Merge tag 'x86_mm_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 LAM (Linear Address Masking) support from Dave Hansen:
 "Add support for the new Linear Address Masking CPU feature.

  This is similar to ARM's Top Byte Ignore and allows userspace to store
  metadata in some bits of pointers without masking it out before use"

* tag 'x86_mm_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm/iommu/sva: Do not allow to set FORCE_TAGGED_SVA bit from outside
  x86/mm/iommu/sva: Fix error code for LAM enabling failure due to SVA
  selftests/x86/lam: Add test cases for LAM vs thread creation
  selftests/x86/lam: Add ARCH_FORCE_TAGGED_SVA test cases for linear-address masking
  selftests/x86/lam: Add inherit test cases for linear-address masking
  selftests/x86/lam: Add io_uring test cases for linear-address masking
  selftests/x86/lam: Add mmap and SYSCALL test cases for linear-address masking
  selftests/x86/lam: Add malloc and tag-bits test cases for linear-address masking
  x86/mm/iommu/sva: Make LAM and SVA mutually exclusive
  iommu/sva: Replace pasid_valid() helper with mm_valid_pasid()
  mm: Expose untagging mask in /proc/$PID/status
  x86/mm: Provide arch_prctl() interface for LAM
  x86/mm: Reduce untagged_addr() overhead for systems without LAM
  x86/uaccess: Provide untagged_addr() and remove tags before address check
  mm: Introduce untagged_addr_remote()
  x86/mm: Handle LAM on context switch
  x86: CPUID and CR3/CR4 flags for Linear Address Masking
  x86: Allow atomic MM_CONTEXT flags setting
  x86/mm: Rework address range check in get_user() and put_user()

3 files changed, 74 insertions, 6 deletions

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b650cde3f64d..50d950771371 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -48,6 +48,7 @@
 #include <asm/frame.h>
 #include <asm/unwind.h>
 #include <asm/tdx.h>
+#include <asm/mmu_context.h>
 
 #include "process.h"
 
@@ -162,6 +163,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	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);
@@ -368,6 +372,8 @@ void arch_setup_new_exec(void)
 		task_clear_spec_ssb_noexec(current);
 		speculation_ctrl_update(read_thread_flags());
 	}
+
+	mm_reset_untag_mask(current->mm);
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bb65a68b4b49..223b223f713f 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -671,7 +671,7 @@ void set_personality_64bit(void)
 	task_pt_regs(current)->orig_ax = __NR_execve;
 	current_thread_info()->status &= ~TS_COMPAT;
 	if (current->mm)
-		current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL;
+		__set_bit(MM_CONTEXT_HAS_VSYSCALL, &current->mm->context.flags);
 
 	/* TBD: overwrites user setup. Should have two bits.
 	   But 64bit processes have always behaved this way,
@@ -708,7 +708,7 @@ static void __set_personality_ia32(void)
 		 * uprobes applied to this MM need to know this and
 		 * cannot use user_64bit_mode() at that time.
 		 */
-		current->mm->context.flags = MM_CONTEXT_UPROBE_IA32;
+		__set_bit(MM_CONTEXT_UPROBE_IA32, &current->mm->context.flags);
 	}
 
 	current->personality |= force_personality32;
@@ -743,6 +743,52 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 }
 #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 (mm_valid_pasid(mm) &&
+	    !test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags))
+		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;
@@ -830,7 +876,23 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	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_FORCE_TAGGED_SVA:
+		if (current != task)
+			return -EINVAL;
+		set_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &task->mm->context.flags);
+		return 0;
+	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;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d317dc3d06a3..8b83d8fbce71 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -671,15 +671,15 @@ static bool try_fixup_enqcmd_gp(void)
 	if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
 		return false;
 
-	pasid = current->mm->pasid;
-
 	/*
 	 * If the mm has not been allocated a
 	 * PASID, the #GP can not be fixed up.
 	 */
-	if (!pasid_valid(pasid))
+	if (!mm_valid_pasid(current->mm))
 		return false;
 
+	pasid = current->mm->pasid;
+
 	/*
 	 * Did this thread already have its PASID activated?
 	 * If so, the #GP must be from something else.