diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a2124343edf5..31ac8e6d9f36 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -25,6 +25,8 @@
 extern void fpu__activate_curr(struct fpu *fpu);
 extern void fpu__activate_fpstate_read(struct fpu *fpu);
 extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__current_fpstate_write_begin(void);
+extern void fpu__current_fpstate_write_end(void);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 299b58bb975b..dea8e76d60c6 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -353,6 +353,69 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 	}
 }
 
+/*
+ * This function must be called before we write the current
+ * task's fpstate.
+ *
+ * This call gets the current FPU register state and moves
+ * it in to the 'fpstate'.  Preemption is disabled so that
+ * no writes to the 'fpstate' can occur from context
+ * swiches.
+ *
+ * Must be followed by a fpu__current_fpstate_write_end().
+ */
+void fpu__current_fpstate_write_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	/*
+	 * Ensure that the context-switching code does not write
+	 * over the fpstate while we are doing our update.
+	 */
+	preempt_disable();
+
+	/*
+	 * Move the fpregs in to the fpu's 'fpstate'.
+	 */
+	fpu__activate_fpstate_read(fpu);
+
+	/*
+	 * The caller is about to write to 'fpu'.  Ensure that no
+	 * CPU thinks that its fpregs match the fpstate.  This
+	 * ensures we will not be lazy and skip a XRSTOR in the
+	 * future.
+	 */
+	fpu->last_cpu = -1;
+}
+
+/*
+ * This function must be paired with fpu__current_fpstate_write_begin()
+ *
+ * This will ensure that the modified fpstate gets placed back in
+ * the fpregs if necessary.
+ *
+ * Note: This function may be called whether or not an _actual_
+ * write to the fpstate occurred.
+ */
+void fpu__current_fpstate_write_end(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	/*
+	 * 'fpu' now has an updated copy of the state, but the
+	 * registers may still be out of date.  Update them with
+	 * an XRSTOR if they are active.
+	 */
+	if (fpregs_active())
+		copy_kernel_to_fpregs(&fpu->state);
+
+	/*
+	 * Our update is done and the fpregs/fpstate are in sync
+	 * if necessary.  Context switches can happen again.
+	 */
+	preempt_enable();
+}
+
 /*
  * 'fpu__restore()' is called to copy FPU registers from
  * the FPU fpstate to the live hw registers and to activate
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index a63ca80fa723..30d144f01eb9 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -678,6 +678,19 @@ void fpu__resume_cpu(void)
 		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
 }
 
+/*
+ * Given an xstate feature mask, calculate where in the xsave
+ * buffer the state is.  Callers should ensure that the buffer
+ * is valid.
+ *
+ * Note: does not work for compacted buffers.
+ */
+void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+{
+	int feature_nr = fls64(xstate_feature_mask) - 1;
+
+	return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
 /*
  * Given the xsave area and a state inside, this function returns the
  * address of the state.
@@ -698,7 +711,6 @@ void fpu__resume_cpu(void)
  */
 void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 {
-	int feature_nr = fls64(xstate_feature) - 1;
 	/*
 	 * Do we even *have* xsave state?
 	 */
@@ -726,7 +738,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	if (!(xsave->header.xfeatures & xstate_feature))
 		return NULL;
 
-	return (void *)xsave + xstate_comp_offsets[feature_nr];
+	return __raw_xsave_addr(xsave, xstate_feature);
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
@@ -761,3 +773,85 @@ const void *get_xsave_field_ptr(int xsave_state)
 
 	return get_xsave_addr(&fpu->state.xsave, xsave_state);
 }
+
+
+/*
+ * Set xfeatures (aka XSTATE_BV) bit for a feature that we want
+ * to take out of its "init state".  This will ensure that an
+ * XRSTOR actually restores the state.
+ */
+static void fpu__xfeature_set_non_init(struct xregs_state *xsave,
+		int xstate_feature_mask)
+{
+	xsave->header.xfeatures |= xstate_feature_mask;
+}
+
+/*
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ *	@xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
+ *	XFEATURE_MASK_SSE, etc...)
+ *	@xsave_state_ptr: a pointer to a copy of the state that you would
+ *	like written in to the current task's FPU xsave state.  This pointer
+ *	must not be located in the current tasks's xsave area.
+ * Output:
+ *	address of the state in the xsave area or NULL if the state
+ *	is not present or is in its 'init state'.
+ */
+static void fpu__xfeature_set_state(int xstate_feature_mask,
+		void *xstate_feature_src, size_t len)
+{
+	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct fpu *fpu = &current->thread.fpu;
+	void *dst;
+
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
+		WARN_ONCE(1, "%s() attempted with no xsave support", __func__);
+		return;
+	}
+
+	/*
+	 * Tell the FPU code that we need the FPU state to be in
+	 * 'fpu' (not in the registers), and that we need it to
+	 * be stable while we write to it.
+	 */
+	fpu__current_fpstate_write_begin();
+
+	/*
+	 * This method *WILL* *NOT* work for compact-format
+	 * buffers.  If the 'xstate_feature_mask' is unset in
+	 * xcomp_bv then we may need to move other feature state
+	 * "up" in the buffer.
+	 */
+	if (xsave->header.xcomp_bv & xstate_feature_mask) {
+		WARN_ON_ONCE(1);
+		goto out;
+	}
+
+	/* find the location in the xsave buffer of the desired state */
+	dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask);
+
+	/*
+	 * Make sure that the pointer being passed in did not
+	 * come from the xsave buffer itself.
+	 */
+	WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself");
+
+	/* put the caller-provided data in the location */
+	memcpy(dst, xstate_feature_src, len);
+
+	/*
+	 * Mark the xfeature so that the CPU knows there is state
+	 * in the buffer now.
+	 */
+	fpu__xfeature_set_non_init(xsave, xstate_feature_mask);
+out:
+	/*
+	 * We are done writing to the 'fpu'.  Reenable preeption
+	 * and (possibly) move the fpstate back in to the fpregs.
+	 */
+	fpu__current_fpstate_write_end();
+}