x86/mm: Provide arch_prctl() interface for LAM

Add a few of arch_prctl() handles:

- ARCH_ENABLE_TAGGED_ADDR enabled LAM. The argument is required number
of tag bits. It is rounded up to the nearest LAM mode that can
provide it. For now only LAM_U57 is supported, with 6 tag bits.

- ARCH_GET_UNTAG_MASK returns untag mask. It can indicates where tag
bits located in the address.

- ARCH_GET_MAX_TAG_BITS returns the maximum tag bits user can request.
Zero if LAM is not supported.

Signed-off-by: Kirill A. Shutemov <[e-mail]>
Signed-off-by: Dave Hansen <[e-mail]>
Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Tested-by: Alexander Potapenko <[e-mail]>
Link: https://lore.kernel.org/all/20230312112612.31869-9-kirill.shutemov%40linux.intel.com

arch/x86/include/asm/mmu.h

···
 #define MM_CONTEXT_UPROBE_IA32		0
 /* vsyscall page is accessible on this MM */
 #define MM_CONTEXT_HAS_VSYSCALL		1
+/* Do not allow changing LAM mode */
+#define MM_CONTEXT_LOCK_LAM		2
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.

arch/x86/include/uapi/asm/prctl.h

···
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+
 #endif /* _ASM_X86_PRCTL_H */

arch/x86/kernel/process.c

···
 
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
+
+	if (p->mm && (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM)
+		set_bit(MM_CONTEXT_LOCK_LAM, &p->mm->context.flags);
 #else
 	p->thread.sp0 = (unsigned long) (childregs + 1);
 	savesegment(gs, p->thread.gs);

arch/x86/kernel/process_64.c

···
 }
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+
+#define LAM_U57_BITS 6
+
+static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_LAM))
+		return -ENODEV;
+
+	/* PTRACE_ARCH_PRCTL */
+	if (current->mm != mm)
+		return -EINVAL;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) {
+		mmap_write_unlock(mm);
+		return -EBUSY;
+	}
+
+	if (!nr_bits) {
+		mmap_write_unlock(mm);
+		return -EINVAL;
+	} else if (nr_bits <= LAM_U57_BITS) {
+		mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
+		mm->context.untag_mask =  ~GENMASK(62, 57);
+	} else {
+		mmap_write_unlock(mm);
+		return -EINVAL;
+	}
+
+	write_cr3(__read_cr3() | mm->context.lam_cr3_mask);
+	set_tlbstate_lam_mode(mm);
+	set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
+
+	mmap_write_unlock(mm);
+
+	return 0;
+}
+#endif
+
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 {
 	int ret = 0;
···
 	case ARCH_MAP_VDSO_64:
 		return prctl_map_vdso(&vdso_image_64, arg2);
 #endif
-
+#ifdef CONFIG_ADDRESS_MASKING
+	case ARCH_GET_UNTAG_MASK:
+		return put_user(task->mm->context.untag_mask,
+				(unsigned long __user *)arg2);
+	case ARCH_ENABLE_TAGGED_ADDR:
+		return prctl_enable_tagged_addr(task->mm, arg2);
+	case ARCH_GET_MAX_TAG_BITS:
+		if (!cpu_feature_enabled(X86_FEATURE_LAM))
+			return put_user(0, (unsigned long __user *)arg2);
+		else
+			return put_user(LAM_U57_BITS, (unsigned long __user *)arg2);
+#endif
 	default:
 		ret = -EINVAL;
 		break;