1
linux/arch/s390/mm/init.c
Gerald Schaefer c1821c2e97 [S390] noexec protection
This provides a noexec protection on s390 hardware. Our hardware does
not have any bits left in the pte for a hw noexec bit, so this is a
different approach using shadow page tables and a special addressing
mode that allows separate address spaces for code and data.

As a special feature of our "secondary-space" addressing mode, separate
page tables can be specified for the translation of data addresses
(storage operands) and instruction addresses. The shadow page table is
used for the instruction addresses and the standard page table for the
data addresses.
The shadow page table is linked to the standard page table by a pointer
in page->lru.next of the struct page corresponding to the page that
contains the standard page table (since page->private is not really
private with the pte_lock and the page table pages are not in the LRU
list).
Depending on the software bits of a pte, it is either inserted into
both page tables or just into the standard (data) page table. Pages of
a vma that does not have the VM_EXEC bit set get mapped only in the
data address space. Any try to execute code on such a page will cause a
page translation exception. The standard reaction to this is a SIGSEGV
with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn)
and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the
kernel to the signal stack frame. Unfortunately, the signal return
mechanism cannot be modified to use an SA_RESTORER because the
exception unwinding code depends on the system call opcode stored
behind the signal stack frame.

This feature requires that user space is executed in secondary-space
mode and the kernel in home-space mode, which means that the addressing
modes need to be switched and that the noexec protection only works
for user space.
After switching the addressing modes, we cannot use the mvcp/mvcs
instructions anymore to copy between kernel and user space. A new
mvcos instruction has been added to the z9 EC/BC hardware which allows
to copy between arbitrary address spaces, but on older hardware the
page tables need to be walked manually.

Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-05 21:18:17 +01:00

209 lines
5.6 KiB
C

/*
* arch/s390/mm/init.c
*
* S390 version
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Hartmut Penner (hp@de.ibm.com)
*
* Derived from "arch/i386/mm/init.c"
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/initrd.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/lowcore.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
char empty_zero_page[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
void diag10(unsigned long addr)
{
if (addr >= 0x7ff00000)
return;
asm volatile(
#ifdef CONFIG_64BIT
" sam31\n"
" diag %0,%0,0x10\n"
"0: sam64\n"
#else
" diag %0,%0,0x10\n"
"0:\n"
#endif
EX_TABLE(0b,0b)
: : "a" (addr));
}
void show_mem(void)
{
int i, total = 0, reserved = 0;
int shared = 0, cached = 0;
struct page *page;
printk("Mem-info:\n");
show_free_areas();
printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
i = max_mapnr;
while (i-- > 0) {
if (!pfn_valid(i))
continue;
page = pfn_to_page(i);
total++;
if (PageReserved(page))
reserved++;
else if (PageSwapCache(page))
cached++;
else if (page_count(page))
shared += page_count(page) - 1;
}
printk("%d pages of RAM\n",total);
printk("%d reserved pages\n",reserved);
printk("%d pages shared\n",shared);
printk("%d pages swap cached\n",cached);
}
static void __init setup_ro_region(void)
{
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte;
pte_t new_pte;
unsigned long address, end;
address = ((unsigned long)&__start_rodata) & PAGE_MASK;
end = PFN_ALIGN((unsigned long)&__end_rodata);
for (; address < end; address += PAGE_SIZE) {
pgd = pgd_offset_k(address);
pmd = pmd_offset(pgd, address);
pte = pte_offset_kernel(pmd, address);
new_pte = mk_pte_phys(address, __pgprot(_PAGE_RO));
*pte = new_pte;
}
}
/*
* paging_init() sets up the page tables
*/
void __init paging_init(void)
{
pgd_t *pg_dir;
int i;
unsigned long pgdir_k;
static const int ssm_mask = 0x04000000L;
unsigned long max_zone_pfns[MAX_NR_ZONES];
pg_dir = swapper_pg_dir;
#ifdef CONFIG_64BIT
pgdir_k = (__pa(swapper_pg_dir) & PAGE_MASK) | _KERN_REGION_TABLE;
for (i = 0; i < PTRS_PER_PGD; i++)
pgd_clear_kernel(pg_dir + i);
#else
pgdir_k = (__pa(swapper_pg_dir) & PAGE_MASK) | _KERNSEG_TABLE;
for (i = 0; i < PTRS_PER_PGD; i++)
pmd_clear_kernel((pmd_t *)(pg_dir + i));
#endif
vmem_map_init();
setup_ro_region();
S390_lowcore.kernel_asce = pgdir_k;
/* enable virtual mapping in kernel mode */
__ctl_load(pgdir_k, 1, 1);
__ctl_load(pgdir_k, 7, 7);
__ctl_load(pgdir_k, 13, 13);
__raw_local_irq_ssm(ssm_mask);
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
}
void __init mem_init(void)
{
unsigned long codesize, reservedpages, datasize, initsize;
max_mapnr = num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
/* clear the zero-page */
memset(empty_zero_page, 0, PAGE_SIZE);
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();
reservedpages = 0;
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
max_mapnr << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >>10,
initsize >> 10);
printk("Write protected kernel read-only data: %#lx - %#lx\n",
(unsigned long)&__start_rodata,
PFN_ALIGN((unsigned long)&__end_rodata) - 1);
}
void free_initmem(void)
{
unsigned long addr;
addr = (unsigned long)(&__init_begin);
for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
printk ("Freeing unused kernel memory: %ldk freed\n",
((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10);
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
if (start < end)
printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
for (; start < end; start += PAGE_SIZE) {
ClearPageReserved(virt_to_page(start));
init_page_count(virt_to_page(start));
free_page(start);
totalram_pages++;
}
}
#endif