powerpc: Restore FPU/VEC/VSX if previously used

Currently the FPU, VEC and VSX facilities are lazily loaded. This is not
a problem unless a process is using these facilities.

Modern versions of GCC are very good at automatically vectorising code,
new and modernised workloads make use of floating point and vector
facilities, even the kernel makes use of vectorised memcpy.

All this combined greatly increases the cost of a syscall since the
kernel uses the facilities sometimes even in syscall fast-path making it
increasingly common for a thread to take an *_unavailable exception soon
after a syscall, not to mention potentially taking all three.

The obvious overcompensation to this problem is to simply always load
all the facilities on every exit to userspace. Loading up all FPU, VEC
and VSX registers every time can be expensive and if a workload does
avoid using them, it should not be forced to incur this penalty.

An 8bit counter is used to detect if the registers have been used in the
past and the registers are always loaded until the value wraps to back
to zero.

Several versions of the assembly in entry_64.S were tested:

  1. Always calling C.
  2. Performing a common case check and then calling C.
  3. A complex check in asm.

After some benchmarking it was determined that avoiding C in the common
case is a performance benefit (option 2). The full check in asm (option
3) greatly complicated that codepath for a negligible performance gain
and the trade-off was deemed not worth it.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
[mpe: Move load_vec in the struct to fill an existing hole, reword change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

fixup

1 files changed, 77 insertions, 11 deletions

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e0c3d2d..55c1eb0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -187,9 +187,22 @@ void enable_kernel_fp(void)
 	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
+
+static int restore_fp(struct task_struct *tsk) {
+	if (tsk->thread.load_fp) {
+		load_fp_state(&current->thread.fp_state);
+		current->thread.load_fp++;
+		return 1;
+	}
+	return 0;
+}
+#else
+static int restore_fp(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
+#define loadvec(thr) ((thr).load_vec)
+
 void giveup_altivec(struct task_struct *tsk)
 {
 	check_if_tm_restore_required(tsk);
@@ -229,6 +242,21 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
+
+static int restore_altivec(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) && tsk->thread.load_vec) {
+		load_vr_state(&tsk->thread.vr_state);
+		tsk->thread.used_vr = 1;
+		tsk->thread.load_vec++;
+
+		return 1;
+	}
+	return 0;
+}
+#else
+#define loadvec(thr) 0
+static inline int restore_altivec(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
@@ -275,6 +303,18 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
+
+static int restore_vsx(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_VSX)) {
+		tsk->thread.used_vsr = 1;
+		return 1;
+	}
+
+	return 0;
+}
+#else
+static inline int restore_vsx(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
@@ -374,6 +414,36 @@ void giveup_all(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(giveup_all);
 
+void restore_math(struct pt_regs *regs)
+{
+	unsigned long msr;
+
+	if (!current->thread.load_fp && !loadvec(current->thread))
+		return;
+
+	msr = regs->msr;
+	msr_check_and_set(msr_all_available);
+
+	/*
+	 * Only reload if the bit is not set in the user MSR, the bit BEING set
+	 * indicates that the registers are hot
+	 */
+	if ((!(msr & MSR_FP)) && restore_fp(current))
+		msr |= MSR_FP | current->thread.fpexc_mode;
+
+	if ((!(msr & MSR_VEC)) && restore_altivec(current))
+		msr |= MSR_VEC;
+
+	if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) &&
+			restore_vsx(current)) {
+		msr |= MSR_VSX;
+	}
+
+	msr_check_and_clear(msr_all_available);
+
+	regs->msr = msr;
+}
+
 void flush_all_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
@@ -832,17 +902,9 @@ void restore_tm_state(struct pt_regs *regs)
 
 	msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
 	msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
-	if (msr_diff & MSR_FP) {
-		msr_check_and_set(MSR_FP);
-		load_fp_state(&current->thread.fp_state);
-		msr_check_and_clear(MSR_FP);
-		regs->msr |= current->thread.fpexc_mode;
-	}
-	if (msr_diff & MSR_VEC) {
-		msr_check_and_set(MSR_VEC);
-		load_vr_state(&current->thread.vr_state);
-		msr_check_and_clear(MSR_VEC);
-	}
+
+	restore_math(regs);
+
 	regs->msr |= msr_diff;
 }
 
@@ -1006,6 +1068,10 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
+
+	if (current_thread_info()->task->thread.regs)
+		restore_math(current_thread_info()->task->thread.regs);
+
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	return last;