Commit c8137ace authored by Thomas Gleixner's avatar Thomas Gleixner
Browse files

x86/iopl: Restrict iopl() permission scope



The access to the full I/O port range can be also provided by the TSS I/O
bitmap, but that would require to copy 8k of data on scheduling in the
task. As shown with the sched out optimization TSS.io_bitmap_base can be
used to switch the incoming task to a preallocated I/O bitmap which has all
bits zero, i.e. allows access to all I/O ports.

Implementing this allows to provide an iopl() emulation mode which restricts
the IOPL level 3 permissions to I/O port access but removes the STI/CLI
permission which is coming with the hardware IOPL mechansim.

Provide a config option to switch IOPL to emulation mode, make it the
default and while at it also provide an option to disable IOPL completely.

Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Acked-by: default avatarAndy Lutomirski <luto@kernel.org>
parent be9afb4b
Loading
Loading
Loading
Loading
+32 −0
Original line number Diff line number Diff line
@@ -1254,6 +1254,38 @@ config X86_VSYSCALL_EMULATION
	 Disabling this option saves about 7K of kernel size and
	 possibly 4K of additional runtime pagetable memory.

choice
	prompt "IOPL"
	default X86_IOPL_EMULATION

config X86_IOPL_EMULATION
	bool "IOPL Emulation"
	---help---
	  Legacy IOPL support is an overbroad mechanism which allows user
	  space aside of accessing all 65536 I/O ports also to disable
	  interrupts. To gain this access the caller needs CAP_SYS_RAWIO
	  capabilities and permission from potentially active security
	  modules.

	  The emulation restricts the functionality of the syscall to
	  only allowing the full range I/O port access, but prevents the
	  ability to disable interrupts from user space.

config X86_IOPL_LEGACY
	bool "IOPL Legacy"
	---help---
	Allow the full IOPL permissions, i.e. user space access to all
	65536 I/O ports and also the ability to disable interrupts, which
	is overbroad and can result in system lockups.

config X86_IOPL_NONE
	bool "IOPL None"
	---help---
	Disable the IOPL permission syscall. That's the safest option as
	no sane application should depend on this functionality.

endchoice

config TOSHIBA
	tristate "Toshiba Laptop support"
	depends on X86_32
+1 −1
Original line number Diff line number Diff line
@@ -44,7 +44,7 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
 * to avoid include recursion hell
 */
#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 41)

#define CPU_ENTRY_AREA_BASE						\
	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
+21 −7
Original line number Diff line number Diff line
@@ -332,19 +332,21 @@ struct x86_hw_tss {
#define IO_BITMAP_BYTES			(IO_BITMAP_BITS / BITS_PER_BYTE)
#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES / sizeof(long))

#define IO_BITMAP_OFFSET_VALID					\
#define IO_BITMAP_OFFSET_VALID_MAP				\
	(offsetof(struct tss_struct, io_bitmap.bitmap) -	\
	 offsetof(struct tss_struct, x86_tss))

#define IO_BITMAP_OFFSET_VALID_ALL				\
	(offsetof(struct tss_struct, io_bitmap.mapall) -	\
	 offsetof(struct tss_struct, x86_tss))

/*
 * sizeof(unsigned long) coming from an extra "long" at the end
 * of the iobitmap.
 *
 * -1? seg base+limit should be pointing to the address of the
 * last valid byte
 * sizeof(unsigned long) coming from an extra "long" at the end of the
 * iobitmap. The limit is inclusive, i.e. the last valid byte.
 */
#define __KERNEL_TSS_LIMIT	\
	(IO_BITMAP_OFFSET_VALID + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
	(IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \
	 sizeof(unsigned long) - 1)

/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */
#define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
@@ -380,6 +382,12 @@ struct x86_io_bitmap {
	 * be within the limit.
	 */
	unsigned long		bitmap[IO_BITMAP_LONGS + 1];

	/*
	 * Special I/O bitmap to emulate IOPL(3). All bytes zero,
	 * except the additional byte at the end.
	 */
	unsigned long		mapall[IO_BITMAP_LONGS + 1];
};

struct tss_struct {
@@ -506,7 +514,13 @@ struct thread_struct {
#endif
	/* IO permissions: */
	struct io_bitmap	*io_bitmap;

	/*
	 * IOPL. Priviledge level dependent I/O permission which includes
	 * user space CLI/STI when granted.
	 */
	unsigned long		iopl;
	unsigned long		iopl_emul;

	mm_segment_t		addr_limit;

+5 −0
Original line number Diff line number Diff line
@@ -1864,6 +1864,11 @@ void cpu_init(void)
	tss->io_bitmap.prev_max = 0;
	tss->io_bitmap.prev_sequence = 0;
	memset(tss->io_bitmap.bitmap, 0xff, sizeof(tss->io_bitmap.bitmap));
	/*
	 * Invalidate the extra array entry past the end of the all
	 * permission bitmap as required by the hardware.
	 */
	tss->io_bitmap.mapall[IO_BITMAP_LONGS] = ~0UL;
	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);

	load_TR_desc();
+61 −26
Original line number Diff line number Diff line
@@ -18,24 +18,40 @@ static atomic64_t io_bitmap_sequence;

void io_bitmap_share(struct task_struct *tsk)
{
	/* Can be NULL when current->thread.iopl_emul == 3 */
	if (current->thread.io_bitmap) {
		/*
		 * Take a refcount on current's bitmap. It can be used by
		 * both tasks as long as none of them changes the bitmap.
		 */
		refcount_inc(&current->thread.io_bitmap->refcnt);
		tsk->thread.io_bitmap = current->thread.io_bitmap;
	}
	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
}

void io_bitmap_exit(void)
static void task_update_io_bitmap(void)
{
	struct io_bitmap *iobm = current->thread.io_bitmap;
	struct thread_struct *t = &current->thread;

	current->thread.io_bitmap = NULL;
	if (t->iopl_emul == 3 || t->io_bitmap) {
		/* TSS update is handled on exit to user space */
		set_thread_flag(TIF_IO_BITMAP);
	} else {
		clear_thread_flag(TIF_IO_BITMAP);
		/* Invalidate TSS */
		preempt_disable();
		tss_update_io_bitmap();
		preempt_enable();
	}
}

void io_bitmap_exit(void)
{
	struct io_bitmap *iobm = current->thread.io_bitmap;

	current->thread.io_bitmap = NULL;
	task_update_io_bitmap();
	if (iobm && refcount_dec_and_test(&iobm->refcnt))
		kfree(iobm);
}
@@ -157,36 +173,55 @@ SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 */
SYSCALL_DEFINE1(iopl, unsigned int, level)
{
	struct pt_regs *regs = current_pt_regs();
	struct thread_struct *t = &current->thread;
	struct pt_regs *regs = current_pt_regs();
	unsigned int old;

	/*
	 * 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 (IS_ENABLED(CONFIG_X86_IOPL_NONE))
		return -ENOSYS;

	if (level > 3)
		return -EINVAL;

	if (IS_ENABLED(CONFIG_X86_IOPL_EMULATION))
		old = t->iopl_emul;
	else
		old = t->iopl >> X86_EFLAGS_IOPL_BIT;

	/* No point in going further if nothing changes */
	if (level == old)
		return 0;

	/* Trying to gain more privileges? */
	if (level > old) {
		if (!capable(CAP_SYS_RAWIO) ||
		    security_locked_down(LOCKDOWN_IOPORT))
			return -EPERM;
	}

	if (IS_ENABLED(CONFIG_X86_IOPL_EMULATION)) {
		t->iopl_emul = level;
		task_update_io_bitmap();
	} else {
		/*
	 * Change the flags value on the return stack, which has been set
	 * up on system-call entry. See also the fork and signal handling
	 * code how this is handled.
		 * Change the flags value on the return stack, which has
		 * been set up on system-call entry. See also the fork and
		 * signal handling code how this is handled.
		 */
		regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
			(level << X86_EFLAGS_IOPL_BIT);
		/* Store the new level in the thread struct */
		t->iopl = level << X86_EFLAGS_IOPL_BIT;
		/*
	 * X86_32 switches immediately and XEN handles it via emulation.
		 * X86_32 switches immediately and XEN handles it via
		 * emulation.
		 */
		set_iopl_mask(t->iopl);
	}

	return 0;
}
Loading