From: Manfred Spraul Actual implementation of the posix message queues, written by Krzysztof Benedyczak and Michal Wronski. The complete implementation is dependant on CONFIG_POSIX_MQUEUE. It passed the openposix test suite with two exceptions: one mq_unlink test was bad and tested undefined behavior. And Linux succeeds mq_close(open(,,,)). The spec mandates EBADF, but we have decided to ignore that: we would have to add a new syscall just for the right error code. The patch intentionally doesn't use all helpers from fs/libfs for kernel-only filesystems: step 5 allows user space mounts of the file system. Signal changes: The patch redefines SI_MESGQ using __SI_CODE: The generic Linux ABI uses a negative value (i.e. from user) for SI_MESGQ, but the kernel internal value must be posive to pass check_kill_value. Additionally, the patch adds support into copy_siginfo_to_user to copy the "new" signal type to user space. Changes in signal code caused by POSIX message queues patch: General & rationale: mqueues generated signals (only upon notification) must have si_code == SI_MESGQ. In fact such a signal is send from one process which caused notification (== sent message to empty message queue) to another which requested it. Both processes can be of course unrelated in terms of uids/euids. So SI_MESGQ signals must be classified as SI_FROMKERNEL to pass check_kill_permissions (not need to say that this signals ARE from kernel). Signals generated by message queues notification need the same fields in siginfo struct's union _sifields as POSIX.1b signals and we can reuse its union entry. SI_MESGQ was previously defined to -3 in kernel and also in glibc. So in userspace SI_MESGQ must be still visible as -3. Solution: SI_MESGQ is defined in the same style as SI_TIMER using __SI_CODE macro. Details: Fortunately copy_siginfo_to_user copies si_code as short. So we can use remaining part of int value freely. __SI_CODE does the work. SI_MESGQ is in kernel: 6<<16 | (-3 & 0xffff) what is > 0 but to userspace is copied (short) SI_MESGQ == -3 Actual changes: Changes in include/asm-generic/siginfo.h __SI_MESGQ added in signal.h to represent inside-kernel prefix of SI_MESGQ. SI_MESGQ is redefined from -3 to __SI_CODE(__SI_MESGQ, -3) Except mips architecture those changes should be arch independent (asm-generic/siginfo.h is included in arch versions). On mips SI_MESGQ is redefined to -4 in order to be compatible with IRIX. But the same schema can be used. Change in copy_siginfo_to_user: We only add one line to order the same copy semantics as for _SI_RT. This change isn't very portable - some arch have its own copy_siginfo_to_user. All those should have similar change (but possibly not one-line as _SI_RT case was sometimes ignored because i wasn't used yet, e.g. see ia64 signal.c). --- 25-akpm/CREDITS | 17 25-akpm/Documentation/filesystems/proc.txt | 25 25-akpm/include/asm-generic/siginfo.h | 4 25-akpm/init/Kconfig | 17 25-akpm/ipc/Makefile | 2 25-akpm/ipc/mqueue.c | 1094 +++++++++++++++++++++++++++++ 25-akpm/kernel/signal.c | 1 7 files changed, 1159 insertions(+), 1 deletion(-) diff -puN CREDITS~mq-03-core CREDITS --- 25/CREDITS~mq-03-core 2004-04-03 20:43:27.380035360 -0800 +++ 25-akpm/CREDITS 2004-04-03 20:43:27.392033536 -0800 @@ -289,6 +289,15 @@ S: Via Delle Palme, 9 S: Terni 05100 S: Italy +N: Krzysztof Benedyczak +E: golbi@mat.uni.torun.pl +W: http://www.mat.uni.torun.pl/~golbi +D: POSIX message queues fs (with M. Wronski) +S: ul. Podmiejska 52 +S: Radunica +S: 83-000 Pruszcz Gdanski +S: Poland + N: Randolph Bentson E: bentson@grieg.seaslug.org W: http://www.aa.net/~bentson/ @@ -3485,6 +3494,14 @@ S: 12725 SW Millikan Way, Suite 400 S: Beaverton, OR 97005 S: USA +N: Michal Wronski +E: wrona@mat.uni.torun.pl +W: http://www.mat.uni.torun.pl/~wrona +D: POSIX message queues fs (with K. Benedyczak) +S: ul. Teczowa 23/12 +S: 80-680 Gdansk-Sobieszewo +S: Poland + N: Frank Xia E: qx@math.columbia.edu D: Xiafs filesystem [defunct] diff -puN Documentation/filesystems/proc.txt~mq-03-core Documentation/filesystems/proc.txt --- 25/Documentation/filesystems/proc.txt~mq-03-core 2004-04-03 20:43:27.381035208 -0800 +++ 25-akpm/Documentation/filesystems/proc.txt 2004-04-03 20:43:27.406031408 -0800 @@ -38,6 +38,7 @@ Table of Contents 2.8 /proc/sys/net/ipv4 - IPV4 settings 2.9 Appletalk 2.10 IPX + 2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem ------------------------------------------------------------------------------ Preface @@ -1814,6 +1815,30 @@ The /proc/net/ipx_route table holds a gives the destination network, the router node (or Directly) and the network address of the router (or Connected) for internal networks. +2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem +---------------------------------------------------------- + +The "mqueue" filesystem provides the necessary kernel features to enable the +creation of a user space library that implements the POSIX message queues +API (as noted by the MSG tag in the POSIX 1003.1-2001 version of the System +Interfaces specification.) + +The "mqueue" filesystem contains values for determining/setting the amount of +resources used by the file system. + +/proc/sys/fs/mqueue/queues_max is a read/write file for setting/getting the +maximum number of message queues allowed on the system. + +/proc/sys/fs/mqueue/msg_max is a read/write file for setting/getting the +maximum number of messages in a queue value. In fact it is the limiting value +for another (user) limit which is set in mq_open invocation. This attribute of +a queue must be less or equal then msg_max. + +/proc/sys/fs/mqueue/msgsize_max is a read/write file for setting/getting the +maximum message size value (it is every message queue's attribute set during +its creation). + + ------------------------------------------------------------------------------ Summary ------------------------------------------------------------------------------ diff -puN include/asm-generic/siginfo.h~mq-03-core include/asm-generic/siginfo.h --- 25/include/asm-generic/siginfo.h~mq-03-core 2004-04-03 20:43:27.383034904 -0800 +++ 25-akpm/include/asm-generic/siginfo.h 2004-04-03 20:43:27.407031256 -0800 @@ -123,6 +123,7 @@ typedef struct siginfo { #define __SI_FAULT (3 << 16) #define __SI_CHLD (4 << 16) #define __SI_RT (5 << 16) +#define __SI_MESGQ (6 << 16) #define __SI_CODE(T,N) ((T) | ((N) & 0xffff)) #else #define __SI_KILL 0 @@ -131,6 +132,7 @@ typedef struct siginfo { #define __SI_FAULT 0 #define __SI_CHLD 0 #define __SI_RT 0 +#define __SI_MESGQ 0 #define __SI_CODE(T,N) (N) #endif @@ -142,7 +144,7 @@ typedef struct siginfo { #define SI_KERNEL 0x80 /* sent by the kernel from somewhere */ #define SI_QUEUE -1 /* sent by sigqueue */ #define SI_TIMER __SI_CODE(__SI_TIMER,-2) /* sent by timer expiration */ -#define SI_MESGQ -3 /* sent by real time mesq state change */ +#define SI_MESGQ __SI_CODE(__SI_MESGQ,-3) /* sent by real time mesq state change */ #define SI_ASYNCIO -4 /* sent by AIO completion */ #define SI_SIGIO -5 /* sent by queued SIGIO */ #define SI_TKILL -6 /* sent by tkill system call */ diff -puN init/Kconfig~mq-03-core init/Kconfig --- 25/init/Kconfig~mq-03-core 2004-04-03 20:43:27.384034752 -0800 +++ 25-akpm/init/Kconfig 2004-04-03 20:43:27.408031104 -0800 @@ -90,6 +90,23 @@ config SYSVIPC section 6.4 of the Linux Programmer's Guide, available from . +config POSIX_MQUEUE + bool "POSIX Message Queues" + ---help--- + POSIX variant of message queues is a part of IPC. In POSIX message + queues every message has a priority which decides about succession + of receiving it by a process. If you want to compile and run + programs written e.g. for Solaris with use of its POSIX message + queues (functions mq_*) say Y here. To use this feature you will + also need mqueue library, available from + + + POSIX message queues are visible as a filesystem called 'mqueue' + and can be mounted somewhere if you want to do filesystem + operations on message queues. + + If unsure, say Y. + config BSD_PROCESS_ACCT bool "BSD Process Accounting" help diff -puN ipc/Makefile~mq-03-core ipc/Makefile --- 25/ipc/Makefile~mq-03-core 2004-04-03 20:43:27.385034600 -0800 +++ 25-akpm/ipc/Makefile 2004-04-03 20:43:27.408031104 -0800 @@ -4,3 +4,5 @@ obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o +obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o + diff -puN /dev/null ipc/mqueue.c --- /dev/null 2003-09-15 06:40:47.000000000 -0700 +++ 25-akpm/ipc/mqueue.c 2004-04-03 20:43:27.412030496 -0800 @@ -0,0 +1,1094 @@ +/* + * 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 "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 + +#define NP_NONE ((void*)NOTIFY_NONE) +#define NP_WOKENUP ((void*)NOTIFY_WOKENUP) +#define NP_REMOVED ((void*)NOTIFY_REMOVED) +/* used by sysctl */ +#define FS_MQUEUE 1 +#define CTL_QUEUESMAX 2 +#define CTL_MSGMAX 3 +#define CTL_MSGSIZEMAX 4 + +/* default values */ +#define DFLT_QUEUESMAX 64 /* max number of message queues */ +#define DFLT_MSGMAX 40 /* max number of messages in each queue */ +#define HARD_MSGMAX (131072/sizeof(void*)) +#define DFLT_MSGSIZEMAX 16384 /* max message size */ + +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 { + struct mq_attr attr; + struct msg_msg **messages; + + pid_t notify_owner; /* != 0 means notification registered */ + struct sigevent notify; + struct file *notify_filp; + + /* for tasks waiting for free space and messages, respectively */ + struct ext_wait_queue e_wait_q[2]; + wait_queue_head_t wait_q; + + unsigned long qsize; /* size of queue in memory (sum of all msgs) */ + spinlock_t lock; + struct inode vfs_inode; +}; + +static struct inode_operations mqueue_dir_inode_operations; +static struct file_operations mqueue_file_operations; +static struct file_operations mqueue_notify_fops; +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 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; + + 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->notify_owner = 0; + info->qsize = 0; + info->attr.mq_curmsgs = 0; + info->messages = NULL; + } else if (S_ISDIR(mode)) { + inode->i_nlink++; + inode->i_op = &mqueue_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + } + } + return inode; +} + +static int mqueue_fill_super(struct super_block *sb, void *data, int silent) +{ + struct inode *inode; + + sb->s_flags = MS_NOUSER; + 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_IRWXUGO); + 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 = (struct mqueue_inode_info *)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; + 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); + + spin_lock(&mq_lock); + queues_count--; + spin_unlock(&mq_lock); +} + +static int mqueue_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd) +{ + struct inode *inode; + 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); + if (!inode) { + error = -ENOMEM; + spin_lock(&mq_lock); + queues_count--; + goto out_lock; + } + + d_instantiate(dentry, inode); + dget(dentry); + return 0; +out_lock: + spin_unlock(&mq_lock); + return error; +} + +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; +} + +/* 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; + } + printk(KERN_WARNING "mqueue: Spurious wakeup in wq_sleep()\n"); + } + 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]; +} + +/* + * 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) { + /* sends signal */ + if (info->notify.sigev_notify == SIGEV_SIGNAL) { + struct siginfo sig_i; + + 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); + } else if (info->notify.sigev_notify == SIGEV_THREAD) { + info->notify_filp->private_data = (void*)NP_WOKENUP; + wake_up(&info->wait_q); + } + /* after notification unregisters process */ + info->notify_owner = 0; + } +} + +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 unsigned int mqueue_notify_poll(struct file *filp, struct poll_table_struct *poll_tab) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode); + int retval; + + poll_wait(filp, &info->wait_q, poll_tab); + + if (filp->private_data == NP_NONE) + retval = 0; + else + retval = POLLIN | POLLRDNORM; + return retval; +} + +static ssize_t mqueue_notify_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +{ + struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode); + char result; + + if (!count) + return 0; + if (*ppos != 0) + return 0; + spin_lock(&info->lock); + while (filp->private_data == NP_NONE) { + DEFINE_WAIT(wait); + if (filp->f_flags & O_NONBLOCK) { + spin_unlock(&info->lock); + return -EAGAIN; + } + prepare_to_wait(&info->wait_q, &wait, TASK_INTERRUPTIBLE); + spin_unlock(&info->lock); + schedule(); + finish_wait(&info->wait_q, &wait); + spin_lock(&info->lock); + } + spin_unlock(&info->lock); + result = (char)(unsigned long)filp->private_data; + if (put_user(result, buf)) + return -EFAULT; + *ppos = 1; + return 1; +} + +static void remove_notification(struct mqueue_inode_info *info) +{ + if (info->notify.sigev_notify == SIGEV_THREAD) { + info->notify_filp->private_data = NP_REMOVED; + wake_up(&info->wait_q); + } + info->notify_owner = 0; +} + +/* + * 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 inode *inode; + struct mqueue_inode_info *info; + struct msg_msg **msgs = NULL; + struct mq_attr attr; + int ret; + + if (u_attr != NULL) { + if (copy_from_user(&attr, u_attr, sizeof(attr))) + return ERR_PTR(-EFAULT); + + if (attr.mq_maxmsg <= 0 || attr.mq_msgsize <= 0) + return ERR_PTR(-EINVAL); + if (capable(CAP_SYS_RESOURCE)) { + if (attr.mq_maxmsg > HARD_MSGMAX) + return ERR_PTR(-EINVAL); + } else { + if (attr.mq_maxmsg > msg_max || attr.mq_msgsize > msgsize_max) + return ERR_PTR(-EINVAL); + } + } else { + attr.mq_maxmsg = DFLT_MSGMAX; + attr.mq_msgsize = DFLT_MSGSIZEMAX; + } + msgs = kmalloc(attr.mq_maxmsg * sizeof(*msgs), GFP_KERNEL); + if (!msgs) + return ERR_PTR(-ENOMEM); + + ret = vfs_create(dir->d_inode, dentry, mode, NULL); + if (ret) { + kfree(msgs); + return ERR_PTR(ret); + } + + inode = dentry->d_inode; + info = MQUEUE_I(inode); + + info->attr.mq_maxmsg = attr.mq_maxmsg; + info->attr.mq_msgsize = attr.mq_msgsize; + info->messages = msgs; + + 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) +{ + struct file *filp; + static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, MAY_READ | MAY_WRITE }; + + 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; + } + + 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; + } + + if (permission(dentry->d_inode, MAY_WRITE, NULL)) { + err = -EACCES; + 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. Do not confuse this with SysV message + * queues terminology. It is little bit different. */ + +/* 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) + 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; + + if (unlikely((timeout = prepare_timeout(u_abs_timeout)) < 0)) + return timeout; + + ret = -EBADF; + filp = fget(mqdes); + if (unlikely(!filp)) + goto out; + + inode = filp->f_dentry->d_inode; + if (unlikely(inode->i_sb != mqueue_mnt->mnt_sb)) + goto out_fput; + info = MQUEUE_I(inode); + + if (unlikely((filp->f_flags & O_ACCMODE) == O_RDONLY)) + 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((void *)u_msg_ptr, msg_len); + if (unlikely(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 { + 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; + + + if (unlikely((timeout = prepare_timeout(u_abs_timeout)) < 0)) + return timeout; + + ret = -EBADF; + filp = fget(mqdes); + if (unlikely(!filp)) + goto out; + + inode = filp->f_dentry->d_inode; + if (unlikely(inode->i_sb != mqueue_mnt->mnt_sb)) + goto out_fput; + info = MQUEUE_I(inode); + + if (unlikely((filp->f_flags & O_ACCMODE) == O_WRONLY)) + 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 { + 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 or SIGEV_NONE) + * 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, fd; + struct file *filp, *nfilp; + struct inode *inode; + struct sigevent notification; + struct mqueue_inode_info *info; + + if (u_notification == NULL) { + notification.sigev_notify = SIGEV_NONE; + } else { + 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; + } + } + + ret = -EBADF; + filp = fget(mqdes); + if (!filp) + goto out; + + inode = filp->f_dentry->d_inode; + if (unlikely(inode->i_sb != mqueue_mnt->mnt_sb)) + goto out_fput; + info = MQUEUE_I(inode); + + ret = 0; + if (notification.sigev_notify == SIGEV_THREAD) { + ret = get_unused_fd(); + if (ret < 0) + goto out_fput; + fd = ret; + nfilp = get_empty_filp(); + if (!nfilp) { + ret = -ENFILE; + goto out_dropfd; + } + nfilp->private_data = NP_NONE; + nfilp->f_op = &mqueue_notify_fops; + nfilp->f_vfsmnt = mntget(mqueue_mnt); + nfilp->f_dentry = dget(filp->f_dentry); + nfilp->f_mapping = filp->f_dentry->d_inode->i_mapping; + nfilp->f_mode = FMODE_READ; + } else { + nfilp = NULL; + fd = -1; + } + + spin_lock(&info->lock); + + if (notification.sigev_notify == SIGEV_NONE) { + if (info->notify_owner == current->tgid) { + remove_notification(info); + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + } else if (info->notify_owner) { + ret = -EBUSY; + } else if (notification.sigev_notify == SIGEV_THREAD) { + info->notify_filp = nfilp; + fd_install(fd, nfilp); + ret = fd; + fd = -1; + nfilp = NULL; + info->notify.sigev_notify = SIGEV_THREAD; + info->notify_owner = current->tgid; + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } else { + info->notify.sigev_signo = notification.sigev_signo; + info->notify.sigev_value = notification.sigev_value; + info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_owner = current->tgid; + inode->i_atime = inode->i_ctime = CURRENT_TIME; + } + spin_unlock(&info->lock); +out_dropfd: + if (fd != -1) + put_unused_fd(fd); +out_fput: + fput(filp); +out: + 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; + } + + ret = -EBADF; + filp = fget(mqdes); + if (!filp) + goto out; + + inode = filp->f_dentry->d_inode; + if (unlikely(inode->i_sb != mqueue_mnt->mnt_sb)) + goto out_fput; + info = MQUEUE_I(inode); + + spin_lock(&info->lock); + + omqstat = info->attr; + omqstat.mq_flags = filp->f_flags; + 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 = simple_unlink, +}; + +static struct file_operations mqueue_file_operations = { + .flush = mqueue_flush_file, +}; + +static struct file_operations mqueue_notify_fops = { + .poll = mqueue_notify_poll, + .read = mqueue_notify_read, +}; + + +static struct super_operations mqueue_super_ops = { + .alloc_inode = mqueue_alloc_inode, + .destroy_inode = mqueue_destroy_inode, + .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_anon_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; + + mq_sysctl_table = register_sysctl_table(mq_sysctl_root, 0); + if (!mq_sysctl_table) { + error = -ENOMEM; + goto out_cache; + } + + 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: + unregister_sysctl_table(mq_sysctl_table); +out_cache: + 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 -puN kernel/signal.c~mq-03-core kernel/signal.c --- 25/kernel/signal.c~mq-03-core 2004-04-03 20:43:27.387034296 -0800 +++ 25-akpm/kernel/signal.c 2004-04-03 20:43:27.414030192 -0800 @@ -2047,6 +2047,7 @@ int copy_siginfo_to_user(siginfo_t __use err |= __put_user(from->si_stime, &to->si_stime); break; case __SI_RT: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ: /* But this is */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); err |= __put_user(from->si_int, &to->si_int); _