[patch V2 08/30] x86/fpu: Do not inherit FPU context for kernel and IO worker threads

[Thomas Gleixner <tglx@linutronix.de>]

There is no reason why kernel and IO worker threads need a full clone of
the parent's FPU state. Both are kernel threads which are not supposed to
use FPU. So copying a large state or doing XSAVE() is pointless. Just clean
out the minimaly required state for those tasks.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/kernel/fpu/core.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)
---
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 191269edac97..9a6b195a8a00 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -212,6 +212,15 @@ static inline void fpstate_init_xstate(struct xregs_state *xsave)
 	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
 }
 
+static inline unsigned int init_fpstate_copy_size(void)
+{
+	if (!use_xsave())
+		return fpu_kernel_xstate_size;
+
+	/* XSAVE(S) just needs the legacy and the xstate header part */
+	return sizeof(init_fpstate.xsave);
+}
+
 static inline void fpstate_init_fxstate(struct fxregs_state *fx)
 {
 	fx->cwd = 0x37f;
@@ -260,6 +269,23 @@ int fpu_clone(struct task_struct *dst)
 		return 0;
 
 	/*
+	 * Enforce reload for user space tasks and prevent kernel threads
+	 * from trying to save the FPU registers on context switch.
+	 */
+	set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
+
+	/*
+	 * No FPU state inheritance for kernel threads and IO
+	 * worker threads.
+	 */
+	if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) {
+		/* Clear out the minimal state */
+		memcpy(&dst_fpu->state, &init_fpstate,
+		       init_fpstate_copy_size());
+		return 0;
+	}
+
+	/*
 	 * If the FPU registers are not owned by current just memcpy() the
 	 * state.  Otherwise save the FPU registers directly into the
 	 * child's FPU context, without any memory-to-memory copying.
@@ -272,8 +298,6 @@ int fpu_clone(struct task_struct *dst)
 		save_fpregs_to_fpstate(dst_fpu);
 	fpregs_unlock();
 
-	set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
-
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
 
@@ -322,15 +346,6 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
 	pkru_write_default();
 }
 
-static inline unsigned int init_fpstate_copy_size(void)
-{
-	if (!use_xsave())
-		return fpu_kernel_xstate_size;
-
-	/* XSAVE(S) just needs the legacy and the xstate header part */
-	return sizeof(init_fpstate.xsave);
-}
-
 /*
  * Reset current->fpu memory state to the init values.
  */