selftests/bpf: Reject graph kptr use after RCU unlockgrafted

Add a sleepable verifier test that loads a graph-node local kptr in an
explicit RCU read-side critical section, then passes its node to
bpf_rbtree_remove() after the section ends.

Before the verifier fix, the stale NON_OWN_REF flag makes the node look like
a live borrowed reference and the program is accepted. After the fix, the
pointer is demoted without NON_OWN_REF and the graph kfunc argument is
rejected.

Also exercise a graph kptr loaded while a spin lock provides implicit RCU
protection. The pointer must be invalidated when the lock is released, which
guards the required ordering between non-owning-reference invalidation and
RCU demotion.

Update the existing fault-protected load test state description. The
post-unlock pointer no longer carries NON_OWN_REF, but remains readable
because the load is rewritten to use BPF_PROBE_MEM.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260904084325.52250-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 204 insertions, 0 deletions

diff --git a/fs/nfs/io.c b/fs/nfs/io.c
new file mode 100644
index 000000000..2faf2003f
--- /dev/null
+++ b/fs/nfs/io.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Trond Myklebust
+ *
+ * I/O and data path helper functionality.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+#include <linux/nfs_fs.h>
+
+#include "internal.h"
+
+/**
+ * nfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int
+nfs_start_io_read(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	nfs_file_block_o_direct(nfsi);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * nfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_read(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}
+
+/**
+ * nfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int
+nfs_start_io_write(struct inode *inode)
+{
+	int err;
+
+	err = down_write_killable(&inode->i_rwsem);
+	if (!err)
+		nfs_file_block_o_direct(NFS_I(inode));
+	return err;
+}
+EXPORT_SYMBOL_GPL(nfs_start_io_write);
+
+/**
+ * nfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_write(struct inode *inode)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL_GPL(nfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		nfs_sync_mapping(inode->i_mapping);
+	}
+}
+
+static int nfs_block_buffered_nowait(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		if (inode->i_mapping->nrpages != 0)
+			return 1;
+		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
+	}
+	return 0;
+}
+
+/**
+ * nfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int
+nfs_start_io_direct(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	nfs_block_buffered(nfsi, inode);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * nfs_start_io_direct_nowait - non-blocking variant of nfs_start_io_direct()
+ * @inode: file inode
+ *
+ * Try to declare that a direct I/O operation is about to start without
+ * blocking.
+ * Ensure all buffered I/O is blocked.
+ * If this could not be done without blocking then returns -EAGAIN.
+ */
+int
+nfs_start_io_direct_nowait(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (!down_read_trylock(&inode->i_rwsem))
+		return -EAGAIN;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags))
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path: try to flip NFS_INO_ODIRECT without blocking. */
+	if (!down_write_trylock(&inode->i_rwsem))
+		return -EAGAIN;
+	if (nfs_block_buffered_nowait(nfsi, inode)) {
+		up_write(&inode->i_rwsem);
+		return -EAGAIN;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+
+/**
+ * nfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_direct(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}