Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 386 insertions, 0 deletions

diff --git a/net/handshake/request.c b/net/handshake/request.c
new file mode 100644
index 000000000..cd30d54d0
--- /dev/null
+++ b/net/handshake/request.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Handshake request lifetime events
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/inet.h>
+#include <linux/file.h>
+#include <linux/rhashtable.h>
+
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+
+#include <kunit/visibility.h>
+
+#include <uapi/linux/handshake.h>
+#include "handshake.h"
+
+#include <trace/events/handshake.h>
+
+/*
+ * We need both a handshake_req -> sock mapping, and a sock ->
+ * handshake_req mapping. Both are one-to-one.
+ *
+ * To avoid adding another pointer field to struct sock, net/handshake
+ * maintains a hash table, indexed by the memory address of @sock, to
+ * find the struct handshake_req outstanding for that socket. The
+ * reverse direction uses a simple pointer field in the handshake_req
+ * struct.
+ */
+
+static struct rhashtable handshake_rhashtbl ____cacheline_aligned_in_smp;
+
+static const struct rhashtable_params handshake_rhash_params = {
+	.key_len		= sizeof_field(struct handshake_req, hr_sk),
+	.key_offset		= offsetof(struct handshake_req, hr_sk),
+	.head_offset		= offsetof(struct handshake_req, hr_rhash),
+	.automatic_shrinking	= true,
+};
+
+int handshake_req_hash_init(void)
+{
+	return rhashtable_init(&handshake_rhashtbl, &handshake_rhash_params);
+}
+
+void handshake_req_hash_destroy(void)
+{
+	rhashtable_destroy(&handshake_rhashtbl);
+}
+
+struct handshake_req *handshake_req_hash_lookup(struct sock *sk)
+{
+	return rhashtable_lookup_fast(&handshake_rhashtbl, &sk,
+				      handshake_rhash_params);
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_req_hash_lookup);
+
+static bool handshake_req_hash_add(struct handshake_req *req)
+{
+	int ret;
+
+	ret = rhashtable_lookup_insert_fast(&handshake_rhashtbl,
+					    &req->hr_rhash,
+					    handshake_rhash_params);
+	return ret == 0;
+}
+
+static void handshake_req_destroy(struct handshake_req *req)
+{
+	if (req->hr_proto->hp_destroy)
+		req->hr_proto->hp_destroy(req);
+	rhashtable_remove_fast(&handshake_rhashtbl, &req->hr_rhash,
+			       handshake_rhash_params);
+	kfree(req);
+}
+
+static void handshake_sk_destruct(struct sock *sk)
+{
+	void (*sk_destruct)(struct sock *sk);
+	struct handshake_req *req;
+
+	req = handshake_req_hash_lookup(sk);
+	if (!req)
+		return;
+
+	trace_handshake_destruct(sock_net(sk), req, sk);
+	sk_destruct = req->hr_odestruct;
+	handshake_req_destroy(req);
+	if (sk_destruct)
+		sk_destruct(sk);
+}
+
+/**
+ * handshake_req_alloc - Allocate a handshake request
+ * @proto: security protocol
+ * @flags: memory allocation flags
+ *
+ * Returns an initialized handshake_req or NULL.
+ */
+struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto,
+					  gfp_t flags)
+{
+	struct handshake_req *req;
+
+	if (!proto)
+		return NULL;
+	if (proto->hp_handler_class <= HANDSHAKE_HANDLER_CLASS_NONE)
+		return NULL;
+	if (proto->hp_handler_class >= HANDSHAKE_HANDLER_CLASS_MAX)
+		return NULL;
+	if (!proto->hp_accept || !proto->hp_done)
+		return NULL;
+
+	req = kzalloc_flex(*req, hr_priv, proto->hp_privsize, flags);
+	if (!req)
+		return NULL;
+
+	INIT_LIST_HEAD(&req->hr_list);
+	req->hr_proto = proto;
+	return req;
+}
+EXPORT_SYMBOL(handshake_req_alloc);
+
+/**
+ * handshake_req_private - Get per-handshake private data
+ * @req: handshake arguments
+ *
+ */
+void *handshake_req_private(struct handshake_req *req)
+{
+	return (void *)&req->hr_priv;
+}
+EXPORT_SYMBOL(handshake_req_private);
+
+static bool __add_pending_locked(struct handshake_net *hn,
+				 struct handshake_req *req)
+{
+	if (WARN_ON_ONCE(!list_empty(&req->hr_list)))
+		return false;
+	hn->hn_pending++;
+	list_add_tail(&req->hr_list, &hn->hn_requests);
+	return true;
+}
+
+static void __remove_pending_locked(struct handshake_net *hn,
+				    struct handshake_req *req)
+{
+	hn->hn_pending--;
+	list_del_init(&req->hr_list);
+}
+
+/*
+ * Returns %true if the request was found on @net's pending list,
+ * otherwise %false.
+ *
+ * If @req was on a pending list, it has not yet been accepted.
+ * Returns %false when the net namespace is draining; the drain
+ * loop has taken ownership of the pending list.
+ */
+static bool remove_pending(struct handshake_net *hn, struct handshake_req *req)
+{
+	bool ret = false;
+
+	spin_lock_bh(&hn->hn_lock);
+	if (!test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags) &&
+	    !list_empty(&req->hr_list)) {
+		__remove_pending_locked(hn, req);
+		ret = true;
+	}
+	spin_unlock_bh(&hn->hn_lock);
+
+	return ret;
+}
+
+/**
+ * handshake_req_next - Return the next queued handshake request
+ * @hn: per-net handshake state
+ * @class: handler class to match
+ *
+ * On a non-NULL return, the caller owns an extra reference
+ * on @req->hr_file.  FD_PREPARE() consumes it on success; on
+ * the FD_PREPARE() failure path the caller must fput() it.
+ *
+ * Return: pointer to a removed handshake_req, or NULL.
+ */
+struct handshake_req *handshake_req_next(struct handshake_net *hn, int class)
+{
+	struct handshake_req *req, *pos;
+
+	req = NULL;
+	spin_lock_bh(&hn->hn_lock);
+	list_for_each_entry(pos, &hn->hn_requests, hr_list) {
+		if (pos->hr_proto->hp_handler_class != class)
+			continue;
+		__remove_pending_locked(hn, pos);
+		/* Hand off a file reference to the accept side under
+		 * hn_lock.  A concurrent handshake_req_cancel() can drop
+		 * hr_file before accept reaches FD_PREPARE(); this extra
+		 * reference keeps the file alive until FD_PREPARE() takes
+		 * ownership.
+		 */
+		get_file(pos->hr_file);
+		req = pos;
+		break;
+	}
+	spin_unlock_bh(&hn->hn_lock);
+
+	return req;
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_req_next);
+
+/**
+ * handshake_req_submit - Submit a handshake request
+ * @sock: open socket on which to perform the handshake
+ * @req: handshake arguments
+ * @flags: memory allocation flags
+ *
+ * Return values:
+ *   %0: Request queued
+ *   %-EINVAL: Invalid argument
+ *   %-EBUSY: A handshake is already under way for this socket
+ *   %-ESRCH: No handshake agent is available
+ *   %-EAGAIN: Too many pending handshake requests
+ *   %-ENOMEM: Failed to allocate memory
+ *   %-EMSGSIZE: Failed to construct notification message
+ *   %-EOPNOTSUPP: Handshake module not initialized
+ *
+ * A zero return value from handshake_req_submit() means that
+ * exactly one subsequent completion callback is guaranteed.
+ *
+ * A negative return value from handshake_req_submit() guarantees that
+ * no completion callback will occur and that @req is no longer owned by
+ * the caller. If cancellation wins the completion race after the request
+ * has been published, final destruction is deferred until socket teardown.
+ *
+ * The caller must hold a reference on @sock->file for the duration
+ * of this call. Once the request is published to the accept side, a
+ * concurrent completion or cancellation may release the request's pin on
+ * @sock->file; the caller's reference is what keeps @sock->sk valid until
+ * handshake_req_submit() returns.
+ */
+int handshake_req_submit(struct socket *sock, struct handshake_req *req,
+			 gfp_t flags)
+{
+	struct handshake_net *hn;
+	struct net *net;
+	int ret;
+
+	if (!sock || !req || !sock->file) {
+		kfree(req);
+		return -EINVAL;
+	}
+
+	req->hr_sk = sock->sk;
+	if (!req->hr_sk) {
+		kfree(req);
+		return -EINVAL;
+	}
+
+	/*
+	 * Pin sock->file for the lifetime of the request so the
+	 * accept side does not race a consumer that releases the
+	 * socket while a handshake is pending.
+	 */
+	req->hr_file = get_file(sock->file);
+
+	req->hr_odestruct = req->hr_sk->sk_destruct;
+	req->hr_sk->sk_destruct = handshake_sk_destruct;
+
+	ret = -EOPNOTSUPP;
+	net = sock_net(req->hr_sk);
+	hn = handshake_pernet(net);
+	if (!hn)
+		goto out_err;
+
+	ret = -EAGAIN;
+	if (READ_ONCE(hn->hn_pending) >= hn->hn_pending_max)
+		goto out_err;
+
+	spin_lock_bh(&hn->hn_lock);
+	ret = -EOPNOTSUPP;
+	if (test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags))
+		goto out_unlock;
+	ret = -EBUSY;
+	if (!handshake_req_hash_add(req))
+		goto out_unlock;
+	if (!__add_pending_locked(hn, req))
+		goto out_unlock;
+	spin_unlock_bh(&hn->hn_lock);
+
+	ret = handshake_genl_notify(net, req->hr_proto, flags);
+	if (ret) {
+		trace_handshake_notify_err(net, req, req->hr_sk, ret);
+		if (remove_pending(hn, req))
+			goto out_err;
+	}
+
+	trace_handshake_submit(net, req, req->hr_sk);
+	return 0;
+
+out_unlock:
+	spin_unlock_bh(&hn->hn_lock);
+out_err:
+	trace_handshake_submit_err(net, req, req->hr_sk, ret);
+	if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+		/* Restore original destructor so socket teardown still runs. */
+		req->hr_sk->sk_destruct = req->hr_odestruct;
+		fput(req->hr_file);
+		handshake_req_destroy(req);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(handshake_req_submit);
+
+void handshake_complete(struct handshake_req *req, int status,
+			struct genl_info *info)
+{
+	struct sock *sk = req->hr_sk;
+	struct net *net = sock_net(sk);
+
+	if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+		struct file *file = req->hr_file;
+
+		trace_handshake_complete(net, req, sk, status);
+		req->hr_proto->hp_done(req, status, info);
+
+		fput(file);
+	}
+}
+EXPORT_SYMBOL_IF_KUNIT(handshake_complete);
+
+/**
+ * handshake_req_cancel - Cancel an in-progress handshake
+ * @sk: socket on which there is an ongoing handshake
+ *
+ * Request cancellation races with request completion. To determine
+ * who won, callers examine the return value from this function.
+ *
+ * Return values:
+ *   %true - Uncompleted handshake request was canceled
+ *   %false - Handshake request already completed or not found
+ */
+bool handshake_req_cancel(struct sock *sk)
+{
+	struct handshake_req *req;
+	struct handshake_net *hn;
+	struct net *net;
+
+	net = sock_net(sk);
+	req = handshake_req_hash_lookup(sk);
+	if (!req) {
+		trace_handshake_cancel_none(net, req, sk);
+		return false;
+	}
+
+	hn = handshake_pernet(net);
+	if (hn && remove_pending(hn, req)) {
+		/* Request hadn't been accepted - mark cancelled */
+		if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+			trace_handshake_cancel_busy(net, req, sk);
+			return false;
+		}
+		goto out_true;
+	}
+	if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) {
+		/* Request already completed */
+		trace_handshake_cancel_busy(net, req, sk);
+		return false;
+	}
+
+out_true:
+	trace_handshake_cancel(net, req, sk);
+
+	fput(req->hr_file);
+	return true;
+}
+EXPORT_SYMBOL(handshake_req_cancel);