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

6 files changed, 107 insertions, 14 deletions

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ac2330820b9a..8ab8a1a9610a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -236,7 +236,9 @@ struct thread_struct {
 #endif
 	struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
 	unsigned long	trap_nr;	/* last trap # on this thread */
+	u8 load_fp;
 #ifdef CONFIG_ALTIVEC
+	u8 load_vec;
 	struct thread_vr_state vr_state;
 	struct thread_vr_state *vr_save_area;
 	unsigned long	vrsave;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 07cebc3514f3..10d5eab19458 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -95,12 +95,14 @@ int main(void)
 	DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state));
 	DEFINE(THREAD_FPSAVEAREA, offsetof(struct thread_struct, fp_save_area));
 	DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr));
+	DEFINE(THREAD_LOAD_FP, offsetof(struct thread_struct, load_fp));
 #ifdef CONFIG_ALTIVEC
 	DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state));
 	DEFINE(THREAD_VRSAVEAREA, offsetof(struct thread_struct, vr_save_area));
 	DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
 	DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
 	DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr));
+	DEFINE(THREAD_LOAD_VEC, offsetof(struct thread_struct, load_vec));
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_VSX
 	DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr));
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 0d525ce3717f..038e0a1425e7 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -210,7 +210,20 @@ system_call:			/* label this so stack traces look sane */
 	li	r11,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
-	cmpld	r3,r11
+
+	andi.	r0,r8,MSR_FP
+	beq 2f
+#ifdef CONFIG_ALTIVEC
+	andis.	r0,r8,MSR_VEC@h
+	bne	3f
+#endif
+2:	addi    r3,r1,STACK_FRAME_OVERHEAD
+	bl	restore_math
+	ld	r8,_MSR(r1)
+	ld	r3,RESULT(r1)
+	li	r11,-MAX_ERRNO
+
+3:	cmpld	r3,r11
 	ld	r5,_CCR(r1)
 	bge-	syscall_error
 .Lsyscall_error_cont:
@@ -602,8 +615,8 @@ _GLOBAL(ret_from_except_lite)
 
 	/* Check current_thread_info()->flags */
 	andi.	r0,r4,_TIF_USER_WORK_MASK
-#ifdef CONFIG_PPC_BOOK3E
 	bne	1f
+#ifdef CONFIG_PPC_BOOK3E
 	/*
 	 * Check to see if the dbcr0 register is set up to debug.
 	 * Use the internal debug mode bit to do this.
@@ -618,7 +631,9 @@ _GLOBAL(ret_from_except_lite)
 	mtspr	SPRN_DBSR,r10
 	b	restore
 #else
-	beq	restore
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	restore_math
+	b	restore
 #endif
 1:	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	2f
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 2117eaca3d28..b06352474ad0 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -130,6 +130,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	or	r12,r12,r4
 	std	r12,_MSR(r1)
 #endif
+	/* Don't care if r4 overflows, this is desired behaviour */
+	lbz	r4,THREAD_LOAD_FP(r5)
+	addi	r4,r4,1
+	stb	r4,THREAD_LOAD_FP(r5)
 	addi	r10,r5,THREAD_FPSTATE
 	lfd	fr0,FPSTATE_FPSCR(r10)
 	MTFSF_L(fr0)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e0c3d2dc7ca3..55c1eb0465af 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;
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 162d0f714941..038cff8cf5f2 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -91,6 +91,10 @@ _GLOBAL(load_up_altivec)
 	oris	r12,r12,MSR_VEC@h
 	std	r12,_MSR(r1)
 #endif
+	/* Don't care if r4 overflows, this is desired behaviour */
+	lbz	r4,THREAD_LOAD_VEC(r5)
+	addi	r4,r4,1
+	stb	r4,THREAD_LOAD_VEC(r5)
 	addi	r6,r5,THREAD_VRSTATE
 	li	r4,1
 	li	r10,VRSTATE_VSCR