[PATCHv3 15/27] x86/vdso: Allocate timens vdso

[Dmitry Safonov]

As it has been discussed on timens RFC, adding a new conditional branch
`if (inside_time_ns)` on VDSO for all processes is undesirable.
It will add a penalty for everybody as branch predictor may mispredict
the jump. Also there are instruction cache lines wasted on cmp/jmp.

Those effects of introducing time namespace are very much unwanted
having in mind how much work have been spent on micro-optimisation
vdso code.

The propose is to allocate a second vdso code with dynamically
patched out (disabled by static_branch) timens code on boot time.

Allocate another vdso and copy original code.

Signed-off-by: Dmitry Safonov <dima@xxxxxxxxxx>
---
 arch/x86/entry/vdso/vdso2c.h |  2 +-
 arch/x86/entry/vdso/vma.c    | 36 +++++++++++++++++++++++++++++++-----
 arch/x86/include/asm/vdso.h  |  9 +++++----
 3 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 086a11aee0e8..660f725a02c1 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -156,7 +156,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "const struct vdso_image %s = {\n", name);
+	fprintf(outfile, "struct vdso_image %s __ro_after_init = {\n", name);
 	fprintf(outfile, "\t.text = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
 	if (alt_sec) {
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 80cbb2167eba..6aae9c0d400d 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -30,26 +30,52 @@
 unsigned int __read_mostly vdso64_enabled = 1;
 #endif
 
-void __init init_vdso_image(const struct vdso_image *image)
+void __init init_vdso_image(struct vdso_image *image)
 {
 	BUG_ON(image->size % PAGE_SIZE != 0);
 
 	apply_alternatives((struct alt_instr *)(image->text + image->alt),
 			   (struct alt_instr *)(image->text + image->alt +
 						image->alt_len));
+#ifdef CONFIG_TIME_NS
+	image->text_timens = vmalloc_32(image->size);
+	if (WARN_ON(image->text_timens == NULL))
+		return;
+
+	memcpy(image->text_timens, image->text, image->size);
+#endif
 }
 
 struct linux_binprm;
 
+#ifdef CONFIG_TIME_NS
+static inline struct timens_offsets *current_timens_offsets(void)
+{
+	struct time_namespace *ns = current->nsproxy->time_ns;
+
+	return ns->offsets;
+}
+#else
+static inline struct timens_offsets *current_timens_offsets(void)
+{
+	return NULL;
+}
+#endif
+
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	unsigned long offset = vmf->pgoff << PAGE_SHIFT;
 
 	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
 		return VM_FAULT_SIGBUS;
 
-	vmf->page = virt_to_page(image->text + (vmf->pgoff << PAGE_SHIFT));
+	if (current_timens_offsets() && image->text_timens)
+		vmf->page = vmalloc_to_page(image->text_timens + offset);
+	else
+		vmf->page = virt_to_page(image->text + offset);
+
 	get_page(vmf->page);
 	return 0;
 }
@@ -138,13 +164,13 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			return vmf_insert_pfn(vma, vmf->address,
 					vmalloc_to_pfn(tsc_pg));
 	} else if (sym_offset == image->sym_timens_page) {
-		struct time_namespace *ns = current->nsproxy->time_ns;
+		struct timens_offsets *offsets = current_timens_offsets();
 		unsigned long pfn;
 
-		if (!ns->offsets)
+		if (!offsets)
 			pfn = page_to_pfn(ZERO_PAGE(0));
 		else
-			pfn = page_to_pfn(virt_to_page(ns->offsets));
+			pfn = page_to_pfn(virt_to_page(offsets));
 
 		return vmf_insert_pfn(vma, vmf->address, pfn);
 	}
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index b0eb59c198eb..a620c7f23425 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -12,6 +12,7 @@
 
 struct vdso_image {
 	void *text;
+	void *text_timens;
 	unsigned long size;   /* Always a multiple of PAGE_SIZE */
 
 	unsigned long alt, alt_len;
@@ -31,18 +32,18 @@ struct vdso_image {
 };
 
 #ifdef CONFIG_X86_64
-extern const struct vdso_image vdso_image_64;
+extern struct vdso_image vdso_image_64;
 #endif
 
 #ifdef CONFIG_X86_X32
-extern const struct vdso_image vdso_image_x32;
+extern struct vdso_image vdso_image_x32;
 #endif
 
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const struct vdso_image vdso_image_32;
+extern struct vdso_image vdso_image_32;
 #endif
 
-extern void __init init_vdso_image(const struct vdso_image *image);
+extern void __init init_vdso_image(struct vdso_image *image);
 
 extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
 
-- 
2.21.0