X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fpipe.c;h=db6eaaba0dd81fb777f2b64f1e385d40eb3f1819;hb=1bf7dbfde8fe7ddaa8e2e1b4e0fc41a9fc6aa7a5;hp=8be381bbcb54ad4108ea3bf453b19afd702314b5;hpb=430e285e0817e3e18aadd814bc078d50d8af0cbf;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/pipe.c b/fs/pipe.c index 8be381b..db6eaab 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -11,17 +11,26 @@ #include #include #include +#include #include #include #include #include #include #include +#include +#include #include #include /* + * The max size that a non-root user is allowed to grow the pipe. Can + * be set by root in /proc/sys/fs/pipe-max-pages + */ +unsigned int pipe_max_pages = PIPE_DEF_BUFFERS * 16; + +/* * We use a start+len construction, which provides full use of the * allocated memory. * -- Florian Coosmann (FGC) @@ -36,6 +45,42 @@ * -- Manfred Spraul 2002-05-09 */ +static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass) +{ + if (pipe->inode) + mutex_lock_nested(&pipe->inode->i_mutex, subclass); +} + +void pipe_lock(struct pipe_inode_info *pipe) +{ + /* + * pipe_lock() nests non-pipe inode locks (for writing to a file) + */ + pipe_lock_nested(pipe, I_MUTEX_PARENT); +} +EXPORT_SYMBOL(pipe_lock); + +void pipe_unlock(struct pipe_inode_info *pipe) +{ + if (pipe->inode) + mutex_unlock(&pipe->inode->i_mutex); +} +EXPORT_SYMBOL(pipe_unlock); + +void pipe_double_lock(struct pipe_inode_info *pipe1, + struct pipe_inode_info *pipe2) +{ + BUG_ON(pipe1 == pipe2); + + if (pipe1 < pipe2) { + pipe_lock_nested(pipe1, I_MUTEX_PARENT); + pipe_lock_nested(pipe2, I_MUTEX_CHILD); + } else { + pipe_lock_nested(pipe2, I_MUTEX_PARENT); + pipe_lock_nested(pipe1, I_MUTEX_CHILD); + } +} + /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe) { @@ -46,12 +91,10 @@ void pipe_wait(struct pipe_inode_info *pipe) * is considered a noninteractive wait: */ prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); + pipe_unlock(pipe); schedule(); finish_wait(&pipe->wait, &wait); - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); } static int @@ -187,6 +230,7 @@ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, return kmap(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_map); /** * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer @@ -206,6 +250,7 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, } else kunmap(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_unmap); /** * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer @@ -236,6 +281,7 @@ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, return 1; } +EXPORT_SYMBOL(generic_pipe_buf_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer @@ -251,6 +297,7 @@ void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { page_cache_get(buf->page); } +EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_confirm - verify contents of the pipe buffer @@ -266,6 +313,22 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info, { return 0; } +EXPORT_SYMBOL(generic_pipe_buf_confirm); + +/** + * generic_pipe_buf_release - put a reference to a &struct pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to put a reference to + * + * Description: + * This function releases a reference to @buf. + */ +void generic_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + page_cache_release(buf->page); +} +EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .can_merge = 1, @@ -341,7 +404,7 @@ redo: if (!buf->len) { buf->ops = NULL; ops->release(pipe, buf); - curbuf = (curbuf + 1) & (PIPE_BUFFERS-1); + curbuf = (curbuf + 1) & (pipe->buffers - 1); pipe->curbuf = curbuf; pipe->nrbufs = --bufs; do_wakeup = 1; @@ -423,7 +486,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */ if (pipe->nrbufs && chars != 0) { int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) & - (PIPE_BUFFERS-1); + (pipe->buffers - 1); struct pipe_buffer *buf = pipe->bufs + lastbuf; const struct pipe_buf_operations *ops = buf->ops; int offset = buf->offset + buf->len; @@ -469,8 +532,8 @@ redo1: break; } bufs = pipe->nrbufs; - if (bufs < PIPE_BUFFERS) { - int newbuf = (pipe->curbuf + bufs) & (PIPE_BUFFERS-1); + if (bufs < pipe->buffers) { + int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1); struct pipe_buffer *buf = pipe->bufs + newbuf; struct page *page = pipe->tmp_page; char *src; @@ -531,7 +594,7 @@ redo2: if (!total_len) break; } - if (bufs < PIPE_BUFFERS) + if (bufs < pipe->buffers) continue; if (filp->f_flags & O_NONBLOCK) { if (!ret) @@ -591,7 +654,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) nrbufs = pipe->nrbufs; while (--nrbufs >= 0) { count += pipe->bufs[buf].len; - buf = (buf+1) & (PIPE_BUFFERS-1); + buf = (buf+1) & (pipe->buffers - 1); } mutex_unlock(&inode->i_mutex); @@ -622,7 +685,7 @@ pipe_poll(struct file *filp, poll_table *wait) } if (filp->f_mode & FMODE_WRITE) { - mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0; + mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0; /* * Most Unices do not set POLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). @@ -666,10 +729,7 @@ pipe_read_fasync(int fd, struct file *filp, int on) retval = fasync_helper(fd, filp, on, &inode->i_pipe->fasync_readers); mutex_unlock(&inode->i_mutex); - if (retval < 0) - return retval; - - return 0; + return retval; } @@ -683,10 +743,7 @@ pipe_write_fasync(int fd, struct file *filp, int on) retval = fasync_helper(fd, filp, on, &inode->i_pipe->fasync_writers); mutex_unlock(&inode->i_mutex); - if (retval < 0) - return retval; - - return 0; + return retval; } @@ -698,32 +755,26 @@ pipe_rdwr_fasync(int fd, struct file *filp, int on) int retval; mutex_lock(&inode->i_mutex); - retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); - - if (retval >= 0) + if (retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); - + if (retval < 0) /* this can happen only if on == T */ + fasync_helper(-1, filp, 0, &pipe->fasync_readers); + } mutex_unlock(&inode->i_mutex); - - if (retval < 0) - return retval; - - return 0; + return retval; } static int pipe_read_release(struct inode *inode, struct file *filp) { - pipe_read_fasync(-1, filp, 0); return pipe_release(inode, 1, 0); } static int pipe_write_release(struct inode *inode, struct file *filp) { - pipe_write_fasync(-1, filp, 0); return pipe_release(inode, 0, 1); } @@ -732,7 +783,6 @@ pipe_rdwr_release(struct inode *inode, struct file *filp) { int decr, decw; - pipe_rdwr_fasync(-1, filp, 0); decr = (filp->f_mode & FMODE_READ) != 0; decw = (filp->f_mode & FMODE_WRITE) != 0; return pipe_release(inode, decr, decw); @@ -741,43 +791,64 @@ pipe_rdwr_release(struct inode *inode, struct file *filp) static int pipe_read_open(struct inode *inode, struct file *filp) { - /* We could have perhaps used atomic_t, but this and friends - below are the only places. So it doesn't seem worthwhile. */ + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - inode->i_pipe->readers++; + + if (inode->i_pipe) { + ret = 0; + inode->i_pipe->readers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } static int pipe_write_open(struct inode *inode, struct file *filp) { + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - inode->i_pipe->writers++; + + if (inode->i_pipe) { + ret = 0; + inode->i_pipe->writers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } static int pipe_rdwr_open(struct inode *inode, struct file *filp) { + int ret = -ENOENT; + mutex_lock(&inode->i_mutex); - if (filp->f_mode & FMODE_READ) - inode->i_pipe->readers++; - if (filp->f_mode & FMODE_WRITE) - inode->i_pipe->writers++; + + if (inode->i_pipe) { + ret = 0; + if (filp->f_mode & FMODE_READ) + inode->i_pipe->readers++; + if (filp->f_mode & FMODE_WRITE) + inode->i_pipe->writers++; + } + mutex_unlock(&inode->i_mutex); - return 0; + return ret; } /* * The file_operations structs are not static because they * are also used in linux/fs/fifo.c to do operations on FIFOs. + * + * Pipes reuse fifos' file_operations structs. */ -const struct file_operations read_fifo_fops = { +const struct file_operations read_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, @@ -789,7 +860,7 @@ const struct file_operations read_fifo_fops = { .fasync = pipe_read_fasync, }; -const struct file_operations write_fifo_fops = { +const struct file_operations write_pipefifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, .write = do_sync_write, @@ -801,44 +872,7 @@ const struct file_operations write_fifo_fops = { .fasync = pipe_write_fasync, }; -const struct file_operations rdwr_fifo_fops = { - .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = do_sync_write, - .aio_write = pipe_write, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_rdwr_open, - .release = pipe_rdwr_release, - .fasync = pipe_rdwr_fasync, -}; - -static const struct file_operations read_pipe_fops = { - .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = bad_pipe_w, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_read_open, - .release = pipe_read_release, - .fasync = pipe_read_fasync, -}; - -static const struct file_operations write_pipe_fops = { - .llseek = no_llseek, - .read = bad_pipe_r, - .write = do_sync_write, - .aio_write = pipe_write, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_write_open, - .release = pipe_write_release, - .fasync = pipe_write_fasync, -}; - -static const struct file_operations rdwr_pipe_fops = { +const struct file_operations rdwr_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, @@ -857,25 +891,32 @@ struct pipe_inode_info * alloc_pipe_info(struct inode *inode) pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL); if (pipe) { - init_waitqueue_head(&pipe->wait); - pipe->r_counter = pipe->w_counter = 1; - pipe->inode = inode; + pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL); + if (pipe->bufs) { + init_waitqueue_head(&pipe->wait); + pipe->r_counter = pipe->w_counter = 1; + pipe->inode = inode; + pipe->buffers = PIPE_DEF_BUFFERS; + return pipe; + } + kfree(pipe); } - return pipe; + return NULL; } void __free_pipe_info(struct pipe_inode_info *pipe) { int i; - for (i = 0; i < PIPE_BUFFERS; i++) { + for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) buf->ops->release(pipe, buf); } if (pipe->tmp_page) __free_page(pipe->tmp_page); + kfree(pipe->bufs); kfree(pipe); } @@ -886,17 +927,6 @@ void free_pipe_info(struct inode *inode) } static struct vfsmount *pipe_mnt __read_mostly; -static int pipefs_delete_dentry(struct dentry *dentry) -{ - /* - * At creation time, we pretended this dentry was hashed - * (by clearing DCACHE_UNHASHED bit in d_flags) - * At delete time, we restore the truth : not hashed. - * (so that dput() can proceed correctly) - */ - dentry->d_flags |= DCACHE_UNHASHED; - return 0; -} /* * pipefs_dname() is called from d_path(). @@ -907,8 +937,7 @@ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) dentry->d_inode->i_ino); } -static struct dentry_operations pipefs_dentry_operations = { - .d_delete = pipefs_delete_dentry, +static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; @@ -926,7 +955,7 @@ static struct inode * get_pipe_inode(void) inode->i_pipe = pipe; pipe->readers = pipe->writers = 1; - inode->i_fop = &rdwr_pipe_fops; + inode->i_fop = &rdwr_pipefifo_fops; /* * Mark the inode dirty from the very beginning, @@ -936,8 +965,8 @@ static struct inode * get_pipe_inode(void) */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; return inode; @@ -949,12 +978,12 @@ fail_inode: return NULL; } -struct file *create_write_pipe(void) +struct file *create_write_pipe(int flags) { int err; struct inode *inode; struct file *f; - struct dentry *dentry; + struct path path; struct qstr name = { .name = "" }; err = -ENFILE; @@ -963,32 +992,30 @@ struct file *create_write_pipe(void) goto err; err = -ENOMEM; - dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name); - if (!dentry) + path.dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name); + if (!path.dentry) goto err_inode; + path.mnt = mntget(pipe_mnt); - dentry->d_op = &pipefs_dentry_operations; - /* - * We dont want to publish this dentry into global dentry hash table. - * We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED - * This permits a working /proc/$pid/fd/XXX on pipes - */ - dentry->d_flags &= ~DCACHE_UNHASHED; - d_instantiate(dentry, inode); + path.dentry->d_op = &pipefs_dentry_operations; + d_instantiate(path.dentry, inode); err = -ENFILE; - f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipe_fops); + f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops); if (!f) goto err_dentry; f->f_mapping = inode->i_mapping; - f->f_flags = O_WRONLY; + f->f_flags = O_WRONLY | (flags & O_NONBLOCK); f->f_version = 0; return f; err_dentry: - dput(dentry); + free_pipe_info(inode); + path_put(&path); + return ERR_PTR(err); + err_inode: free_pipe_info(inode); iput(inode); @@ -999,59 +1026,52 @@ struct file *create_write_pipe(void) void free_write_pipe(struct file *f) { free_pipe_info(f->f_dentry->d_inode); - dput(f->f_path.dentry); - mntput(f->f_path.mnt); + path_put(&f->f_path); put_filp(f); } -struct file *create_read_pipe(struct file *wrf) +struct file *create_read_pipe(struct file *wrf, int flags) { - struct file *f = get_empty_filp(); + /* Grab pipe from the writer */ + struct file *f = alloc_file(&wrf->f_path, FMODE_READ, + &read_pipefifo_fops); if (!f) return ERR_PTR(-ENFILE); - /* Grab pipe from the writer */ - f->f_path.mnt = mntget(wrf->f_path.mnt); - f->f_path.dentry = dget(wrf->f_path.dentry); - f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping; - - f->f_pos = 0; - f->f_flags = O_RDONLY; - f->f_op = &read_pipe_fops; - f->f_mode = FMODE_READ; - f->f_version = 0; + path_get(&wrf->f_path); + f->f_flags = O_RDONLY | (flags & O_NONBLOCK); return f; } -int do_pipe(int *fd) +int do_pipe_flags(int *fd, int flags) { struct file *fw, *fr; int error; int fdw, fdr; - fw = create_write_pipe(); + if (flags & ~(O_CLOEXEC | O_NONBLOCK)) + return -EINVAL; + + fw = create_write_pipe(flags); if (IS_ERR(fw)) return PTR_ERR(fw); - fr = create_read_pipe(fw); + fr = create_read_pipe(fw, flags); error = PTR_ERR(fr); if (IS_ERR(fr)) goto err_write_pipe; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; - error = audit_fd_pair(fdr, fdw); - if (error < 0) - goto err_fdw; - + audit_fd_pair(fdr, fdw); fd_install(fdr, fr); fd_install(fdw, fw); fd[0] = fdr; @@ -1059,13 +1079,10 @@ int do_pipe(int *fd) return 0; - err_fdw: - put_unused_fd(fdw); err_fdr: put_unused_fd(fdr); err_read_pipe: - dput(fr->f_dentry); - mntput(fr->f_vfsmnt); + path_put(&fr->f_path); put_filp(fr); err_write_pipe: free_write_pipe(fw); @@ -1073,6 +1090,119 @@ int do_pipe(int *fd) } /* + * sys_pipe() is the normal C calling standard for creating + * a pipe. It's not the way Unix traditionally does this, though. + */ +SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) +{ + int fd[2]; + int error; + + error = do_pipe_flags(fd, flags); + if (!error) { + if (copy_to_user(fildes, fd, sizeof(fd))) { + sys_close(fd[0]); + sys_close(fd[1]); + error = -EFAULT; + } + } + return error; +} + +SYSCALL_DEFINE1(pipe, int __user *, fildes) +{ + return sys_pipe2(fildes, 0); +} + +/* + * Allocate a new array of pipe buffers and copy the info over. Returns the + * pipe size if successful, or return -ERROR on error. + */ +static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) +{ + struct pipe_buffer *bufs; + + /* + * Must be a power-of-2 currently + */ + if (!is_power_of_2(arg)) + return -EINVAL; + + /* + * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't + * expect a lot of shrink+grow operations, just free and allocate + * again like we would do for growing. If the pipe currently + * contains more buffers than arg, then return busy. + */ + if (arg < pipe->nrbufs) + return -EBUSY; + + bufs = kcalloc(arg, sizeof(struct pipe_buffer), GFP_KERNEL); + if (unlikely(!bufs)) + return -ENOMEM; + + /* + * The pipe array wraps around, so just start the new one at zero + * and adjust the indexes. + */ + if (pipe->nrbufs) { + const unsigned int tail = pipe->nrbufs & (pipe->buffers - 1); + const unsigned int head = pipe->nrbufs - tail; + + if (head) + memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer)); + if (tail) + memcpy(bufs + head, pipe->bufs + pipe->curbuf, tail * sizeof(struct pipe_buffer)); + } + + pipe->curbuf = 0; + kfree(pipe->bufs); + pipe->bufs = bufs; + pipe->buffers = arg; + return arg; +} + +long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pipe_inode_info *pipe; + long ret; + + pipe = file->f_path.dentry->d_inode->i_pipe; + if (!pipe) + return -EBADF; + + mutex_lock(&pipe->inode->i_mutex); + + switch (cmd) { + case F_SETPIPE_SZ: + if (!capable(CAP_SYS_ADMIN) && arg > pipe_max_pages) { + ret = -EINVAL; + goto out; + } + /* + * The pipe needs to be at least 2 pages large to + * guarantee POSIX behaviour. + */ + if (arg < 2) { + ret = -EINVAL; + goto out; + } + ret = pipe_set_size(pipe, arg); + break; + case F_GETPIPE_SZ: + ret = pipe->buffers; + break; + default: + ret = -EINVAL; + break; + } + +out: + mutex_unlock(&pipe->inode->i_mutex); + return ret; +} + +/* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial