linux/arch/x86/vdso/vma.c
Andy Lutomirski 8c49d9a74b x86-64: Clean up vdso/kernel shared variables
Variables that are shared between the vdso and the kernel are
currently a bit of a mess.  They are each defined with their own
magic, they are accessed differently in the kernel, the vsyscall page,
and the vdso, and one of them (vsyscall_clock) doesn't even really
exist.

This changes them all to use a common mechanism.  All of them are
delcared in vvar.h with a fixed address (validated by the linker
script).  In the kernel (as before), they look like ordinary
read-write variables.  In the vsyscall page and the vdso, they are
accessed through a new macro VVAR, which gives read-only access.

The vdso is now loaded verbatim into memory without any fixups.  As a
side bonus, access from the vdso is faster because a level of
indirection is removed.

While we're at it, pack jiffies and vgetcpu_mode into the same
cacheline.

Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C7357882fbb51fa30491636a7b6528747301b7ee9.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2011-05-24 14:51:28 +02:00

116 lines
2.7 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>
unsigned int __read_mostly vdso_enabled = 1;
extern char vdso_start[], vdso_end[];
extern unsigned short vdso_sync_cpuid;
static struct page **vdso_pages;
static unsigned vdso_size;
static int __init init_vdso_vars(void)
{
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
int i;
vdso_size = npages << PAGE_SHIFT;
vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
if (!vdso_pages)
goto oom;
for (i = 0; i < npages; i++) {
struct page *p;
p = alloc_page(GFP_KERNEL);
if (!p)
goto oom;
vdso_pages[i] = p;
copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
}
return 0;
oom:
printk("Cannot allocate vdso\n");
vdso_enabled = 0;
return -ENOMEM;
}
subsys_initcall(init_vdso_vars);
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;
return addr;
}
/* Setup a VMA at program startup for the vsyscall page.
Not called for compat tasks */
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
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, vdso_size);
addr = get_unmapped_area(NULL, addr, vdso_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, vdso_size,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
VM_ALWAYSDUMP,
vdso_pages);
if (ret) {
current->mm->context.vdso = NULL;
goto up_fail;
}
up_fail:
up_write(&mm->mmap_sem);
return ret;
}
static __init int vdso_setup(char *s)
{
vdso_enabled = simple_strtoul(s, NULL, 0);
return 0;
}
__setup("vdso=", vdso_setup);