[RESEND Patch v10 07/23] x86/fpu: Add update_fpu_state_and_flag() helper

Add update_fpu_state_and_flag() as suggested by Peter and Dave.
The helper saves user FPU state and then sets TIF_NEED_FPU_LOAD,
ensuring the task FPU state is saved whenever the flag is set.

Subsequent patches will use this guarantee in NMI context by checking
TIF_NEED_FPU_LOAD before retrieving user FPU state from the saved
task FPU state.

Also add barrier() in the host/guest FPU state switch path and move
clearing of fpu->__task_fpstate after switching back to host state. So
fpu->__task_fpstate is always observed as host FPU state when non-NULL.

Link: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Dapeng Mi <[email protected]>
---
 arch/x86/include/asm/fpu/sched.h |  5 +++--
 arch/x86/kernel/fpu/core.c       | 33 ++++++++++++++++++++++++++------
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index 89004f4ca208..dcb2fa5f06d6 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -10,6 +10,8 @@
 #include <asm/trace/fpu.h>
 
 extern void save_fpregs_to_fpstate(struct fpu *fpu);
+extern void update_fpu_state_and_flag(struct fpu *fpu,
+				      struct task_struct *task);
 extern void fpu__drop(struct task_struct *tsk);
 extern int  fpu_clone(struct task_struct *dst, u64 clone_flags, bool minimal,
 		      unsigned long shstk_addr);
@@ -36,8 +38,7 @@ 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);
+		update_fpu_state_and_flag(old_fpu, old);
 		/*
 		 * 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 584fb9913be4..9e029b2f8937 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -213,6 +213,19 @@ void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask)
 	}
 }
 
+/*
+ * Save the FPU register state in fpu->fpstate->regs and set
+ * TIF_NEED_FPU_LOAD subsequently.
+ *
+ * Must be called with fpregs_lock() held, ensuring flag
+ * TIF_NEED_FPU_LOAD is set last.
+ */
+void update_fpu_state_and_flag(struct fpu *fpu, struct task_struct *task)
+{
+	save_fpregs_to_fpstate(fpu);
+	set_tsk_thread_flag(task, TIF_NEED_FPU_LOAD);
+}
+
 void fpu_reset_from_exception_fixup(void)
 {
 	restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE);
@@ -383,13 +396,13 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 
 	/* 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;
 	}
 
 	cur_fps = fpu->fpstate;
@@ -406,6 +419,16 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 		xfd_update_state(cur_fps);
 	}
 
+	/*
+	 * Clear fpu->__task_fpstate after switching back to host state.
+	 * A non-NULL __task_fpstate means guest state is still resident in
+	 * hardware; reset it only once host state has been restored.
+	 */
+	if (!enter_guest) {
+		barrier();
+		WRITE_ONCE(fpu->__task_fpstate, NULL);
+	}
+
 	fpregs_mark_activate();
 	fpregs_unlock();
 	return 0;
@@ -481,10 +504,8 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 	this_cpu_write(kernel_fpu_allowed, false);
 
 	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));
-	}
+	    !test_thread_flag(TIF_NEED_FPU_LOAD))
+		update_fpu_state_and_flag(x86_task_fpu(current), current);
 	__cpu_invalidate_fpregs_state();
 
 	/* Put sane initial values into the control registers. */
-- 
2.34.1