lkml.org 
[lkml]   [2007]   [Jun]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 2/18] vmsplice: add vmsplice-to-user support
Date
A bit of a cheat, it actually just copies the data to userspace. But
this makes the interface nice and symmetric and enables people to build
on splice, with room for future improvement in performance.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
fs/splice.c | 142 ++++++++++++++++++++++++++++++++++++++-------
include/linux/pipe_fs_i.h | 8 ++-
2 files changed, 127 insertions(+), 23 deletions(-)

diff --git a/fs/splice.c b/fs/splice.c
index 6871de6..837be82 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1282,28 +1282,107 @@ static int get_iovec_page_array(const struct iovec __user *iov,
return error;
}

+static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
+{
+ int ret;
+
+ ret = buf->ops->pin(pipe, buf);
+ if (!ret) {
+ /*
+ * use non-atomic map, can be optimized to map atomically if we
+ * prefault the user memory.
+ */
+ char *src = buf->ops->map(pipe, buf, 0);
+
+ if (copy_to_user(sd->userptr, src, sd->len))
+ ret = -EFAULT;
+
+ buf->ops->unmap(pipe, buf, src);
+
+ if (!ret)
+ return sd->len;
+ }
+
+ return ret;
+}
+
+/*
+ * For lack of a better implementation, implement vmsplice() to userspace
+ * as a simple copy of the pipes pages to the user iov.
+ */
+static long vmsplice_to_user(struct file *file, const struct iovec __user *iov,
+ unsigned long nr_segs, unsigned int flags)
+{
+ struct pipe_inode_info *pipe;
+ struct splice_desc sd;
+ ssize_t size;
+ int error;
+ long ret;
+
+ pipe = pipe_info(file->f_path.dentry->d_inode);
+ if (!pipe)
+ return -EBADF;
+
+ if (pipe->inode)
+ mutex_lock(&pipe->inode->i_mutex);
+
+ ret = 0;
+ while (nr_segs) {
+ void __user *base;
+ size_t len;
+
+ /*
+ * 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))
+ break;
+
+ /*
+ * Sanity check this iovec. 0 read succeeds.
+ */
+ if (unlikely(!len))
+ break;
+ error = -EFAULT;
+ if (unlikely(!base))
+ break;
+
+ sd.len = 0;
+ sd.total_len = len;
+ sd.flags = flags;
+ sd.userptr = base;
+ sd.pos = 0;
+
+ size = __splice_from_pipe(pipe, &sd, pipe_to_user);
+ if (size < 0) {
+ if (!ret)
+ ret = size;
+
+ break;
+ }
+
+ nr_segs--;
+ iov++;
+ ret += size;
+ }
+
+ if (pipe->inode)
+ mutex_unlock(&pipe->inode->i_mutex);
+
+ return ret;
+}
+
/*
* vmsplice splices a user address range into a pipe. It can be thought of
* as splice-from-memory, where the regular splice is splice-from-file (or
* to file). In both cases the output is a pipe, naturally.
- *
- * Note that vmsplice only supports splicing _from_ user memory to a pipe,
- * not the other way around. Splicing from user memory is a simple operation
- * that can be supported without any funky alignment restrictions or nasty
- * vm tricks. We simply map in the user memory and fill them into a pipe.
- * The reverse isn't quite as easy, though. There are two possible solutions
- * for that:
- *
- * - memcpy() the data internally, at which point we might as well just
- * do a regular read() on the buffer anyway.
- * - Lots of nasty vm tricks, that are neither fast nor flexible (it
- * has restriction limitations on both ends of the pipe).
- *
- * Alas, it isn't here.
- *
*/
-static long do_vmsplice(struct file *file, const struct iovec __user *iov,
- unsigned long nr_segs, unsigned int flags)
+static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
+ unsigned long nr_segs, unsigned int flags)
{
struct pipe_inode_info *pipe;
struct page *pages[PIPE_BUFFERS];
@@ -1318,10 +1397,6 @@ static long do_vmsplice(struct file *file, const struct iovec __user *iov,
pipe = pipe_info(file->f_path.dentry->d_inode);
if (!pipe)
return -EBADF;
- if (unlikely(nr_segs > UIO_MAXIOV))
- return -EINVAL;
- else if (unlikely(!nr_segs))
- return 0;

spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
flags & SPLICE_F_GIFT);
@@ -1331,6 +1406,22 @@ static long do_vmsplice(struct file *file, const struct iovec __user *iov,
return splice_to_pipe(pipe, &spd);
}

+/*
+ * Note that vmsplice only really supports true splicing _from_ user memory
+ * to a pipe, not the other way around. Splicing from user memory is a simple
+ * operation that can be supported without any funky alignment restrictions
+ * or nasty vm tricks. We simply map in the user memory and fill them into
+ * a pipe. The reverse isn't quite as easy, though. There are two possible
+ * solutions for that:
+ *
+ * - memcpy() the data internally, at which point we might as well just
+ * do a regular read() on the buffer anyway.
+ * - Lots of nasty vm tricks, that are neither fast nor flexible (it
+ * has restriction limitations on both ends of the pipe).
+ *
+ * Currently we punt and implement it as a normal copy, see pipe_to_user().
+ *
+ */
asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
unsigned long nr_segs, unsigned int flags)
{
@@ -1338,11 +1429,18 @@ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
long error;
int fput;

+ if (unlikely(nr_segs > UIO_MAXIOV))
+ return -EINVAL;
+ else if (unlikely(!nr_segs))
+ return 0;
+
error = -EBADF;
file = fget_light(fd, &fput);
if (file) {
if (file->f_mode & FMODE_WRITE)
- error = do_vmsplice(file, iov, nr_segs, flags);
+ error = vmsplice_to_pipe(file, iov, nr_segs, flags);
+ else if (file->f_mode & FMODE_READ)
+ error = vmsplice_to_user(file, iov, nr_segs, flags);

fput_light(file, fput);
}
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 883ba9b..c2bda03 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -88,7 +88,13 @@ int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
struct splice_desc {
unsigned int len, total_len; /* current and remaining length */
unsigned int flags; /* splice flags */
- struct file *file; /* file to read/write */
+ /*
+ * actor() private data
+ */
+ union {
+ void __user *userptr; /* memory to write to */
+ struct file *file; /* file to read/write */
+ };
loff_t pos; /* file position */
};

--
1.5.2.1.174.gcd03
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2007-06-12 09:05    [W:0.105 / U:0.112 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site