* @spd: data to fill
*
* Description:
- * @spd contains a map of pages and len/offset tupples, a long with
+ * @spd contains a map of pages and len/offset tuples, along with
* the struct pipe_buf_operations associated with these pages. This
* function will link that data to the pipe.
*
}
while (page_nr < spd_pages)
- page_cache_release(spd->pages[page_nr++]);
+ spd->spd_release(spd, page_nr++);
return ret;
}
+static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
+{
+ page_cache_release(spd->pages[i]);
+}
+
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
- unsigned int loff, nr_pages;
+ unsigned int loff, nr_pages, req_pages;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct page *page;
.partial = partial,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
+ .spd_release = spd_release_page,
};
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
- nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
- if (nr_pages > PIPE_BUFFERS)
- nr_pages = PIPE_BUFFERS;
+ req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS);
/*
* Lookup the (hopefully) full range of pages we need.
* readahead/allocate the rest and fill in the holes.
*/
if (spd.nr_pages < nr_pages)
- page_cache_readahead_ondemand(mapping, &in->f_ra, in,
- NULL, index, nr_pages - spd.nr_pages);
+ page_cache_sync_readahead(mapping, &in->f_ra, in,
+ index, req_pages - spd.nr_pages);
error = 0;
while (spd.nr_pages < nr_pages) {
page = pages[page_nr];
if (PageReadahead(page))
- page_cache_readahead_ondemand(mapping, &in->f_ra, in,
- page, index, nr_pages - page_nr);
+ page_cache_async_readahead(mapping, &in->f_ra, in,
+ page, index, req_pages - page_nr);
/*
* If the page isn't uptodate, we may need to start io on it
*/
while (page_nr < nr_pages)
page_cache_release(pages[page_nr++]);
- in->f_ra.prev_index = index;
+ in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
if (spd.nr_pages)
return splice_to_pipe(pipe, &spd);
struct address_space *mapping = file->f_mapping;
unsigned int offset, this_len;
struct page *page;
- pgoff_t index;
+ void *fsdata;
int ret;
/*
if (unlikely(ret))
return ret;
- index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
-find_page:
- page = find_lock_page(mapping, index);
- if (!page) {
- ret = -ENOMEM;
- page = page_cache_alloc_cold(mapping);
- if (unlikely(!page))
- goto out_ret;
-
- /*
- * This will also lock the page
- */
- ret = add_to_page_cache_lru(page, mapping, index,
- GFP_KERNEL);
- if (unlikely(ret))
- goto out;
- }
-
- ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
- if (unlikely(ret)) {
- loff_t isize = i_size_read(mapping->host);
-
- if (ret != AOP_TRUNCATED_PAGE)
- unlock_page(page);
- page_cache_release(page);
- if (ret == AOP_TRUNCATED_PAGE)
- goto find_page;
-
- /*
- * prepare_write() may have instantiated a few blocks
- * outside i_size. Trim these off again.
- */
- if (sd->pos + this_len > isize)
- vmtruncate(mapping->host, isize);
-
- goto out_ret;
- }
+ ret = pagecache_write_begin(file, mapping, sd->pos, this_len,
+ AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
+ if (unlikely(ret))
+ goto out;
if (buf->page != page) {
/*
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
-
- ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
- if (ret) {
- if (ret == AOP_TRUNCATED_PAGE) {
- page_cache_release(page);
- goto find_page;
- }
- if (ret < 0)
- goto out;
- /*
- * Partial write has happened, so 'ret' already initialized by
- * number of bytes written, Where is nothing we have to do here.
- */
- } else
- ret = this_len;
- /*
- * Return the number of bytes written and mark page as
- * accessed, we are now done!
- */
- mark_page_accessed(page);
+ ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
+ page, fsdata);
out:
- page_cache_release(page);
- unlock_page(page);
-out_ret:
return ret;
}
{
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
+ int killsuid, killpriv;
ssize_t ret;
- int err;
+ int err = 0;
- err = should_remove_suid(out->f_path.dentry);
- if (unlikely(err)) {
+ killpriv = security_inode_need_killpriv(out->f_path.dentry);
+ killsuid = should_remove_suid(out->f_path.dentry);
+ if (unlikely(killsuid || killpriv)) {
mutex_lock(&inode->i_mutex);
- err = __remove_suid(out->f_path.dentry, err);
+ if (killpriv)
+ err = security_inode_killpriv(out->f_path.dentry);
+ if (!err && killsuid)
+ err = __remove_suid(out->f_path.dentry, killsuid);
mutex_unlock(&inode->i_mutex);
if (err)
return err;
if (unlikely(ret < 0))
return ret;
- ret = security_file_permission(out, MAY_WRITE);
- if (unlikely(ret < 0))
- return ret;
-
return out->f_op->splice_write(pipe, out, ppos, len, flags);
}
if (unlikely(ret < 0))
return ret;
- ret = security_file_permission(in, MAY_READ);
- if (unlikely(ret < 0))
- return ret;
-
return in->f_op->splice_read(in, ppos, pipe, len, flags);
}
* Description:
* This is a special case helper to splice directly between two
* points, without requiring an explicit pipe. Internally an allocated
- * pipe is cached in the process, and reused during the life time of
+ * pipe is cached in the process, and reused during the lifetime of
* that process.
*
*/
goto out_release;
}
+done:
pipe->nrbufs = pipe->curbuf = 0;
+ file_accessed(in);
return bytes;
out_release:
buf->ops = NULL;
}
}
- pipe->nrbufs = pipe->curbuf = 0;
-
- /*
- * If we transferred some data, return the number of bytes:
- */
- if (bytes > 0)
- return bytes;
- return ret;
+ if (!bytes)
+ bytes = ret;
+ goto done;
}
EXPORT_SYMBOL(splice_direct_to_actor);
}
/*
+ * Do a copy-from-user while holding the mmap_semaphore for reading, in a
+ * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
+ * for writing) and page faulting on the user memory pointed to by src.
+ * This assumes that we will very rarely hit the partial != 0 path, or this
+ * will not be a win.
+ */
+static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
+{
+ int partial;
+
+ if (!access_ok(VERIFY_READ, src, n))
+ return -EFAULT;
+
+ pagefault_disable();
+ partial = __copy_from_user_inatomic(dst, src, n);
+ pagefault_enable();
+
+ /*
+ * Didn't copy everything, drop the mmap_sem and do a faulting copy
+ */
+ if (unlikely(partial)) {
+ up_read(¤t->mm->mmap_sem);
+ partial = copy_from_user(dst, src, n);
+ down_read(¤t->mm->mmap_sem);
+ }
+
+ return partial;
+}
+
+/*
* Map an iov into an array of pages and offset/length tupples. With the
* partial_page structure, we can map several non-contiguous ranges into
* our ones pages[] map instead of splitting that operation into pieces.
{
int buffers = 0, error = 0;
- /*
- * It's ok to take the mmap_sem for reading, even
- * across a "get_user()".
- */
down_read(¤t->mm->mmap_sem);
while (nr_vecs) {
unsigned long off, npages;
+ struct iovec entry;
void __user *base;
size_t len;
int i;
- /*
- * Get user address base and length for this iovec.
- */
- error = get_user(base, &iov->iov_base);
- if (unlikely(error))
- break;
- error = get_user(len, &iov->iov_len);
- if (unlikely(error))
+ error = -EFAULT;
+ if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
break;
+ base = entry.iov_base;
+ len = entry.iov_len;
+
/*
* Sanity check this iovec. 0 read succeeds.
*/
+ error = 0;
if (unlikely(!len))
break;
error = -EFAULT;
- if (unlikely(!base))
+ if (!access_ok(VERIFY_READ, base, len))
break;
/*
if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len))
ret = -EFAULT;
+ buf->ops->unmap(pipe, buf, src);
out:
if (ret > 0)
sd->u.userptr += ret;
- buf->ops->unmap(pipe, buf, src);
return ret;
}
break;
}
+ if (unlikely(!access_ok(VERIFY_WRITE, base, len))) {
+ error = -EFAULT;
+ break;
+ }
+
sd.len = 0;
sd.total_len = len;
sd.flags = flags;
.partial = partial,
.flags = flags,
.ops = &user_page_pipe_buf_ops,
+ .spd_release = spd_release_page,
};
pipe = pipe_info(file->f_path.dentry->d_inode);
i++;
} while (len);
+ /*
+ * return EAGAIN if we have the potential of some data in the
+ * future, otherwise just return 0
+ */
+ if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK))
+ ret = -EAGAIN;
+
inode_double_unlock(ipipe->inode, opipe->inode);
/*
ret = link_ipipe_prep(ipipe, flags);
if (!ret) {
ret = link_opipe_prep(opipe, flags);
- if (!ret) {
+ if (!ret)
ret = link_pipe(ipipe, opipe, len, flags);
- if (!ret && (flags & SPLICE_F_NONBLOCK))
- ret = -EAGAIN;
- }
}
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff