linux/arch/x86/kernel/ioport.c
Andy Lutomirski c482feefe1 x86/entry/64: Make cpu_entry_area.tss read-only
The TSS is a fairly juicy target for exploits, and, now that the TSS
is in the cpu_entry_area, it's no longer protected by kASLR.  Make it
read-only on x86_64.

On x86_32, it can't be RO because it's written by the CPU during task
switches, and we use a task gate for double faults.  I'd also be
nervous about errata if we tried to make it RO even on configurations
without double fault handling.

[ tglx: AMD confirmed that there is no problem on 64-bit with TSS RO.  So
  	it's probably safe to assume that it's a non issue, though Intel
  	might have been creative in that area. Still waiting for
  	confirmation. ]

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bpetkov@suse.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Link: https://lkml.kernel.org/r/20171204150606.733700132@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-17 14:27:52 +01:00

134 lines
3.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* This contains the io-permission bitmap code - written by obz, with changes
* by Linus. 32/64 bits code unification by Miguel Botón.
*/
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/ioport.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/thread_info.h>
#include <linux/syscalls.h>
#include <linux/bitmap.h>
#include <asm/syscalls.h>
#include <asm/desc.h>
/*
* this changes the io permissions bitmap in the current task.
*/
asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
{
struct thread_struct *t = &current->thread;
struct tss_struct *tss;
unsigned int i, max_long, bytes, bytes_updated;
if ((from + num <= from) || (from + num > IO_BITMAP_BITS))
return -EINVAL;
if (turn_on && !capable(CAP_SYS_RAWIO))
return -EPERM;
/*
* If it's the first ioperm() call in this thread's lifetime, set the
* IO bitmap up. ioperm() is much less timing critical than clone(),
* this is why we delay this operation until now:
*/
if (!t->io_bitmap_ptr) {
unsigned long *bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
if (!bitmap)
return -ENOMEM;
memset(bitmap, 0xff, IO_BITMAP_BYTES);
t->io_bitmap_ptr = bitmap;
set_thread_flag(TIF_IO_BITMAP);
/*
* Now that we have an IO bitmap, we need our TSS limit to be
* correct. It's fine if we are preempted after doing this:
* with TIF_IO_BITMAP set, context switches will keep our TSS
* limit correct.
*/
preempt_disable();
refresh_tss_limit();
preempt_enable();
}
/*
* do it in the per-thread copy and in the TSS ...
*
* Disable preemption via get_cpu() - we must not switch away
* because the ->io_bitmap_max value must match the bitmap
* contents:
*/
tss = &per_cpu(cpu_tss_rw, get_cpu());
if (turn_on)
bitmap_clear(t->io_bitmap_ptr, from, num);
else
bitmap_set(t->io_bitmap_ptr, from, num);
/*
* Search for a (possibly new) maximum. This is simple and stupid,
* to keep it obviously correct:
*/
max_long = 0;
for (i = 0; i < IO_BITMAP_LONGS; i++)
if (t->io_bitmap_ptr[i] != ~0UL)
max_long = i;
bytes = (max_long + 1) * sizeof(unsigned long);
bytes_updated = max(bytes, t->io_bitmap_max);
t->io_bitmap_max = bytes;
/* Update the TSS: */
memcpy(tss->io_bitmap, t->io_bitmap_ptr, bytes_updated);
put_cpu();
return 0;
}
/*
* sys_iopl has to be used when you want to access the IO ports
* beyond the 0x3ff range: to get the full 65536 ports bitmapped
* you'd need 8kB of bitmaps/process, which is a bit excessive.
*
* Here we just change the flags value on the stack: we allow
* only the super-user to do it. This depends on the stack-layout
* on system-call entry - see also fork() and the signal handling
* code.
*/
SYSCALL_DEFINE1(iopl, unsigned int, level)
{
struct pt_regs *regs = current_pt_regs();
struct thread_struct *t = &current->thread;
/*
* Careful: the IOPL bits in regs->flags are undefined under Xen PV
* and changing them has no effect.
*/
unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT;
if (level > 3)
return -EINVAL;
/* Trying to gain more privileges? */
if (level > old) {
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
}
regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
(level << X86_EFLAGS_IOPL_BIT);
t->iopl = level << X86_EFLAGS_IOPL_BIT;
set_iopl_mask(t->iopl);
return 0;
}