Ensure that the TIF_NEED_FPU_LOAD flag is always set after saving the
FPU state. This guarantees that the user space FPU state has been saved
whenever the TIF_NEED_FPU_LOAD flag is set.

A subsequent patch will verify if the user space FPU state can be
retrieved from the saved task FPU state in the NMI context by checking
the TIF_NEED_FPU_LOAD flag.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---

v6: new patch.

 arch/x86/include/asm/fpu/sched.h |  2 +-
 arch/x86/kernel/fpu/core.c       | 12 ++++++++----
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index 89004f4ca208..2d57a7bf5406 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -36,8 +36,8 @@ static inline void switch_fpu(struct task_struct *old, int cpu)
 	    !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
 		struct fpu *old_fpu = x86_task_fpu(old);
 
-		set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD);
 		save_fpregs_to_fpstate(old_fpu);
+		set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD);
 		/*
 		 * The save operation preserved register state, so the
 		 * fpu_fpregs_owner_ctx is still @old_fpu. Store the
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index da233f20ae6f..0f91a0d7e799 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -359,18 +359,22 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 	struct fpstate *cur_fps = fpu->fpstate;
 
 	fpregs_lock();
-	if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD))
+	if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD)) {
 		save_fpregs_to_fpstate(fpu);
+		set_thread_flag(TIF_NEED_FPU_LOAD);
+	}
 
 	/* Swap fpstate */
 	if (enter_guest) {
-		fpu->__task_fpstate = cur_fps;
+		WRITE_ONCE(fpu->__task_fpstate, cur_fps);
+		barrier();
 		fpu->fpstate = guest_fps;
 		guest_fps->in_use = true;
 	} else {
 		guest_fps->in_use = false;
 		fpu->fpstate = fpu->__task_fpstate;
-		fpu->__task_fpstate = NULL;
+		barrier();
+		WRITE_ONCE(fpu->__task_fpstate, NULL);
 	}
 
 	cur_fps = fpu->fpstate;
@@ -456,8 +460,8 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 
 	if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) &&
 	    !test_thread_flag(TIF_NEED_FPU_LOAD)) {
-		set_thread_flag(TIF_NEED_FPU_LOAD);
 		save_fpregs_to_fpstate(x86_task_fpu(current));
+		set_thread_flag(TIF_NEED_FPU_LOAD);
 	}
 	__cpu_invalidate_fpregs_state();
 
-- 
2.34.1