[PATCH] x86/fpu: don't set TIF_NEED_FPU_LOAD for PF_IO_WORKER threads

From: Jens Axboe
Date: Tue Jan 24 2023 - 10:23:36 EST


We don't set it on PF_KTHREAD threads as they never return to userspace,
and PF_IO_WORKER threads are identical in that regard. As they keep
running in the kernel until they die, skip setting the FPU flag on them.

Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>

---

Not urgent, more of a cosmetic thing that was found while debugging and
issue and pondering why the FPU flag is set on these threads.

diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index b2486b2cbc6e..c2d6cd78ed0c 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -39,7 +39,7 @@ extern void fpu_flush_thread(void);
static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
if (cpu_feature_enabled(X86_FEATURE_FPU) &&
- !(current->flags & PF_KTHREAD)) {
+ !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) {
save_fpregs_to_fpstate(old_fpu);
/*
* The save operation preserved register state, so the
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
index 958accf2ccf0..9fcfa5c4dad7 100644
--- a/arch/x86/kernel/fpu/context.h
+++ b/arch/x86/kernel/fpu/context.h
@@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void)
struct fpu *fpu = &current->thread.fpu;
int cpu = smp_processor_id();

- if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
+ if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER)))
return;

if (!fpregs_state_valid(fpu, cpu)) {
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 9baa89a8877d..2babc537ff36 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)

this_cpu_write(in_kernel_fpu, true);

- if (!(current->flags & PF_KTHREAD) &&
+ if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
!test_thread_flag(TIF_NEED_FPU_LOAD)) {
set_thread_flag(TIF_NEED_FPU_LOAD);
save_fpregs_to_fpstate(&current->thread.fpu);

--
Jens Axboe