mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2026-01-27 08:58:16 +00:00
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>
143 lines
3.4 KiB
C
143 lines
3.4 KiB
C
/*
|
|
* Set up the VMAs to tell the VM about the vDSO.
|
|
* Copyright 2007 Andi Kleen, SUSE Labs.
|
|
* Subject to the GPL, v.2
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init.h>
|
|
#include <linux/random.h>
|
|
#include <linux/elf.h>
|
|
#include <asm/vsyscall.h>
|
|
#include <asm/vgtod.h>
|
|
#include <asm/proto.h>
|
|
#include <asm/vdso.h>
|
|
#include <asm/page.h>
|
|
|
|
#if defined(CONFIG_X86_64)
|
|
unsigned int __read_mostly vdso64_enabled = 1;
|
|
|
|
extern unsigned short vdso_sync_cpuid;
|
|
#endif
|
|
|
|
void __init init_vdso_image(const struct vdso_image *image)
|
|
{
|
|
int i;
|
|
int npages = (image->size) / PAGE_SIZE;
|
|
|
|
BUG_ON(image->size % PAGE_SIZE != 0);
|
|
for (i = 0; i < npages; i++)
|
|
image->pages[i] = virt_to_page(image->data + i*PAGE_SIZE);
|
|
|
|
apply_alternatives((struct alt_instr *)(image->data + image->alt),
|
|
(struct alt_instr *)(image->data + image->alt +
|
|
image->alt_len));
|
|
}
|
|
|
|
|
|
#if defined(CONFIG_X86_64)
|
|
static int __init init_vdso(void)
|
|
{
|
|
init_vdso_image(&vdso_image_64);
|
|
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
init_vdso_image(&vdso_image_x32);
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
subsys_initcall(init_vdso);
|
|
|
|
struct linux_binprm;
|
|
|
|
/* Put the vdso above the (randomized) stack with another randomized offset.
|
|
This way there is no hole in the middle of address space.
|
|
To save memory make sure it is still in the same PTE as the stack top.
|
|
This doesn't give that many random bits */
|
|
static unsigned long vdso_addr(unsigned long start, unsigned len)
|
|
{
|
|
unsigned long addr, end;
|
|
unsigned offset;
|
|
end = (start + PMD_SIZE - 1) & PMD_MASK;
|
|
if (end >= TASK_SIZE_MAX)
|
|
end = TASK_SIZE_MAX;
|
|
end -= len;
|
|
/* This loses some more bits than a modulo, but is cheaper */
|
|
offset = get_random_int() & (PTRS_PER_PTE - 1);
|
|
addr = start + (offset << PAGE_SHIFT);
|
|
if (addr >= end)
|
|
addr = end;
|
|
|
|
/*
|
|
* page-align it here so that get_unmapped_area doesn't
|
|
* align it wrongfully again to the next page. addr can come in 4K
|
|
* unaligned here as a result of stack start randomization.
|
|
*/
|
|
addr = PAGE_ALIGN(addr);
|
|
addr = align_vdso_addr(addr);
|
|
|
|
return addr;
|
|
}
|
|
|
|
/* Setup a VMA at program startup for the vsyscall page.
|
|
Not called for compat tasks */
|
|
static int setup_additional_pages(struct linux_binprm *bprm,
|
|
int uses_interp,
|
|
struct page **pages,
|
|
unsigned size)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long addr;
|
|
int ret;
|
|
|
|
if (!vdso64_enabled)
|
|
return 0;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
addr = vdso_addr(mm->start_stack, size);
|
|
addr = get_unmapped_area(NULL, addr, size, 0, 0);
|
|
if (IS_ERR_VALUE(addr)) {
|
|
ret = addr;
|
|
goto up_fail;
|
|
}
|
|
|
|
current->mm->context.vdso = (void __user *)addr;
|
|
|
|
ret = install_special_mapping(mm, addr, size,
|
|
VM_READ|VM_EXEC|
|
|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
|
|
pages);
|
|
if (ret) {
|
|
current->mm->context.vdso = NULL;
|
|
goto up_fail;
|
|
}
|
|
|
|
up_fail:
|
|
up_write(&mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
return setup_additional_pages(bprm, uses_interp, vdso_image_64.pages,
|
|
vdso_image_64.size);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
return setup_additional_pages(bprm, uses_interp, vdso_image_x32.pages,
|
|
vdso_image_x32.size);
|
|
}
|
|
#endif
|
|
|
|
static __init int vdso_setup(char *s)
|
|
{
|
|
vdso64_enabled = simple_strtoul(s, NULL, 0);
|
|
return 0;
|
|
}
|
|
__setup("vdso=", vdso_setup);
|
|
#endif
|