ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 76 insertions, 0 deletions

diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
new file mode 100644
index 000000000..d95b6d0d9
--- /dev/null
+++ b/net/xdp/xsk_queue.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include <linux/overflow.h>
+#include <linux/vmalloc.h>
+#include <net/xdp_sock_drv.h>
+
+#include <asm/shmparam.h>
+
+#include "xsk_queue.h"
+
+static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue)
+{
+	struct xdp_umem_ring *umem_ring;
+	struct xdp_rxtx_ring *rxtx_ring;
+
+	if (umem_queue)
+		return struct_size(umem_ring, desc, q->nentries);
+	return struct_size(rxtx_ring, desc, q->nentries);
+}
+
+static void *xskq_vmalloc_user(unsigned long size)
+{
+	return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END,
+				     GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL,
+				     VM_USERMAP, NUMA_NO_NODE,
+				     __builtin_return_address(0));
+}
+
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
+{
+	struct xsk_queue *q;
+	size_t size;
+
+	q = kzalloc_obj(*q);
+	if (!q)
+		return NULL;
+
+	q->nentries = nentries;
+	q->ring_mask = nentries - 1;
+
+	size = xskq_get_ring_size(q, umem_queue);
+
+	/* size which is overflowing or close to SIZE_MAX will become 0 in
+	 * PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous
+	 * is_power_of_2(), the rest will be handled by vmalloc_user()
+	 */
+	if (unlikely(size == SIZE_MAX)) {
+		kfree(q);
+		return NULL;
+	}
+
+	size = PAGE_ALIGN(size);
+
+	q->ring = xskq_vmalloc_user(size);
+	if (!q->ring) {
+		kfree(q);
+		return NULL;
+	}
+
+	q->ring_vmalloc_size = size;
+	return q;
+}
+
+void xskq_destroy(struct xsk_queue *q)
+{
+	if (!q)
+		return;
+
+	vfree(q->ring);
+	kfree(q);
+}