a591afc01d
Pull x32 support for x86-64 from Ingo Molnar: "This tree introduces the X32 binary format and execution mode for x86: 32-bit data space binaries using 64-bit instructions and 64-bit kernel syscalls. This allows applications whose working set fits into a 32 bits address space to make use of 64-bit instructions while using a 32-bit address space with shorter pointers, more compressed data structures, etc." Fix up trivial context conflicts in arch/x86/{Kconfig,vdso/vma.c} * 'x86-x32-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits) x32: Fix alignment fail in struct compat_siginfo x32: Fix stupid ia32/x32 inversion in the siginfo format x32: Add ptrace for x32 x32: Switch to a 64-bit clock_t x32: Provide separate is_ia32_task() and is_x32_task() predicates x86, mtrr: Use explicit sizing and padding for the 64-bit ioctls x86/x32: Fix the binutils auto-detect x32: Warn and disable rather than error if binutils too old x32: Only clear TIF_X32 flag once x32: Make sure TS_COMPAT is cleared for x32 tasks fs: Remove missed ->fds_bits from cessation use of fd_set structs internally fs: Fix close_on_exec pointer in alloc_fdtable x32: Drop non-__vdso weak symbols from the x32 VDSO x32: Fix coding style violations in the x32 VDSO code x32: Add x32 VDSO support x32: Allow x32 to be configured x32: If configured, add x32 system calls to system call tables x32: Handle process creation x32: Signal-related system calls x86: Add #ifdef CONFIG_COMPAT to <asm/sys_ia32.h> ...
206 lines
5.1 KiB
C
206 lines
5.1 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>
|
|
|
|
unsigned int __read_mostly vdso_enabled = 1;
|
|
|
|
extern char vdso_start[], vdso_end[];
|
|
extern unsigned short vdso_sync_cpuid;
|
|
|
|
extern struct page *vdso_pages[];
|
|
static unsigned vdso_size;
|
|
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
extern char vdsox32_start[], vdsox32_end[];
|
|
extern struct page *vdsox32_pages[];
|
|
static unsigned vdsox32_size;
|
|
|
|
static void __init patch_vdsox32(void *vdso, size_t len)
|
|
{
|
|
Elf32_Ehdr *hdr = vdso;
|
|
Elf32_Shdr *sechdrs, *alt_sec = 0;
|
|
char *secstrings;
|
|
void *alt_data;
|
|
int i;
|
|
|
|
BUG_ON(len < sizeof(Elf32_Ehdr));
|
|
BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
|
|
|
|
sechdrs = (void *)hdr + hdr->e_shoff;
|
|
secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (i = 1; i < hdr->e_shnum; i++) {
|
|
Elf32_Shdr *shdr = &sechdrs[i];
|
|
if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
|
|
alt_sec = shdr;
|
|
goto found;
|
|
}
|
|
}
|
|
|
|
/* If we get here, it's probably a bug. */
|
|
pr_warning("patch_vdsox32: .altinstructions not found\n");
|
|
return; /* nothing to patch */
|
|
|
|
found:
|
|
alt_data = (void *)hdr + alt_sec->sh_offset;
|
|
apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
|
|
}
|
|
#endif
|
|
|
|
static void __init patch_vdso64(void *vdso, size_t len)
|
|
{
|
|
Elf64_Ehdr *hdr = vdso;
|
|
Elf64_Shdr *sechdrs, *alt_sec = 0;
|
|
char *secstrings;
|
|
void *alt_data;
|
|
int i;
|
|
|
|
BUG_ON(len < sizeof(Elf64_Ehdr));
|
|
BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
|
|
|
|
sechdrs = (void *)hdr + hdr->e_shoff;
|
|
secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
|
|
|
|
for (i = 1; i < hdr->e_shnum; i++) {
|
|
Elf64_Shdr *shdr = &sechdrs[i];
|
|
if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
|
|
alt_sec = shdr;
|
|
goto found;
|
|
}
|
|
}
|
|
|
|
/* If we get here, it's probably a bug. */
|
|
pr_warning("patch_vdso64: .altinstructions not found\n");
|
|
return; /* nothing to patch */
|
|
|
|
found:
|
|
alt_data = (void *)hdr + alt_sec->sh_offset;
|
|
apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
|
|
}
|
|
|
|
static int __init init_vdso(void)
|
|
{
|
|
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
|
|
int i;
|
|
|
|
patch_vdso64(vdso_start, vdso_end - vdso_start);
|
|
|
|
vdso_size = npages << PAGE_SHIFT;
|
|
for (i = 0; i < npages; i++)
|
|
vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
|
|
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
|
|
npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
|
|
vdsox32_size = npages << PAGE_SHIFT;
|
|
for (i = 0; i < npages; i++)
|
|
vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE);
|
|
#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_addr(addr, NULL, ALIGN_VDSO);
|
|
|
|
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 (!vdso_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 *)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_pages,
|
|
vdso_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, vdsox32_pages,
|
|
vdsox32_size);
|
|
}
|
|
#endif
|
|
|
|
static __init int vdso_setup(char *s)
|
|
{
|
|
vdso_enabled = simple_strtoul(s, NULL, 0);
|
|
return 0;
|
|
}
|
|
__setup("vdso=", vdso_setup);
|