[v3 2/2] [PowerPC] Allow use of SIMD in interrupts from kernel code

[Shawn Landden]

This second patch is separate because it could be wrong,
like I am not sure about how kernel thread migration works,
and it is even allowing simd in preemptible kernel code.

Signed-off-by: Shawn Landden <shawn at git.icu>
---
 arch/powerpc/include/asm/switch_to.h | 15 ++-----
 arch/powerpc/kernel/process.c        | 60 ++++++++++++++++++++++++++--
 2 files changed, 59 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 5b03d8a82..c79f7d24a 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -30,10 +30,7 @@ extern void enable_kernel_fp(void);
 extern void flush_fp_to_thread(struct task_struct *);
 extern void giveup_fpu(struct task_struct *);
 extern void save_fpu(struct task_struct *);
-static inline void disable_kernel_fp(void)
-{
-	msr_check_and_clear(MSR_FP);
-}
+extern void disable_kernel_fp(void);
 #else
 static inline void save_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
@@ -44,10 +41,7 @@ extern void enable_kernel_altivec(void);
 extern void flush_altivec_to_thread(struct task_struct *);
 extern void giveup_altivec(struct task_struct *);
 extern void save_altivec(struct task_struct *);
-static inline void disable_kernel_altivec(void)
-{
-	msr_check_and_clear(MSR_VEC);
-}
+extern void disable_kernel_altivec(void);
 #else
 static inline void save_altivec(struct task_struct *t) { }
 static inline void __giveup_altivec(struct task_struct *t) { }
@@ -56,10 +50,7 @@ static inline void __giveup_altivec(struct task_struct *t) { }
 #ifdef CONFIG_VSX
 extern void enable_kernel_vsx(void);
 extern void flush_vsx_to_thread(struct task_struct *);
-static inline void disable_kernel_vsx(void)
-{
-	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
-}
+extern void disable_kernel_vsx(void);
 #endif
 
 #ifdef CONFIG_SPE
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ef534831f..4ffc9c664 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -170,6 +170,29 @@ void __msr_check_and_clear(unsigned long bits)
 EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ *   - by IRQ context code to potentially use the FPU
+ *     if it's unused.
+ *
+ *   - to debug kernel_fpu/altivec/vsx_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+static bool kernel_fpu_disabled(void)
+{
+	return this_cpu_read(in_kernel_fpu);
+}
+
+static bool interrupted_kernel_fpu_idle(void)
+{
+	return !kernel_fpu_disabled();
+}
+
 static void __giveup_fpu(struct task_struct *tsk)
 {
 	unsigned long msr;
@@ -230,7 +253,8 @@ void enable_kernel_fp(void)
 {
 	unsigned long cpumsr;
 
-	WARN_ON(preemptible());
+	WARN_ON_ONCE(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
 
 	cpumsr = msr_check_and_set(MSR_FP);
 
@@ -251,6 +275,15 @@ void enable_kernel_fp(void)
 }
 EXPORT_SYMBOL(enable_kernel_fp);
 
+void disable_kernel_fp(void)
+{
+	WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+
+	msr_check_and_clear(MSR_FP);
+}
+EXPORT_SYMBOL(disable_kernel_fp);
+
 static int restore_fp(struct task_struct *tsk)
 {
 	if (tsk->thread.load_fp || tm_active_with_fp(tsk)) {
@@ -295,7 +328,8 @@ void enable_kernel_altivec(void)
 {
 	unsigned long cpumsr;
 
-	WARN_ON(preemptible());
+	WARN_ON_ONCE(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
 
 	cpumsr = msr_check_and_set(MSR_VEC);
 
@@ -316,6 +350,14 @@ void enable_kernel_altivec(void)
 }
 EXPORT_SYMBOL(enable_kernel_altivec);
 
+extern void disable_kernel_altivec(void)
+{
+	WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+	msr_check_and_clear(MSR_VEC);
+}
+EXPORT_SYMBOL(disable_kernel_altivec);
+
 /*
  * Make sure the VMX/Altivec register state in the
  * the thread_struct is up to date for task tsk.
@@ -371,7 +413,8 @@ static bool interrupted_user_mode(void)
 bool may_use_simd(void)
 {
 	return !in_interrupt() ||
-		interrupted_user_mode();
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
 }
 EXPORT_SYMBOL(may_use_simd);
 
@@ -411,7 +454,8 @@ void enable_kernel_vsx(void)
 {
 	unsigned long cpumsr;
 
-	WARN_ON(preemptible());
+	WARN_ON_ONCE(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
 
 	cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 
@@ -433,6 +477,14 @@ void enable_kernel_vsx(void)
 }
 EXPORT_SYMBOL(enable_kernel_vsx);
 
+void disable_kernel_vsx(void)
+{
+	WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
+}
+EXPORT_SYMBOL(disable_kernel_vsx);
+
 void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
-- 
2.21.0.1020.gf2820cf01a