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, 129 insertions, 0 deletions

diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
new file mode 100644
index 000000000..1426bf4e0
--- /dev/null
+++ b/lib/vdso/datastore.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/time_namespace.h>
+#include <linux/types.h>
+#include <linux/vdso_datastore.h>
+#include <vdso/datapage.h>
+
+static u8 vdso_initdata[VDSO_NR_PAGES * PAGE_SIZE] __aligned(PAGE_SIZE) __initdata = {};
+
+#ifdef CONFIG_GENERIC_GETTIMEOFDAY
+struct vdso_time_data *vdso_k_time_data __ro_after_init =
+	(void *)&vdso_initdata[VDSO_TIME_PAGE_OFFSET * PAGE_SIZE];
+
+static_assert(sizeof(struct vdso_time_data) <= PAGE_SIZE);
+#endif /* CONFIG_GENERIC_GETTIMEOFDAY */
+
+#ifdef CONFIG_VDSO_GETRANDOM
+struct vdso_rng_data *vdso_k_rng_data __ro_after_init =
+	(void *)&vdso_initdata[VDSO_RNG_PAGE_OFFSET * PAGE_SIZE];
+
+static_assert(sizeof(struct vdso_rng_data) <= PAGE_SIZE);
+#endif /* CONFIG_VDSO_GETRANDOM */
+
+#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA
+struct vdso_arch_data *vdso_k_arch_data __ro_after_init =
+	(void *)&vdso_initdata[VDSO_ARCH_PAGES_START * PAGE_SIZE];
+#endif /* CONFIG_ARCH_HAS_VDSO_ARCH_DATA */
+
+static struct page *vdso_data_pages __ro_after_init;
+
+void __init vdso_setup_data_pages(void)
+{
+	unsigned int order = get_order(VDSO_NR_PAGES * PAGE_SIZE);
+
+	/*
+	 * Allocate the data pages dynamically. SPARC does not support mapping
+	 * static pages to be mapped into userspace.
+	 * It is also a requirement for mlockall() support.
+	 *
+	 * Do not use folios. In time namespaces the pages are mapped in a different order
+	 * to userspace, which is not handled by the folio optimizations in finish_fault().
+	 */
+	vdso_data_pages = alloc_pages(GFP_KERNEL, order);
+	if (!vdso_data_pages)
+		panic("Unable to allocate VDSO storage pages");
+
+	/* The pages are mapped one-by-one into userspace and each one needs to be refcounted. */
+	split_page(vdso_data_pages, order);
+
+	/* Move the data already written by other subsystems to the new pages */
+	memcpy(page_address(vdso_data_pages), vdso_initdata, VDSO_NR_PAGES * PAGE_SIZE);
+
+	if (IS_ENABLED(CONFIG_GENERIC_GETTIMEOFDAY))
+		vdso_k_time_data = page_address(vdso_data_pages + VDSO_TIME_PAGE_OFFSET);
+
+	if (IS_ENABLED(CONFIG_VDSO_GETRANDOM))
+		vdso_k_rng_data = page_address(vdso_data_pages + VDSO_RNG_PAGE_OFFSET);
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_VDSO_ARCH_DATA))
+		vdso_k_arch_data = page_address(vdso_data_pages + VDSO_ARCH_PAGES_START);
+}
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *page, *timens_page;
+
+	if (unlikely(vmf->flags & FAULT_FLAG_REMOTE))
+		return VM_FAULT_SIGBUS;
+
+	page = vdso_data_pages + vmf->pgoff;
+	timens_page = find_timens_vvar_page(vma);
+
+	switch (vmf->pgoff) {
+	case VDSO_TIME_PAGE_OFFSET:
+		if (!IS_ENABLED(CONFIG_GENERIC_GETTIMEOFDAY) || !timens_page)
+			break;
+		/*
+		 * Fault in VVAR page too, since it will be accessed
+		 * to get clock data anyway.
+		 */
+		unsigned long addr;
+		vm_fault_t err;
+
+		addr = vmf->address + VDSO_TIMENS_PAGE_OFFSET * PAGE_SIZE;
+		err = vmf_insert_page(vma, addr, page);
+		if (unlikely(err & VM_FAULT_ERROR))
+			return err;
+		page = timens_page;
+		break;
+	case VDSO_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!IS_ENABLED(CONFIG_TIME_NS) || !timens_page)
+			break;
+		page = vdso_data_pages + VDSO_TIME_PAGE_OFFSET;
+		break;
+	case VDSO_RNG_PAGE_OFFSET:
+	case VDSO_ARCH_PAGES_START ... VDSO_ARCH_PAGES_END:
+		break;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	get_page(page);
+	vmf->page = page;
+	return 0;
+}
+
+const struct vm_special_mapping vdso_vvar_mapping = {
+	.name	= "[vvar]",
+	.fault	= vvar_fault,
+};
+
+struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr)
+{
+	return _install_special_mapping(mm, addr, VDSO_NR_PAGES * PAGE_SIZE,
+					VM_READ | VM_MAYREAD | VM_DONTDUMP |
+					VM_MIXEDMAP | VM_SEALED_SYSMAP,
+					&vdso_vvar_mapping);
+}