From 10d91611f426d4bafd2a83d966c36da811b2f7ad Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 13 Apr 2019 00:30:52 +1000 Subject: powerpc/64s: Reimplement book3s idle code in C Reimplement Book3S idle code in C, moving POWER7/8/9 implementation speific HV idle code to the powernv platform code. Book3S assembly stubs are kept in common code and used only to save the stack frame and non-volatile GPRs before executing architected idle instructions, and restoring the stack and reloading GPRs then returning to C after waking from idle. The complex logic dealing with threads and subcores, locking, SPRs, HMIs, timebase resync, etc., is all done in C which makes it more maintainable. This is not a strict translation to C code, there are some significant differences: - Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs, but saves and restores them itself. - The optimisation where EC=ESL=0 idle modes did not have to save GPRs or change MSR is restored, because it's now simple to do. ESL=1 sleeps that do not lose GPRs can use this optimization too. - KVM secondary entry and cede is now more of a call/return style rather than branchy. nap_state_lost is not required because KVM always returns via NVGPR restoring path. - KVM secondary wakeup from offline sequence is moved entirely into the offline wakeup, which avoids a hwsync in the normal idle wakeup path. Performance measured with context switch ping-pong on different threads or cores, is possibly improved a small amount, 1-3% depending on stop state and core vs thread test for shallow states. Deep states it's in the noise compared with other latencies. KVM improvements: - Idle sleepers now always return to caller rather than branch out to KVM first. - This allows optimisations like very fast return to caller when no state has been lost. - KVM no longer requires nap_state_lost because it controls NVGPR save/restore itself on the way in and out. - The heavy idle wakeup KVM request check can be moved out of the normal host idle code and into the not-performance-critical offline code. - KVM nap code now returns from where it is called, which makes the flow a bit easier to follow. Reviewed-by: Gautham R. Shenoy Signed-off-by: Nicholas Piggin [mpe: Squash the KVM changes in] Signed-off-by: Michael Ellerman --- arch/powerpc/xmon/xmon.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/xmon') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a0f44f992360..e583ed3f6b93 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2431,7 +2431,6 @@ static void dump_one_paca(int cpu) DUMP(p, irq_happened, "%#-*x"); DUMP(p, io_sync, "%#-*x"); DUMP(p, irq_work_pending, "%#-*x"); - DUMP(p, nap_state_lost, "%#-*x"); DUMP(p, sprg_vdso, "%#-*llx"); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -2439,19 +2438,16 @@ static void dump_one_paca(int cpu) #endif #ifdef CONFIG_PPC_POWERNV - DUMP(p, core_idle_state_ptr, "%-*px"); - DUMP(p, thread_idle_state, "%#-*x"); - DUMP(p, thread_mask, "%#-*x"); - DUMP(p, subcore_sibling_mask, "%#-*x"); - DUMP(p, requested_psscr, "%#-*llx"); - DUMP(p, stop_sprs.pid, "%#-*llx"); - DUMP(p, stop_sprs.ldbar, "%#-*llx"); - DUMP(p, stop_sprs.fscr, "%#-*llx"); - DUMP(p, stop_sprs.hfscr, "%#-*llx"); - DUMP(p, stop_sprs.mmcr1, "%#-*llx"); - DUMP(p, stop_sprs.mmcr2, "%#-*llx"); - DUMP(p, stop_sprs.mmcra, "%#-*llx"); - DUMP(p, dont_stop.counter, "%#-*x"); + DUMP(p, idle_state, "%#-*lx"); + if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) { + DUMP(p, thread_idle_state, "%#-*x"); + DUMP(p, subcore_sibling_mask, "%#-*x"); + } else { +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + DUMP(p, requested_psscr, "%#-*llx"); + DUMP(p, dont_stop.counter, "%#-*x"); +#endif + } #endif DUMP(p, accounting.utime, "%#-*lx"); -- cgit v1.2.3-73-gaa49b