diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index cdb78d590c868880e474e8190ce789d6bc97e0ab..99a8820e8cc4cf63fb4b1fc65b6aff72fc04d15f 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -11,7 +11,7 @@
 
 extern void save_fpregs_to_fpstate(struct fpu *fpu);
 extern void fpu__drop(struct fpu *fpu);
-extern int  fpu_clone(struct task_struct *dst);
+extern int  fpu_clone(struct task_struct *dst, unsigned long clone_flags);
 extern void fpu_flush_thread(void);
 
 /*
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 4018083c5b3627f27a37c7cdbb78c078a4a10867..1ff6b83094a14338b96634d0d78de2c1288a5d78 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -423,8 +423,20 @@ void fpstate_reset(struct fpu *fpu)
 	fpu->perm.__user_state_size	= fpu_user_cfg.default_size;
 }
 
+static inline void fpu_inherit_perms(struct fpu *dst_fpu)
+{
+	if (fpu_state_size_dynamic()) {
+		struct fpu *src_fpu = &current->group_leader->thread.fpu;
+
+		spin_lock_irq(&current->sighand->siglock);
+		/* Fork also inherits the permissions of the parent */
+		dst_fpu->perm = src_fpu->perm;
+		spin_unlock_irq(&current->sighand->siglock);
+	}
+}
+
 /* Clone current's FPU state on fork */
-int fpu_clone(struct task_struct *dst)
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
 {
 	struct fpu *src_fpu = &current->thread.fpu;
 	struct fpu *dst_fpu = &dst->thread.fpu;
@@ -455,17 +467,20 @@ int fpu_clone(struct task_struct *dst)
 	}
 
 	/*
-	 * If the FPU registers are not owned by current just memcpy() the
-	 * state.  Otherwise save the FPU registers directly into the
-	 * child's FPU context, without any memory-to-memory copying.
+	 * Save the default portion of the current FPU state into the
+	 * clone. Assume all dynamic features to be defined as caller-
+	 * saved, which enables skipping both the expansion of fpstate
+	 * and the copying of any dynamic state.
+	 *
+	 * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because
+	 * copying is not valid when current uses non-default states.
 	 */
 	fpregs_lock();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD)) {
-		memcpy(&dst_fpu->fpstate->regs, &src_fpu->fpstate->regs,
-		       dst_fpu->fpstate->size);
-	} else {
-		save_fpregs_to_fpstate(dst_fpu);
-	}
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		fpregs_restore_userregs();
+	save_fpregs_to_fpstate(dst_fpu);
+	if (!(clone_flags & CLONE_THREAD))
+		fpu_inherit_perms(dst_fpu);
 	fpregs_unlock();
 
 	trace_x86_fpu_copy_src(src_fpu);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index da4f44e00fe4d08b8001937a7a58180f85dee228..c517dd76cf845873fef9055ec826ebe872d7f029 100755
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -164,7 +164,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	frame->flags = X86_EFLAGS_FIXED;
 #endif
 
-	fpu_clone(p);
+	fpu_clone(p, clone_flags);
 
 	/* Kernel thread ? */
 	if (unlikely(p->flags & PF_KTHREAD)) {