From: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
These three are used in a subsequent patch to allow the kernel c/r
code to call vfs_read/write() to read and write data to and from the
checkpoint image.
This patch makes the following changes:
1) Move kernel_write() from fs/splice.c to fs/exec.c to be near
kernel_read()
2) Make kernel_read/write() iterate if they face partial reads or
writes, and retry if they face -EAGAIN.
3) Adjust prototypes of kernel_read/write() to use size_t and ssize_t
4) Move file_pos_read/write() to include/linux/fs.h
Changelog [ckpt-v21]
- Introduce kernel_write(), fix kernel_read()
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Signed-off-by: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
Acked-by: Serge E. Hallyn <serue@xxxxxxxxxx>
---
fs/exec.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++----
fs/read_write.c | 10 -------
fs/splice.c | 17 +------------
include/linux/fs.h | 13 +++++++++-
4 files changed, 77 insertions(+), 32 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index 99d33a1..5d7a67b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -720,23 +720,82 @@ exit:
}
EXPORT_SYMBOL(open_exec);
-int kernel_read(struct file *file, loff_t offset,
- char *addr, unsigned long count)
+static ssize_t _kernel_read(struct file *file, loff_t offset,
+ char __user *ubuf, size_t count)
{
- mm_segment_t old_fs;
+ ssize_t nread;
+ size_t nleft;
loff_t pos = offset;
- int result;
+
+ for (nleft = count; nleft; nleft -= nread) {
+ nread = vfs_read(file, ubuf, nleft, &pos);
+ if (nread <= 0) {
+ if (nread == -EAGAIN) {
+ nread = 0;
+ continue;
+ } else if (nread == 0)
+ break;
+ else
+ return nread;
+ }
+ ubuf += nread;
+ }
+ return count - nleft;
+}
+
+ssize_t kernel_read(struct file *file, loff_t offset,
+ char *addr, size_t count)
+{
+ mm_segment_t old_fs;
+ ssize_t result;
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
- result = vfs_read(file, (void __user *)addr, count, &pos);
+ result = _kernel_read(file, offset, (void __user *)addr, count);
set_fs(old_fs);
return result;
}
EXPORT_SYMBOL(kernel_read);
+static ssize_t _kernel_write(struct file *file, loff_t offset,
+ const char __user *ubuf, size_t count)
+{
+ ssize_t nwrite;
+ size_t nleft;
+ loff_t pos = offset;
+
+ for (nleft = count; nleft; nleft -= nwrite) {
+ nwrite = vfs_write(file, ubuf, nleft, &pos);
+ if (nwrite < 0) {
+ if (nwrite == -EAGAIN) {
+ nwrite = 0;
+ continue;
+ } else
+ return nwrite;
+ }
+ ubuf += nwrite;
+ }
+ return count - nleft;
+}
+
+ssize_t kernel_write(struct file *file, loff_t offset,
+ const char *addr, size_t count)
+{
+ mm_segment_t old_fs;
+ ssize_t result;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ result = _kernel_write(file, offset, (void __user *)addr, count);
+ set_fs(old_fs);
+ return result;
+}
+
+EXPORT_SYMBOL(kernel_write);
+
static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
diff --git a/fs/read_write.c b/fs/read_write.c
index 431a0ed..91baf85 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -395,16 +395,6 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
EXPORT_SYMBOL(vfs_write);
-static inline loff_t file_pos_read(struct file *file)
-{
- return file->f_pos;
-}
-
-static inline void file_pos_write(struct file *file, loff_t pos)
-{
- file->f_pos = pos;
-}
-
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct file *file;
diff --git a/fs/splice.c b/fs/splice.c
index 8f1dfae..b9e90e0 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -562,21 +562,6 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
return res;
}
-static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
- loff_t pos)
-{
- mm_segment_t old_fs;
- ssize_t res;
-
- old_fs = get_fs();
- set_fs(get_ds());
- /* The cast to a user pointer is valid due to the set_fs() */
- res = vfs_write(file, (const char __user *)buf, count, &pos);
- set_fs(old_fs);
-
- return res;
-}
-
ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
@@ -1049,7 +1034,7 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
return ret;
data = buf->ops->map(pipe, buf, 0);
- ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+ ret = kernel_write(sd->u.file, sd->pos, data + buf->offset, sd->len);
buf->ops->unmap(pipe, buf, data);
return ret;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 334d68a..12cc2e6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1581,6 +1581,16 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
struct iovec *fast_pointer,
struct iovec **ret_pointer);
+static inline loff_t file_pos_read(struct file *file)
+{
+ return file->f_pos;
+}
+
+static inline void file_pos_write(struct file *file, loff_t pos)
+{
+ file->f_pos = pos;
+}
+
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
@@ -2186,7 +2196,8 @@ extern struct file *do_filp_open(int dfd, const char *pathname,
int open_flag, int mode, int acc_mode);
extern int may_open(struct path *, int, int);
-extern int kernel_read(struct file *, loff_t, char *, unsigned long);
+extern ssize_t kernel_read(struct file *, loff_t, char *, size_t);
+extern ssize_t kernel_write(struct file *, loff_t, const char *, size_t);
extern struct file * open_exec(const char *);
/* fs/dcache.c -- generic fs support functions */
--
1.7.2.2
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
