Recent change in how get_user() handles pointers [1] has a specific case
for LAM. It assigns a different bitmask that's later used to check
whether a pointer comes from userland in get_user().

Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses
get_user() in its implementation. Execute the syscall with differently
tagged pointers to verify that valid user pointers are passing through
and invalid kernel/non-canonical pointers are not.

[1] https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundation.org/

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
---
Changelog v4:
- Use the changed cpu_has_la57() instead of mmap() to figure out current
  paging level.
- Apply Kirill's other comments: Remove redundant always true check,
  close the ioctl file before exiting, change mapping size to PAGE_SIZE
  so it looks less odd.
- Turn this patch into a series and move some text to the cover letter.

Changelog v3:
- mmap the pointer passed to get_user to high address if 5 level paging
  is enabled and to low address if 4 level paging is enabled.

Changelog v2:
- Use mmap with HIGH_ADDR to check if we're in 5 or 4 level pagetables.

 tools/testing/selftests/x86/lam.c | 102 ++++++++++++++++++++++++++++++
 1 file changed, 102 insertions(+)

diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 4ec37a4be007..b602541e7bdf 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -4,6 +4,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/syscall.h>
+#include <sys/ioctl.h>
 #include <time.h>
 #include <signal.h>
 #include <setjmp.h>
@@ -43,7 +44,15 @@
 #define FUNC_INHERITE           0x20
 #define FUNC_PASID              0x40
 
+/* get_user() pointer test cases */
+#define GET_USER_USER           0
+#define GET_USER_KERNEL_TOP     1
+#define GET_USER_KERNEL_BOT     2
+#define GET_USER_KERNEL         3
+
 #define TEST_MASK               0x7f
+#define L5_SIGN_EXT_MASK        (0xFFUL << 56)
+#define L4_SIGN_EXT_MASK        (0x1FFFFUL << 47)
 
 #define LOW_ADDR                (0x1UL << 30)
 #define HIGH_ADDR               (0x3UL << 48)
@@ -373,6 +382,72 @@ static int handle_syscall(struct testcases *test)
 	return ret;
 }
 
+static int get_user_syscall(struct testcases *test)
+{
+	uint64_t ptr_address, bitmask;
+	int fd, ret = 0;
+	void *ptr;
+
+	if (cpu_has_la57()) {
+		bitmask = L5_SIGN_EXT_MASK;
+		ptr_address = HIGH_ADDR;
+	} else {
+		bitmask = L4_SIGN_EXT_MASK;
+		ptr_address = LOW_ADDR;
+	}
+
+	ptr = mmap((void *)ptr_address, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+
+	if (ptr == MAP_FAILED) {
+		perror("failed to map byte to pass into get_user");
+		return 1;
+	}
+
+	if (set_lam(test->lam) != 0) {
+		ret = 2;
+		goto error;
+	}
+
+	fd = memfd_create("lam_ioctl", 0);
+	if (fd == -1) {
+		munmap(ptr, PAGE_SIZE);
+		exit(EXIT_FAILURE);
+	}
+
+	switch (test->later) {
+	case GET_USER_USER:
+		/* Control group - properly tagger user pointer */
+		ptr = (void *)set_metadata((uint64_t)ptr, test->lam);
+		break;
+	case GET_USER_KERNEL_TOP:
+		/* Kernel address with top bit cleared */
+		bitmask &= (bitmask >> 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL_BOT:
+		/* Kernel address with bottom sign-extension bit cleared */
+		bitmask &= (bitmask << 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL:
+		/* Try to pass a kernel address */
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	default:
+		printf("Invalid test case value passed!\n");
+		break;
+	}
+
+	if (ioctl(fd, FIOASYNC, ptr) != 0)
+		ret = 1;
+
+	close(fd);
+error:
+	munmap(ptr, PAGE_SIZE);
+	return ret;
+}
+
 int sys_uring_setup(unsigned int entries, struct io_uring_params *p)
 {
 	return (int)syscall(__NR_io_uring_setup, entries, p);
@@ -886,6 +961,33 @@ static struct testcases syscall_cases[] = {
 		.test_func = handle_syscall,
 		.msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n",
 	},
+	{
+		.later = GET_USER_USER,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_TOP,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_BOT,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n",
+	},
 };
 
 static struct testcases mmap_cases[] = {
-- 
2.47.1

On 11/27/24 09:35, Maciej Wieczor-Retman wrote:
...
> +	switch (test->later) {
> +	case GET_USER_USER:
> +		/* Control group - properly tagger user pointer */
> +		ptr = (void *)set_metadata((uint64_t)ptr, test->lam);
> +		break;

s/tagger/tagged/ ?

> +	default:
> +		printf("Invalid test case value passed!\n");
> +		break;
> +	}
> +
> +	if (ioctl(fd, FIOASYNC, ptr) != 0)
> +		ret = 1;
> +
> +	close(fd);
> +error:
> +	munmap(ptr, PAGE_SIZE);
> +	return ret;
> +}

I'd really prefer that the theory of operation be in a code comment and
not just in the changelog.

On 2025-01-24 at 08:32:18 -0800, Dave Hansen wrote:
>On 11/27/24 09:35, Maciej Wieczor-Retman wrote:
>...
>> +	switch (test->later) {
>> +	case GET_USER_USER:
>> +		/* Control group - properly tagger user pointer */
>> +		ptr = (void *)set_metadata((uint64_t)ptr, test->lam);
>> +		break;
>
>s/tagger/tagged/ ?

Thanks!

>
>> +	default:
>> +		printf("Invalid test case value passed!\n");
>> +		break;
>> +	}
>> +
>> +	if (ioctl(fd, FIOASYNC, ptr) != 0)
>> +		ret = 1;
>> +
>> +	close(fd);
>> +error:
>> +	munmap(ptr, PAGE_SIZE);
>> +	return ret;
>> +}
>
>I'd really prefer that the theory of operation be in a code comment and
>not just in the changelog.

Sure, I'll comment the ioctl() usage so it's more clear what's happening.

-- 
Kind regards
Maciej Wieczór-Retman