin = pos; + } + if(pos > offset + length) + goto done; + } + } + *eof = 1; +done: + up(&shm_ids.sem); + *start = buffer + (offset - begin); + len -= (offset - begin); + if(len > length) + len = length; + if(len < 0) + len = 0; + return len; +} +#endif diff --git a/ipc/util.c b/ipc/util.c new file mode 100644 index 000000000000..e00c35f7b2b8 --- /dev/null +++ b/ipc/util.c @@ -0,0 +1,580 @@ +/* + * 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, + * Nov 1999 - ipc helper functions, unified SMP locking + * Manfred Spraul + * Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary(). + * Mingming Cao + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "util.h" + +/** + * ipc_init - initialise IPC subsystem + * + * The various system5 IPC resources (semaphores, messages and shared + * memory are initialised + */ + +static int __init ipc_init(void) +{ + sem_init(); + msg_init(); + shm_init(); + return 0; +} +__initcall(ipc_init); + +/** + * ipc_init_ids - initialise IPC identifiers + * @ids: Identifier set + * @size: Number of identifiers + * + * Given a size for the ipc identifier range (limited below IPCMNI) + * set up the sequence range to use then allocate and initialise the + * array itself. + */ + +void __init ipc_init_ids(struct ipc_ids* ids, int size) +{ + int i; + sema_init(&ids->sem,1); + + if(size > IPCMNI) + size = IPCMNI; + ids->in_use = 0; + ids->max_id = -1; + ids->seq = 0; + { + int seq_limit = INT_MAX/SEQ_MULTIPLIER; + if(seq_limit > USHRT_MAX) + ids->seq_max = USHRT_MAX; + else + ids->seq_max = seq_limit; + } + + ids->entries = ipc_rcu_alloc(sizeof(struct kern_ipc_perm *)*size + + sizeof(struct ipc_id_ary)); + + if(ids->entries == NULL) { + printk(KERN_ERR "ipc_init_ids() failed, ipc service disabled.\n"); + size = 0; + ids->entries = &ids->nullentry; + } + ids->entries->size = size; + for(i=0;ientries->p[i] = NULL; +} + +/** + * ipc_findkey - find a key in an ipc identifier set + * @ids: Identifier set + * @key: The key to find + * + * Requires ipc_ids.sem locked. + * Returns the identifier if found or -1 if not. + */ + +int ipc_findkey(struct ipc_ids* ids, key_t key) +{ + int id; + struct kern_ipc_perm* p; + int max_id = ids->max_id; + + /* + * rcu_dereference() is not needed here + * since ipc_ids.sem is held + */ + for (id = 0; id <= max_id; id++) { + p = ids->entries->p[id]; + if(p==NULL) + continue; + if (key == p->key) + return id; + } + return -1; +} + +/* + * Requires ipc_ids.sem locked + */ +static int grow_ary(struct ipc_ids* ids, int newsize) +{ + struct ipc_id_ary* new; + struct ipc_id_ary* old; + int i; + int size = ids->entries->size; + + if(newsize > IPCMNI) + newsize = IPCMNI; + if(newsize <= size) + return newsize; + + new = ipc_rcu_alloc(sizeof(struct kern_ipc_perm *)*newsize + + sizeof(struct ipc_id_ary)); + if(new == NULL) + return size; + new->size = newsize; + memcpy(new->p, ids->entries->p, sizeof(struct kern_ipc_perm *)*size + + sizeof(struct ipc_id_ary)); + for(i=size;ip[i] = NULL; + } + old = ids->entries; + + /* + * Use rcu_assign_pointer() to make sure the memcpyed contents + * of the new array are visible before the new array becomes visible. + */ + rcu_assign_pointer(ids->entries, new); + + ipc_rcu_putref(old); + return newsize; +} + +/** + * ipc_addid - add an IPC identifier + * @ids: IPC identifier set + * @new: new IPC permission set + * @size: new size limit for the id array + * + * Add an entry 'new' to the IPC arrays. The permissions object is + * initialised and the first free entry is set up and the id assigned + * is returned. The list is returned in a locked state on success. + * On failure the list is not locked and -1 is returned. + * + * Called with ipc_ids.sem held. + */ + +int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) +{ + int id; + + size = grow_ary(ids,size); + + /* + * rcu_dereference()() is not needed here since + * ipc_ids.sem is held + */ + for (id = 0; id < size; id++) { + if(ids->entries->p[id] == NULL) + goto found; + } + return -1; +found: + ids->in_use++; + if (id > ids->max_id) + ids->max_id = id; + + 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; + + spin_lock_init(&new->lock); + new->deleted = 0; + rcu_read_lock(); + spin_lock(&new->lock); + ids->entries->p[id] = new; + return id; +} + +/** + * ipc_rmid - remove an IPC identifier + * @ids: identifier set + * @id: Identifier to remove + * + * The identifier must be valid, and in use. The kernel will panic if + * fed an invalid identifier. The entry is removed and internal + * variables recomputed. The object associated with the identifier + * is returned. + * ipc_ids.sem and the spinlock for this ID is hold before this function + * is called, and remain locked on the exit. + */ + +struct kern_ipc_perm* ipc_rmid(struct ipc_ids* ids, int id) +{ + struct kern_ipc_perm* p; + int lid = id % SEQ_MULTIPLIER; + if(lid >= ids->entries->size) + BUG(); + + /* + * do not need a rcu_dereference()() here to force ordering + * on Alpha, since the ipc_ids.sem is held. + */ + p = ids->entries->p[lid]; + ids->entries->p[lid] = NULL; + if(p==NULL) + BUG(); + ids->in_use--; + + if (lid == ids->max_id) { + do { + lid--; + if(lid == -1) + break; + } while (ids->entries->p[lid] == NULL); + ids->max_id = lid; + } + p->deleted = 1; + return p; +} + +/** + * 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++; +} + +/** + * ipc_schedule_free - free ipc + rcu space + * + * 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 = + container_of(head, struct ipc_rcu_grace, rcu); + struct ipc_rcu_sched *sched = + container_of(&(grace->data[0]), struct ipc_rcu_sched, data[0]); + + INIT_WORK(&sched->work, vfree, sched); + schedule_work(&sched->work); +} + +/** + * ipc_immediate_free - free ipc + rcu space + * + * 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 */ + int requested_mode, granted_mode; + + 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 old ipc permissions to new + * @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; +} + +/* + * So far only shm_get_stat() calls ipc_get() via shm_get(), so ipc_get() + * is called with shm_ids.sem locked. Since grow_ary() is also called with + * shm_ids.sem down(for Shared Memory), there is no need to add read + * barriers here to gurantee the writes in grow_ary() are seen in order + * here (for Alpha). + * + * However ipc_get() itself does not necessary require ipc_ids.sem down. So + * if in the future ipc_get() is used by other places without ipc_ids.sem + * down, then ipc_get() needs read memery barriers as ipc_lock() does. + */ +struct kern_ipc_perm* ipc_get(struct ipc_ids* ids, int id) +{ + struct kern_ipc_perm* out; + int lid = id % SEQ_MULTIPLIER; + if(lid >= ids->entries->size) + return NULL; + out = ids->entries->p[lid]; + return out; +} + +struct kern_ipc_perm* ipc_lock(struct ipc_ids* ids, int id) +{ + struct kern_ipc_perm* out; + int lid = id % SEQ_MULTIPLIER; + struct ipc_id_ary* entries; + + rcu_read_lock(); + entries = rcu_dereference(ids->entries); + if(lid >= entries->size) { + rcu_read_unlock(); + return NULL; + } + out = entries->p[lid]; + if(out == NULL) { + rcu_read_unlock(); + return NULL; + } + 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 NULL; + } + return out; +} + +void ipc_lock_by_ptr(struct kern_ipc_perm *perm) +{ + rcu_read_lock(); + spin_lock(&perm->lock); +} + +void ipc_unlock(struct kern_ipc_perm* perm) +{ + spin_unlock(&perm->lock); + rcu_read_unlock(); +} + +int ipc_buildid(struct ipc_ids* ids, int id, int seq) +{ + return SEQ_MULTIPLIER*seq + id; +} + +int ipc_checkid(struct ipc_ids* ids, struct kern_ipc_perm* ipcp, int uid) +{ + if(uid/SEQ_MULTIPLIER != ipcp->seq) + return 1; + return 0; +} + +#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 */ diff --git a/ipc/util.h b/ipc/util.h new file mode 100644 index 000000000000..07d689452363 --- /dev/null +++ b/ipc/util.h @@ -0,0 +1,81 @@ +/* + * linux/ipc/util.h + * Copyright (C) 1999 Christoph Rohland + * + * ipc helper functions (c) 1999 Manfred Spraul + */ + +#ifndef _IPC_UTIL_H +#define _IPC_UTIL_H + +#define USHRT_MAX 0xffff +#define SEQ_MULTIPLIER (IPCMNI) + +void sem_init (void); +void msg_init (void); +void shm_init (void); + +struct ipc_id_ary { + int size; + struct kern_ipc_perm *p[0]; +}; + +struct ipc_ids { + int in_use; + int max_id; + unsigned short seq; + unsigned short seq_max; + struct semaphore sem; + struct ipc_id_ary nullentry; + struct ipc_id_ary* entries; +}; + +void __init ipc_init_ids(struct ipc_ids* ids, int size); + +/* must be called with ids->sem acquired.*/ +int ipc_findkey(struct ipc_ids* ids, key_t key); +int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size); + +/* must be called with both locks acquired. */ +struct kern_ipc_perm* ipc_rmid(struct ipc_ids* ids, int id); + +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_get(struct ipc_ids* ids, int id); +struct kern_ipc_perm* ipc_lock(struct ipc_ids* ids, int id); +void ipc_lock_by_ptr(struct kern_ipc_perm *ipcp); +void ipc_unlock(struct kern_ipc_perm* perm); +int ipc_buildid(struct ipc_ids* ids, int id, int seq); +int ipc_checkid(struct ipc_ids* ids, struct kern_ipc_perm* ipcp, int uid); + +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); + +#if defined(__ia64__) || defined(__x86_64__) || defined(__hppa__) + /* 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); + +#endif -- cgit v1.2.3