*/
unsigned int pipe_min_size = PAGE_SIZE;
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
/*
* We use a start+len construction, which provides full use of the
* allocated memory.
}
static int
-pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
- int atomic)
+pipe_iov_copy_from_user(void *addr, int *offset, struct iovec *iov,
+ size_t *remaining, int atomic)
{
unsigned long copy;
- while (len > 0) {
+ while (*remaining > 0) {
while (!iov->iov_len)
iov++;
- copy = min_t(unsigned long, len, iov->iov_len);
+ copy = min_t(unsigned long, *remaining, iov->iov_len);
if (atomic) {
- if (__copy_from_user_inatomic(to, iov->iov_base, copy))
+ if (__copy_from_user_inatomic(addr + *offset,
+ iov->iov_base, copy))
return -EFAULT;
} else {
- if (copy_from_user(to, iov->iov_base, copy))
+ if (copy_from_user(addr + *offset,
+ iov->iov_base, copy))
return -EFAULT;
}
- to += copy;
- len -= copy;
+ *offset += copy;
+ *remaining -= copy;
iov->iov_base += copy;
iov->iov_len -= copy;
}
}
static int
-pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len,
- int atomic)
+pipe_iov_copy_to_user(struct iovec *iov, void *addr, int *offset,
+ size_t *remaining, int atomic)
{
unsigned long copy;
- while (len > 0) {
+ while (*remaining > 0) {
while (!iov->iov_len)
iov++;
- copy = min_t(unsigned long, len, iov->iov_len);
+ copy = min_t(unsigned long, *remaining, iov->iov_len);
if (atomic) {
- if (__copy_to_user_inatomic(iov->iov_base, from, copy))
+ if (__copy_to_user_inatomic(iov->iov_base,
+ addr + *offset, copy))
return -EFAULT;
} else {
- if (copy_to_user(iov->iov_base, from, copy))
+ if (copy_to_user(iov->iov_base,
+ addr + *offset, copy))
return -EFAULT;
}
- from += copy;
- len -= copy;
+ *offset += copy;
+ *remaining -= copy;
iov->iov_base += copy;
iov->iov_len -= copy;
}
.get = generic_pipe_buf_get,
};
+static const struct pipe_buf_operations packet_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = anon_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
static ssize_t
pipe_read(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t pos)
struct pipe_buffer *buf = pipe->bufs + curbuf;
const struct pipe_buf_operations *ops = buf->ops;
void *addr;
- size_t chars = buf->len;
+ size_t chars = buf->len, remaining;
int error, atomic;
+ int offset;
if (chars > total_len)
chars = total_len;
}
atomic = !iov_fault_in_pages_write(iov, chars);
+ remaining = chars;
+ offset = buf->offset;
redo:
addr = ops->map(pipe, buf, atomic);
- error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
+ error = pipe_iov_copy_to_user(iov, addr, &offset,
+ &remaining, atomic);
ops->unmap(pipe, buf, addr);
if (unlikely(error)) {
/*
ret += chars;
buf->offset += chars;
buf->len -= chars;
+
+ /* Was it a packet buffer? Clean up and exit */
+ if (buf->flags & PIPE_BUF_FLAG_PACKET) {
+ total_len = chars;
+ buf->len = 0;
+ }
+
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
return ret;
}
+static inline int is_packetized(struct file *file)
+{
+ return (file->f_flags & O_DIRECT) != 0;
+}
+
static ssize_t
pipe_write(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t ppos)
if (ops->can_merge && offset + chars <= PAGE_SIZE) {
int error, atomic = 1;
void *addr;
+ size_t remaining = chars;
error = ops->confirm(pipe, buf);
if (error)
iov_fault_in_pages_read(iov, chars);
redo1:
addr = ops->map(pipe, buf, atomic);
- error = pipe_iov_copy_from_user(offset + addr, iov,
- chars, atomic);
+ error = pipe_iov_copy_from_user(addr, &offset, iov,
+ &remaining, atomic);
ops->unmap(pipe, buf, addr);
ret = error;
do_wakeup = 1;
struct page *page = pipe->tmp_page;
char *src;
int error, atomic = 1;
+ int offset = 0;
+ size_t remaining;
if (!page) {
page = alloc_page(GFP_HIGHUSER);
chars = total_len;
iov_fault_in_pages_read(iov, chars);
+ remaining = chars;
redo2:
if (atomic)
src = kmap_atomic(page, KM_USER0);
else
src = kmap(page);
- error = pipe_iov_copy_from_user(src, iov, chars,
- atomic);
+ error = pipe_iov_copy_from_user(src, &offset, iov,
+ &remaining, atomic);
if (atomic)
kunmap_atomic(src, KM_USER0);
else
buf->ops = &anon_pipe_buf_ops;
buf->offset = 0;
buf->len = chars;
+ buf->flags = 0;
+ if (is_packetized(filp)) {
+ buf->ops = &packet_pipe_buf_ops;
+ buf->flags = PIPE_BUF_FLAG_PACKET;
+ }
pipe->nrbufs = ++bufs;
pipe->tmp_page = NULL;
{
int ret = -ENOENT;
+ if (!(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+ return -EINVAL;
+
mutex_lock(&inode->i_mutex);
if (inode->i_pipe) {
.fasync = pipe_rdwr_fasync,
};
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+ unsigned long old, unsigned long new)
+{
+ atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+ return pipe_user_pages_soft &&
+ atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+ return pipe_user_pages_hard &&
+ atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
struct pipe_inode_info * alloc_pipe_info(struct inode *inode)
{
struct pipe_inode_info *pipe;
pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
if (pipe) {
- pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+ unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+ struct user_struct *user = get_current_user();
+
+ if (!too_many_pipe_buffers_hard(user)) {
+ if (too_many_pipe_buffers_soft(user))
+ pipe_bufs = 1;
+ pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, 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;
+ pipe->buffers = pipe_bufs;
+ pipe->user = user;
+ account_pipe_buffers(pipe, 0, pipe_bufs);
return pipe;
}
+ free_uid(user);
kfree(pipe);
}
{
int i;
+ account_pipe_buffers(pipe, pipe->buffers, 0);
+ free_uid(pipe->user);
for (i = 0; i < pipe->buffers; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops)
goto err_dentry;
f->f_mapping = inode->i_mapping;
- f->f_flags = O_WRONLY | (flags & O_NONBLOCK);
+ f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
f->f_version = 0;
return f;
int error;
int fdw, fdr;
- if (flags & ~(O_CLOEXEC | O_NONBLOCK))
+ if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
return -EINVAL;
fw = create_write_pipe(flags);
memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
}
+ account_pipe_buffers(pipe, pipe->buffers, nr_pages);
pipe->curbuf = 0;
kfree(pipe->bufs);
pipe->bufs = bufs;
if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
ret = -EPERM;
goto out;
+ } else if ((too_many_pipe_buffers_hard(pipe->user) ||
+ too_many_pipe_buffers_soft(pipe->user)) &&
+ !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+ ret = -EPERM;
+ goto out;
}
ret = pipe_set_size(pipe, nr_pages);
break;