vdso: Add generic time data storage

Historically each architecture defined their own way to store the vDSO
data page. Add a generic mechanism to provide storage for that page.

Furthermore this generic storage will be extended to also provide
uniform storage for *non*-time-related data, like the random state or
architecture-specific data. These will have their own pages and data
structures, so rename 'vdso_data' into 'vdso_time_data' to make that
split clear from the name.

Also introduce a new consistent naming scheme for the symbols related to
the vDSO, which makes it clear if the symbol is accessible from
userspace or kernel space and the type of data behind the symbol.

The generic fault handler contains an optimization to prefault the vvar
page when the timens page is accessed. This was lifted from s390 and x86.

Co-developed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250204-vdso-store-rng-v3-5-13a4669dfc8c@linutronix.de

1 files changed, 103 insertions, 0 deletions

diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c
new file mode 100644
index 000000000000..d3181768424c
--- /dev/null
+++ b/lib/vdso/datastore.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/linkage.h>
+#include <linux/mmap_lock.h>
+#include <linux/mm.h>
+#include <linux/time_namespace.h>
+#include <linux/types.h>
+#include <linux/vdso_datastore.h>
+#include <vdso/datapage.h>
+
+/*
+ * The vDSO data page.
+ */
+#ifdef CONFIG_HAVE_GENERIC_VDSO
+static union vdso_data_store vdso_time_data_store __page_aligned_data;
+struct vdso_time_data *vdso_k_time_data = vdso_time_data_store.data;
+static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE);
+#endif /* CONFIG_HAVE_GENERIC_VDSO */
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long addr, pfn;
+	vm_fault_t err;
+
+	switch (vmf->pgoff) {
+	case VDSO_TIME_PAGE_OFFSET:
+		if (!IS_ENABLED(CONFIG_HAVE_GENERIC_VDSO))
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data));
+		if (timens_page) {
+			/*
+			 * Fault in VVAR page too, since it will be accessed
+			 * to get clock data anyway.
+			 */
+			addr = vmf->address + VDSO_TIMENS_PAGE_OFFSET * PAGE_SIZE;
+			err = vmf_insert_pfn(vma, addr, pfn);
+			if (unlikely(err & VM_FAULT_ERROR))
+				return err;
+			pfn = page_to_pfn(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)
+			return VM_FAULT_SIGBUS;
+		pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data));
+		break;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+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_IO | VM_DONTDUMP | VM_PFNMAP,
+					&vdso_vvar_mapping);
+}
+
+#ifdef CONFIG_TIME_NS
+/*
+ * The vvar page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will be re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_data() for details.
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma) {
+		if (vma_is_special_mapping(vma, &vdso_vvar_mapping))
+			zap_vma_pages(vma);
+	}
+	mmap_read_unlock(mm);
+
+	return 0;
+}
+
+struct vdso_time_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_time_data *)vvar_page;
+}
+#endif