ceph: Provide a splice-read wrapper

Provide a splice_read wrapper for Ceph.  This does the inode shutdown check
before proceeding and jumps to copy_splice_read() if the file has inline
data or is a synchronous file.

We try and get FILE_RD and either FILE_CACHE and/or FILE_LAZYIO caps and
hold them across filemap_splice_read().  If we fail to get FILE_CACHE or
FILE_LAZYIO capabilities, we use copy_splice_read() instead.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
cc: Christoph Hellwig <hch@lst.de>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: ceph-devel@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-block@vger.kernel.org
cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20230522135018.2742245-17-dhowells@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f4d8bf7dec88a8eddeffbb0de171514566c6fa21..4285f6cb5d3b868cbfa2cc4e7c529baab7ead1db 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1745,6 +1745,69 @@ again:
        return ret;
 }
 
+/*
+ * Wrap filemap_splice_read with checks for cap bits on the inode.
+ * Atomically grab references, so that those bits are not released
+ * back to the MDS mid-read.
+ */
+static ssize_t ceph_splice_read(struct file *in, loff_t *ppos,
+                               struct pipe_inode_info *pipe,
+                               size_t len, unsigned int flags)
+{
+       struct ceph_file_info *fi = in->private_data;
+       struct inode *inode = file_inode(in);
+       struct ceph_inode_info *ci = ceph_inode(inode);
+       ssize_t ret;
+       int want = 0, got = 0;
+       CEPH_DEFINE_RW_CONTEXT(rw_ctx, 0);
+
+       dout("splice_read %p %llx.%llx %llu~%zu trying to get caps on %p\n",
+            inode, ceph_vinop(inode), *ppos, len, inode);
+
+       if (ceph_inode_is_shutdown(inode))
+               return -ESTALE;
+
+       if (ceph_has_inline_data(ci) ||
+           (fi->flags & CEPH_F_SYNC))
+               return copy_splice_read(in, ppos, pipe, len, flags);
+
+       ceph_start_io_read(inode);
+
+       want = CEPH_CAP_FILE_CACHE;
+       if (fi->fmode & CEPH_FILE_MODE_LAZY)
+               want |= CEPH_CAP_FILE_LAZYIO;
+
+       ret = ceph_get_caps(in, CEPH_CAP_FILE_RD, want, -1, &got);
+       if (ret < 0)
+               goto out_end;
+
+       if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) == 0) {
+               dout("splice_read/sync %p %llx.%llx %llu~%zu got cap refs on %s\n",
+                    inode, ceph_vinop(inode), *ppos, len,
+                    ceph_cap_string(got));
+
+               ceph_put_cap_refs(ci, got);
+               ceph_end_io_read(inode);
+               return copy_splice_read(in, ppos, pipe, len, flags);
+       }
+
+       dout("splice_read %p %llx.%llx %llu~%zu got cap refs on %s\n",
+            inode, ceph_vinop(inode), *ppos, len, ceph_cap_string(got));
+
+       rw_ctx.caps = got;
+       ceph_add_rw_context(fi, &rw_ctx);
+       ret = filemap_splice_read(in, ppos, pipe, len, flags);
+       ceph_del_rw_context(fi, &rw_ctx);
+
+       dout("splice_read %p %llx.%llx dropping cap refs on %s = %zd\n",
+            inode, ceph_vinop(inode), ceph_cap_string(got), ret);
+
+       ceph_put_cap_refs(ci, got);
+out_end:
+       ceph_end_io_read(inode);
+       return ret;
+}
+
 /*
  * Take cap references to avoid releasing caps to MDS mid-write.
  *
@@ -2593,7 +2656,7 @@ const struct file_operations ceph_file_fops = {
        .lock = ceph_lock,
        .setlease = simple_nosetlease,
        .flock = ceph_flock,
-       .splice_read = generic_file_splice_read,
+       .splice_read = ceph_splice_read,
        .splice_write = iter_file_splice_write,
        .unlocked_ioctl = ceph_ioctl,
        .compat_ioctl = compat_ptr_ioctl,