summaryrefslogtreecommitdiffstats
path: root/fs/read_write.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/read_write.c')
-rw-r--r--fs/read_write.c235
1 files changed, 126 insertions, 109 deletions
diff --git a/fs/read_write.c b/fs/read_write.c
index 4771701c89..d4c036e82b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -354,6 +354,9 @@ out_putf:
int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
{
+ int mask = read_write == READ ? MAY_READ : MAY_WRITE;
+ int ret;
+
if (unlikely((ssize_t) count < 0))
return -EINVAL;
@@ -371,8 +374,11 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
}
}
- return security_file_permission(file,
- read_write == READ ? MAY_READ : MAY_WRITE);
+ ret = security_file_permission(file, mask);
+ if (ret)
+ return ret;
+
+ return fsnotify_file_area_perm(file, mask, ppos, count);
}
EXPORT_SYMBOL(rw_verify_area);
@@ -773,12 +779,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
return ret;
}
-static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
- loff_t *pos, rwf_t flags)
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+ struct iov_iter *iter)
{
size_t tot_len;
ssize_t ret = 0;
+ if (!file->f_op->read_iter)
+ return -EINVAL;
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_READ))
@@ -787,22 +795,20 @@ static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
tot_len = iov_iter_count(iter);
if (!tot_len)
goto out;
- ret = rw_verify_area(READ, file, pos, tot_len);
+ ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
if (ret < 0)
return ret;
- if (file->f_op->read_iter)
- ret = do_iter_readv_writev(file, iter, pos, READ, flags);
- else
- ret = do_loop_readv_writev(file, iter, pos, READ, flags);
+ ret = call_read_iter(file, iocb, iter);
out:
if (ret >= 0)
fsnotify_access(file);
return ret;
}
+EXPORT_SYMBOL(vfs_iocb_iter_read);
-ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
- struct iov_iter *iter)
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
+ rwf_t flags)
{
size_t tot_len;
ssize_t ret = 0;
@@ -817,33 +823,30 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
tot_len = iov_iter_count(iter);
if (!tot_len)
goto out;
- ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
+ ret = rw_verify_area(READ, file, ppos, tot_len);
if (ret < 0)
return ret;
- ret = call_read_iter(file, iocb, iter);
+ ret = do_iter_readv_writev(file, iter, ppos, READ, flags);
out:
if (ret >= 0)
fsnotify_access(file);
return ret;
}
-EXPORT_SYMBOL(vfs_iocb_iter_read);
-
-ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
- rwf_t flags)
-{
- if (!file->f_op->read_iter)
- return -EINVAL;
- return do_iter_read(file, iter, ppos, flags);
-}
EXPORT_SYMBOL(vfs_iter_read);
-static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
- loff_t *pos, rwf_t flags)
+/*
+ * Caller is responsible for calling kiocb_end_write() on completion
+ * if async iocb was queued.
+ */
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+ struct iov_iter *iter)
{
size_t tot_len;
ssize_t ret = 0;
+ if (!file->f_op->write_iter)
+ return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
@@ -852,88 +855,127 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
tot_len = iov_iter_count(iter);
if (!tot_len)
return 0;
- ret = rw_verify_area(WRITE, file, pos, tot_len);
+ ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
if (ret < 0)
return ret;
- if (file->f_op->write_iter)
- ret = do_iter_readv_writev(file, iter, pos, WRITE, flags);
- else
- ret = do_loop_readv_writev(file, iter, pos, WRITE, flags);
+ kiocb_start_write(iocb);
+ ret = call_write_iter(file, iocb, iter);
+ if (ret != -EIOCBQUEUED)
+ kiocb_end_write(iocb);
if (ret > 0)
fsnotify_modify(file);
+
return ret;
}
+EXPORT_SYMBOL(vfs_iocb_iter_write);
-ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
- struct iov_iter *iter)
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
+ rwf_t flags)
{
size_t tot_len;
- ssize_t ret = 0;
+ ssize_t ret;
- if (!file->f_op->write_iter)
- return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
+ if (!file->f_op->write_iter)
+ return -EINVAL;
tot_len = iov_iter_count(iter);
if (!tot_len)
return 0;
- ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
+
+ ret = rw_verify_area(WRITE, file, ppos, tot_len);
if (ret < 0)
return ret;
- ret = call_write_iter(file, iocb, iter);
+ file_start_write(file);
+ ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags);
if (ret > 0)
fsnotify_modify(file);
+ file_end_write(file);
return ret;
}
-EXPORT_SYMBOL(vfs_iocb_iter_write);
-
-ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
- rwf_t flags)
-{
- if (!file->f_op->write_iter)
- return -EINVAL;
- return do_iter_write(file, iter, ppos, flags);
-}
EXPORT_SYMBOL(vfs_iter_write);
static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
- unsigned long vlen, loff_t *pos, rwf_t flags)
+ unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
- ssize_t ret;
+ size_t tot_len;
+ ssize_t ret = 0;
- ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
- if (ret >= 0) {
- ret = do_iter_read(file, &iter, pos, flags);
- kfree(iov);
- }
+ if (!(file->f_mode & FMODE_READ))
+ return -EBADF;
+ if (!(file->f_mode & FMODE_CAN_READ))
+ return -EINVAL;
+
+ ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov,
+ &iter);
+ if (ret < 0)
+ return ret;
+
+ tot_len = iov_iter_count(&iter);
+ if (!tot_len)
+ goto out;
+ ret = rw_verify_area(READ, file, pos, tot_len);
+ if (ret < 0)
+ goto out;
+
+ if (file->f_op->read_iter)
+ ret = do_iter_readv_writev(file, &iter, pos, READ, flags);
+ else
+ ret = do_loop_readv_writev(file, &iter, pos, READ, flags);
+out:
+ if (ret >= 0)
+ fsnotify_access(file);
+ kfree(iov);
return ret;
}
static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
- unsigned long vlen, loff_t *pos, rwf_t flags)
+ unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
- ssize_t ret;
+ size_t tot_len;
+ ssize_t ret = 0;
- ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
- if (ret >= 0) {
- file_start_write(file);
- ret = do_iter_write(file, &iter, pos, flags);
- file_end_write(file);
- kfree(iov);
- }
+ if (!(file->f_mode & FMODE_WRITE))
+ return -EBADF;
+ if (!(file->f_mode & FMODE_CAN_WRITE))
+ return -EINVAL;
+
+ ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov,
+ &iter);
+ if (ret < 0)
+ return ret;
+
+ tot_len = iov_iter_count(&iter);
+ if (!tot_len)
+ goto out;
+
+ ret = rw_verify_area(WRITE, file, pos, tot_len);
+ if (ret < 0)
+ goto out;
+
+ file_start_write(file);
+ if (file->f_op->write_iter)
+ ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags);
+ else
+ ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags);
+ if (ret > 0)
+ fsnotify_modify(file);
+ file_end_write(file);
+out:
+ kfree(iov);
return ret;
}
@@ -1178,7 +1220,7 @@ COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
#endif /* CONFIG_COMPAT */
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
- size_t count, loff_t max)
+ size_t count, loff_t max)
{
struct fd in, out;
struct inode *in_inode, *out_inode;
@@ -1250,10 +1292,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
- file_start_write(out.file);
retval = do_splice_direct(in.file, &pos, out.file, &out_pos,
count, fl);
- file_end_write(out.file);
} else {
if (out.file->f_flags & O_NONBLOCK)
fl |= SPLICE_F_NONBLOCK;
@@ -1362,38 +1402,6 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
}
#endif
-/**
- * generic_copy_file_range - copy data between two files
- * @file_in: file structure to read from
- * @pos_in: file offset to read from
- * @file_out: file structure to write data to
- * @pos_out: file offset to write data to
- * @len: amount of data to copy
- * @flags: copy flags
- *
- * This is a generic filesystem helper to copy data from one file to another.
- * It has no constraints on the source or destination file owners - the files
- * can belong to different superblocks and different filesystem types. Short
- * copies are allowed.
- *
- * This should be called from the @file_out filesystem, as per the
- * ->copy_file_range() method.
- *
- * Returns the number of bytes copied or a negative error indicating the
- * failure.
- */
-
-ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- size_t len, unsigned int flags)
-{
- lockdep_assert(sb_write_started(file_inode(file_out)->i_sb));
-
- return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
- len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
-}
-EXPORT_SYMBOL(generic_copy_file_range);
-
/*
* Performs necessary checks before doing a file copy
*
@@ -1478,6 +1486,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
{
ssize_t ret;
bool splice = flags & COPY_FILE_SPLICE;
+ bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb;
if (flags & ~COPY_FILE_SPLICE)
return -EINVAL;
@@ -1509,19 +1518,24 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
ret = file_out->f_op->copy_file_range(file_in, pos_in,
file_out, pos_out,
len, flags);
- goto done;
- }
-
- if (!splice && file_in->f_op->remap_file_range &&
- file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
+ } else if (!splice && file_in->f_op->remap_file_range && samesb) {
ret = file_in->f_op->remap_file_range(file_in, pos_in,
file_out, pos_out,
min_t(loff_t, MAX_RW_COUNT, len),
REMAP_FILE_CAN_SHORTEN);
- if (ret > 0)
- goto done;
+ /* fallback to splice */
+ if (ret <= 0)
+ splice = true;
+ } else if (samesb) {
+ /* Fallback to splice for same sb copy for backward compat */
+ splice = true;
}
+ file_end_write(file_out);
+
+ if (!splice)
+ goto done;
+
/*
* We can get here for same sb copy of filesystems that do not implement
* ->copy_file_range() in case filesystem does not support clone or in
@@ -1533,11 +1547,16 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
* and which filesystems do not, that will allow userspace tools to
* make consistent desicions w.r.t using copy_file_range().
*
- * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE.
+ * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE
+ * for server-side-copy between any two sb.
+ *
+ * In any case, we call do_splice_direct() and not splice_file_range(),
+ * without file_start_write() held, to avoid possible deadlocks related
+ * to splicing from input file, while file_start_write() is held on
+ * the output file on a different sb.
*/
- ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
- flags);
-
+ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+ min_t(size_t, len, MAX_RW_COUNT), 0);
done:
if (ret > 0) {
fsnotify_access(file_in);
@@ -1549,8 +1568,6 @@ done:
inc_syscr(current);
inc_syscw(current);
- file_end_write(file_out);
-
return ret;
}
EXPORT_SYMBOL(vfs_copy_file_range);