[patch V2 2/2] x86/ldt: Prevent ldt inheritance on exec

[Thomas Gleixner]

From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

The LDT is inheritet independent of fork or exec, but that makes no sense
at all because exec is supposed to start the process clean.

The reason why this happens is that init_new_context_ldt() is called from
init_new_context() which obviously needs to be called for both fork() and
exec().

It would be surprising if anything relies on that behaviour, so it seems to
be safe to remove that misfeature.

Split the context initialization into two parts. Clear the ldt pointer and
initialize the mutex from the general context init and move the LDT
duplication to arch_dup_mmap() which is only called on fork(). Fix up the
selftest accordingly.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/mmu_context.h    |   22 +++++++++++++++-------
 arch/x86/kernel/ldt.c                 |   17 +++++------------
 tools/testing/selftests/x86/ldt_gdt.c |    9 +++------
 3 files changed, 23 insertions(+), 25 deletions(-)

--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -57,11 +57,17 @@ struct ldt_struct {
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	mutex_init(&mm->context.lock);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
@@ -135,16 +141,18 @@ static inline int init_new_context(struc
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
+
 static inline void destroy_context(struct mm_struct *mm)
 {
 	destroy_context_ldt(mm);
@@ -179,7 +187,7 @@ do {						\
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
-	return 0;
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -124,27 +124,20 @@ static void free_ldt_struct(struct ldt_s
 }
 
 /*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
-	struct mm_struct *old_mm;
 	int retval = 0;
 
-	mutex_init(&mm->context.lock);
-	old_mm = current->mm;
-	if (!old_mm) {
-		mm->context.ldt = NULL;
+	if (!old_mm)
 		return 0;
-	}
 
 	mutex_lock(&old_mm->context.lock);
-	if (!old_mm->context.ldt) {
-		mm->context.ldt = NULL;
+	if (!old_mm->context.ldt)
 		goto out_unlock;
-	}
 
 	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
 	if (!new_ldt) {
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -627,13 +627,10 @@ static void do_multicpu_tests(void)
 static int finish_exec_test(void)
 {
 	/*
-	 * In a sensible world, this would be check_invalid_segment(0, 1);
-	 * For better or for worse, though, the LDT is inherited across exec.
-	 * We can probably change this safely, but for now we test it.
+	 * Older kernel versions did inherit the LDT on exec() which is
+	 * wrong because exec() starts from a clean state.
 	 */
-	check_valid_segment(0, 1,
-			    AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB,
-			    42, true);
+	check_invalid_segment(0, 1);
 
 	return nerrs ? 1 : 0;
 }