diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 72ba21a8b5fc..da5e96756570 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -67,6 +67,34 @@ extern void finit_soft_fpu(struct i387_soft_struct *soft);
 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
 #endif
 
+/*
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
+/*
+ * Used to indicate that the FPU state in memory is newer than the FPU
+ * state in registers, and the FPU state should be reloaded next time the
+ * task is run. Only safe on the current task, or non-running tasks.
+ */
+static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
+{
+	tsk->thread.fpu.last_cpu = ~0;
+}
+
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+	return new == this_cpu_read_stable(fpu_owner_task) &&
+		cpu == new->thread.fpu.last_cpu;
+}
+
 static inline int is_ia32_compat_frame(void)
 {
 	return config_enabled(CONFIG_IA32_EMULATION) &&
@@ -107,7 +135,6 @@ static __always_inline __pure bool use_fxsr(void)
 
 static inline void fx_finit(struct i387_fxsave_struct *fx)
 {
-	memset(fx, 0, xstate_size);
 	fx->cwd = 0x37f;
 	fx->mxcsr = MXCSR_DEFAULT;
 }
@@ -351,17 +378,6 @@ static inline void __thread_fpu_begin(struct task_struct *tsk)
 	__thread_set_has_fpu(tsk);
 }
 
-static inline void __drop_fpu(struct task_struct *tsk)
-{
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
-	}
-}
-
 static inline void drop_fpu(struct task_struct *tsk)
 {
 	/*
@@ -369,21 +385,37 @@ static inline void drop_fpu(struct task_struct *tsk)
 	 */
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
-	__drop_fpu(tsk);
+
+	if (__thread_has_fpu(tsk)) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		__thread_fpu_end(tsk);
+	}
+
 	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
-static inline void drop_init_fpu(struct task_struct *tsk)
+static inline void restore_init_xstate(void)
+{
+	if (use_xsave())
+		xrstor_state(init_xstate_buf, -1);
+	else
+		fxrstor_checking(&init_xstate_buf->i387);
+}
+
+/*
+ * Reset the FPU state in the eager case and drop it in the lazy case (later use
+ * will reinit it).
+ */
+static inline void fpu_reset_state(struct task_struct *tsk)
 {
 	if (!use_eager_fpu())
 		drop_fpu(tsk);
-	else {
-		if (use_xsave())
-			xrstor_state(init_xstate_buf, -1);
-		else
-			fxrstor_checking(&init_xstate_buf->i387);
-	}
+	else
+		restore_init_xstate();
 }
 
 /*
@@ -400,24 +432,6 @@ static inline void drop_init_fpu(struct task_struct *tsk)
  */
 typedef struct { int preload; } fpu_switch_t;
 
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
-	per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
-	return new == this_cpu_read_stable(fpu_owner_task) &&
-		cpu == new->thread.fpu.last_cpu;
-}
-
 static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
 {
 	fpu_switch_t fpu;
@@ -426,13 +440,17 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 	 * If the task has used the math, pre-load the FPU on xsave processors
 	 * or if the past 5 consecutive context-switches used math.
 	 */
-	fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
-					     new->thread.fpu_counter > 5);
+	fpu.preload = tsk_used_math(new) &&
+		      (use_eager_fpu() || new->thread.fpu_counter > 5);
+
 	if (__thread_has_fpu(old)) {
 		if (!__save_init_fpu(old))
-			cpu = ~0;
-		old->thread.fpu.last_cpu = cpu;
-		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
+			task_disable_lazy_fpu_restore(old);
+		else
+			old->thread.fpu.last_cpu = cpu;
+
+		/* But leave fpu_owner_task! */
+		old->thread.fpu.has_fpu = 0;
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
@@ -443,10 +461,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 			stts();
 	} else {
 		old->thread.fpu_counter = 0;
-		old->thread.fpu.last_cpu = ~0;
+		task_disable_lazy_fpu_restore(old);
 		if (fpu.preload) {
 			new->thread.fpu_counter++;
-			if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
+			if (fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -466,7 +484,7 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 {
 	if (fpu.preload) {
 		if (unlikely(restore_fpu_checking(new)))
-			drop_init_fpu(new);
+			fpu_reset_state(new);
 	}
 }
 
@@ -495,10 +513,12 @@ static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
 }
 
 /*
- * Need to be preemption-safe.
+ * Needs to be preemption-safe.
  *
  * NOTE! user_fpu_begin() must be used only immediately before restoring
- * it. This function does not do any save/restore on their own.
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
  */
 static inline void user_fpu_begin(void)
 {
@@ -519,24 +539,6 @@ static inline void __save_fpu(struct task_struct *tsk)
 		fpu_fxsave(&tsk->thread.fpu);
 }
 
-/*
- * These disable preemption on their own and are safe
- */
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	WARN_ON_ONCE(!__thread_has_fpu(tsk));
-
-	if (use_eager_fpu()) {
-		__save_fpu(tsk);
-		return;
-	}
-
-	preempt_disable();
-	__save_init_fpu(tsk);
-	__thread_fpu_end(tsk);
-	preempt_enable();
-}
-
 /*
  * i387 state interaction
  */
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 29c740deafec..367f39d35e9c 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -42,8 +42,8 @@ void kernel_fpu_enable(void)
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
  *
- * Except for the eagerfpu case when we return 1 unless we've already
- * been eager and saved the state in kernel_fpu_begin().
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
@@ -51,7 +51,7 @@ static inline bool interrupted_kernel_fpu_idle(void)
 		return false;
 
 	if (use_eager_fpu())
-		return __thread_has_fpu(current);
+		return true;
 
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
@@ -94,9 +94,10 @@ void __kernel_fpu_begin(void)
 
 	if (__thread_has_fpu(me)) {
 		__save_init_fpu(me);
-	} else if (!use_eager_fpu()) {
+	} else {
 		this_cpu_write(fpu_owner_task, NULL);
-		clts();
+		if (!use_eager_fpu())
+			clts();
 	}
 }
 EXPORT_SYMBOL(__kernel_fpu_begin);
@@ -107,7 +108,7 @@ void __kernel_fpu_end(void)
 
 	if (__thread_has_fpu(me)) {
 		if (WARN_ON(restore_fpu_checking(me)))
-			drop_init_fpu(me);
+			fpu_reset_state(me);
 	} else if (!use_eager_fpu()) {
 		stts();
 	}
@@ -120,10 +121,13 @@ void unlazy_fpu(struct task_struct *tsk)
 {
 	preempt_disable();
 	if (__thread_has_fpu(tsk)) {
-		__save_init_fpu(tsk);
-		__thread_fpu_end(tsk);
-	} else
-		tsk->thread.fpu_counter = 0;
+		if (use_eager_fpu()) {
+			__save_fpu(tsk);
+		} else {
+			__save_init_fpu(tsk);
+			__thread_fpu_end(tsk);
+		}
+	}
 	preempt_enable();
 }
 EXPORT_SYMBOL(unlazy_fpu);
@@ -221,11 +225,12 @@ void fpu_finit(struct fpu *fpu)
 		return;
 	}
 
+	memset(fpu->state, 0, xstate_size);
+
 	if (cpu_has_fxsr) {
 		fx_finit(&fpu->state->fxsave);
 	} else {
 		struct i387_fsave_struct *fp = &fpu->state->fsave;
-		memset(fp, 0, xstate_size);
 		fp->cwd = 0xffff037fu;
 		fp->swd = 0xffff0000u;
 		fp->twd = 0xffffffffu;
@@ -247,7 +252,7 @@ int init_fpu(struct task_struct *tsk)
 	if (tsk_used_math(tsk)) {
 		if (cpu_has_fpu && tsk == current)
 			unlazy_fpu(tsk);
-		tsk->thread.fpu.last_cpu = ~0;
+		task_disable_lazy_fpu_restore(tsk);
 		return 0;
 	}
 
@@ -336,6 +341,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 		unsigned int pos, unsigned int count,
 		void *kbuf, void __user *ubuf)
 {
+	struct xsave_struct *xsave = &target->thread.fpu.state->xsave;
 	int ret;
 
 	if (!cpu_has_xsave)
@@ -350,14 +356,12 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 	 * memory layout in the thread struct, so that we can copy the entire
 	 * xstateregs to the user using one user_regset_copyout().
 	 */
-	memcpy(&target->thread.fpu.state->fxsave.sw_reserved,
-	       xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
-
+	memcpy(&xsave->i387.sw_reserved,
+		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
 	/*
 	 * Copy the xstate memory layout.
 	 */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.fpu.state->xsave, 0, -1);
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
 	return ret;
 }
 
@@ -365,8 +369,8 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 		  unsigned int pos, unsigned int count,
 		  const void *kbuf, const void __user *ubuf)
 {
+	struct xsave_struct *xsave = &target->thread.fpu.state->xsave;
 	int ret;
-	struct xsave_hdr_struct *xsave_hdr;
 
 	if (!cpu_has_xsave)
 		return -ENODEV;
@@ -375,22 +379,16 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (ret)
 		return ret;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.fpu.state->xsave, 0, -1);
-
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
 	/*
 	 * mxcsr reserved bits must be masked to zero for security reasons.
 	 */
-	target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
-	xsave_hdr = &target->thread.fpu.state->xsave.xsave_hdr;
-
-	xsave_hdr->xstate_bv &= pcntxt_mask;
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
+	xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
 	/*
 	 * These bits must be zero.
 	 */
-	memset(xsave_hdr->reserved, 0, 48);
-
+	memset(&xsave->xsave_hdr.reserved, 0, 48);
 	return ret;
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 0c8992dbead5..8213da62b1b7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -89,8 +89,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	dst->thread.fpu_counter = 0;
 	dst->thread.fpu.has_fpu = 0;
-	dst->thread.fpu.last_cpu = ~0;
 	dst->thread.fpu.state = NULL;
+	task_disable_lazy_fpu_restore(dst);
 	if (tsk_used_math(src)) {
 		int err = fpu_alloc(&dst->thread.fpu);
 		if (err)
@@ -151,13 +151,18 @@ void flush_thread(void)
 
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
-	drop_init_fpu(tsk);
-	/*
-	 * Free the FPU state for non xsave platforms. They get reallocated
-	 * lazily at the first use.
-	 */
-	if (!use_eager_fpu())
+
+	if (!use_eager_fpu()) {
+		/* FPU state will be reallocated lazily at the first use. */
+		drop_fpu(tsk);
 		free_thread_xstate(tsk);
+	} else if (!used_math()) {
+		/* kthread execs. TODO: cleanup this horror. */
+		if (WARN_ON(init_fpu(tsk)))
+			force_sig(SIGKILL, tsk);
+		user_fpu_begin();
+		restore_init_xstate();
+	}
 }
 
 static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 53cc4085c3d7..3e581865c8e2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -680,7 +680,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
 		if (used_math())
-			drop_init_fpu(current);
+			fpu_reset_state(current);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 6751c5c58eec..f4fa991406cd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -731,7 +731,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	/*
 	 * Save the info for the exception handler and clear the error.
 	 */
-	save_init_fpu(task);
+	unlazy_fpu(task);
 	task->thread.trap_nr = trapnr;
 	task->thread.error_code = error_code;
 	info.si_signo = SIGFPE;
@@ -860,7 +860,7 @@ void math_state_restore(void)
 	kernel_fpu_disable();
 	__thread_fpu_begin(tsk);
 	if (unlikely(restore_fpu_checking(tsk))) {
-		drop_init_fpu(tsk);
+		fpu_reset_state(tsk);
 		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 	} else {
 		tsk->thread.fpu_counter++;
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index cdc6cf903078..87a815b85f3e 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -342,7 +342,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 			 config_enabled(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		drop_init_fpu(tsk);
+		fpu_reset_state(tsk);
 		return 0;
 	}
 
@@ -416,7 +416,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 */
 		user_fpu_begin();
 		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
-			drop_init_fpu(tsk);
+			fpu_reset_state(tsk);
 			return -1;
 		}
 	}
@@ -678,19 +678,13 @@ void xsave_init(void)
 	this_func();
 }
 
-static inline void __init eager_fpu_init_bp(void)
+/*
+ * setup_init_fpu_buf() is __init and it is OK to call it here because
+ * init_xstate_buf will be unset only once during boot.
+ */
+void __init_refok eager_fpu_init(void)
 {
-	current->thread.fpu.state =
-	    alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct));
-	if (!init_xstate_buf)
-		setup_init_fpu_buf();
-}
-
-void eager_fpu_init(void)
-{
-	static __refdata void (*boot_func)(void) = eager_fpu_init_bp;
-
-	clear_used_math();
+	WARN_ON(used_math());
 	current_thread_info()->status = 0;
 
 	if (eagerfpu == ENABLE)
@@ -701,21 +695,8 @@ void eager_fpu_init(void)
 		return;
 	}
 
-	if (boot_func) {
-		boot_func();
-		boot_func = NULL;
-	}
-
-	/*
-	 * This is same as math_state_restore(). But use_xsave() is
-	 * not yet patched to use math_state_restore().
-	 */
-	init_fpu(current);
-	__thread_fpu_begin(current);
-	if (cpu_has_xsave)
-		xrstor_state(init_xstate_buf, -1);
-	else
-		fxrstor_checking(&init_xstate_buf->i387);
+	if (!init_xstate_buf)
+		setup_init_fpu_buf();
 }
 
 /*