x86, vdso: Reimplement vdso.so preparation in build-time C

Currently, vdso.so files are prepared and analyzed by a combination
of objcopy, nm, some linker script tricks, and some simple ELF
parsers in the kernel.  Replace all of that with plain C code that
runs at build time.

All five vdso images now generate .c files that are compiled and
linked in to the kernel image.

This should cause only one userspace-visible change: the loaded vDSO
images are stripped more heavily than they used to be.  Everything
outside the loadable segment is dropped.  In particular, this causes
the section table and section name strings to be missing.  This
should be fine: real dynamic loaders don't load or inspect these
tables anyway.  The result is roughly equivalent to eu-strip's
--strip-sections option.

The purpose of this change is to enable the vvar and hpet mappings
to be moved to the page following the vDSO load segment.  Currently,
it is possible for the section table to extend into the page after
the load segment, so, if we map it, it risks overlapping the vvar or
hpet page.  This happens whenever the load segment is just under a
multiple of PAGE_SIZE.

The only real subtlety here is that the old code had a C file with
inline assembler that did 'call VDSO32_vsyscall' and a linker script
that defined 'VDSO32_vsyscall = __kernel_vsyscall'.  This most
likely worked by accident: the linker script entry defines a symbol
associated with an address as opposed to an alias for the real
dynamic symbol __kernel_vsyscall.  That caused ld to relocate the
reference at link time instead of leaving an interposable dynamic
relocation.  Since the VDSO32_vsyscall hack is no longer needed, I
now use 'call __kernel_vsyscall', and I added -Bsymbolic to make it
work.  vdso2c will generate an error and abort the build if the
resulting image contains any dynamic relocations, so we won't
silently generate bad vdso images.

(Dynamic relocations are a problem because nothing will even attempt
to relocate the vdso.)

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/2c4fcf45524162a34d87fdda1eb046b2a5cecee7.1399317206.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

1 files changed, 20 insertions, 30 deletions

diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 9c78d5b24874..d41460118a28 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -29,6 +29,7 @@
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
 #include <asm/vvar.h>
+#include <asm/vdso32.h>
 
 #ifdef CONFIG_COMPAT_VDSO
 #define VDSO_DEFAULT	0
@@ -67,9 +68,6 @@ __setup("vdso32=", vdso32_setup);
 __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 #endif
 
-static struct page **vdso32_pages;
-static unsigned vdso32_size;
-
 #ifdef CONFIG_X86_64
 
 #define	vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SYSENTER32))
@@ -82,34 +80,23 @@ static unsigned vdso32_size;
 
 #endif	/* CONFIG_X86_64 */
 
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+const struct vdso_image *selected_vdso32;
+#endif
+
 int __init sysenter_setup(void)
 {
-	char *vdso32_start, *vdso32_end;
-	int npages, i;
-
 #ifdef CONFIG_COMPAT
-	if (vdso32_syscall()) {
-		vdso32_start = vdso32_syscall_start;
-		vdso32_end = vdso32_syscall_end;
-		vdso32_pages = vdso32_syscall_pages;
-	} else
+	if (vdso32_syscall())
+		selected_vdso32 = &vdso_image_32_syscall;
+	else
 #endif
-	if (vdso32_sysenter()) {
-		vdso32_start = vdso32_sysenter_start;
-		vdso32_end = vdso32_sysenter_end;
-		vdso32_pages = vdso32_sysenter_pages;
-	} else {
-		vdso32_start = vdso32_int80_start;
-		vdso32_end = vdso32_int80_end;
-		vdso32_pages = vdso32_int80_pages;
-	}
-
-	npages = ((vdso32_end - vdso32_start) + PAGE_SIZE - 1) / PAGE_SIZE;
-	vdso32_size = npages << PAGE_SHIFT;
-	for (i = 0; i < npages; i++)
-		vdso32_pages[i] = virt_to_page(vdso32_start + i*PAGE_SIZE);
+	if (vdso32_sysenter())
+		selected_vdso32 = &vdso_image_32_sysenter;
+	else
+		selected_vdso32 = &vdso_image_32_int80;
 
-	patch_vdso32(vdso32_start, vdso32_size);
+	init_vdso_image(selected_vdso32);
 
 	return 0;
 }
@@ -121,6 +108,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	unsigned long addr;
 	int ret = 0;
 	struct vm_area_struct *vma;
+	unsigned long vdso32_size = selected_vdso32->size;
 
 #ifdef CONFIG_X86_X32_ABI
 	if (test_thread_flag(TIF_X32))
@@ -140,7 +128,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	addr += VDSO_OFFSET(VDSO_PREV_PAGES);
 
-	current->mm->context.vdso = (void *)addr;
+	current->mm->context.vdso = (void __user *)addr;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -150,7 +138,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 			vdso32_size,
 			VM_READ|VM_EXEC|
 			VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-			vdso32_pages);
+			selected_vdso32->pages);
 
 	if (ret)
 		goto up_fail;
@@ -188,8 +176,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	}
 #endif
 
-	current_thread_info()->sysenter_return =
-		VDSO32_SYMBOL(addr, SYSENTER_RETURN);
+	if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
+		current_thread_info()->sysenter_return =
+			current->mm->context.vdso +
+			selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
 
   up_fail:
 	if (ret)