X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fpipe.c;h=f31e2d472984182d8d06ebadc4e66c8dd423b735;hp=b1626f269a3445e38f34c1bc338734e0893bbd32;hb=1d862f41222b7f385bada9f85a67ca5592ffd33e;hpb=d6cbd281d189977b38eac7eb2a4678de19b6b483 diff --git a/fs/pipe.c b/fs/pipe.c index b1626f2..f31e2d4 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -11,16 +11,31 @@ #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-size + */ +unsigned int pipe_max_size = 1048576; + +/* + * Minimum pipe size, as required by POSIX + */ +unsigned int pipe_min_size = PAGE_SIZE; + +/* * We use a start+len construction, which provides full use of the * allocated memory. * -- Florian Coosmann (FGC) @@ -35,6 +50,42 @@ * -- 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) { @@ -44,14 +95,11 @@ void pipe_wait(struct pipe_inode_info *pipe) * Pipes are system-local resources, so sleeping on them * is considered a noninteractive wait: */ - prepare_to_wait(&pipe->wait, &wait, - TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE); - if (pipe->inode) - mutex_unlock(&pipe->inode->i_mutex); + prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); + pipe_unlock(pipe); schedule(); finish_wait(&pipe->wait, &wait); - if (pipe->inode) - mutex_lock(&pipe->inode->i_mutex); + pipe_lock(pipe); } static int @@ -163,6 +211,20 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe, page_cache_release(page); } +/** + * generic_pipe_buf_map - virtually map a pipe buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer that should be mapped + * @atomic: whether to use an atomic map + * + * Description: + * This function returns a kernel virtual address mapping for the + * pipe_buffer passed in @buf. If @atomic is set, an atomic map is provided + * and the caller has to be careful not to fault before calling + * the unmap function. + * + * Note that this function occupies KM_USER0 if @atomic != 0. + */ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, struct pipe_buffer *buf, int atomic) { @@ -173,7 +235,17 @@ 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 + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer that should be unmapped + * @map_data: the data that the mapping function returned + * + * Description: + * This function undoes the mapping that ->map() provided. + */ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, struct pipe_buffer *buf, void *map_data) { @@ -183,12 +255,30 @@ 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 + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to attempt to steal + * + * Description: + * This function attempts to steal the &struct page attached to + * @buf. If successful, this function returns 0 and returns with + * the page locked. The caller may then reuse the page for whatever + * he wishes; the typical use is insertion into a different file + * page cache. + */ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; + /* + * A reference of one is golden, that means that the owner of this + * page is the only one holding a reference to it. lock the page + * and return OK. + */ if (page_count(page) == 1) { lock_page(page); return 0; @@ -196,22 +286,60 @@ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, return 1; } +EXPORT_SYMBOL(generic_pipe_buf_steal); -void generic_pipe_buf_get(struct pipe_inode_info *info, struct pipe_buffer *buf) +/** + * generic_pipe_buf_get - get a reference to a &struct pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to get a reference to + * + * Description: + * This function grabs an extra reference to @buf. It's used in + * in the tee() system call, when we duplicate the buffers in one + * pipe into another. + */ +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); -int generic_pipe_buf_pin(struct pipe_inode_info *info, struct pipe_buffer *buf) +/** + * generic_pipe_buf_confirm - verify contents of the pipe buffer + * @info: the pipe that the buffer belongs to + * @buf: the buffer to confirm + * + * Description: + * This function does nothing, because the generic pipe code uses + * pages that are always good when inserted into the pipe. + */ +int generic_pipe_buf_confirm(struct pipe_inode_info *info, + struct pipe_buffer *buf) { 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 struct pipe_buf_operations anon_pipe_buf_ops = { +static const struct pipe_buf_operations anon_pipe_buf_ops = { .can_merge = 1, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, - .pin = generic_pipe_buf_pin, + .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = generic_pipe_buf_steal, .get = generic_pipe_buf_get, @@ -222,7 +350,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct pipe_inode_info *pipe; int do_wakeup; ssize_t ret; @@ -243,7 +371,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, if (bufs) { int curbuf = pipe->curbuf; struct pipe_buffer *buf = pipe->bufs + curbuf; - struct pipe_buf_operations *ops = buf->ops; + const struct pipe_buf_operations *ops = buf->ops; void *addr; size_t chars = buf->len; int error, atomic; @@ -251,7 +379,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, if (chars > total_len) chars = total_len; - error = ops->pin(pipe, buf); + error = ops->confirm(pipe, buf); if (error) { if (!ret) error = ret; @@ -281,7 +409,7 @@ 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; @@ -322,7 +450,7 @@ redo: /* Signal writers asynchronously that there is more room. */ if (do_wakeup) { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } if (ret > 0) @@ -335,7 +463,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t ppos) { struct file *filp = iocb->ki_filp; - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct pipe_inode_info *pipe; ssize_t ret; int do_wakeup; @@ -363,16 +491,16 @@ 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; - struct pipe_buf_operations *ops = buf->ops; + const struct pipe_buf_operations *ops = buf->ops; int offset = buf->offset + buf->len; if (ops->can_merge && offset + chars <= PAGE_SIZE) { int error, atomic = 1; void *addr; - error = ops->pin(pipe, buf); + error = ops->confirm(pipe, buf); if (error) goto out; @@ -409,8 +537,8 @@ 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; @@ -471,7 +599,7 @@ redo2: if (!total_len) break; } - if (bufs < PIPE_BUFFERS) + if (bufs < pipe->buffers) continue; if (filp->f_flags & O_NONBLOCK) { if (!ret) @@ -495,7 +623,7 @@ redo2: out: mutex_unlock(&inode->i_mutex); if (do_wakeup) { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } if (ret > 0) @@ -516,11 +644,9 @@ bad_pipe_w(struct file *filp, const char __user *buf, size_t count, return -EBADF; } -static int -pipe_ioctl(struct inode *pino, struct file *filp, - unsigned int cmd, unsigned long arg) +static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct pipe_inode_info *pipe; int count, buf, nrbufs; @@ -533,7 +659,7 @@ pipe_ioctl(struct inode *pino, struct file *filp, 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); @@ -548,7 +674,7 @@ static unsigned int pipe_poll(struct file *filp, poll_table *wait) { unsigned int mask; - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct pipe_inode_info *pipe = inode->i_pipe; int nrbufs; @@ -564,7 +690,7 @@ 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(). @@ -589,7 +715,7 @@ pipe_release(struct inode *inode, int decr, int decw) if (!pipe->readers && !pipe->writers) { free_pipe_info(inode); } else { - wake_up_interruptible(&pipe->wait); + wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -601,71 +727,59 @@ pipe_release(struct inode *inode, int decr, int decw) static int pipe_read_fasync(int fd, struct file *filp, int on) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; int retval; mutex_lock(&inode->i_mutex); 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; } static int pipe_write_fasync(int fd, struct file *filp, int on) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; int retval; mutex_lock(&inode->i_mutex); 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; } static int pipe_rdwr_fasync(int fd, struct file *filp, int on) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct pipe_inode_info *pipe = inode->i_pipe; 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); } @@ -674,7 +788,6 @@ 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); @@ -683,111 +796,95 @@ 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 = { - .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = bad_pipe_w, - .poll = pipe_poll, - .ioctl = pipe_ioctl, - .open = pipe_read_open, - .release = pipe_read_release, - .fasync = pipe_read_fasync, -}; - -const struct file_operations write_fifo_fops = { - .llseek = no_llseek, - .read = bad_pipe_r, - .write = do_sync_write, - .aio_write = pipe_write, - .poll = pipe_poll, - .ioctl = pipe_ioctl, - .open = pipe_write_open, - .release = pipe_write_release, - .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, - .ioctl = pipe_ioctl, - .open = pipe_rdwr_open, - .release = pipe_rdwr_release, - .fasync = pipe_rdwr_fasync, -}; - -static struct file_operations read_pipe_fops = { +const struct file_operations read_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, .write = bad_pipe_w, .poll = pipe_poll, - .ioctl = pipe_ioctl, + .unlocked_ioctl = pipe_ioctl, .open = pipe_read_open, .release = pipe_read_release, .fasync = pipe_read_fasync, }; -static struct file_operations write_pipe_fops = { +const struct file_operations write_pipefifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, .write = do_sync_write, .aio_write = pipe_write, .poll = pipe_poll, - .ioctl = pipe_ioctl, + .unlocked_ioctl = pipe_ioctl, .open = pipe_write_open, .release = pipe_write_release, .fasync = pipe_write_fasync, }; -static struct file_operations rdwr_pipe_fops = { +const struct file_operations rdwr_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, .write = do_sync_write, .aio_write = pipe_write, .poll = pipe_poll, - .ioctl = pipe_ioctl, + .unlocked_ioctl = pipe_ioctl, .open = pipe_rdwr_open, .release = pipe_rdwr_release, .fasync = pipe_rdwr_fasync, @@ -799,25 +896,32 @@ 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); } @@ -828,13 +932,18 @@ void free_pipe_info(struct inode *inode) } static struct vfsmount *pipe_mnt __read_mostly; -static int pipefs_delete_dentry(struct dentry *dentry) + +/* + * pipefs_dname() is called from d_path(). + */ +static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { - return 1; + return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]", + 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, }; static struct inode * get_pipe_inode(void) @@ -851,7 +960,7 @@ 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, @@ -861,8 +970,8 @@ 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; @@ -874,104 +983,100 @@ 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; - char name[32]; - struct qstr this; + struct path path; + struct qstr name = { .name = "" }; - f = get_empty_filp(); - if (!f) - return ERR_PTR(-ENFILE); err = -ENFILE; inode = get_pipe_inode(); if (!inode) - goto err_file; + goto err; - sprintf(name, "[%lu]", inode->i_ino); - this.name = name; - this.len = strlen(name); - this.hash = inode->i_ino; /* will go */ err = -ENOMEM; - dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &this); - 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; - d_add(dentry, inode); - f->f_vfsmnt = mntget(pipe_mnt); - f->f_dentry = dentry; + path.dentry->d_op = &pipefs_dentry_operations; + d_instantiate(path.dentry, inode); + + err = -ENFILE; + 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_op = &write_pipe_fops; - f->f_mode = FMODE_WRITE; + f->f_flags = O_WRONLY | (flags & O_NONBLOCK); f->f_version = 0; return f; + err_dentry: + free_pipe_info(inode); + path_put(&path); + return ERR_PTR(err); + err_inode: free_pipe_info(inode); iput(inode); - err_file: - put_filp(f); + err: return ERR_PTR(err); } void free_write_pipe(struct file *f) { - mntput(f->f_vfsmnt); - dput(f->f_dentry); + free_pipe_info(f->f_dentry->d_inode); + 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_vfsmnt = mntget(wrf->f_vfsmnt); - f->f_dentry = dget(wrf->f_dentry); - f->f_mapping = wrf->f_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; + audit_fd_pair(fdr, fdw); fd_install(fdr, fr); fd_install(fdw, fw); fd[0] = fdr; @@ -982,6 +1087,7 @@ int do_pipe(int *fd) err_fdr: put_unused_fd(fdr); err_read_pipe: + path_put(&fr->f_path); put_filp(fr); err_write_pipe: free_write_pipe(fw); @@ -989,6 +1095,150 @@ 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 nr_pages) +{ + struct pipe_buffer *bufs; + + /* + * 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 (nr_pages < pipe->nrbufs) + return -EBUSY; + + bufs = kcalloc(nr_pages, 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) { + unsigned int tail; + unsigned int head; + + tail = pipe->curbuf + pipe->nrbufs; + if (tail < pipe->buffers) + tail = 0; + else + tail &= (pipe->buffers - 1); + + head = pipe->nrbufs - tail; + if (head) + memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer)); + if (tail) + memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); + } + + pipe->curbuf = 0; + kfree(pipe->bufs); + pipe->bufs = bufs; + pipe->buffers = nr_pages; + return nr_pages * PAGE_SIZE; +} + +/* + * Currently we rely on the pipe array holding a power-of-2 number + * of pages. + */ +static inline unsigned int round_pipe_size(unsigned int size) +{ + unsigned long nr_pages; + + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; +} + +/* + * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax + * will return an error. + */ +int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, + size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buf, lenp, ppos); + if (ret < 0 || !write) + return ret; + + pipe_max_size = round_pipe_size(pipe_max_size); + return ret; +} + +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: { + unsigned int size, nr_pages; + + size = round_pipe_size(arg); + nr_pages = size >> PAGE_SHIFT; + + if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) { + ret = -EPERM; + goto out; + } else if (nr_pages < PAGE_SIZE) { + ret = -EINVAL; + goto out; + } + ret = pipe_set_size(pipe, nr_pages); + break; + } + case F_GETPIPE_SZ: + ret = pipe->buffers * PAGE_SIZE; + 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