#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/log2.h>
#include <linux/mount.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
#include <linux/audit.h>
#include <linux/syscalls.h>
+#include <linux/fcntl.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
/*
+ * 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)
pipe_lock_nested(pipe1, I_MUTEX_PARENT);
pipe_lock_nested(pipe2, I_MUTEX_CHILD);
} else {
- pipe_lock_nested(pipe2, I_MUTEX_CHILD);
- pipe_lock_nested(pipe1, I_MUTEX_PARENT);
+ pipe_lock_nested(pipe2, I_MUTEX_PARENT);
+ pipe_lock_nested(pipe1, I_MUTEX_CHILD);
}
}
return kmap(buf->page);
}
+EXPORT_SYMBOL(generic_pipe_buf_map);
/**
* generic_pipe_buf_unmap - unmap a previously mapped pipe buffer
} else
kunmap(buf->page);
}
+EXPORT_SYMBOL(generic_pipe_buf_unmap);
/**
* generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
return 1;
}
+EXPORT_SYMBOL(generic_pipe_buf_steal);
/**
* generic_pipe_buf_get - get a reference to a &struct pipe_buffer
{
page_cache_get(buf->page);
}
+EXPORT_SYMBOL(generic_pipe_buf_get);
/**
* generic_pipe_buf_confirm - verify contents of the pipe buffer
{
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,
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;
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;
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;
if (!total_len)
break;
}
- if (bufs < PIPE_BUFFERS)
+ if (bufs < pipe->buffers)
continue;
if (filp->f_flags & O_NONBLOCK) {
if (!ret)
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);
}
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().
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;
}
/*
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);
}
}
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().
}
static const struct dentry_operations pipefs_dentry_operations = {
- .d_delete = pipefs_delete_dentry,
.d_dname = pipefs_dname,
};
int err;
struct inode *inode;
struct file *f;
- struct dentry *dentry;
+ struct path path;
struct qstr name = { .name = "" };
err = -ENFILE;
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_pipefifo_fops);
+ f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops);
if (!f)
goto err_dentry;
f->f_mapping = inode->i_mapping;
err_dentry:
free_pipe_info(inode);
- dput(dentry);
+ path_put(&path);
return ERR_PTR(err);
err_inode:
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 = wrf->f_path;
path_get(&wrf->f_path);
- f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
-
- f->f_pos = 0;
f->f_flags = O_RDONLY | (flags & O_NONBLOCK);
- f->f_op = &read_pipefifo_fops;
- f->f_mode = FMODE_READ;
- f->f_version = 0;
return f;
}
}
/*
+ * 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