x86_64, switch_to(): Load TLS descriptors before switching DS and ES

Otherwise, if buggy user code points DS or ES into the TLS
array, they would be corrupted after a context switch.

This also significantly improves the comments and documents some
gotchas in the code.

Before this patch, the both tests below failed.  With this
patch, the es test passes, although the gsbase test still fails.

 ----- begin es test -----

/*
 * Copyright (c) 2014 Andy Lutomirski
 * GPL v2
 */

static unsigned short GDT3(int idx)
{
	return (idx << 3) | 3;
}

static int create_tls(int idx, unsigned int base)
{
	struct user_desc desc = {
		.entry_number    = idx,
		.base_addr       = base,
		.limit           = 0xfffff,
		.seg_32bit       = 1,
		.contents        = 0, /* Data, grow-up */
		.read_exec_only  = 0,
		.limit_in_pages  = 1,
		.seg_not_present = 0,
		.useable         = 0,
	};

	if (syscall(SYS_set_thread_area, &desc) != 0)
		err(1, "set_thread_area");

	return desc.entry_number;
}

int main()
{
	int idx = create_tls(-1, 0);
	printf("Allocated GDT index %d\n", idx);

	unsigned short orig_es;
	asm volatile ("mov %%es,%0" : "=rm" (orig_es));

	int errors = 0;
	int total = 1000;
	for (int i = 0; i < total; i++) {
		asm volatile ("mov %0,%%es" : : "rm" (GDT3(idx)));
		usleep(100);

		unsigned short es;
		asm volatile ("mov %%es,%0" : "=rm" (es));
		asm volatile ("mov %0,%%es" : : "rm" (orig_es));
		if (es != GDT3(idx)) {
			if (errors == 0)
				printf("[FAIL]\tES changed from 0x%hx to 0x%hx\n",
				       GDT3(idx), es);
			errors++;
		}
	}

	if (errors) {
		printf("[FAIL]\tES was corrupted %d/%d times\n", errors, total);
		return 1;
	} else {
		printf("[OK]\tES was preserved\n");
		return 0;
	}
}

 ----- end es test -----

 ----- begin gsbase test -----

/*
 * gsbase.c, a gsbase test
 * Copyright (c) 2014 Andy Lutomirski
 * GPL v2
 */

static unsigned char *testptr, *testptr2;

static unsigned char read_gs_testvals(void)
{
	unsigned char ret;
	asm volatile ("movb %%gs:%1, %0" : "=r" (ret) : "m" (*testptr));
	return ret;
}

int main()
{
	int errors = 0;

	testptr = mmap((void *)0x200000000UL, 1, PROT_READ | PROT_WRITE,
		       MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS, -1, 0);
	if (testptr == MAP_FAILED)
		err(1, "mmap");

	testptr2 = mmap((void *)0x300000000UL, 1, PROT_READ | PROT_WRITE,
		       MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS, -1, 0);
	if (testptr2 == MAP_FAILED)
		err(1, "mmap");

	*testptr = 0;
	*testptr2 = 1;

	if (syscall(SYS_arch_prctl, ARCH_SET_GS,
		    (unsigned long)testptr2 - (unsigned long)testptr) != 0)
		err(1, "ARCH_SET_GS");

	usleep(100);

	if (read_gs_testvals() == 1) {
		printf("[OK]\tARCH_SET_GS worked\n");
	} else {
		printf("[FAIL]\tARCH_SET_GS failed\n");
		errors++;
	}

	asm volatile ("mov %0,%%gs" : : "r" (0));

	if (read_gs_testvals() == 0) {
		printf("[OK]\tWriting 0 to gs worked\n");
	} else {
		printf("[FAIL]\tWriting 0 to gs failed\n");
		errors++;
	}

	usleep(100);

	if (read_gs_testvals() == 0) {
		printf("[OK]\tgsbase is still zero\n");
	} else {
		printf("[FAIL]\tgsbase was corrupted\n");
		errors++;
	}

	return errors == 0 ? 0 : 1;
}

 ----- end gsbase test -----

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: <stable@vger.kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/509d27c9fec78217691c3dad91cec87e1006b34a.1418075657.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
1 file changed