x86/mm: Only set IBPB when the new thread cannot ptrace current thread

CVE-2017-5715 (Spectre v2 Intel)

To reduce overhead of setting IBPB, we only do that when
the new thread cannot ptrace the current one.  If the new
thread has ptrace capability on current thread, it is safe.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andy Whitcroft <apw@canonical.com>
(backported from commit 294ed6288a44f78781cf33cc9de32c50630c1646)
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Acked-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

arch/x86/mm/tlb.c

@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/ptrace.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -140,7 +141,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		/* Null tsk means switching to kernel, so that's safe */
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) && tsk &&
+			___ptrace_may_access(tsk, current, PTRACE_MODE_IBPB))
 			native_wrmsrl(MSR_IA32_PRED_CMD, FEATURE_SET_IBPB);
 
 		/* Load per-mm CR4 state */

include/linux/ptrace.h

@@ -59,12 +59,15 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_NOAUDIT	0x04
 #define PTRACE_MODE_FSCREDS 0x08
 #define PTRACE_MODE_REALCREDS 0x10
+#define PTRACE_MODE_NOACCESS_CHK 0x20
 
 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */
 #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS)
 #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS)
 #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS)
+#define PTRACE_MODE_IBPB (PTRACE_MODE_ATTACH | PTRACE_MODE_NOAUDIT \
+			| PTRACE_MODE_NOACCESS_CHK | PTRACE_MODE_REALCREDS)
 
 /**
  * ptrace_may_access - check whether the caller is permitted to access
@@ -82,6 +85,9 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
  */
 extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
+extern int ___ptrace_may_access(struct task_struct *cur, struct task_struct *task,
+	unsigned int mode);
+
 static inline int ptrace_reparented(struct task_struct *child)
 {
 	return !same_thread_group(child->real_parent, child->parent);

kernel/ptrace.c

@@ -235,9 +235,10 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 }
 
 /* Returns 0 on success, -errno on denial. */
-static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
+int ___ptrace_may_access(struct task_struct *cur, struct task_struct *task,
+		unsigned int mode)
 {
-	const struct cred *cred = current_cred(), *tcred;
+	const struct cred *cred = __task_cred(cur), *tcred;
 	struct mm_struct *mm;
 	kuid_t caller_uid;
 	kgid_t caller_gid;
@@ -257,7 +258,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	 */
 
 	/* Don't let security modules deny introspection */
-	if (same_thread_group(task, current))
+	if (same_thread_group(task, cur))
 		return 0;
 	rcu_read_lock();
 	if (mode & PTRACE_MODE_FSCREDS) {
@@ -295,7 +296,16 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	     !ptrace_has_cap(mm->user_ns, mode)))
 	    return -EPERM;
 
-	return security_ptrace_access_check(task, mode);
+	if (!(mode & PTRACE_MODE_NOACCESS_CHK))
+		return security_ptrace_access_check(task, mode);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(___ptrace_may_access);
+
+static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
+{
+	return ___ptrace_may_access(current, task, mode);
 }
 
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)