summaryrefslogtreecommitdiff
path: root/fs/zonefs/file.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 21:52:12 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 21:52:12 +0300
commit3eccc0c886b1796f95a289c9d127c8ca1a254bd5 (patch)
tree021761894d246df22d53e1c64810f6cbf3ece716 /fs/zonefs/file.c
parentcc423f6337d0a5ff1906f3b3d465d28c0d1705f6 (diff)
parent9eee8bd81421c5e961cbb1a3c3fa1a06fad545e8 (diff)
downloadlinux-3eccc0c886b1796f95a289c9d127c8ca1a254bd5.tar.xz
Merge tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux
Pull splice updates from Jens Axboe: "This kills off ITER_PIPE to avoid a race between truncate, iov_iter_revert() on the pipe and an as-yet incomplete DMA to a bio with unpinned/unref'ed pages from an O_DIRECT splice read. This causes memory corruption. Instead, we either use (a) filemap_splice_read(), which invokes the buffered file reading code and splices from the pagecache into the pipe; (b) copy_splice_read(), which bulk-allocates a buffer, reads into it and then pushes the filled pages into the pipe; or (c) handle it in filesystem-specific code. Summary: - Rename direct_splice_read() to copy_splice_read() - Simplify the calculations for the number of pages to be reclaimed in copy_splice_read() - Turn do_splice_to() into a helper, vfs_splice_read(), so that it can be used by overlayfs and coda to perform the checks on the lower fs - Make vfs_splice_read() jump to copy_splice_read() to handle direct-I/O and DAX - Provide shmem with its own splice_read to handle non-existent pages in the pagecache. We don't want a ->read_folio() as we don't want to populate holes, but filemap_get_pages() requires it - Provide overlayfs with its own splice_read to call down to a lower layer as overlayfs doesn't provide ->read_folio() - Provide coda with its own splice_read to call down to a lower layer as coda doesn't provide ->read_folio() - Direct ->splice_read to copy_splice_read() in tty, procfs, kernfs and random files as they just copy to the output buffer and don't splice pages - Provide wrappers for afs, ceph, ecryptfs, ext4, f2fs, nfs, ntfs3, ocfs2, orangefs, xfs and zonefs to do locking and/or revalidation - Make cifs use filemap_splice_read() - Replace pointers to generic_file_splice_read() with pointers to filemap_splice_read() as DIO and DAX are handled in the caller; filesystems can still provide their own alternate ->splice_read() op - Remove generic_file_splice_read() - Remove ITER_PIPE and its paraphernalia as generic_file_splice_read was the only user" * tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux: (31 commits) splice: kdoc for filemap_splice_read() and copy_splice_read() iov_iter: Kill ITER_PIPE splice: Remove generic_file_splice_read() splice: Use filemap_splice_read() instead of generic_file_splice_read() cifs: Use filemap_splice_read() trace: Convert trace/seq to use copy_splice_read() zonefs: Provide a splice-read wrapper xfs: Provide a splice-read wrapper orangefs: Provide a splice-read wrapper ocfs2: Provide a splice-read wrapper ntfs3: Provide a splice-read wrapper nfs: Provide a splice-read wrapper f2fs: Provide a splice-read wrapper ext4: Provide a splice-read wrapper ecryptfs: Provide a splice-read wrapper ceph: Provide a splice-read wrapper afs: Provide a splice-read wrapper 9p: Add splice_read wrapper net: Make sock_splice_read() use copy_splice_read() by default tty, proc, kernfs, random: Use copy_splice_read() ...
Diffstat (limited to 'fs/zonefs/file.c')
-rw-r--r--fs/zonefs/file.c40
1 files changed, 39 insertions, 1 deletions
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index d11b08d5e4d1..1451e7b48669 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -753,6 +753,44 @@ inode_unlock:
return ret;
}
+static ssize_t zonefs_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len, unsigned int flags)
+{
+ struct inode *inode = file_inode(in);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ struct zonefs_zone *z = zonefs_inode_zone(inode);
+ loff_t isize;
+ ssize_t ret = 0;
+
+ /* Offline zones cannot be read */
+ if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
+ return -EPERM;
+
+ if (*ppos >= z->z_capacity)
+ return 0;
+
+ inode_lock_shared(inode);
+
+ /* Limit read operations to written data */
+ mutex_lock(&zi->i_truncate_mutex);
+ isize = i_size_read(inode);
+ if (*ppos >= isize)
+ len = 0;
+ else
+ len = min_t(loff_t, len, isize - *ppos);
+ mutex_unlock(&zi->i_truncate_mutex);
+
+ if (len > 0) {
+ ret = filemap_splice_read(in, ppos, pipe, len, flags);
+ if (ret == -EIO)
+ zonefs_io_error(inode, false);
+ }
+
+ inode_unlock_shared(inode);
+ return ret;
+}
+
/*
* Write open accounting is done only for sequential files.
*/
@@ -898,7 +936,7 @@ const struct file_operations zonefs_file_operations = {
.llseek = zonefs_file_llseek,
.read_iter = zonefs_file_read_iter,
.write_iter = zonefs_file_write_iter,
- .splice_read = generic_file_splice_read,
+ .splice_read = zonefs_file_splice_read,
.splice_write = iter_file_splice_write,
.iopoll = iocb_bio_iopoll,
};