powerpc/vdso: Add support for time namespaces

This patch adds the necessary glue to provide time namespaces.

Things are mainly copied from ARM64.

__arch_get_timens_vdso_data() calculates timens vdso data position
based on the vdso data position, knowing it is the next page in vvar.
This avoids having to redo the mflr/bcl/mflr/mtlr dance to locate
the page relative to running code position.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com> # vDSO parts
Acked-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1a15495f80ec19a87b16cf874dbf7c3fa5ec40fe.1617209142.git.christophe.leroy@csgroup.eu

1 files changed, 100 insertions, 16 deletions

diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index b14907209822..717f2c9a7573 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -18,6 +18,7 @@
 #include <linux/security.h>
 #include <linux/memblock.h>
 #include <linux/syscalls.h>
+#include <linux/time_namespace.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
@@ -50,6 +51,12 @@ static union {
 } vdso_data_store __page_aligned_data;
 struct vdso_arch_data *vdso_data = &vdso_data_store.data;
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
@@ -73,8 +80,12 @@ static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_str
 	return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
 }
 
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf);
+
 static struct vm_special_mapping vvar_spec __ro_after_init = {
 	.name = "[vvar]",
+	.fault = vvar_fault,
 };
 
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
@@ -87,6 +98,94 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.mremap = vdso64_mremap,
 };
 
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return ((struct vdso_arch_data *)vvar_page)->data;
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, &vvar_spec))
+			zap_page_range(vma, vma->vm_start, size);
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
+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 pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = virt_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_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 (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = virt_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -95,7 +194,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 {
 	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
-	unsigned long vvar_size = PAGE_SIZE;
+	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
@@ -266,19 +365,6 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 	return pagelist;
 }
 
-static struct page ** __init vvar_setup_pages(void)
-{
-	struct page **pagelist;
-
-	/* .pages is NULL-terminated */
-	pagelist = kcalloc(2, sizeof(struct page *), GFP_KERNEL);
-	if (!pagelist)
-		panic("%s: Cannot allocate page list for VVAR", __func__);
-
-	pagelist[0] = virt_to_page(vdso_data);
-	return pagelist;
-}
-
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
@@ -317,8 +403,6 @@ static int __init vdso_init(void)
 	if (IS_ENABLED(CONFIG_PPC64))
 		vdso64_spec.pages = vdso_setup_pages(&vdso64_start, &vdso64_end);
 
-	vvar_spec.pages = vvar_setup_pages();
-
 	smp_wmb();
 
 	return 0;